Feeds:
Posts
Comments

Posts Tagged ‘Prostate cancer’

Bisphosphonates and Bone Metastasis [6.3.1]

Curator: Stephen J. Williams, Ph.D.

bisophosphonates chemical

General Structure of Bisphosphonates

One of the hallmarks of advanced cancer is the ability to metastasize (tumor cells migrating from primary tumor and colonize in a different anatomical site in the body) and many histologic types of primary tumors have the propensity to metastasize to the bone. One of the frequent complications occurring from bone metastasis is bone fractures and severe pain associated with these cancer-associated bone fractures. An additional problem is cancer-associated hypercalcemia, which may or may not be dependent on bone-metastasis. The main humoral factor associated with cancer-related hypercalcemia is parathyroid hormone–related protein, which is produced by many solid tumors (Paget’s disease). Parathyroid hormone–related protein increases calcium by activating parathyroid hormone receptors in tissue, which results in osteoclastic bone resorption; it also increases renal tubular resorption of calcium {see (1) Bower reference for more information). This curation involves three areas:

  1. The Changing Views How Bone Remodeling Occurs
  2. Early Development of Agents that Alter Bone Remodeling and Early Use in Cancer Patients
  3. Recent Developments Regarding Use of Bisphosphonates in Cancer Patients

As there are numerous articles (1360; more than to manually curate) on “bone”, “metastasis” and “bisphosphonates” the following link is to a Pubmed search on the terms

http://www.ncbi.nlm.nih.gov/pubmed/?term=bone+metastasis+bisphosphonates

In addition there are subset searches to show use of bisphosphonates in common cancers and files given below with numbers of articles:

Search terms with Pubmed link # citations
bone metastasis bisphosphonates 1360
+ breast 559
+ prostate 349
+ colon 9
+ lung 222
  1. The Changing Views How Bone Remodeling Occurs

Bone remodeling (or bone metabolism) is a lifelong process where mature bone tissue is removed from the skeleton (a process called bone resorption) and new bone tissue is formed (a process called ossification or new bone formation). These processes also control the reshaping or replacement of bone following injuries like fractures but also micro-damage, which occurs during normal activity. Remodeling responds also to functional demands of the mechanical loading.

In the first year of life, almost 100% of the skeleton is replaced. In adults, remodeling proceeds at about 10% per year.[1]

An imbalance in the regulation of bone remodeling’s two sub-processes, bone resorption and bone formation, results in many metabolic bone diseases, such as osteoporosis. Two main types of cells are responsible for bone metabolism: osteoblasts (which secrete new bone), and osteoclasts (which break bone down). The structure of bones as well as adequate supply of calcium requires close cooperation between these two cell types and other cell populations present at the bone remodeling sites (ex. immune cells).[4] Bone metabolism relies on complex signaling pathways and control mechanisms to achieve proper rates of growth and differentiation. These controls include the action of several hormones, including parathyroid hormone (PTH), vitamin D, growth hormone, steroids, and calcitonin, as well as several bone marrow-derived membrane and soluble cytokines and growth factors (ex. M-CSF, RANKL, VEGF, IL-6 family…). It is in this way that the body is able to maintain proper levels of calcium required for physiological processes.

Subsequent to appropriate signaling, osteoclasts move to resorb the surface of the bone, followed by deposition of bone by osteoblasts. Together, the cells that are responsible for bone remodeling are known as the basic multicellular unit (BMU), and the temporal duration (i.e. lifespan) of the BMU is referred to as the bone remodeling period.

For a good review on bone remodeling please see Bone remodelling in a nutshell

boneremodelPTHumich

bone remodeling 3

  1. Early Development of Agents that Alter Bone Remodeling and Early Use in Cancer Patients

Bisphosphonates had been first synthesized in the late 1800’s yet their development and approval for the indication of osteoporosis occurred over 100 years later, in the 1990’s. For a good review on the history of bisphosphonates please see the following review:

Historical perspectives on the clinical development of bisphosphonates in the treatment of bone diseases. Francis MD1, Valent DJ. J Musculoskelet Neuronal Interact. 2007 Jan-Mar;7(1):2-8.

For a good reference on bisphosphonates as a class, as well as indication, contraindication and side effects see University of Washington web page at http://courses.washington.edu/bonephys/opbis.html

 

Please view slideshow in the following link: The Evolving Role of Bisphosphonates for Cancer Treatment-Induced Bone Loss presentation by Richard L. Theriault, DO, MBA at MD Anderson Cancer Center

bisphosphonatecancerslide1

  1. Recent Developments Regarding Use of Bisphosphonates in Cancer Patients

Bone Metastasis Treatment with Bisphosphonates; A review form OncoLink

Source: From University of Pennsylvania OncoLink® at http://www.oncolink.org/types/article.cfm?c=708&id=9629

Julia Draznin Maltzman, MD and Modified by Lara Bonner Millar, MD
The Abramson Cancer Center of the University of Pennsylvania
Last Modified: December 18, 2014

Introduction

Bone metastases are a common complication of advanced cancer. They are especially prevalent (up to 70%) in breast and prostate cancer. Bone metastases can cause severe pain, bone fractures, life-threatening electrolyte imbalances, and nerve compression syndromes. The pain and neurologic dysfunction may be difficult to treat and significantly compromises the patients’ quality of life. Bone metastases usually signify advanced, often incurable disease.

Osteolytic vs. osteoblastic

Bony metastases are characterized as being either osteolytic or osteoblastic. Osteolytic means that the tumor caused bone break down or dissolution. This usually results in loss of calcium from bone. On X-rays these are seen as holes called “lucencies” within the bone. Diffuse osteolytic lesions are most characteristic of a blood cancer called Multiple Myeloma, however they may be present in patients with many other types of cancer.

Osteoblastic bony lesions, by contrast, are characterized by increased bone production. The tumor somehow signals to the bone to overproduce bone cells and result in rigid, inflexible bone formation. The cancer that typically causes osteoblastic bony lesions is prostate cancer. Most cancers result in either osteolytic or osteoblastic bony changes, but some malignancies can lead to both. Breast cancer patients usually develop osteolytic lesions, although at least 15-20 percent can have osteoblastic pathology.

Why the bone?

The bone is a common site of metastasis for many solid tissue cancers including prostate, breast, lung, kidney, stomach, bladder, uterus, thyroid, colon and rectum. Researchers speculate that this may be due to the high blood flow to the bone and bone marrow. Once cancer cells gain access to the blood vessels, they can travel all over the body and usually go where there is the highest flow of blood. Furthermore, tumor cells themselves secrete adhesive molecules that can bind to the bone marrow and bone matrix. This molecular interaction can cause the tumor to signal for increased bone destruction and enhance tumor growth within the bone. A recent scientific discovery showed that the bone is actually a rich source of growth factors. These growth factors signal cells to divide, grow, and mature. As the cancer attacks the bone, these growth factors are released and serve to further stimulate the tumor cells to grow. This results in a self-generating growth loop.

What are the symptoms of bone metastasis?

It must be recognized that the symptoms of bone metastasis can mimic many other disease conditions. Most people with bony pain do not have bone metastasis. That being noted, the most common symptom of a metastasis to the bone is pain. Another common presentation is a bone fracture without any history of trauma. Fracture is more common in lytic metastases than blastic metastases.

Some people with more advanced disease may come to medical attention because of numbness and tingling sensation in their feet and legs. They may have bowel and bladder dysfunction – either losing continence to urine and/or stool, or severe constipation and urinary retention. Others may complain of leg weakness and difficulty moving their legs against gravity. This would imply that there is tumor impinging on the spinal cord and compromising the nerves. This is considered an emergency called spinal cord compression, and requires immediate medical attention. Another less common presentation of metastatic disease to the bone is high levels of calcium in the body. High calcium can make patients constipated, result in abdominal pain, and at very high levels, can lead to confusion and mental status changes.

Diagnosis of bone metastasis

Once a patient experiences any of the symptoms of bone metastasis, various tests can be done to find the true cause. In some cases bone metastasis can be detected before the symptoms arise. X-rays, bone scans, and MRIs are used to diagnose this complication of cancer. X-rays are especially helpful in finding osteolytic lesions. These often appear as “holes” or dark spots in the bone on the x-ray film. Unfortunately, bone metastases often do not show up on plain x-rays until they are quite advanced. By contrast, a bone scan can detect very early bone metastases. This test is done by injecting the patient with a small amount of radio-tracing material in the vein. Special x-rays are taken sometime after the injection. The radiotracer will preferentially go to the site of disease and will appear as a darker, denser, area on the film. Because this technique is so sensitive, sometimes infections, arthritis, and old fractures can appear as dark spots on the bone scan and may be difficult to differentiate from a true cancer. Bone scans are also used to follow patients with known bone metastasis. Sometimes CT scan images can show if a cancer has spread to the bone. An MRI is most useful when examining nerve roots suspected of being compressed by tumor or bone fragments due to tumor destruction. It is used most often in the setting of spinal cord compromise.

There are no real blood tests that are currently used to diagnose a bone metastasis. There are, however, a number of blood tests that a provider can obtain that may suggest the presence of bone lesions, but the diagnosis rests with the combination of radiographic evidence, clinical picture, and natural history of the malignancy. For example, elevated levels of calcium or an enzyme called alkaline phosphatase can be related to bone metastasis, but these lab tests alone are insufficient to prove their presence.

Treatment

The best treatment for bony metastasis is the treatment of the primary cancer. Therapies may include chemotherapy, hormone therapy, radiation therapy, immunotherapy, or treatment with monoclonal antibodies. Pain is often treated with narcotics and other pain medications, such as non-steroidal anti-inflammatory agents. Physical therapy may be helpful and surgery may have an important role if the cancer resulted in a fracture of the bone.

Bisphosphonates

Bisphosphonates are s category of medications that decrease pain from bone metastasis and may improve overall bone health. Bisphosphonates man-made versions of a naturally occurring compound called pyrophosphate that prevents bone breakdown. They are a class of medications widely used in the treatment and prevention of osteoporosis and certain other bone diseases (such as Paget’s Disease), as well as in the treatment of elevated blood calcium. These drugs suppress bone breakdown by cells called osteoclasts, and, can indirectly stimulate the bone forming cells called osteoblasts. It is for this reason, and for the fact that bisphosphonates are very effective in relieving bone pain associated with metastatic disease, that they have transitioned to the oncology arena. However, treatment of bone metastases is not curative. There is increasing evidence that bisphosphonates can prevent bony complications in some metastatic cancers and may even improve survival in some cancers. Most researchers agree that these drugs are more helpful in osteolytic lesions and less so in osteoblastic metastasis in terms of bone restoration and health, but the bisphosphonates are able to alleviate pain associated with both types of lesions. The appropriate time to start treatment is once a bone metastasis has been identified on imaging.

Bisphosphonates can be given either orally or intravenously. The latter is the preferred route of administration for many oncologists as it is given monthly as a short infusion and does not have the gastrointestinal side effects that the oral bisphosphonates have. There are currently two approved and commonly used IV bisphosphonates –Pamidronate disodium (Aredia, Novartis) and zolendronic acid (Zometa, Novartis). Their side effect profile is fairly mild and includes a flu-like reaction during the first 48 hours after the infusion, kidney impairment and osteonecrosis of the jaw with long term use. Patients with renal impairment may not be candidates for this therapy.

Bisphophonates may have some level of anti-tumor activity in breast cancer. A recent Phase III clinical trial revealed that the addition of Zometa to endocrine therapy, improves disease-free survival, but not overall survival, in pre-menopausal patients with estrogen-receptor postive early breast cancer. Another trial called AZURE found no effect from the bisphosphonate zolendronic acid (Zometa, Novartis) on the recurrence of breast cancer or on overall survival. However, several other studies on bisphosphonates and breast cancer are ongoing, and for now, their use is not recommended in patients without metastases.

In addition to bisphosphonates, osteoclast inhibition can also be achieved through other means. Another medication, Denosumab (XGEVA, Amgen), targets a receptor called receptor activator of nuclear factor kappa B ligand (RANKL), is able to block osteoclast formation. A few studies comparing Denosumab to bisphosphonates have found Denosumab results in a longer time to skeletal events, on the order of a few months, compared to bisphosphonates, however many experts believe that the evidence is not strong enough to support one class of drug over another. The most common side effects of Denosumab are fatigue or asthenia, hypophosphatemia, hypocalcemia and nausea. Patients receiving bisphosphonates or denosumab should also be taking calcium and vitamin D supplementation.

The future

Skeletal metastases remain one of the more debilitating problems for cancer patients. Research is ongoing to identify the molecular mechanisms that result in both osteolytic and osteoblastic bone lesions. Perhaps the use of proteomics and gene array data may permit us to identify some factors specific to the tumor or to the bony lesion itself that could be used as therapeutic targets to teat or even prevent this complication.

In summary

  •  there is well established evidence in preclinical models that bisphosphonates:reduce the total tumor burden in bone
  • it is unclear as to the mechanisms of this preclinical finding as bisphosphonates have been shown to directly have antitumor activity
  • as the review by Holen I1, Coleman RE.show “Bisphosphonates as treatment of bone metastases” (abstract given below) there is conflicting clinical evidence of this effect found in preclinical models

Accelerated bone loss is a common clinical feature of advanced breast cancer, and anti-resorptive bisphosphonates are the current standard therapy used to reduce the number and frequency of skeletal-related complications experienced by patients. Bisphosphonates are potent inhibitors of bone resorption, acting by inducing osteoclast apoptosis and thereby preventing the development of cancer-induced bone lesions. In clinical use bisphosphonates are mainly considered to be bone-specific agents, but anti-tumour effects have been reported in a number of in vitro and in vivo studies. By combining bisphosphonates with chemotherapy agents, growth and progression of breast cancer bone metastases can be virtually eliminated in model systems. Recent clinical trials have indicated that there may be additional benefits from bisphosphonate treatment, including positive effects on recurrence and survival when added to standard endocrine therapy. Whereas the ability of bisphosphonates to reduce cancer-induced bone disease is well established, their potential direct anti-tumour effect remain controversial. Ongoing clinical trials will establish whether bisphosphonates can inhibit the development of bone metastases in high-risk breast cancer patients. This review summarizes the main studies that have investigated the effects of bisphosphonates, alone and in combination with other anti-cancer agents, using in vivo model systems of breast cancer bone metastases. We also give an overview of the use of bisphosphonates in the treatment of breast cancer, including examples of key clinical trials. The potential side effects and future clinical applications of bisphosphonates will be outlined.

References

  1. Bower M, Cox S. Endocrine and metabolic complications of advanced cancer. In: Doyle D, Hanks G, Cherny NI, Calman K, editors. Oxford textbook of palliative medicine. 3rd ed. New York, NY: Oxford University Press; 2004. p. 688-90.

Henry DH, Costa L, Goldwasser F, et al. Randomized, double-blind study of denosumab versus zoledronic acid in the treatment of bone metastases in patients with advanced cancer (excluding breast and prostate cancer) or multiple myeloma. J Clin Oncol. 2011;29(9):1125-32.

Van Poznak CH, Temin S, Yee GC, et al. American Society of Clinical Oncology executive summary of the clinical practice guideline update on the role of bone-modifying agents in metastatic breast cancer. J Clin Oncol. 2011;29(9):1221-7.

West, H. Denosumab for prevention of skeletal-related events in patients with bone metastases from solid tumors: incremental benefit, debatable value. J Clin Oncol. 2011;29(9):1095-8.

Gnant M, Mlineritsch B, Schippinger W et al.: Endocrine therapy plus zoledronic acid in premenopausal breast cancer. N Engl J Med. 360(7),679–691 (2009).

Treatment Guidelines by Cancer Organizations

ASCO Issues Updated Guideline on the Role of Bone-Modifying Agents in the Prevention and Treatment of Bone Metastases in Patients with Metastatic Breast Cancer

For Immediate Release

February 22, 2011

Contact:

Steven Benowitz
571-483-1370
steven.benowitz@asco.org

ALEXANDRIA, Va. – The American Society of Clinical Oncology (ASCO) today issued an update to its clinical practice guideline on the use of bone-modifying agents, in particular, osteoclast inhibitors, to prevent and treat skeletal complications from bone metastases in patients with metastatic breast cancer. The new guideline includes recommendations on the use of a new drug option, denosumab (Xgeva), and addresses osteonecrosis of the jaw, an uncommon condition that may occur in association with bone-modifying agents. The updated guideline also provides new recommendations on monitoring of patients who undergo treatment with bone-modifying agents and highlights priorities for future research on these drugs.

ASCO’s Bisphosphonates in Breast Cancer Panel conducted a systematic review of the medical literature to develop the new recommendations. The updated guideline, American Society of Clinical Oncology Clinical Practice Guideline Update on the Role of Bone-Modifying Agents in Metastatic Breast Cancer, was published online today in the Journal of Clinical Oncology.

The guideline recommends that patients with breast cancer who have evidence of bone metastases be given one of three agents – denosumab, pamidronate or zoledronic acid – approved by the U.S. Food and Drug Administration. It does not support use of any one drug over the others. These drugs are all considered osteoclast inhibitors, but they belong to different drug families: pamidronate and zoledronic acid are part of a class of drugs called bisphosphonates, while denosumab is a monoclonal antibody that targets receptor activator of nuclear factor-kappa beta ligand (RANKL).

The guideline also recommends against initiating bone-modifying agents in the absence of bone metastases outside of a clinical trial. It notes that an abnormal bone scan result alone, without confirmation by a radiograph, CT or MRI scan, is not sufficient evidence to support treatment with these drugs.

“The updated recommendations take into account recent progress in controlling potential bone damage in metastatic breast cancer,” said Catherine Van Poznak, MD, co-chair of the Bisphosphonates in Breast Cancer Panel and assistant professor of medicine at the University of Michigan. “We’ve established that a growing number of osteoclast inhibitors can have a positive effect and decrease of the risk of skeletal-related events in women with bone metastases. Because many factors – including medical and economic – must be considered when selecting a therapy for an individual, it’s good to have several effective choices.”

Bone is one of the most common sites to which breast cancer spreads. Bone metastases occur in approximately 70 percent of patients with metastatic disease. These metastases can cause bone cells (osteoclasts) to become overactive, which can result in excessive bone loss, disrupting the bone architecture and causing skeletal-related events (SREs), such as fracture, the need for surgery or radiation therapy to bone, spinal cord compression and hypercalcemia of malignancy.

This document updates guideline recommendations that were first issued in 2000 and revised in 2003, and focused on the use of bisphosphonates. The current guideline uses the more inclusive term, bone-modifying agents, to reflect a wider category of therapeutic agents such as monoclonal antibodies that use different mechanisms of action to prevent and treat damage from bone metastases. The guideline notes that research remains to be conducted to address several areas where questions remain.

“The guideline considers new data in a variety of areas, including studies showing that denosumab has equivalent effectiveness compared with other currently available drug therapies,” explained bisphosphonates panel co-chair Jamie Von Roenn, MD, professor of medicine at Northwestern University. “The guideline also provides guidance on preventing a rare, but significant complication of therapy with bone-modifying agents, osteonecrosis of the jaw.”

Denosumab is a human monoclonal antibody that targets a receptor, RANKL, involved in the regulation of bone remodeling. The guideline cites evidence from a randomized Phase III trial showing that denosumab appears to be comparable to zoledronic acid in reducing the risk of SREs in women with bone metastases from breast cancer. Denosumab is given subcutaneously, and can have side effects such as hypocalcemia.

The guideline also addresses the recently discovered osteonecrosis of the jaw. The first reports of this degenerative condition were published in the medical and dental literature in 2003. The committee recommended that all patients with breast cancer get dental evaluations and receive preventive dentistry care before beginning treatment with bone-modifying osteoclast inhibitors.

The panel updated its recommendations regarding the effects of bisphosphonates on kidney function, particularly for those taking either pamidronate or zoledronic acid, which have been associated with deteriorating kidney function. It said that clinicians should monitor serum creatinine clearance prior to each dose of pamidronate or zoledronic acid according to FDA-approved labeling.

The panel did not recommend using biochemical markers to monitor bone-modifying agent effectiveness and use outside of a clinical trial.

While many of the 2003 recommendations remain the same, the guideline notes several research directions to be addressed, including:

  • Duration of therapy with bone modifying agents, and the timing or intervals between delivery.
  • The development of a risk index for SREs, and better ways to stratify patient risk of SRE or risk of toxicity from a bone-modifying agent. Individual risk may guide selection of timing for use of a bone-modifying agent therapy.
  • Trials specifically examining whether stage IV breast cancer patients who do not have evidence of bone metastases would benefit from bone-modifying agents.
  • The role of biomarkers in treatment selection and monitoring drug effectiveness.
  • Understanding the optimal dosing of calcium and vitamin D supplementation in patients treated with bone-modifying agents.

The meta-analysis from the Early Breast Cancer Trialists’ Collaborative Group (EBCTCG) was published in Lancet and suggested that “Adjuvant bisphosphonates reduce the rate of breast cancer recurrence in the bone and improve breast cancer survival, but there is definite benefit only in women who were postmenopausal when treatment began”.

Results

  • Of 18, 206 women in trials of 2-5 years of bisphosphonate3453 first recurrences, and 2106 subsequent deaths.
  • Overall, the reductions in recurrence (RR 0·94, 95% CI 0·87-1·01; 2p=0·08), distant recurrence (0·92, 0·85-0·99; 2p=0·03), and breast cancer mortality (0·91, 0·83-0·99; 2p=0·04) were of only borderline significance
  • Among premenopausal women, treatment had no apparent effect on any outcome, but among 11 767 postmenopausal women it produced highly significant reductions in recurrence (RR 0·86, 95% CI 0·78-0·94; 2p=0·002), distant recurrence (0·82, 0·74-0·92; 2p=0·0003), bone recurrence (0·72, 0·60-0·86; 2p=0·0002), and breast cancer mortality (0·82, 0·73-0·93; 2p=0·002). “This was iregardless of age or bisphosphonate type.

Lancet. 2015 Jul 23. pii: S0140-6736(15)60908-4. doi: 10.1016/S0140-6736(15)60908-4. Adjuvant bisphosphonate treatment in early breast cancer: meta-analyses of individual patient data from randomised trials.

Early Breast Cancer Trialists’ Collaborative Group (EBCTCG).

This Study was reported at the 36th Annual San Antonio Breast Cancer Symposium (SABCS): Abstract S4-07. Presented December 12, 2013 and Medscape Medical News journalist Kate Johnson covered the finding with author interviews in the following article:

Bisphosphonates: ‘New Addition’ to Breast Cancer Treatment?

Kate Johnson

December 13, 2013

Editors’ Recommendations

SAN ANTONIO — Adjuvant bisphosphonate treatment significantly improves breast cancer survival and reduces bone recurrence in postmenopausal women with early breast cancer, according to a meta-analysis reported here at the 36th Annual San Antonio Breast Cancer Symposium.

“We have finally defined a new addition to standard treatment,” announced lead investigator Robert Coleman, MD, professor of oncology at the University of Sheffield in the United Kingdom. He emphasized that, as hypothesized, the benefits of this therapy were confined to postmenopausal women.

“There is absolutely no effect on mortality in premenopausal women, with a hazard ratio [HR] of 1.0,” he reported. “But for postmenopausal women, we see a 17% reduction in the risk of death [HR, 0.83], which is highly statistically significant.”

In terms of the absolute benefit, bisphosphonates decreased the breast cancer mortality rate from 18.3% to 15.2% in postmenopausal women (P = .004).

The separation of benefit by menopausal status was also seen in the bone recurrence data.

In premenopausal women, there is no significant effect on bone recurrence (HR, 0.93), whereas in postmenopausal women, there was a 34% reduction. The difference was “highly significant,” said Dr. Coleman.

“I personally believe adjuvant bisphosphonates should be standard treatment in postmenopausal women with breast cancer,” said Michael Gnant, MD, professor of surgery at the Medical University of Vienna, who was one of the study investigators. He spoke during a plenary session before the results were formally announced. (Please click this LINK to See VIDEO Interview with Dr. Gnant)

“This is an important analysis,” said Rowan Chlebowski, MD, PhD, medical oncologist from the Harbor-UCLA Medical Center in Los Angeles.

“There will be a substantial increase in the use of bisphosphonates,” he told Medscape Medical News after the presentation.

“The only question is whether people will accept this analysis as the final word.” Dr. Chlebowski explained that some people might criticize the study as being a post hoc analysis of previous findings.

“You might find some mixed feelings about whether this should be accepted, but I think this will get people thinking,” he said. Dr. Chlebowski previously reported a large observational study that demonstrated that postmenopausal women taking oral bisphosphonates for osteoporosis had a significantly lower risk for breast cancer.

Bisphosphonates were originally indicated for the treatment of osteoporosis, and include agents such as alendronate (Fosamax, Merck), ibandronate (Boniva, Genentech), risedronate (Actonel, sanofi-aventis), and zoledronic acid (Reclast, Novartis). But they are also indicated for bone-related use in breast cancer patients, Dr. Chlebowski pointed out.

Because bisphosphonates “also have an indication for preventing bone loss associated with aromatase inhibitor use, they are already approved in this setting, and would prevent recurrences. It will be interesting to see if guideline panels” like these findings, he noted.

Why Postmenopausal Women Benefit

In the plenary session, Dr. Gnant acknowledged that the data on bisphosphonates to date have been mixed.

There are “many trials showing controversial results” for bisphosphonates in the context of breast cancer, he said. “When we put them all together in an unselected population, some show beneficial effects and some do not.”

Dr. Gnant explained why bisphosphonates appear to be effective in older but not younger women. “When you confine your analysis to the low-estrogen environment, postmenopausal women, or women rendered menopausal by ovarian function suppression, we see that all these trials show a consistent benefit for these patients,” he said.

“Essentially, this low-estrogen hypothesis as a prerequisite for adjuvant bisphosphonate activity means that we believe these treatments can silence the bone marrow microenvironment. However, this only translates to relevant clinical benefits in low-estrogen environments,” he added.

More Study Details

The meta-analysis involved 36 trials of adjuvant bisphosphonates in breast cancer with 17,791 pre- and postmenopausal women.

The primary outcomes of the study were time to distant recurrence, local recurrence, and new second primary breast cancer (ipsilateral or contralateral), time to first distant recurrence (ignoring any previous locoregional or contralateral recurrences), and breast cancer mortality.

Planned subgroup analyses based on hypotheses generated from previous findings included site of recurrence, site of first distant metastasis, menopausal status, and type and schedule of bisphosphonate therapy, said Dr. Coleman.

With bisphosphonate therapy, there was a nonsignificant 1% reduction in breast cancer recurrence at 10 years in postmenopausal women, compared with premenopausal women (25.4% vs 26.5%), and “a small borderline advantage” for distant recurrence (20.9% vs 22.3%), he reported.

However, there was a significant benefit of bisphosphonates in bone recurrence in postmenopausal women (6.9% vs 8.4%; P = .0009), with no effect on nonbone recurrence.

There was no impact of bisphosphonates on local recurrence or cancer in the contralateral breast.

For distant recurrence, there was a 3.5% absolute benefit in postmenopausal women (18.4% vs 21.9%; P = .0003); for distant recurrence, there is was a significant improvement of 2.9% in bone recurrence (5.9% vs 8.8%; P < .00001).

There was no significant reduction in first distant recurrence outside bone, and risk reductions were similar, irrespective of estrogen-receptor status, node status, or use or not of chemotherapy.

“Adjuvant bisphosphonates reduce bone metastases and improve survival in postmenopausal women,” concluded Dr. Coleman. “We have statistical security in this result, with a 34% reduction in the risk of bone recurrence (P = .00001), and a 17% — or 1 in 6 — reduction in the risk of breast cancer death (P =.004).”

The analysis struck a clear line between pre- and postmenopausal women — something that was revealed in a subgroup analysis the AZURE trial, which Dr. Coleman was involved in (N Engl J Med. 2011;365:1396-1405).

Because of this, he was asked about the validity of basing the current analysis on the AZURE hypothesis-generating population.

“We repeated the analysis without the AZURE patients, because they are the hypothesis-generating population, and the P values and risk reductions did not change,” he explained.

Source: Medscape Medical News at http://www.medscape.com/viewarticle/817787#vp_1

Updated on 10/20/2015: Other articles for reference on Bisphosphonates and Metastasis

Clin Exp Metastasis. 2015 Oct;32(7):689-702. doi: 10.1007/s10585-015-9737-y. Epub 2015 Aug 1.

Human breast cancer bone metastasis in vitro and in vivo: a novel 3D model system for studies of tumour cell-bone cell interactions.

Author information

  • 1Academic Unit of Clinical Oncology, Department of Oncology, Mellanby Centre for Bone Research, Medical School, University of Sheffield, Sheffield, S10 2RX, UK.
  • 2Department of Human Metabolism, Mellanby Centre for Bone Research, Medical School, University of Sheffield, Sheffield, S10 2RX, UK.
  • 3Academic Unit of Clinical Oncology, Department of Oncology, Mellanby Centre for Bone Research, Medical School, University of Sheffield, Sheffield, S10 2RX, UK. p.d.ottewell@sheffield.ac.uk.

Abstract

Bone is established as the preferred site of breast cancer metastasis. However, the precise mechanisms responsible for this preference remain unidentified. In order to improve outcome for patients with advanced breast cancer and skeletal involvement, we need to better understand how this process is initiated and regulated. As bone metastasis cannot be easily studied in patients, researchers have to date mainly relied on in vivo xenograft models. A major limitation of these is that they do not contain a human bone microenvironment, increasingly considered to be an important component of metastases. In order to address this shortcoming, we have developed a novel humanised bone model, where 1 × 10(5) luciferase-expressing MDA-MB-231 or T47D human breast tumour cells are seeded on viable human subchaodral bone discs in vitro. These discs contain functional osteoclasts 2-weeks after in vitro culture and positive staining for calcine 1-week after culture demonstrating active bone resorption/formation. In vitro inoculation of MDA-MB-231 or T47D cells colonised human bone cores and remained viable for <4 weeks, however, use of matrigel to enhance adhesion or a moving platform to increase diffusion of nutrients provided no additional advantage. Following colonisation by the tumour cells, bone discs pre-seeded with MDA-MB-231 cells were implanted subcutaneously into NOD SCID mice, and tumour growth monitored using in vivo imaging for up to 6 weeks. Tumour growth progressed in human bone discs in 80 % of the animals mimicking the later stages of human bone metastasis. Immunohistochemical and PCR analysis revealed that growing MDA-MB-231 cells in human bone resulted in these cells acquiring a molecular phenotype previously associated with breast cancer bone metastases. MDA-MB-231 cells grown in human bone discs showed increased expression of IL-1B, HRAS and MMP9 and decreased expression of S100A4, whereas, DKK2 and FN1 were unaltered compared with the same cells grown in mammary fat pads of mice not implanted with human bone discs.

Cancer. 2000 Jun 15;88(12 Suppl):2979-88.

Actions of bisphosphonate on bone metastasis in animal models of breast carcinoma.

Abstract

BACKGROUND:

Bone, which abundantly stores a variety of growth factors, provides a fertile soil for cancer cells to develop metastases by supplying these growth factors as a consequence of osteoclastic bone resorption. Accordingly, suppression of osteoclast activity is a primary approach to inhibit bone metastasis, and bisphosphonate (BP), a specific inhibitor of osteoclasts, has been widely used for the treatment of bone metastases in cancer patients. To obtain further insights into the therapeutic usefulness of BP, the authors studied the effects of BP on bone and visceral metastases in animal models of metastasis.

METHODS:

The authors used two animal models of breast carcinoma metastasis that they had developed in their laboratory over the last several years. One model uses female young nude mice in which inoculation of the MDA-MB-231 or MCF-7 human breast carcinoma cells into the left cardiac ventricle selectively develops osteolytic or osteosclerotic bone metastases, respectively. Another model uses syngeneic female mice (Balb/c) in which orthotopic inoculation of the 4T1 murine mammary carcinoma cells develops metastases in bone and visceral organs including lung, liver, and kidney.

RESULTS:

BP inhibited the development and progression of osteolytic bone metastases of MDA-MB-231 breast carcinoma through increased apoptosis in osteoclasts and breast carcinoma cells colonized in bone. In a preventative administration, however, BP alone increased the metastases to visceral organs with profound inhibition of bone metastases. However, combination of BP with anticancer agents such as uracil and tegafur or doxorubicin suppressed the metastases not only in bone but also visceral organs and prolonged the survival in 4T1 mammary tumor-bearing animals. Of interest, inhibition of early osteolysis by BP inhibited the subsequent development of osteosclerotic bone metastases of MCF-7 breast carcinoma.

CONCLUSIONS:

These results suggest that BP has beneficial effects on bone metastasis of breast carcinoma and is more effective when combined with anticancer agents. They also suggest that the animal models of bone metastasis described here allow us to design optimized regimen of BP administration for the treatment of breast carcinoma patients with bone and visceral metastases.

Other posts related to Pain, Cancer, Bone Metabolism and Palliative Care on this Open Access Journal Include

Palliative Care_4.6

Requiem for Palliative Cardiology: The Voice of Dr. Esselstyn on Plant-Based Nutrition

Cancer and Nutrition

Thyme Oil Beats Ibuprofen for Pain Management.

Pain Management Drug Market: Insight Pharma Reports

New target for chronic pain treatment found

The Genetics of Pain: An Integrated Approach

Parathyroids and Bone Metabolism

Nitric Oxide in bone metabolism

Summary and Perspectives: Impairments in Pathological States: Endocrine Disorders, Stress Hypermetabolism and Cancer

Bone regeneration and nanotechnology

Osteocytes: A Special Issue in Bone

Bone remodelling in a nutshell

Read Full Post »

Cancer Biology and Genomics for Disease Diagnosis (Vol. I) Now Available for Amazon Kindle

Cancer Biology and Genomics for Disease Diagnosis (Vol. I) Now Available for Amazon Kindle

Reporter: Stephen J Williams, PhD

Article ID #179: Cancer Biology and Genomics for Disease Diagnosis (Vol. I) Now Available for Amazon Kindle. Published on 8/14/2015

WordCloud Image Produced by Adam Tubman

Leaders in Pharmaceutical Business Intelligence would like to announce the First volume of their BioMedical E-Book Series C: e-Books on Cancer & Oncology

Volume One: Cancer Biology and Genomics for Disease Diagnosis

CancerandOncologyseriesCcoverwhich is now available on Amazon Kindle at                          http://www.amazon.com/dp/B013RVYR2K.

This e-Book is a comprehensive review of recent Original Research on Cancer & Genomics including related opportunities for Targeted Therapy written by Experts, Authors, Writers. This ebook highlights some of the recent trends and discoveries in cancer research and cancer treatment, with particular attention how new technological and informatics advancements have ushered in paradigm shifts in how we think about, diagnose, and treat cancer. The results of Original Research are gaining value added for the e-Reader by the Methodology of Curation. The e-Book’s articles have been published on the Open Access Online Scientific Journal, since April 2012.  All new articles on this subject, will continue to be incorporated, as published with periodical updates.

We invite e-Readers to write an Article Reviews on Amazon for this e-Book on Amazon. All forthcoming BioMed e-Book Titles can be viewed at:

http://pharmaceuticalintelligence.com/biomed-e-books/

Leaders in Pharmaceutical Business Intelligence, launched in April 2012 an Open Access Online Scientific Journal is a scientific, medical and business multi expert authoring environment in several domains of  life sciences, pharmaceutical, healthcare & medicine industries. The venture operates as an online scientific intellectual exchange at their website http://pharmaceuticalintelligence.com and for curation and reporting on frontiers in biomedical, biological sciences, healthcare economics, pharmacology, pharmaceuticals & medicine. In addition the venture publishes a Medical E-book Series available on Amazon’s Kindle platform.

Analyzing and sharing the vast and rapidly expanding volume of scientific knowledge has never been so crucial to innovation in the medical field. WE are addressing need of overcoming this scientific information overload by:

  • delivering curation and summary interpretations of latest findings and innovations
  • on an open-access, Web 2.0 platform with future goals of providing primarily concept-driven search in the near future
  • providing a social platform for scientists and clinicians to enter into discussion using social media
  • compiling recent discoveries and issues in yearly-updated Medical E-book Series on Amazon’s mobile Kindle platform

This curation offers better organization and visibility to the critical information useful for the next innovations in academic, clinical, and industrial research by providing these hybrid networks.

Table of Contents for Cancer Biology and Genomics for Disease Diagnosis

Preface

Introduction  The evolution of cancer therapy and cancer research: How we got here?

Part I. Historical Perspective of Cancer Demographics, Etiology, and Progress in Research

Chapter 1:  The Occurrence of Cancer in World Populations

Chapter 2.  Rapid Scientific Advances Changes Our View on How Cancer Forms

Chapter 3:  A Genetic Basis and Genetic Complexity of Cancer Emerge

Chapter 4: How Epigenetic and Metabolic Factors Affect Tumor Growth

Chapter 5: Advances in Breast and Gastrointestinal Cancer Research Supports Hope for Cure

Part II. Advent of Translational Medicine, “omics”, and Personalized Medicine Ushers in New Paradigms in Cancer Treatment and Advances in Drug Development

Chapter 6:  Treatment Strategies

Chapter 7:  Personalized Medicine and Targeted Therapy

Part III.Translational Medicine, Genomics, and New Technologies Converge to Improve Early Detection

Chapter 8:  Diagnosis                                     

Chapter 9:  Detection

Chapter 10:  Biomarkers

Chapter 11:  Imaging In Cancer

Chapter 12: Nanotechnology Imparts New Advances in Cancer Treatment, Detection, &  Imaging                                 

Epilogue by Larry H. Bernstein, MD, FACP: Envisioning New Insights in Cancer Translational Biology

 

Read Full Post »

Ablation Techniques in Interventional Oncology

Author and Curator: Dror Nir, PhD

“Ablation is removal of material from the surface of an object by vaporization, chipping, or other erosive processes.”; WikipediA.

The use of ablative techniques in medicine is known for decades. By the late 90s, the ability to manipulate ablation sources and control their application to area of interest improved to a level that triggered their adaptation to cancer treatment. To date, ablation  is still a controversial treatment, yet steadily growing in it’s offerings to very specific cancer patients’ population.

The attractiveness in ablation as a form of cancer treatment is in the promise of minimal invasiveness, focused tissue destruction and better quality of life due to the ability to partially maintain viability of affected organs.  The main challenges preventing wider adaptation of ablative treatments are: the inability to noninvasively assess the level of cancerous tissue destruction during treatment; resulting in metastatic recurrence of the disease and the insufficient isolation of the treatment area from its surrounding.   This frequently results In addition, post-ablation salvage treatments are much more complicated. Since failed ablative treatment represents a lost opportunity to apply effective treatment to the primary tumor the current trend is to apply such treatments to low-grade cancers.

Nevertheless, the attractiveness of treating cancer in a focused way that preserves the long-term quality of life continuously feeds the development efforts and investments related to introduction of new and improved ablative treatments giving the hope that sometime in the future focused ablative treatment will reach its full potential.

The following paper reviews the main ablation techniques that are available for use today: Percutaneous image-guided ablation of bone and soft tissue tumours: a review of available techniques and protective measures.

Abstract

Background

Primary or metastatic osseous and soft tissue lesions can be treated by ablation techniques.

Methods

These techniques are classified into chemical ablation (including ethanol or acetic acid injection) and thermal ablation (including laser, radiofrequency, microwave, cryoablation, radiofrequency ionisation and MR-guided HIFU). Ablation can be performed either alone or in combination with surgical or other percutaneous techniques.

Results

In most cases, ablation provides curative treatment for benign lesions and malignant lesions up to 3 cm. Furthermore, it can be a palliative treatment providing pain reduction and local control of the disease, diminishing the tumor burden and mass effect on organs. Ablation may result in bone weakening; therefore, whenever stabilization is undermined, bone augmentation should follow ablation depending on the lesion size and location.

Conclusion

Thermal ablation of bone and soft tissues demonstrates high success and relatively low complication rates. However, the most common complication is the iatrogenic thermal damage of surrounding sensitive structures. Nervous structures are very sensitive to extremely high and low temperatures with resultant transient or permanent neurological damage. Thermal damage can cause normal bone osteonecrosis in the lesion’s periphery, surrounding muscular atrophy and scarring, and skin burns. Successful thermal ablation requires a sufficient ablation volume and thermal protection of the surrounding vulnerable structures.

Teaching points

Percutaneous ablations constitute a safe and efficacious therapy for treatment of osteoid osteoma.

Ablation techniques can treat painful malignant MSK lesions and provide local tumor control.

Thermal ablation of bone and soft tissues demonstrates high success and low complication rates.

Nerves, cartilage and skin are sensitive to extremely high and low temperatures.

Successful thermal ablation occasionally requires thermal protection of the surrounding structures.

For the purpose of this chapter we picked up three techniques:

Radiofrequency ablation

Straight or expandable percutaneously placed electrodes deliver a high-frequency alternating current, which causes ionic agitation with resultant frictional heat (temperatures of 60–100 ˚C) that produces protein denaturation and coagulation necrosis [8]. Concerning active protective techniques, all kinds of gas dissection can be performed. Hydrodissection is performed with dextrose 5 % (acts as an insulator as opposed to normal saline, which acts as a conductor). All kinds of skin cooling, thermal and neural monitoring can be performed.

 

Microwave ablation

Straight percutaneously placed antennae deliver electromagnetic microwaves (915 or 2,450 MHz) with resultant frictional heat (temperatures of 60–100 ˚C) that produces protein denaturation and coagulation necrosis [8]. Concerning active protective techniques, all kinds of gas dissection can be performed, whilst hydrodissection is usually avoided (MWA is based on agitation of water molecules for energy transmission). All kinds of skin cooling, thermal and neural monitoring can be performed.

Percutaneous ablation of malignant metastatic lesions is performed under imaging guidance, extended local sterility measures and antibiotic prophylaxis. Whenever the ablation zone is expected to extend up to 1 cm close to critical structures (e.g. the nerve root, skin, etc.), all the necessary thermal protection techniques should be applied (Fig. 3).

13244_2014_332_Fig3_HTML

a Painful soft tissue mass infiltrating the left T10 posterior rib. b A microwave antenna is percutaneously inserted inside the mass. Due to the proximity to the skin a sterile glove filled with cold water is placed over the skin. c CT axial scan 3 months

Irreversible Electroporation (IRE)

Each cell membrane point has a local transmembrane voltage that determines a dynamic phenomenon called electroporation (reversible or irreversible) [16]. Electroporation is manifested by specific transmembrane voltage thresholds related to a given pulse duration and shape. Thus, a threshold for an electronic field magnitude is defined and only cells with higher electric field magnitudes than this threshold are electroporated. IRE produces persistent nano-sized membrane pores compromising the viability of cells [16]. On the other hand, collagen and other supporting structures remain unaffected. The IRE generator produces direct current (25–45 A) electric pulses of high voltage (1,500–3,000 V).

Lastly we wish to highlight a method that is mostly used on patients diagnosed at intermediate or advanced clinical stages of Hepatocellular Carcinoma (HCC); transarterial chemoembolization  (TACE)

“Transcatheter arterial chemoembolization (also called transarterial chemoembolization or TACE) is a minimally invasive procedure performed in interventional radiology  to restrict a tumor’s blood supply. Small embolic particles coated with chemotherapeutic agents are injected selectively into an artery directly supplying a tumor. TACE derives its beneficial effect by two primary mechanisms. Most tumors within the liver are supplied by the proper hepatic artery, so arterial embolization preferentially interrupts the tumor’s blood supply and stalls growth until neovascularization. Secondly, focused administration of chemotherapy allows for delivery of a higher dose to the tissue while simultaneously reducing systemic exposure, which is typically the dose limiting factor. This effect is potentiated by the fact that the chemotherapeutic drug is not washed out from the tumor vascular bed by blood flow after embolization. Effectively, this results in a higher concentration of drug to be in contact with the tumor for a longer period of time. Park et al. conceptualized carcinogenesis of HCC as a multistep process involving parenchymal arterialization, sinusoidal capillarization, and development of unpaired arteries (a vital component of tumor angiogenesis). All these events lead to a gradual shift in tumor blood supply from portal to arterial circulation. This concept has been validated using dynamic imaging modalities by various investigators. Sigurdson et al. demonstrated that when an agent was infused via the hepatic artery, intratumoral concentrations were ten times greater compared to when agents were administered through the portal vein. Hence, arterial treatment targets the tumor while normal liver is relatively spared. Embolization induces ischemic necrosis of tumor causing a failure of the transmembrane pump, resulting in a greater absorption of agents by the tumor cells. Tissue concentration of agents within the tumor is greater than 40 times that of the surrounding normal liver.”; WikipediA

A recent open access research paper: Conventional transarterial chemoembolization versus drug-eluting bead transarterial chemoembolization for the treatment of hepatocellular carcinoma is discussing recent clinical approaches  related to this techniques.

Abstract

Background

To compare the overall survival of patients with hepatocellular carcinoma (HCC) who were treated with lipiodol-based conventional transarterial chemoembolization (cTACE) with that of patients treated with drug-eluting bead transarterial chemoembolization (DEB-TACE).

Methods

By an electronic search of our radiology information system, we identified 674 patients that received TACE between November 2002 and July 2013. A total of 520 patients received cTACE, and 154 received DEB-TACE. In total, 424 patients were excluded for the following reasons: tumor type other than HCC (n = 91), liver transplantation after TACE (n = 119), lack of histological grading (n = 58), incomplete laboratory values (n = 15), other reasons (e.g., previous systemic chemotherapy) (n = 114), or were lost to follow-up (n = 27). Therefore, 250 patients were finally included for comparative analysis (n = 174 cTACE; n = 76 DEB-TACE).

Results

There were no significant differences between the two groups regarding sex, overall status (Barcelona Clinic Liver Cancer classification), liver function (Child-Pugh), portal invasion, tumor load, or tumor grading (all p > 0.05). The mean number of treatment sessions was 4 ± 3.1 in the cTACE group versus 2.9 ± 1.8 in the DEB-TACE group (p = 0.01). Median survival was 409 days (95 % CI: 321–488 days) in the cTACE group, compared with 369 days (95 % CI: 310–589 days) in the DEB-TACE group (p = 0.76). In the subgroup of Child A patients, the survival was 602 days (484–792 days) for cTACE versus 627 days (364–788 days) for DEB-TACE (p = 0.39). In Child B/C patients, the survival was considerably lower: 223 days (165–315 days) for cTACE versus 226 days (114–335 days) for DEB-TACE (p = 0.53).

Conclusion

The present study showed no significant difference in overall survival between cTACE and DEB-TACE in patients with HCC. However, the significantly lower number of treatments needed in the DEB-TACE group makes it a more appealing treatment option than cTACE for appropriately selected patients with unresectable HCC.

Read Full Post »

Imaging Technology in Cancer Surgery

Author and curator: Dror Nir, PhD

The advent of medical-imaging technologies such as image-fusion, functional-imaging and noninvasive tissue characterisation is playing an imperative role in answering this demand thus transforming the concept of personalized medicine in cancer into practice. The leading modality in that respect is medical imaging. To date, the main imaging systems that can provide reasonable level of cancer detection and localization are: CT, mammography, Multi-Sequence MRI, PET/CT and ultrasound. All of these require skilled operators and experienced imaging interpreters in order to deliver what is required at a reasonable level. It is generally agreed by radiologists and oncologists that in order to provide a comprehensive work-flow that complies with the principles of personalized medicine, future cancer patients’ management will heavily rely on computerized image interpretation applications that will extract from images in a standardized manner measurable imaging biomarkers leading to better clinical assessment of cancer patients.

As consequence of the human genome project and technological advances in gene-sequencing, the understanding of cancer advanced considerably. This led to increase in the offering of treatment options. Yet, surgical resection is still the leading form of therapy offered to patients with organ confined tumors. Obtaining “cancer free” surgical margins is crucial to the surgery outcome in terms of overall survival and patients’ quality of life/morbidity. Currently, a significant portion of surgeries ends up with positive surgical margins leading to poor clinical outcome and increase of costs. To improve on this, large variety of intraoperative imaging-devices aimed at resection-guidance have been introduced and adapted in the last decade and it is expected that this trend will continue.

The Status of Contemporary Image-Guided Modalities in Oncologic Surgery is a review paper presenting a variety of cancer imaging techniques that have been adapted or developed for intra-operative surgical guidance. It also covers novel, cancer-specific contrast agents that are in early stage development and demonstrate significant promise to improve real-time detection of sub-clinical cancer in operative setting.

Another good (free access) review paper is: uPAR-targeted multimodal tracer for pre- and intraoperative imaging in cancer surgery

Abstract

Pre- and intraoperative diagnostic techniques facilitating tumor staging are of paramount importance in colorectal cancer surgery. The urokinase receptor (uPAR) plays an important role in the development of cancer, tumor invasion, angiogenesis, and metastasis and over-expression is found in the majority of carcinomas. This study aims to develop the first clinically relevant anti-uPAR antibody-based imaging agent that combines nuclear (111In) and real-time near-infrared (NIR) fluorescent imaging (ZW800-1). Conjugation and binding capacities were investigated and validated in vitro using spectrophotometry and cell-based assays. In vivo, three human colorectal xenograft models were used including an orthotopic peritoneal carcinomatosis model to image small tumors. Nuclear and NIR fluorescent signals showed clear tumor delineation between 24h and 72h post-injection, with highest tumor-to-background ratios of 5.0 ± 1.3 at 72h using fluorescence and 4.2 ± 0.1 at 24h with radioactivity. 1-2 mm sized tumors could be clearly recognized by their fluorescent rim. This study showed the feasibility of an uPAR-recognizing multimodal agent to visualize tumors during image-guided resections using NIR fluorescence, whereas its nuclear component assisted in the pre-operative non-invasive recognition of tumors using SPECT imaging. This strategy can assist in surgical planning and subsequent precision surgery to reduce the number of incomplete resections.

INTRODUCTION
Diagnosis, staging, and surgical planning of colorectal cancer patients increasingly rely on imaging techniques that provide information about tumor biology and anatomical structures [1-3]. Single-photon emission computed tomography (SPECT) and positron emission tomography (PET) are preoperative nuclear imaging modalities used to provide insights into tumor location, tumor biology, and the surrounding micro-environment [4]. Both techniques depend on the recognition of tumor cells using radioactive ligands. Various monoclonal antibodies, initially developed as therapeutic agents (e.g. cetuximab, bevacizumab, labetuzumab), are labeled with radioactive tracers and evaluated for pre-operative imaging purposes [5-9]. Despite these techniques, during surgery the surgeons still rely mostly on their eyes and hands to distinguish healthy from malignant tissues, resulting in incomplete resections or unnecessary tissue removal in up to 27% of rectal cancer patients [10, 11]. Incomplete resections (R1) are shown to be a strong predictor of development of distant metastasis, local recurrence, and decreased survival of colorectal cancer patients [11, 12]. Fluorescence-guided surgery (FGS) is an intraoperative imaging technique already introduced and validated in the clinic for sentinel lymph node (SLN) mapping and biliary imaging [13]. Tumor-specific FGS can be regarded as an extension of SPECT/PET, using fluorophores instead of radioactive labels conjugated to tumor-specific ligands, but with higher spatial resolution than SPECT/PET imaging and real-time anatomical feedback [14]. A powerful synergy can be achieved when nuclear and fluorescent imaging modalities are combined, extending the nuclear diagnostic images with real-time intraoperative imaging. This combination can lead to improved diagnosis and management by integrating pre-intra and postoperative imaging. Nuclear imaging enables pre-operative evaluation of tumor spread while during surgery deeper lying spots can be localized using the gamma probe counter. The (NIR) fluorescent signal aids the surgeon in providing real-time anatomical feedback to accurately recognize and resect malignant tissues. Postoperative, malignant cells can be recognized using NIR fluorescent microscopy. Clinically, the advantages of multimodal agents in image-guided surgery have been shown in patients with melanoma and prostate cancer, but those studies used a-specific agents, following the natural lymph drainage pattern of colloidal tracers after peritumoral injection [15, 16]. The urokinase-type plasminogen activator receptor (uPAR) is implicated in many aspects of tumor growth and (micro) metastasis [17, 18]. The levels of uPAR are undetectable in normal tissues except for occasional macrophages and granulocytes in the uterus, thymus, kidneys and spleen [19]. Enhanced tumor levels of uPAR and its circulating form (suPAR) are independent prognostic markers for overall survival in colorectal cancer patients [20, 21]. The relatively selective and high overexpression of uPAR in a wide range of human cancers including colorectal, breast, and pancreas nominate uPAR as a widely applicable and potent molecular target [17,22]. The current study aims to develop a clinically relevant uPAR-specific multimodal agent that can be used to visualize tumors pre- and intraoperatively after a single injection. We combined the 111Indium isotope with NIR fluorophore ZW800-1 using a hybrid linker to an uPAR specific monoclonal antibody (ATN-658) and evaluated its performance using a pre-clinical SPECT system (U-SPECT-II) and a clinically-applied NIR fluorescence camera system (FLARE™).

Fig1 Fig2 Fig3

Robotic surgery is a growing trend as a form of surgery, specifically in urology. The following review paper propose a good discussion on the added value of imaging in urologic robotic surgery:

The current and future use of imaging in urological robotic surgery: a survey of the European Association of Robotic Urological Surgeons

 Abstract

Background

With the development of novel augmented reality operating platforms the way surgeons utilize imaging as a real-time adjunct to surgical technique is changing.

Methods

A questionnaire was distributed via the European Robotic Urological Society mailing list. The questionnaire had three themes: surgeon demographics, current use of imaging and potential uses of an augmented reality operating environment in robotic urological surgery.

Results

117 of the 239 respondents (48.9%) were independently practicing robotic surgeons. 74% of surgeons reported having imaging available in theater for prostatectomy 97% for robotic partial nephrectomy and 95% cystectomy. 87% felt there was a role for augmented reality as a navigation tool in robotic surgery.

Conclusions

This survey has revealed the contemporary robotic surgeon to be comfortable in the use of imaging for intraoperative planning it also suggests that there is a desire for augmented reality platforms within the urological community. Copyright © 2014 John Wiley & Sons, Ltd.

 Introduction

Since Röntgen first utilized X-rays to image the carpal bones of the human hand in 1895, medical imaging has evolved and is now able to provide a detailed representation of a patient’s intracorporeal anatomy, with recent advances now allowing for 3-dimensional (3D) reconstructions. The visualization of anatomy in 3D has been shown to improve the ability to localize structures when compared with 2D with no change in the amount of cognitive loading [1]. This has allowed imaging to move from a largely diagnostic tool to one that can be used for both diagnosis and operative planning.

One potential interface to display 3D images, to maximize its potential as a tool for surgical guidance, is to overlay them onto the endoscopic operative scene (augmented reality). This addresses, in part, a criticism often leveled at robotic surgery, the loss of haptic feedback. Augmented reality has the potential to mitigate this sensory loss by enhancing the surgeons visual cues with information regarding subsurface anatomical relationships [2].

Augmented reality surgery is in its infancy for intra-abdominal procedures due in large part to the difficulties of applying static preoperative imaging to a constantly deforming intraoperative scene [3]. There are case reports and ex vivo studies in the literature examining the technology in minimal access prostatectomy [3-6] and partial nephrectomy [7-10], but there remains a lack of evidence determining whether surgeons feel there is a role for the technology and if so for what procedures they feel it would be efficacious.

This questionnaire-based study was designed to assess first, the pre- and intra-operative imaging modalities utilized by robotic urologists; second, the current use of imaging intraoperatively for surgical planning; and finally whether there is a desire for augmented reality among the robotic urological community.

Methods

Recruitment

A web based survey instrument was designed and sent out, as part of a larger survey, to members of the EAU robotic urology section (ERUS). Only independently practicing robotic surgeons performing robot-assisted laparoscopic prostatectomy (RALP), robot-assisted partial nephrectomy (RAPN) and/or robotic cystectomy were included in the analysis, those surgeons exclusively performing other procedures were excluded. Respondents were offered no incentives to reply. All data collected was anonymous.

Survey design and administration

The questionnaire was created using the LimeSurvey platform (www.limesurvey.com) and hosted on their website. All responses (both complete and incomplete) were included in the analysis. The questionnaire was dynamic with the questions displayed tailored to the respondents’ previous answers.

When computing fractions or percentages the denominator was the number of respondents to answer the question, this number is variable due to the dynamic nature of the questionnaire.

Demographics

All respondents to the survey were asked in what country they practiced and what robotic urological procedures they performed. In addition to what procedures they performed surgeons were asked to specify the number of cases they had undertaken for each procedure.

 Current imaging practice

Procedure-specific questions in this group were displayed according to the operations the respondent performed. A summary of the questions can be seen in Appendix 1. Procedure-nonspecific questions were also asked. Participants were asked whether they routinely used the Tile Pro™ function of the da Vinci console (Intuitive Surgical, Sunnyvale, USA) and whether they routinely viewed imaging intra-operatively.

 Augmented reality

Before answering questions in this section, participants were invited to watch a video demonstrating an augmented reality platform during RAPN, performed by our group at Imperial College London. A still from this video can be seen in Figure 1. They were then asked whether they felt augmented reality would be of use as a navigation or training tool in robotic surgery.

f1

Figure 1. A still taken from a video of augmented reality robot assisted partial nephrectomy performed. Here the tumour has been painted into the operative view allowing the surgeon to appreciate the relationship of the tumour with the surface of the kidney

Once again, in this section, procedure-specific questions were displayed according to the operations the respondent performed. Only those respondents who felt augmented reality would be of use as a navigation tool were asked procedure-specific questions. Questions were asked to establish where in these procedures they felt an augmented reality environment would be of use.

Results

Demographics

Of the 239 respondents completing the survey 117 were independently practising robotic surgeons and were therefore eligible for analysis. The majority of the surgeons had both trained (210/239, 87.9%) and worked in Europe (215/239, 90%). The median number of cases undertaken by those surgeons reporting their case volume was: 120 (6–2000), 9 (1–120) and 30 (1–270), for RALP, robot assisted cystectomy and RAPN, respectively.

 

Contemporary use of imaging in robotic surgery

When enquiring about the use of imaging for surgical planning, the majority of surgeons (57%, 65/115) routinely viewed pre-operative imaging intra-operatively with only 9% (13/137) routinely capitalizing on the TilePro™ function in the console to display these images. When assessing the use of TilePro™ among surgeons who performed RAPN 13.8% (9/65) reported using the technology routinely.

When assessing the imaging modalities that are available to a surgeon in theater the majority of surgeons performing RALP (74%, 78/106)) reported using MRI with an additional 37% (39/106) reporting the use of CT for pre-operative staging and/or planning. For surgeons performing RAPN and robot-assisted cystectomy there was more of a consensus with 97% (68/70) and 95% (54/57) of surgeons, respectively, using CT for routine preoperative imaging (Table 1).

Table 1. Which preoperative imaging modalities do you use for diagnosis and surgical planning?

  CT MRI USS None Other
RALP (n = 106) 39.8% 73.5% 2% 15.1% 8.4%
(39) (78) (3) (16) (9)
RAPN (n = 70) 97.1% 42.9% 17.1% 0% 2.9%
(68) (30) (12) (0) (2)
Cystectomy (n = 57) 94.7% 26.3% 1.8% 1.8% 5.3%
(54) (15) (1) (1) (3)

Those surgeons performing RAPN were found to have the most diversity in the way they viewed pre-operative images in theater, routinely viewing images in sagittal, coronal and axial slices (Table 2). The majority of these surgeons also viewed the images as 3D reconstructions (54%, 38/70).

Table 2. How do you typically view preoperative imaging in the OR? 3D recons = three-dimensional reconstructions

  Axial slices (n) Coronal slices (n) Sagittal slices (n) 3D recons. (n) Do not view (n)  
RALP (n = 106) 49.1% 44.3% 31.1% 9.4% 31.1%
(52) (47) (33) (10) (33)
RAPN (n = 70) 68.6% 74.3% 60% (42) 54.3% 0%
(48) (52) (38) (0)
Cystectomy (n = 57) 70.2% 52.6% 50.9% 21.1% 8.8%
(40) (30) (29) (12) (5)

The majority of surgeons used ultrasound intra-operatively in RAPN (51%, 35/69) with a further 25% (17/69) reporting they would use it if they had access to a ‘drop-in’ ultrasound probe (Figure 2).

f2

Figure 2. Chart demonstrating responses to the question – Do you use intraoperative ultrasound for robotic partial nephrectomy?

Desire for augmented reality

Overall, 87% of respondents envisaged a role for augmented reality as a navigation tool in robotic surgery and 82% (88/107) felt that there was an additional role for the technology as a training tool.

The greatest desire for augmented reality was among those surgeons performing RAPN with 86% (54/63) feeling the technology would be of use. The largest group of surgeons felt it would be useful in identifying tumour location, with significant numbers also feeling it would be efficacious in tumor resection (Figure 3).

f3

Figure 3. Chart demonstrating responses to the question – In robotic partial nephrectomy which parts of the operation do you feel augmented reality image overlay would be of assistance?

When enquiring about the potential for augmented reality in RALP, 79% (20/96) of respondents felt it would be of use during the procedure, with the largest group feeling it would be helpful for nerve sparing 65% (62/96) (Figure 4). The picture in cystectomy was similar with 74% (37/50) of surgeons believing augmented reality would be of use, with both nerve sparing and apical dissection highlighted as specific examples (40%, 20/50) (Figure 5). The majority also felt that it would be useful for lymph node dissection in both RALP and robot assisted cystectomy (55% (52/95) and 64% (32/50), respectively).

f4

Figure 4. Chart demonstrating responses to the question – In robotic prostatectomy which parts of the operation do you feel augmented reality image overlay would be of assistance?

f5

Figure 5. Chart demonstrating responses to the question – In robotic cystectomy which parts of the operation do you feel augmented reality overlay technology would be of assistance?

Discussion

The results from this study suggest that the contemporary robotic surgeon views imaging as an important adjunct to operative practice. The way these images are being viewed is changing; although the majority of surgeons continue to view images as two-dimensional (2D) slices a significant minority have started to capitalize on 3D reconstructions to give them an improved appreciation of the patient’s anatomy.

This study has highlighted surgeons’ willingness to take the next step in the utilization of imaging in operative planning, augmented reality, with 87% feeling it has a role to play in robotic surgery. Although there appears to be a considerable desire for augmented reality, the technology itself is still in its infancy with the limited evidence demonstrating clinical application reporting only qualitative results [3, 7, 11, 12].

There are a number of significant issues that need to be overcome before augmented reality can be adopted in routine clinical practice. The first of these is registration (the process by which two images are positioned in the same coordinate system such that the locations of corresponding points align [13]). This process has been performed both manually and using automated algorithms with varying degrees of accuracy [2, 14]. The second issue pertains to the use of static pre-operative imaging in a dynamic operative environment; in order for the pre-operative imaging to be accurately registered it must be deformable. This problem remains as yet unresolved.

Live intra-operative imaging circumvents the problems of tissue deformation and in RAPN 51% of surgeons reported already using intra-operative ultrasound to aid in tumour resection. Cheung and colleagues [9] have published an ex vivo study highlighting the potential for intra-operative ultrasound in augmented reality partial nephrectomy. They report the overlaying of ultrasound onto the operative scene to improve the surgeon’s appreciation of the subsurface tumour anatomy, this improvement in anatomical appreciation resulted in improved resection quality over conventional ultrasound guided resection [9]. Building on this work the first in vivo use of overlaid ultrasound in RAPN has recently been reported [10]. Although good subjective feedback was received from the operating surgeon, the study was limited to a single case demonstrating feasibility and as such was not able to show an outcome benefit to the technology [10].

RAPN also appears to be the area in which augmented reality would be most readily adopted with 86% of surgeons claiming they see a use for the technology during the procedure. Within this operation there are two obvious steps to augmentation, anatomical identification (in particular vessel identification to facilitate both routine ‘full clamping’ and for the identification of secondary and tertiary vessels for ‘selective clamping’ [15]) and tumour resection. These two phases have different requirements from an augmented reality platform; the first phase of identification requires a gross overview of the anatomy without the need for high levels of registration accuracy. Tumor resection, however, necessitates almost sub-millimeter accuracy in registration and needs the system to account for the dynamic intra-operative environment. The step of anatomical identification is amenable to the use of non-deformable 3D reconstructions of pre-operative imaging while that of image-guided tumor resection is perhaps better suited to augmentation with live imaging such as ultrasound [2, 9, 16].

For RALP and robot-assisted cystectomy the steps in which surgeons felt augmented reality would be of assistance were those of neurovascular bundle preservation and apical dissection. The relative, perceived, efficacy of augmented reality in these steps correlate with previous examinations of augmented reality in RALP [17, 18]. Although surgeon preference for utilizing augmented reality while undertaking robotic prostatectomy has been demonstrated, Thompson et al. failed to demonstrate an improvement in oncological outcomes in those patients undergoing AR RALP [18].

Both nerve sparing and apical dissection require a high level of registration accuracy and a necessity for either live imaging or the deformation of pre-operative imaging to match the operative scene; achieving this level of registration accuracy is made more difficult by the mobilization of the prostate gland during the operation [17]. These problems are equally applicable to robot-assisted cystectomy. Although guidance systems have been proposed in the literature for RALP [3-5, 12, 17], none have achieved the level of accuracy required to provide assistance during nerve sparing. In addition, there are still imaging challenges that need to be overcome. Although multiparametric MRI has been shown to improve decision making in opting for a nerve sparing approach to RALP [19] the imaging is not yet able to reliably discern the exact location of the neurovascular bundle. This said, significant advances are being made with novel imaging modalities on the horizon that may allow for imaging of the neurovascular bundle in the near future [20].

 

Limitations

The number of operations included represents a significant limitation of the study, had different index procedures been chosen different results may have been seen. This being said the index procedures selected were chosen as they represent the vast majority of uro-oncological robotic surgical practice, largely mitigating for this shortfall.

Although the available ex vivo evidence suggests that introducing augmented reality operating environments into surgical practice would help to improve outcomes [9, 21] the in vivo experience to date is limited to small volume case series reporting feasibility [2, 3, 14]. To date no study has demonstrated an in vivo outcome advantage to augmented reality guidance. In addition to this limitation augmented reality has been demonstrated to increased rates of inattention blindness among surgeons suggesting there is a trade-off between increasing visual information and the surgeon’s ability to appreciate unexpected operative events [21].

 

Conclusions

This survey shows the contemporary robotic surgeon to be comfortable with the use of imaging to aid intra-operative planning; furthermore it highlights a significant interest among the urological community in augmented reality operating platforms.

Short- to medium-term development of augmented reality systems in robotic urology surgery would be best performed using RAPN as the index procedure. Not only was this the operation where surgeons saw the greatest potential benefits, but it may also be the operation where it is most easily achievable by capitalizing on the respective benefits of technologies the surgeons are already using; pre-operative CT for anatomical identification and intra-operative ultrasound for tumour resection.

 

Conflict of interest

None of the authors have any conflicts of interest to declare.

Appendix 1

Question Asked Question Type
Demographics
In which country do you usually practise? Single best answer
Which robotic procedures do you perform?* Single best answer
Current Imaging Practice
What preoperative imaging modalities do you use for the staging and surgical planning in renal cancer? Multiple choice
How do you typically view preoperative imaging in theatre for renal cancer surgery? Multiple choice
Do you use intraoperative ultrasound for partial nephrectomy? Yes or No
What preoperative imaging modalities do you use for the staging and surgical planning in prostate cancer? Multiple choice
How do you typically view preoperative imaging in theatre for prostate cancer? Multiple choice
Do you use intraoperative ultrasound for robotic partial nephrectomy? Yes or No
Which preoperative imaging modality do you use for staging and surgical planning in muscle invasive TCC? Multiple choice
How do you typically view preoperative imaging in theatre for muscle invasive TCC? Multiple choice
Do you routinely refer to preoperative imaging intraoperativley? Yes or No
Do you routinely use Tilepro intraoperativley? Yes or No
Augmented Reality
Do you feel there is a role for augmented reality as a navigation tool in robotic surgery? Yes or No
Do you feel there is a role for augmented reality as a training tool in robotic surgery? Yes or No
In robotic partial nephrectomy which parts of the operation do you feel augmented reality image overlay technology would be of assistance? Multiple choice
In robotic nephrectomy which parts of the operation do you feel augmented reality image overlay technology would be of assistance? Multiple choice
In robotic prostatectomy which parts of the operation do you feel augmented reality image overlay technology would be of assistance? Multiple choice
Would augmented reality guidance be of use in lymph node dissection in robotic prostatectomy? Yes or No
In robotic cystectomy which parts of the operation do you feel augmented reality image overlay technology would be of assistance? Multiple choice
Would augmented reality guidance be of use in lymph node dissection in robotic cystectomy? Yes or No
*The relevant procedure related questions were displayed based on the answer to this question

References

1. Foo J-L, Martinez-Escobar M, Juhnke B, et al.Evaluating mental workload of two-dimensional and three-dimensional visualization for anatomical structure localization. J Laparoendosc Adv Surg Tech A 2013; 23(1):65–70.

2. Hughes-Hallett A, Mayer EK, Marcus HJ, et al.Augmented reality partial nephrectomy: examining the current status and future perspectives. Urology 2014; 83(2): 266–273.

3. Sridhar AN, Hughes-Hallett A, Mayer EK, et al.Image-guided robotic interventions for prostate cancer. Nat Rev Urol 2013; 10(8): 452–462.

4. Cohen D, Mayer E, Chen D, et al.Eddie’ Augmented reality image guidance in minimally invasive prostatectomy. Lect Notes Comput Sci 2010; 6367: 101–110.

5. Simpfendorfer T, Baumhauer M, Muller M, et al.Augmented reality visualization during laparoscopic radical prostatectomy. J Endourol 2011; 25(12): 1841–1845.

6. Teber D, Simpfendorfer T, Guven S, et al.In vitro evaluation of a soft-tissue navigation system for laparoscopic prostatectomy. J Endourol 2010; 24(9): 1487–1491.

7. Teber D, Guven S, Simpfendörfer T, et al.Augmented reality: a new tool to improve surgical accuracy during laparoscopic partial nephrectomy? Preliminary in vitro and in vivo Eur Urol 2009; 56(2): 332–338.

8. Pratt P, Mayer E, Vale J, et al.An effective visualisation and registration system for image-guided robotic partial nephrectomy. J Robot Surg 2012; 6(1): 23–31.

9. Cheung CL, Wedlake C, Moore J, et al.Fused video and ultrasound images for minimally invasive partial nephrectomy: a phantom study. Med Image Comput Comput Assist Interv 2010; 13(Pt 3): 408–415.

10. Hughes-Hallett A, Pratt P, Mayer E, et al.Intraoperative ultrasound overlay in robot-assisted partial nephrectomy: first clinical experience. Eur Urol 2014; 65(3): 671–672.

11. Nakamura K, Naya Y, Zenbutsu S, et al.Surgical navigation using three-dimensional computed tomography images fused intraoperatively with live video. J Endourol 2010; 24(4): 521–524.

12. Ukimura O, Gill IS. Imaging-assisted endoscopic surgery: Cleveland clinic experience. J Endourol2008; 22(4):803–809.

13. Altamar HO, Ong RE, Glisson CL, et al.Kidney deformation and intraprocedural registration: a study of elements of image-guided kidney surgery. J Endourol 2011; 25(3): 511–517.

14. Nicolau S, Soler L, Mutter D, Marescaux J. Augmented reality in laparoscopic surgical oncology. Surg Oncol2011; 20(3): 189–201.

15. Ukimura O, Nakamoto M, Gill IS. Three-dimensional reconstruction of renovascular-tumor anatomy to facilitate zero-ischemia partial nephrectomy. Eur Urol2012; 61(1): 211–217.

16. Pratt P, Hughes-Hallett A, Di Marco A, et al. Multimodal reconstruction for image-guided interventions. In:Yang GZ, Darzi A (eds) Proceedings of the Hamlyn symposium on medical robotics: London. 2013; 59–61.

17. Mayer EK, Cohen D, Chen D, et al.Augmented reality image guidance in minimally invasive prostatectomy. Eur Urol Supp 2011; 10(2): 300.

18. Thompson S, Penney G, Billia M, et al.Design and evaluation of an image-guidance system for robot-assisted radical prostatectomy. BJU Int 2013; 111(7): 1081–1090.

19. Panebianco V, Salciccia S, Cattarino S, et al.Use of multiparametric MR with neurovascular bundle evaluation to optimize the oncological and functional management of patients considered for nerve-sparing radical prostatectomy. J Sex Med 2012; 9(8): 2157–2166.

20. Rai S, Srivastava A, Sooriakumaran P, Tewari A. Advances in imaging the neurovascular bundle. Curr Opin Urol2012; 22(2): 88–96.

21. Dixon BJ, Daly MJ, Chan H, et al.Surgeons blinded by enhanced navigation: the effect of augmented reality on attention. Surg Endosc 2013; 27(2): 454–461.

Read Full Post »

Hormone Therapy [9.6]

Writer and Curator: Larry H. Bernstein, MD, FCAP

The structure of this article is as follows:

9.6.1 Hormone Treatment Fights Prostate Cancer

9.6.2 Diabetes and Cardiovascular Disease During Androgen Deprivation Therapy for Prostate Cancer

9.6.3 Breast Cancer and Hormone Therapy

9.6.4 Hormone Therapy and Different Ovarian Cancers

9.6.5 Chemotherapy versus hormonal treatment in platinum- and paclitaxel-refractory ovarian cancer: a randomised trial of the German Arbeitsgemeinschaft Gynaekologische Onkologie (AGO) Study Group Ovarian Cancer

Introduction

9.6.1 Hormone Treatment Fights Prostate Cancer

By R. Morgan Griffin
http://www.webmd.com/prostate-cancer/features/hormone-therapy-for-prostate-cancer

Hormone therapy for prostate cancer has come a long way in the past few decades. Not so long ago, the only hormonal treatment for this disease was drastic: an orchiectomy, the surgical removal of the testicles.

Now we have a number of medications — available as pills, injections, and implants — that can give men the benefits of decreasing male hormone levels without irreversible surgery.

“I think hormonal therapy has done wonders for men with prostate cancer,” Stuart Holden, MD, Medical Director of the Prostate Cancer Foundation.

Hormone therapy for prostate cancer does have limitations. Right now, it’s usually used only in men whose cancer has recurred or spread elsewhere in the body.

But even in cases where removing or killing the cancer isn’t possible, hormone therapy can help slow down cancer growth. Though it isn’t a cure, hormone therapy for prostate cancer can help men with prostate cancer feel better and add years to their lives.

On average, hormone therapy can stop the advance of cancer for two to three years. However, it varies from case to case. Some men do well on hormone therapy for much longer.

The idea that hormones have an effect on prostate cancer is not new. The scientist Charles Huggins first established this over 60 years ago in work that led to his winning the Nobel Prize. Huggins found that removing one of the main sources of male hormones from the body — the testicles — could slow the growth of the disease.

“This procedure worked dramatically,” says Holden, who is also director of the Prostate Cancer Center at Cedar Sinai Medical Center in Los Angeles. “Before, these men were confined to bed and wracked with pain. Almost immediately afterwards, they improved.”

Huggins found that some types of prostate cancer cells androgens — to grow. Testosterone is one kind of androgen. About 90% to 95% of all androgens are made in the testicles, while the rest are made in the adrenal glands.

Hormone therapy for prostate cancer works by either preventing the body from making these androgens or by blocking their effects. Either way, the hormone levels drop, and the cancer’s growth slows.

In 85% to 90% of cases of advanced prostate cancer, hormone therapy can shrink the tumor.

However, hormone therapy for prostate cancer doesn’t work forever. The problem is that not all cancer cells need hormones to grow. Over time, these cells that aren’t reliant on hormones will spread. If this happens, hormone therapy won’t help anymore, and your doctor will need to shift to a different treatment approach.

There are two basic kinds of hormone therapy for prostate cancer. One class of drugs stops the body from making certain hormones. The other allows the body to make these hormones, but prevents them from attaching to the cancer cells. Some doctors start treatment with both drugs in an effort to achieve a total androgen block. This approach goes by several names: combined androgen blockade, complete androgen blockade, or total androgen blockade.

Here’s a rundown of the techniques.

  • Luteinizing hormone-releasing hormone agonists (LHRH agonists.)These are chemicals that stop the production of testosterone in the testicles. Essentially, they provide the benefits of an orchiectomy for men with advanced prostate cancer without surgery. This approach is sometimes called “chemical castration.” However, the effects are fully reversible if you stop taking the medication.Most LHRH agonists are injected every one to four months. Some examples are Lupron, Trelstar, Vantas, and Zoladex. A new drug, Viadur, is an implant placed in the arm just once a year.

    Side effects can be significant. They include: loss of sex drivehot flashes, development of breasts (gynecomastia) or painful breasts, loss of muscle, weight gain, fatigue, and decrease in levels of “good”cholesterol.

    Plenaxis is a drug that’s similar to LHRH agonists. However, because it can cause serious allergic reactions, it’s not used that often.

  • Anti-androgens. LHRH agonists and orchiectomies only affect the androgens that are made in the testicles. Thus they have no effect on the 5% to 10% of a man’s “male” hormones that are made in the adrenal glands. Anti-androgens are designed to affect the hormones made in the adrenal glands. They don’t stop the hormones from being made, but they stop them from having an effect on the cancer cells.The advantage of anti-androgens is that they have fewer side effects than LHRH agonists. Many men prefer them because they are less likely to diminish libido. Side effects include tenderness of the breasts, diarrhea, and nausea. These drugs are also taken as pills each day, which may be more convenient than injections. Examples are CasodexEulexin, and Nilandron.

    In some cases, starting treatment with an LHRH agonist can cause a “tumor flare,” a temporary acceleration of the cancer’s growth due to an initial increase in testosterone before the levels drop. This may cause the prostate gland to enlarge, obstructing the bladder and making it difficult to urinate. It’s believed that starting with an anti-androgen drug and then switching to an LHRH agonist can help avoid this problem. In patients with bone metastases, this “flare” can lead to significant complications such as bone pain, fractures, and nerve compression.

    Strangely, if treatment with an anti-androgen doesn’t work, stopping it may actually improve symptoms for a short time. This phenomenon is called “androgen withdrawal,” and experts aren’t sure why it happens.

  • Combined Androgen Blockade. This approach combines anti-androgens with LHRH agonists or an orchiectomy. By using both approaches, you can cut off or block the effects of hormones made by both the adrenal glands and the testicles. However, using both treatments can also increase the side effects. An orchiectomy or an LHRH agonist on its own can cause significant side effects like a loss of libido, impotence, and hot flashes. Adding an anti-androgen can cause diarrhea, and less often, nauseafatigue, and liver problems.
  • Estrogens. Some synthetic versions of female hormones are used for prostate cancer. In fact, they were one of the early treatments used for the disease. However, because of their serious cardiovascular side effects, they’re not used as often anymore. J. Brantley Thrasher, MD, a spokesman for the American Urological Association and chairman of urology at the University of Kansas Medical Center, says they’re usually used only after initial hormone treatments have failed. Examples of estrogens are DES (diethylstilbestrol), Premarin, and Estradiol.
  • Other Drugs. Proscar (finasteride) is another drug that indirectly blocks an androgen that helps prostate cancer cells grow. Depending

on the case, doctors sometimes use other anticancer drugs like Nizoral (ketoconazole) and Cytadren (aminoglutethimide.)

  • Orchiectomy. The surgical removal of the testicles was the earliest form of hormone therapy for prostate cancer. However, the procedure is permanent. As with LHRH agonists, side effects can be significant. They include: Loss of sex drive, hot flashes, development of breasts (gynecomastia) or painful breasts, loss of muscle, weight gain, fatigue, and decrease in levels of “good” cholesterol.

Hormone therapy for prostate cancer can cause osteoporosis, which can lead to broken bones. However, treatment with bisphosphonates — like ArediaFosamax, and Zometa — may help prevent this condition from developing.

Hormone (androgen deprivation) therapy for prostate cancer

http://www.cancer.org/cancer/prostatecancer/detailedguide/prostate-cancer-treating-hormone-therapy

Hormone therapy is also called androgen deprivation therapy (ADT) or androgen suppression therapy. The goal is to reduce levels of male hormones, called androgens, in the body, or to stop them from affecting prostate cancer cells.

The main androgens are testosterone and dihydrotestosterone (DHT). Most of the body’s androgens come from the testicles, but the adrenal glands also make a small amount. Androgens stimulate prostate cancer cells to grow. Lowering androgen levels or stopping them from getting into prostate cancer cells often makes prostate cancers shrink or grow more slowly for a time. But hormone therapy alone does not cure prostate cancer.

Hormone therapy may be used:

  • If the cancer has spread too far to be cured by surgery or radiation, or if you can’t have these treatments for some other reason
  • If your cancer remains or comes back after treatment with surgery or radiation therapy
  • Along with radiation therapy as initial treatment if you are at higher risk of the cancer coming back after treatment (based on a high Gleason score, high PSA level, and/or growth of the cancer outside the prostate)
  • Before radiation to try to shrink the cancer to make treatment more effective

Several types of hormone therapy can be used to treat prostate cancer. Some lower the levels of testosterone or other androgens (male hormones). Others block the action of those hormones.

Luteinizing hormone-releasing hormone (LHRH) analogs

These drugs lower the amount of testosterone made by the testicles. Treatment with these drugs is sometimes calledchemical castration or medical castration because they lower androgen levels just as well as orchiectomy.

Even though LHRH analogs (also called LHRH agonists or GnRH agonists) cost more than orchiectomy and require more frequent doctor visits, most men choose this method. These drugs allow the testicles to remain in place, but the testicles will shrink over time, and they may even become too small to feel.

LHRH analogs are injected or placed as small implants under the skin. Depending on the drug used, they are given anywhere from once a month up to once a year. The LHRH analogs available in the United States include leuprolide (Lupron®, Eligard®), goserelin (Zoladex®), triptorelin (Trelstar®), and histrelin (Vantas®).

When LHRH analogs are first given, testosterone levels go up briefly before falling to very low levels. This effect is called flare and results from the complex way in which LHRH analogs work. Men whose cancer has spread to the bones may have bone pain. If the cancer has spread to the spine, even a short-term increase in tumor growth as a result of the flare could compress the spinal cord and cause pain or paralysis. Flare can be avoided by giving drugs called anti-androgens for a few weeks when starting treatment with LHRH analogs. (Anti-androgens are discussed further on.)

Degarelix (Firmagon®)

Degarelix is an LHRH antagonist. LHRH antagonists work like LHRH agonists, but they reduce testosterone levels more quickly and do not cause tumor flare like the LHRH agonists do.

This drug is used to treat advanced prostate cancer. It is given as a monthly injection under the skin. The most common side effects are problems at the injection site (pain, redness, and swelling) and increased levels of liver enzymes on lab tests. Other side effects are discussed in detail below.

Abiraterone (Zytiga®)

Drugs such as LHRH agonists can stop the testicles from making androgens, but other cells in the body, including prostate cancer cells themselves, can still make small amounts, which can fuel cancer growth. Abiraterone blocks an enzyme called CYP17, which helps stop these cells from making androgens.

Abiraterone can be used in men with advanced castrate-resistant prostate cancer (cancer that is still growing despite low testosterone levels from an LHRH agonist, LHRH antagonist, or orchiectomy). Abiraterone has been shown to shrink or slow the growth of some of these tumors and help some of these men live longer.

This drug is taken as pills every day. This drug doesn’t stop the testicles from making testosterone, so men who haven’t had an orchiectomy need to continue treatment with an LHRH agonist or antagonist. Because abiraterone also lowers the level of some other hormones in the body, prednisone (a cortisone-like drug) needs to be taken during treatment as well to avoid certain side effects.

Drugs that stop androgens from working

Anti-androgens

Androgens have to bind to a protein in the cell called an androgen receptor to work. Anti-androgens are drugs that bind to these receptors so the androgens can’t.

Drugs of this type, such as flutamide (Eulexin®), bicalutamide (Casodex®), and nilutamide (Nilandron®), are pills taken daily.

Anti-androgens are not often used by themselves in the United States. An anti-androgen may be added to treatment if orchiectomy, an LHRH analog, or LHRH antagonist is no longer working by itself. An anti-androgen is also sometimes given for a few weeks when an LHRH analog is first started to prevent a tumor flare.

Anti-androgen treatment can be combined with orchiectomy or an LHRH analog as first-line hormone therapy. This is called combined androgen blockade (CAB).

9.6.2 Diabetes and Cardiovascular Disease During Androgen Deprivation Therapy for Prostate Cancer

Nancy L. KeatingA. James O’Malley and Matthew R. Smith
JCO Sep 20, 2006; 24(27):4448-4456
http://dx.doi.org:/10.1200/JCO.2006.06.2497

Purpose Androgen deprivation therapy with a gonadotropin-releasing hormone (GnRH) agonist is associated with increased fat mass and insulin resistance in men with prostate cancer, but the risk of obesity-related disease during treatment has not been well studied. We assessed whether androgen deprivation therapy is associated with an increased incidence of diabetes and cardiovascular disease. Patients and Methods Observational study of a population-based cohort of 73,196 fee-for-service Medicare enrollees age 66 years or older who were diagnosed with locoregional prostate cancer during 1992 to 1999 and observed through 2001. We used Cox proportional hazards models to assess whether treatment with GnRH agonists or orchiectomy was associated with diabetes, coronary heart disease, myocardial infarction, and sudden cardiac death. Results More than one third of men received a GnRH agonist during follow-up. GnRH agonist use was associated with increased risk of incident diabetes (adjusted hazard ratio [HR], 1.44; P < .001), coronary heart disease (adjusted HR, 1.16; P < .001), myocardial infarction (adjusted HR, 1.11; P = .03), and sudden cardiac death (adjusted HR, 1.16; P = .004). Men treated with orchiectomy were more likely to develop diabetes (adjusted HR, 1.34; P < .001) but not coronary heart disease, myocardial infarction, or sudden cardiac death (all P > .20). Conclusion GnRH agonist treatment for men with locoregional prostate cancer may be associated with an increased risk of incident diabetes and cardiovascular disease.

9.6.3 Breast Cancer and Hormone Therapy

http://www.webmd.com/breast-cancer/hormone-therapy-overview

There are certain hormones that can attach to breast cancer cells and affect their ability to multiply. The purpose of hormone therapy, also called endocrine therapy, is to add, block, or remove hormones.

With breast cancer, the female hormones estrogen andprogesterone can promote the growth of some breast cancer cells. Therefore in some patients, hormone therapy is given to block the body’s naturally occurring estrogen to slow or stop the cancer‘s growth.

There are two types of hormone therapy for breast cancer.

  • Drugs that inhibit estrogen and progesterone from promotingbreast cancer cell growth.
  • Drugs or surgery to turn off the production of hormones from the ovaries.

Faslodex, a estrogen receptor antagonist, binds to estrogen receptors and blocks their effects on cancer cells. Given as an injection, the drug is for HER2-positive metastatic disease in postmenopausal women who have already tried anti-estrogen therapy. Common side effects of Faslodex include:

  • Injection site pain
  • Nausea and vomiting
  • Loss of appetite
  • Weakness, fatigue
  • Hot flashes
  • Cough
  • Muscle, joint, and bone pain
  • Constipation
  • Shortness of breath

Zoladex and Lupron for Breast Cancer

Zoladex and Lupron are drugs that stop the production of estrogen by the ovaries. They are used in premenopausal women for the treatment of estrogen sensitive breast cancer.

Side effects of Zoladex and Lupron include:

  • Fluid retention
  • Hot flashes
  • Irregular menstrual periods
  • Pain at the injection site

http://www.cancer.gov/types/breast/breast-hormone-therapy-fact-sheet

Hormone-sensitive breast cancer cells contain proteins known as hormone receptors that become activated when hormones bind to them. The activated receptors cause changes in the expression of specific genes, which can lead to the stimulation of cell growth.

To determine whether breast cancer cells contain hormone receptors, doctors test samples of tumor tissue that have been removed by surgery. If the tumor cells contain estrogen receptors, the cancer is called estrogen receptor-positive (ER-positive), estrogen-sensitive, or estrogen-responsive. Similarly, if the tumor cells contain progesterone receptors, the cancer is called progesterone receptor-positive (PR- or PgR-positive). Approximately 70 percent of breast cancers are ER-positive. Most ER-positive breast cancers are also PR-positive (1).

Breast cancers that lack estrogen receptors are called estrogen receptor-negative (ER-negative). These tumors are estrogen-insensitive, meaning that they do not use estrogen to grow. Breast tumors that lack progesterone receptors are called progesterone receptor-negative (PR- or PgR-negative).

Hormone therapy (also called hormonal therapy, hormone treatment, or endocrine therapy) slows or stops the growth of hormone-sensitive tumors by blocking the body’s ability to produce hormones or by interfering with hormone action. Tumors that are hormone-insensitive do not respond to hormone therapy.

Hormone therapy for breast cancer is not the same as menopausal hormone therapy or female hormone replacement therapy, in which hormones are given to reduce the symptoms of menopause.

Several strategies have been developed to treat hormone-sensitive breast cancer, including the following:

Blocking ovarian function: Because the ovaries are the main source of estrogen in premenopausal women, estrogen levels in these women can be reduced by eliminating or suppressing ovarian function. Blocking ovarian function is called ovarian ablation.

Ovarian ablation can be done surgically in an operation to remove the ovaries (called oophorectomy) or by treatment with radiation. This type of ovarian ablation is usually permanent.

Alternatively, ovarian function can be suppressed temporarily by treatment with drugs called gonadotropin-releasing hormone (GnRH) agonists, which are also known as luteinizing hormone-releasing hormone (LH-RH) agonists. These medicines interfere with signals from the pituitary gland that stimulate the ovaries to produce estrogen.

Examples of ovarian suppression drugs that have been approved by the U.S. Food and Drug Administration (FDA) are goserelin (Zoladex®) and leuprolide (Lupron®).

Blocking estrogen production: Drugs called aromatase inhibitors can be used to block the activity of an enzyme called aromatase, which the body uses to make estrogen in the ovaries and in other tissues. Aromatase inhibitors are used primarily in postmenopausal women because the ovaries in premenopausal women produce too much aromatase for the inhibitors to block effectively. However, these drugs can be used in premenopausal women if they are given together with a drug that suppresses ovarian function.

Examples of aromatase inhibitors approved by the FDA are anastrozole (Arimidex®) and letrozole (Femara®), both of which temporarily inactivate aromatase, and exemestane (Aromasin®), which permanently inactivates the enzyme.

Blocking estrogen’s effects: Several types of drugs interfere with estrogen’s ability to stimulate the growth of breast cancer cells:

  • Selective estrogen receptor modulators (SERMs) bind to estrogen receptors, preventing estrogen from binding. Examples of SERMs approved by the FDA are tamoxifen (Nolvadex®), raloxifene (Evista®), andtoremifene (Fareston®). Tamoxifen has been used for more than 30 years to treat hormone receptor-positive breast cancer.Because SERMs bind to estrogen receptors, they can potentially not only block estrogen activity (i.e., serve as estrogen antagonists) but also mimic estrogen effects (i.e., serve as estrogen agonists). Most SERMs behave as estrogen antagonists in some tissues and as estrogen agonists in other tissues. For example, tamoxifen blocks the effects of estrogen in breast tissue but acts like estrogen in the uterus and bone.
  • Other antiestrogen drugs, such as fulvestrant (Faslodex®), work in a somewhat different way to block estrogen’s effects. Like SERMs, fulvestrant attaches to the estrogen receptor and functions as an estrogen antagonist. However, unlike SERMs, fulvestrant has no estrogen agonist effects. It is a pure antiestrogen. In addition, when fulvestrant binds to the estrogen receptor, the receptor is targeted for destruction.

There are three main ways that hormone therapy is used to treat hormone-sensitive breast cancer:

Adjuvant therapy for early-stage breast cancer: Research has shown that women treated for early-stage ER-positive breast cancer benefit from receiving at least 5 years of adjuvant hormone therapy (2). Adjuvant therapy is treatment given after the main treatment (surgery, in the case of early-stage breast cancer) to increase the likelihood of a cure.

Adjuvant therapy may include radiation therapy and some combination of chemotherapy, hormone therapy, and targeted therapyTamoxifen has been approved by the FDA for adjuvant hormone treatment of premenopausal and postmenopausal women (and men) with ER-positive early-stage breast cancer, andanastrozole and letrozole have been approved for this use in postmenopausal women.

A third aromatase inhibitorexemestane, is approved for adjuvant treatment of early-stage breast cancer in postmenopausal women who have received tamoxifen previously.

Until recently, most women who received adjuvant hormone therapy to reduce the chance of a breast cancer recurrence took tamoxifen every day for 5 years. However, with the advent of newer hormone therapies, some of which have been compared with tamoxifen in clinical trials, additional approaches to hormone therapy have become common (35). For example, some women may take an aromatase inhibitor every day for 5 years, instead of tamoxifen. Other women may receive additional treatment with an aromatase inhibitor after 5 years of tamoxifen. Finally, some women may switch to an aromatase inhibitor after 2 or 3 years of tamoxifen, for a total of 5 or more years of hormone therapy.

Decisions about the type and duration of adjuvant hormone therapy must be made on an individual basis. This complicated decision-making process is best carried out by talking with an oncologist, a doctor who specializes in cancer treatment.

Treatment of metastatic breast cancer: Several types of hormone therapy are approved to treat hormone-sensitive breast cancer that is metastatic (has spread to other parts of the body).

Studies have shown that tamoxifen is effective in treating women and men with metastatic breast cancer (6).Toremifene is also approved for this use. The antiestrogen fulvestrant can be used in postmenopausal women with metastatic ER-positive breast cancer after treatment with other antiestrogens (7).

The aromatase inhibitors anastrozole and letrozole can be given to postmenopausal women as initial therapy for metastatic hormone-sensitive breast cancer (89). These two drugs, as well as the aromatase inhibitor exemestane, can also be used to treat postmenopausal women with advanced breast cancer whose disease has worsened after treatment with tamoxifen (10).

Neoadjuvant treatment of breast cancer: The use of hormone therapy to treat breast cancer before surgery (neoadjuvant therapy) has been studied in clinical trials (11). The goal of neoadjuvant therapy is to reduce the size of a breast tumor to allow breast-conserving surgery. Data from randomized controlled trials have shown that neoadjuvant hormone therapies—in particular, aromatase inhibitors—can be effective in reducing the size of breast tumors in postmenopausal women. The results in premenopausal women are less clear because only a few small trials involving relatively few premenopausal women have been conducted thus far.

No hormone therapy has yet been approved by the FDA for the neoadjuvant treatment of breast cancer.

9.6.4 Hormone Therapy and Different Ovarian Cancers

Lina Steinrud Mørch, Ellen Løkkegaard, Anne Helms Andreasen, Susanne Krüger Kjær, Øjvind Lidegaard
Am J Epidemiol. 2012; 175(12):1234-1242
http://www.medscape.com/viewarticle/766010

Postmenopausal hormone therapy use increases the risk of ovarian cancer. In the present study, the authors examined the risks of different histologic types of ovarian cancer associated with hormone therapy. Using Danish national registers, the authors identified 909,946 women who were followed from 1995–2005. The women were 50–79 years of age and had no prior hormone-sensitive cancers or bilateral oophorectomy. Hormone therapy prescription data were obtained from the National Register of Medicinal Product Statistics. The National Cancer and Pathology Register provided data on ovarian cancers, including information about tumor histology. The authors performed Poisson regression analyses that included hormone exposures and confounders as time-dependent covariates. In an average of 8.0 years of follow up, 2,681 cases of epithelial ovarian cancer were detected. Compared with never users, women taking unopposed oral estrogen therapy had increased risks of both serous tumors (incidence rate ratio (IRR) = 1.7, 95% confidence interval: 1.4, 2.2) and endometrioid tumors (IRR = 1.5, 95% confidence interval: 1.0, 2.4) but decreased risk of mucinous tumors (IRR = 0.3, 95% confidence interval: 0.1, 0.8). Similar increased risks of serous and endometrioid tumors were found with estrogen/progestin therapy, whereas no association was found with mucinous tumors. Consistent with results from recent cohort studies, the authors found that ovarian cancer risk varied according to tumor histology. The types of ovarian tumors should be given attention in future studies.

Introduction

Ovarian cancer is the most lethal of gynecologic cancers. Unfortunately, little is known about its etiology. In recent meta-analyses, investigators have concluded that women taking postmenopausal hormone therapy (HT) have an increased risk of ovarian cancer compared with never users.[1, 2] Two large prospective studies, the Million Women Study and Danish Sex Hormone Register Study, found an overall increased risk of 30%–40%.[3, 4]

Less is known about the association between hormone use and the risk of different histologic subtypes of epithelial ovarian cancer. Other risk factors for ovarian cancer have been found to differ between mucinous and nonmucinous ovarian tumors, supporting the hypothesis of different etiologies.[5, 6]However, previous studies on HT and different types of ovarian tumors were mainly case-control studies, and the numbers of cases were small, especially for mucinous tumors.[1, 7–10] Most prospective cohort studies either did not examine tumor type[1, 4] or had incomplete information on histology.[11]

Recently, Danforth et al.[12] found that estrogen-only therapy (ET) was more strongly associated with the risk of endometrioid tumors than with the risk of other types of epithelial tumors in the Nurses’ Health Study (NHS). The Million Women Study found that with HT use, the highest risk was for serous tumors, whereas there was a lower risk of mucinous tumors.[3] Knowledge about the associations between HTs and subtypes of ovarian cancer will add to the understanding of how HT acts as a promoter of ovarian cancer carcinogenesis. Moreover, if different types of ovarian tumors are to be viewed as separate diseases, that fact should be considered when creating the study designs for future research. Therefore, the aim of the present study was to explore the risks of HT associated with different histologic types of ovarian cancer.

The study cohort was linked to the National Register of Medicinal Product Statistics using participants’ personal identification numbers as the key identifiers. The National Register of Medicinal Product Statistics includes information on the date of the redeemed prescriptions and the specific Anatomical Therapeutic Chemical code, dose, number of packages, defined daily doses, and route of administration (tablet, patch, gel, etc.) The specific Anatomical Therapeutic Chemical codes included in the present study have been described previously.[13]

The information on initiation of HT use (i.e., redeemed prescriptions) was updated daily for each individual during follow-up. The prescribed defined daily doses were used to determine the length of use. We included 4 months after the expiration of the prescription in all records of hormone exposure to account for any delay in recorded diagnoses in Danish registers, prolonged HT use for those taking less than the defined daily dose prescribed, and minor latency time. Thus, gaps between prescriptions of less than 4 month were filled prospectively; that is, a woman was classified as user of the drug at a given point in time if the dispensed supply from the last redemption had not run out or if it had run out within the last m days (where m is the allowed gap length).[14]

Because HT is likely to act as a promoter of ovarian cancer carcinogenesis with a yet unknown latency time, women currently taking hormones were categorized by the regimen that they took for the longest period during the study period. These variables were time varying; that is, if a woman began a new HT regimen, she would be recategorized if and when the time taking that regimen exceeded the amount of time she took the prior categorization HT regimen. The length of use was calculated as the time spent taking all systemic treatments during the study period. Whether a woman had taken hormones before 50 years of age but within the 11-year study period was accounted for in the hormone status categories, and the amount of time for which she took the hormones was accounted for in the duration of use category. The HT categories were HT use (never, past, current nonvaginal HT use, or other current use (i.e., current use of vaginal ET or a hormone intrauterine device)); hormone formulation (ET, estrogen/progestin therapy (EPT), or other (i.e., tibolone, raloxifene, progestin only, or vaginal estrogen)); hormone regimen (cyclic EPT, continuous EPT, or other); route of administration (oral ET, oral EPT or tibolone, dermal ET, dermal EPT, or other); duration of HT in years (never, current, 0.01–4 years, 4.01–7 years, or >7 years or use of vaginal ET or a hormone intrauterine device); and time since last use among former users (never, current, 0.01–2 years, 2.01–4 years, 4.01–6 years, or >6 years or use of vaginal ET or a hormone intrauterine device).

Ovarian Cancer Cases

Until December 31, 2002, we used the Danish Cancer Register to identify cases of primary invasive ovarian cancers and their histologies, using the International Classification of Diseases for Oncologytopography code 183.0 and morphology codes ending with a 3. At time of the present study, information from January 2003 had not been updated in the Danish Cancer Register. Thus, from 2003 onward, the Pathology Register was used for case findings and information on histology. The invasive epithelial tumors were classified as serous (codes M84413, M84603, M84613, and M90143), endometrioid (codes M83803 and M83813), mucinous (codes M84703, M84803, and M90153), clear-cell (codes M83103 and M83133), adenocarcinoma not otherwise specified (code M81403), or epithelial not otherwise specified (codes M80203, M80703, M81303, M85603, M89333, M89803, and M90003). Nonepithelial invasive tumors and borderline tumors were not included. Eight women for whom we did not have histologic information were excluded. Information on the stages of disease was available from the Danish Cancer Register until December 31, 2002.

From 1995 to 2005, a total of 909,946 perimenopausal and postmenopausal women with no previous cancer or removal of ovaries accumulated 7.3 million person-years of observation, corresponding to an average follow-up period of 8.0 years. The number of incident malignant epithelial ovarian cancers during the study period was 2,681. Of these, 1,336 were serous tumors, 377 were endometrioid tumors, 293 were mucinous tumors, 159 were clear-cell tumors, 115 were nonspecified epithelial tumors, and 401 were adenocarcinomas not otherwise specified. At the end of follow up, 63% of the women remained never users of HT, 22% were previous users, and 9% were current users. Compared with never users, hormone users were more likely to have undergone a hysterectomy (18.0% versus 6.2%) or unilateral salpingo-oophorectomy (5.7% versus 1.9%), to have been sterilized (8.4% versus 5.4%), and to be parous (80.8% versus 75.2%). The characteristics of the study population have been published previously.[4]

Compared with never users, current users of hormones had an increased risk of serous tumors (incidence rate ratio (IRR) = 1.7, 95% confidence interval (CI): 1.5, 1.9) and of endometrioid tumors (IRR = 1.7, 95% CI: 1.3, 2.2). Current use of hormones was not associated with the risk of mucinous or clear-cell tumors (Figure 1). The incidence rate ratios for serous ovarian cancer increased with duration of hormone use (0.01–4 years, IRR = 1.5, 95% CI: 1.3, 1.8; 4.01–7 years, IRR = 1.7, 95% CI: 1.4, 2.1; and >7 years, IRR = 2.1, 95% CI: 1.6, 2.8). The incidence rate ratios for other types of epithelial ovarian cancer were not consistently associated with duration of use (Figure 2).

(Enlarge Image)

Figure 1.

Incidence rate ratios of epithelial ovarian cancers associated with current use of hormone therapy, Danish Sex Hormone Register Study, 1995–2005. Values were adjusted for age, period of use, number of births, hysterectomy, sterilization, unilateral oophorectomy or salpingo-oophorectomy, endometriosis, infertility, and educational level. The reference group was never users of hormone therapy (dashed line). Bars, 95% confidence interval.

(Enlarge Image)

Figure 2.

Incidence rate ratios of epithelial ovarian cancers associated with durations of hormone therapy in years, Danish Sex Hormone Register Study, 1995–2005. Values were adjusted for age, period of use, number of births, hysterectomy, sterilization, unilateral oophorectomy or salpingo-oophorectomy, endometriosis, infertility, and educational level. The reference group was never users of hormone therapy (dashed line). Risk estimates for clear-cell cancer are not shown because there were few cases. Bars, 95% confidence interval.

Time Since Hormone Use

We found increased incidence rate ratios for serous ovarian cancers for a period of up to 2 years after cessation of HT. Thereafter, the risk approached that observed in never users. For endometrioid tumors, the risk was not significantly increased after cessation of HT (Figure 3).

(Enlarge Image)

Figure 3.

Incidence rate ratios of serous and endometrioid ovarian cancers associated with time since last hormone therapy use in years, Danish Sex Hormone Register Study, 1995–2005. Values were adjusted for age, period of use, number of births, hysterectomy, sterilization, unilateral oophorectomy or salpingo-oophorectomy, endometriosis, infertility, and educational level. The reference group was never users of hormone therapy (dashed line). Bars, 95% confidence interval.

Estrogen Therapy

Compared with never users, women on unopposed ET had an increased risk of serous tumors (IRR = 1.7, 95% CI: 1.4, 2.1) and a tendency toward an increased risk of endometrioid tumors (IRR = 1.4, 95% CI: 0.9, 2.1). In contrast, the risk of mucinous tumors was decreased (IRR = 0.3, 95% CI: 0.1, 0.8). No association was found between ET and the risk of clear-cell tumors (IRR = 0.6, 95% CI: 0.2, 1.5) (Figure 4).

(Enlarge Image)

Figure 4.

Incidence rate ratios of epithelial ovarian cancers associated with hormone therapy, Danish Sex Hormone Register Study, 1995–2005. A) Estrogen-only therapy; B) estrogen/progestin therapy. Values were adjusted for age, period of use, number of births, hysterectomy, sterilization, unilateral oophorectomy or salpingo-oophorectomy, endometriosis, infertility, and educational level. The reference group was never users of hormone therapy (dashed line). Bars, 95% confidence interval.

Women on oral ET had a statistically significantly increased risk of endometrioid tumors (IRR = 1.5, 95% CI: 1.0, 2.4), and the risks for serous, mucinous, and clear-cell tumors were similar to the risks found for all ET. Because the risk associations between transdermal ET and ovarian cancers were based on a few cases, the data are not shown. Vaginal estrogen alone was associated with an increased risk of serous tumors (IRR = 1.4, 95% CI: 1.1, 1.9), whereas no associations were found with endometrioid, mucinous, or clear-cell tumors (data not shown).

Combined Therapy

Women on combined EPT had increased incidence rate ratios for serous tumors (IRR = 1.6, 95% CI: 1.4, 1.9) and endometrioid tumors (IRR = 2.0, 95% CI: 1.5, 2.6), whereas no associations were found with mucinous or clear-cell tumors (Figure 4). Similar risk associations were found among women on oral EPT. Because there were few cases, data for transdermal EPT are not shown.

Duration of HT

The incidence rate ratios for serous ovarian cancer increased with increased duration of ET and after 7 years reached an incidence rate ratio of 2.9 (95% CI: 1.9, 4.3). The risks for endometrioid ovarian cancer were similar for all durations of ET (Table 1).

Among women on cyclic EPT, the risk of endometrioid ovarian cancer was increased by 70%–140%, whereas the risk was not increased among women on continuous EPT. The risks for serous ovarian cancer were similar regardless of the duration of cyclic or continuous EPT (Table 1). Results from crude and adjusted analyses were almost identical (data not shown).

Stage of Disease

Overall, the associations between HT and risks of different ovarian tumors did not change after adjustment for the stage of disease (Table 2). Although the analyses were slightly weakened by a lower number of cases, the results roughly showed similar incidence rate ratios across the stages of disease (Table 2).

Discussion

The present large cohort study suggests that there is a differential influence of HT on different subtypes of ovarian cancer. Hormone users had an excess risk of serous and endometrioid tumors but not of mucinous and clear-cell cancers of the ovaries. Both combined EPT and unopposed ET were associated with increased risks of serous ovarian cancer. Furthermore, cyclic EPT and oral ET were associated with increased risks of endometrioid ovarian cancer. In contrast, no HT was associated with risk of clear-cell ovarian cancer, and women who had used ET had a decreased risk of mucinous ovarian cancer.

Serous Ovarian Cancer

Two large prospective cohort studies, the NHS and the Million Women Study, also found an increased risk of serous ovarian cancer among hormone users.[3, 12] In accordance with our finding, the Million Women Study reported an approximately 50% increased risk with HT.[3] The NHS supports our finding that increasing duration of ET is associated with increasing rate ratios for serous ovarian cancer.[12]

Endometrioid Ovarian Cancer

Although the Million Women Study found no association between any HT and the risk of endometrioid ovarian cancer, we found a 70% increased risk.[3] The NHS found a 50% increased risk of endometrioid tumors after 5 years of ET.[12] In our study, women on oral ET had an up to 2-fold increased risk of endometrioid tumors. Because ET increases the risk of endometrial cancer[15] and endometrioid ovarian tumors are histologically similar to endometrial tissue (16), it seems likely that ET acts through similar biologic mechanisms in the development of endometrioid ovarian cancer, a hypothesis suggested by Danforth et al..[12]

Furthermore, the present study suggests that women on cyclic EPT have an increased risk of endometrioid ovarian cancer, whereas the risk is not increased in women on continuous EPT. Only one study addressed the risk of endometrioid ovarian tumors among women on cyclic versus continuous EPT, and those investigators were not able to demonstrate an increased risk with cyclic or continuous EPT.[7] With regard to the development of endometrial cancer, the increased risk has been found to be confined to women on cyclic EPT.[15] Thus, it is possible that cyclic EPT acts through similar biologic mechanisms in the development of endometrioid ovarian cancer.

Mucinous Ovarian Cancer

Compared with women who were never prescribed HT, women on ET had a 70% decreased risk of mucinous ovarian cancer. The Million Women Study also found a decreased risk of approximately 30% with the use of HT.[3] A few other studies have also suggested that HT is associated with a decreased risk of mucinous ovarian cancer.[12, 17, 18] One group of mucinous tumors is similar to endocervical epithelium and another is similar to colonic epithelium.[16] Both HT in general and ET specifically have been found to decrease the risk of colon cancer.[19, 20] It therefore seems plausible that ET could also decrease the risk of mucinous ovarian cancer. Risch et al.[5] were the first to suggest different etiologies for mucinous and nonmucinous ovarian cancers, and a recent Danish study supported this hypothesis by suggesting significant differences in the risk between mucinous and nonmucinous tumors.[6]

Implications

Using the same data as in current study, Mørch et al.[4] found a 40% increase in the overall risk of ovarian cancer in current users of hormones, regardless of the duration and type of HT. However, in the present study, the risk of serous ovarian tumors increased with increasing durations of hormone use. This association was more pronounced among women using ET. After 7 years, the risk of serous ovarian cancer had increased 3-fold among women using ET compared with never users. On the other hand, restricting the analysis to mucinous tumors showed a decreased risk among women using ET. Thus, important information about a differential impact of HT, HT types, and associations with duration of hormone use are not described when different ovarian tumors are examined as a combined outcome.

Moreover, the clarification of the different associations between HT and subtypes of ovarian cancer adds to the understanding of how HT acts as a promoter of ovarian cancer carcinogenesis, as the results are in line with the current knowledge about HT-associated risks of cancers with similar epithelial origins. Because of this, it seems plausible that there is a causal association between HT and ovarian cancer. Other risk factors for ovarian cancer differ based on the type of tumor (mucinous vs. nonmucinous), supporting the hypothesis of different etiologies.[5, 6] The differences should be considered in research study design and suggest that different types of ovarian tumors should be viewed as separate diseases.

Strengths of Study

To our knowledge, our nationwide cohort study is the largest conducted thus far to explore the influence of HT on the risk of histologic subtypes of epithelial ovarian cancer. The validity of our outcome is considered to be high, as data from the Cancer Register validated the diagnoses (21–23). The agreement of histologic ovarian cancer diagnoses between the Pathology Register and the Cancer Register is high, and our estimates did not depend on the source of diagnoses.[24] The information on prescribed HT is transferred electronically from all Danish pharmacies by using bar codes, eliminating recall bias. Our information on both exposures and confounders was updated daily through the national registers, making it possible for us to account for changes in exposures. We excluded women with previous cancer because it might affect both the use of hormones and the subsequent risk of ovarian cancer. Our results were adjusted for age, time period, educational level, number of births, and history of hysterectomy, sterilization, unilateral oophorectomy, salpingo-oophorectomy, endometriosis, or infertility. There was, however, no significant confounding by any of the included variables. We found no evidence of earlier detection (surveillance bias) of ovarian tumors among women on HT. Finally, the stage of disease did not bias the differential association between HT and different tumor types.

Limitations of Study

Data from the National Register of Medicinal Product Statistics is not complete for the time period before January 1995. Thus, information about prescriptions for oral contraceptive use was not available for the women in current study who were 50 years of age or older from 1995−2005. Our incidence rate ratios may be underestimated because of confounding by use of oral contraceptives, as oral contraceptive use decreases the risk of ovarian cancer and often leads to HT.[25, 26] We were not able to restrict our analyses to nonobese women. The ovarian cancer risk associated with HT use is probably clearer in nonobese women (i.e., in women with a body mass index, measured as weight in kilograms divided by height in meters squared, <30).[27] Consequently, our results might be underestimated among nonobese. However, the Million Women Study adjusted data for oral contraceptive use, body mass index, age at menopause, alcohol consumption, smoking, and physical activity, and the adjustments did not result in material changes in their estimates.[3] Also, the NHS reported only minimal changes in the association between HT and the risk of ovarian cancer after adjustment for relevant potential confounders, including duration of oral contraceptive use, occurrence of natural menopause, and age at menarche.[12] The lack of information on family history of cancer might have caused an underestimation of risk in our results, as women with a family history of cancer are probably less likely to use hormones. Information on women who underwent surgical procedures was not available in the registers for the oldest women. Hysterectomy and oophorectomy reduce the risk of ovarian cancer and often lead to HT use, probably causing an underestimation of risk in older women in our results. However, despite our uneven adjustment for confounders, the risks for ovarian tumors were nearly identical across age groups.

9.6.5 Chemotherapy versus hormonal treatment in platinum- and paclitaxel-refractory ovarian cancer: a randomised trial of the German Arbeitsgemeinschaft Gynaekologische Onkologie (AGO) Study Group Ovarian Cancer

  1. du Bois, W. Meier, H. J. Lück, G. Emons, V. Moebus, et al.
    Ann Oncol (2002) 13 (2): 251-257
    http://dx.doi.org://10.1093/annonc/mdf038

The majority of patients with ovarian cancer are not cured by first-line treatment.Until now, no study could demonstrate any substantial benefit when exposing ovarian cancer patients to second-line chemotherapy. However, most treatment regimens induce toxicity, thus negatively influencing the quality of rather limited life spans. Here we evaluate whether a second-line chemotherapy can offer any benefit compared with a less toxic hormonal treatment. Patients and methods Patients with ovarian cancer progressing during platinum-paclitaxel containing first-line therapy or experiencing relapse within 6 months were eligible. Patients were stratified for response to primary treatment (progression versus no change/response), and measurable versus non-measurable disease. Treatment consisted of either treosulfan 7 g/m2infused over 30 min or leuprorelin 3.75 mg injected subcutaneously or intramuscularly. Both regimens were repeated every 4 weeks. Results This study began in late 1996, and after 2.5 years accrual an interim analysis was performed when several investigators reported their concern about a suspected lack of efficacy. Following this analysis the recruitment was stopped early and the 78 patients already enrolled were followed up. The majority of patients received treatment until progressive disease was diagnosed or death occurred. Treatment delay was observed rarely and dose reduction was performed only in the treosulfan arm in 5% of 150 courses. Overall, both treatment arms were well tolerated. No objective responses were observed. The median survival time was 36 and 30 weeks in the treosulfan and leuprorelin arms, respectively. Overall survival did not differ between patients with relapse 3–6 months after first-line chemotherapy compared with patients with progressive disease within 3 months.

Conclusions The selected patient population represents a subgroup with extremely poor prognosis. Accordingly, results were not impressive. Both treatment arms showed favourable toxicity data, but failed to show remarkable activity, thus adding only limited evidence to the issue of whether patients with refractory ovarian cancer might benefit from second-line chemotherapy. Even stratified analysis did not identify any subgroup of patients in whom the administration of second-line chemotherapy could demonstrate a clinically relevant survival benefit.

Despite the considerable progress that has been achieved in the treatment of advanced ovarian cancer during the last de-cades, the majority of patients are still not cured by first-line treatment. Therefore, development of effective second-line treatment strategies remains a clinically relevant issue. Today standard first-line regimens in many countries contain both paclitaxel and a platinum analogue (e.g. cisplatin [12] or carboplatin [35]). There are only limited data available reporting results gained from second-line therapy following failure of this new first-line regimen. Until now, no guidelines for the selection of second-line treatment regimens have reached universal acceptance [6]. Furthermore, the definitions of recurrent or relapsed disease according to the status of platinum resistance [7] were solely based on data from patients who did not receive the actual standard first-line regimens containing paclitaxel, and therefore have to be re-evaluated. The treatment-free interval, which offers a chance of gaining a benefit from re-treatment with paclitaxel and/or platinum, remains to be defined. However, patients progressing during or relapsing shortly after platinum-paclitaxel probably have a poor prognosis and can be regarded as refractory to both of the drugs they were exposed to. Until now, no study has demonstrated clearly any substantial benefit for these patients when treating them with second-line chemotherapy. However, most treatment regimens induce toxicity, thus negatively influencing the quality of rather limited life spans in this strictly palliative setting. Therefore, the AGO Study Group set about evaluating whether a second-line chemotherapy could offer any benefit compared with a less toxic hormonal treatment.

The decision to use an alkylating agent for second-line chemotherapy was based on the assumption that these agents, which had been part of first-line treatment of ovarian cancer for decades, could offer some benefit as second-line agent after removal from first-line regimens. Treosulfan (Ovastat®, medac, Germany) was chosen as alkylating agent because it has been registered and used frequently in older first-line regimens in Germany, due to a more favourable non-haematological toxicity profile compared with cyclophosphamide [89]. The published data for treosulfan as second-line treatment after platinum failure had been partially contradictory. Two studies using intravenous treosulfan reported response rates of up to 20% in 25 and 72 patients, respectively [1011]. The latter trial included 43 patients with platinum refractory ovarian cancer and showed a 21% response rate. Orally administered treosulfan resulted in response rates of 3, 14 and 19% in 30, 22 and 16 platinum pre-treated patients, respectively [1214]. The only study reporting results of oral treosulfan in platinum refractory patients observed only one response in 30 patients. Therefore, we decided to use intravenous treosulfan as standard chemotherapy arm in this trial.

Leuprorelin (leuproreline acetate; Enantone®, Takeda, Germany), a gonadotropin-releasing hormone (GnRH) analogue, was selected as hormonal treatment in the experimental arm of this study. It could be administered in a similar time schedule as the chemotherapy regimen (monthly injections) and had shown some activity in previously reported studies in platinum pre-treated ovarian cancer. In these trials, leuprorelin had been used either as single agent [1517] or in combination with megestrole acetate or tamoxifen [1819]. Overall, nine responses have been reported in 46 platinum pre-treated patients [cumulative odds ratio (OR) 19.6%; 95% confidence interval (CI) 9% to 34%]. A retrospective review reported higher efficacy for leuprorelin compared with goserelin, thus providing further support for selecting leuprorelin in favour of other GnRH analogues [17]. However, platinum resistance had been reported inconsistently in all these studies, thus leaving some questions unanswered regarding efficiency in this particular group of patients. Toxicity profiles of leuprorelin had been uniformely reported as being mild, making this option potentially useful in this strictly palliative setting. Tamoxifen, another hormonal treatment with an 11% overall response rate reported in a meta-analysis in recurrent ovarian cancer [20], was not selected for this study, because the study group felt that the different mode of application could hamper comparability.

The median observation period was 22.5 months for all patients. The early termination of recruitment resulted in a statistical power of 80% to detect a 20% survival difference (50% versus 69.9%) after 6 months with two-sided testing and an α error of 0.05.

Treatment and tolerability

The majority of patients received treatment until progressive disease was diagnosed or death occurred. The mean and median treatment periods, respectively, were 18 and 16 weeks in the treosulfan arm, and 13 and 10 weeks in the leuprorelin arm. Treatment delay was observed rarely and median intervals per course were 30.8 and 28.6 days in the treosulfan and leuprorelin arms, respectively. Dose reduction was performed only in the treosulfan arm in eight of 150 courses (5%) because of myelosuppression.

Overall, 150 chemotherapy courses and 122 hormonal treatment courses were evaluable for toxicity. Haematological toxicities higher than grade 2 were observed in only a few patients. Thrombocytopenia grade 3/4 occurred in four and one courses in the treosulfan and leuprorelin arms, respectively. Neutropenia grade 3/4 was only observed in one course in each arm and no infections or neutropenic fever was reported. Anaemia greater than grade 2 was observed after seven courses in the treosulfan arm and after two courses in the leuprorelin arm.

Non-haematological toxicities grade 3 or 4 were reported in only few patients in both arms. Treosulfan induced nausea and emesis in 9% of patients compared with 6% of patients in the leuprorelin arm. Hot flushes were reported by one patient in each arm. Three further patients in the treosulfan arm reported grade 3 pain (two patients) and neurotoxicity (one). The latter was due to remaining toxicity from prior platinum-paclitaxel. Alopecia was common but was due to prior treatment. Re-growth of patients’ hair took longer in the treosulfan arm than in the leuprorelin arm. About one-third of patients still had alopecia after treatment with treosulfan compared with 11% in the leuprorelin arm. Fatigue was reported more frequently in the chemotherapy arm (eight of 36 patients versus one of 37 patients, treosulfan versus leuprorelin;P = 0.014, Fisher’s exact test). Overall, both treatment arms were relatively well tolerated resulting in only one treatment cessation due to toxicity.

Efficacy

No objective responses were observed in either of the treatment arms. Disease stabilisation lasting at least 4 weeks (no change) was reported in nine and four patients in the chemotherapy and hormonal treatment arm, respectively. All but one patient showed progressive disease within a median observation period of 22 months. Median progression-free survival was 17 weeks for treosulfan and 10 weeks for leuprorelin (P = 0.035, Wilcoxon test). The difference between both treatment arms remained significant in favour of treosulfan after adjusting for treatment-free interval before study entry (P = 0.028). However, after 6 months only 23% and 14% of patients in the treosulfan and leuprorelin arms had not progressed; corresponding figures for the 12 month observation period were 9% and 5%, respectively (Figure 1).

View larger version:

Figure 1. Progression-free survival (median 17 and 10 weeks for treosulfan and leuprorelin, respectively; P<0.05, log rank test; Kaplan–Meier curves).

At the time of this analysis, seven patients in the treosulfan arm and eight patients in the leuprorelin arm are still alive with disease [hazard ratio (HR) 0.98; 95% CI 0.58–1.67]. The differences observed between the treatment arms did not reach statistical significance (P = 0.87, Wilcoxon test; Figure2). Again, adjusting for a treatment-free interval before study entry did not alter results. The median survival time was 36 and 30 weeks in the treosulfan and leuprorelin arm, respectively. About one-third of patients in each arm were alive after 12 months.

View larger version:

Figure 2. Survival (median 36 and 30 weeks for treosulfan and leuprorelin, respectively; P = 0.87, log rank test; Kaplan–Meier curves).

The impact of time to treatment failure after first-line chemo-therapy on second-line therapy efficacy was analysed bi-categorially. The cut-off was set at 13 weeks, thus comparing patients with progression under first-line therapy or early relapse within 3 months with patients who relapsed 3–6 months after completion of first-line chemotherapy. Overall, the difference between the groups with respect to progression-free survival did not reach statistical significance. Median progression-free survival was 11 and 12 weeks, respectively, for the two groups (P = 0.46, log rank test; HR 0.83; 95% CI 0.51–1.35). Furthermore, overall survival did not differ significantly between patients with relapse 3–6 months after first-line chemotherapy compared with patients with progressive disease within 3 months (P = 0.34, log rank test; HR 0.77; 95% CI 0.46–1.31). However, median survival was slightly superior in the group with a longer progression-free interval after first-line therapy (42 versus 25 weeks). The latter difference did not reach statistical significance and the Kaplan–Meier curves almost fell on top of each other shortly after 1 year of observation (data not shown).

The presence of bi-dimensionally measurable disease had a negative impact on treatment results. Patients with measurable disease showed a median progression-free survival of 11 weeks compared with 19 weeks in patients with non-measurable disease (P = 0.0006, log rank test). Again, overall survival was superior in the group of patients with non-measurable disease, but this difference did not reach statistical significance (median 47 versus 24 weeks; P = 0.18, log rank test). Only 29% of patients with measurable disease compared with 46% of patients with non-measurable disease were alive after 12 months (HR 1.93; 95% CI 0.73–5.16).

Subsequent treatment

In the treosulfan arm, 15 patients received third-line treatments, of whom three were changed over to leuprorelin. The remaining eight patients received: radiotherapy (one), tamoxifen (one) or chemotherapeutic drugs [topotecan (six), etoposide (one), liposomal doxorubicin (one), carboplatin (one), carboplatin-paclitaxel (one)]. Furthermore, 14 patients received fourth-line treatment, including tamoxifen (two), MPA (one), etoposide (two), topotecan (two), and one patient each idarubicin, gemcitabin or mitoxantrone i.p. Finally,three patients received fifth-line cyclophosphamide (one), etoposide (one) or radiotherapy (one). In the leuproreline arm, almost all patients received third-line therapy. Sixteen patients were crossed over to treosulfan, four received intraperitoneal mitoxantrone, two had liposomal doxorubicin and one patient each received etoposide, topotecan, carboplatin, paclitaxel-mitoxantrone or carboplatin-paclitaxel. Two patients received hormonal third-line treatment (one each received tamoxifen and MPA). Fourth-line treatment was offered to seven patients, including radiotherapy (one), topotecan (two), and one patient each liposomal doxorubicin-etoposide, etoposide or etoposide–5-fluorouracil (5-FU). Fifth-line treatment was offered to three patients, including paclitaxel, gemcitabin and 5-FU–platinum. The considerable use of third-line therapies after progression of disease might have hampered survival analysis, which in fact showed no significant difference between the treatment arms (although progression-free survival differed).

Previous SectionNext Section

Discussion

This study represents a prospectively randomised trial in a very homogenous population. Only patients who were refractory to the standard first-line treatment of advanced ovarian cancer (i.e. platinum plus paclitaxel) were recruited. This selection represents a patient group with an extremely poor prognosis. At the moment, there is only limited evidence that these patients benefit from second-line chemotherapy at all, and more studies in this subgroup are necessary before any recommendations or guidelines can be established.

A randomised trial of the National Cancer Institute of Canada has shown an advantage for one arm over another when comparing 3-weekly topotecan days 1–5 to weekly topotecan in 78 patients, of whom 60% had received prior paclitaxel,and 60% were platinum refractory [23]. This advantage was limited to overall response (23% versus 8%). Progression-free survival differed only at a non-significant level (8 versus 13 weeks), and overall survival did not differ at all. Our trial showed a statistically significant advantage of one arm (treosulfan) with respect to progression-free survival, but failed to show any difference in overall survival. In addition, no differences with respect to response rates were observed. In fact, we did not observe any objective response. The latter could indicate a lack of activity of both study drugs, treosulfan and leuprorelin. However, even higher response rates as reported in the literature did not translate to longer progression-free and overall survival. A prospectively randomised trial comparing liposomal doxorubicin with topotecan included 254 platinum refractory patients; in addition, about two-thirds had received paclitaxel as part of prior therapy [24]. No significant differences were observed in the refractory subgroup: response rates were 7% and 12%, median progression-free survival was 9 and 14 weeks, and median survival was 33 and 37 weeks, respectively. Our observations of median progression free survival of 11 and 17 weeks and median survival of 30 and 36 weeks fit well with the reported data in this poor prognostic subgroup, although we did not observe any objective responses. Another randomised trial in 81 platinum refractory patients comparing paclitaxel with paclitaxel–epirubicin reported response rates of 17% and 34% translating to 2-year survival of 10% and 18% [25]. The corresponding 2-year survival in our trial was 19% and 22%, thus indicating the limited value of objective response rates as predictors for survival or progression-free survival in this poor prognostic subgroup of patients with truely refractory ovarian cancer.

Nevertheless, achieving an objective response might be beneficial in this palliative setting, especially if bulky tumours induce symptoms such as pain or bowl obstruction. However, objective response rates might not sufficiently reflect this potential benefit. Therefore, different response criteria that better reflect the palliative approach in these patients should be evaluated prospectively (e.g. symptom relief, reduction of pain medication or ability of enteral food intake). The development of better tools for the evaluation of genuine second-line chemotherapies becomes even more necessary when taking into account the fact that ovarian cancer becomes more of a chronic disease: mortality does not change substantially, but median and 5-year survival improves, thus indicating a growing need for efficient second-line and higher treatment. These therapies should allow tumour control and simultaneously should not reduce life quality.

This study reports mild toxicity data for both treatment arms, treosulfan and leuprorelin acetate, but, due to the very poor activity levels observed in both arms, adds only limited evidence to the issue of whether patients with refractory ovarian cancer benefit from second-line chemotherapy at all. Even stratified analysis in patients with progressive ovarian cancer versus patients experiencing relapse 3–6 months after first-line therapy, or patients with measurable versus non-measurable diseases, did not demonstrate any subgroup of patients in whom the administration of treosulfan second-line chemotherapy could demonstrate a clinically relevant benefit. Although a very short progression-free interval and the presence of bi-dimensionally measurable disease seemed to turn a bad prognosis into a worse prognosis, none of the differences between the strata showed a consistent and clinically relevant difference in survival. Only progression-free survival was influenced by these factors to some extent. Our data did not indicate that patients with a progression-free interval of >3 months but

However, results were disappointing in all subgroups. A rather small benefit was traded for a higher rate of fatigue in patients receiving chemotherapy. A gain of 6 weeks median progression-free survival in the superior chemotherapy arm in our study and some advantages with respect to response rates in other trials do not convincingly answer the question of whether second-line chemotherapy offers any benefit for patients with refractory ovarian cancer. Further studies are necessary to help to evaluate whether chemotherapy has a role in this subgroup of patients with a very unfavourable prognosis. A randomised comparison between best supportive care and the most active chemotherapy regimen available could theoretically be an appropriate design for such a trial. However, the German AGO investigators did not even broadly accept a randomisation between a hormonal treatment and a chemotherapy arm, as measured by an extremely slow recruitment rate. Furthermore, this study had to be closed prematurely after an interim analysis indicated only very limited activity in both treatment arms. A trial using best supportive care as one treatment arm would probably not be accepted either, although the above-mentioned efficacy data from chemotherapy studies do not provide more optimistic results.

Treosulfan showed an acceptable toxicity profile and at least some activity compared with leuprorelin acetate, thus allowing continuation of clinical research with this alkylating agent. Our subsequent trial in the refractory population compares treosulfan with topotecan (AGO protocol OVAR-2.3) and recruitment is much better, indicating that investigators more easily accept trials comparing two chemotherapy regimens. Quality of life evaluation was included in this protocol in an attempt to improve understanding of the nature of potential gains from second-line therapy.

Besides treosulfan and topotecan, which are further evaluated by our group, several chemotherapy agents have shown some activity in platinum- and paclitaxel-refractory ovarian cancer, and could serve as comparators in pending further trials: ifosfamide [26], hexamethylmelamine [27], gemcitabin [28] and liposomal doxorubicin [23,29]. The difficult task of recruiting large homogenous patient populations to second-line trials supports the ongoing discussions and activities in cooperative groups and networks, such as the worldwide Gynecologic Cancer InterGroup (GCIG), which is already planning and performing intergroup trials of second-line treatment of ovarian cancer.

Read Full Post »

Urological Cancers of Men

Reporter and Curator: Larry H. Bernstein, MD, FCAP

 

Impact of the U.S. Preventive Services Task Force Recommendations Against PSA Screening on Prostate Biopsy and Cancer Detection Rates.

B Bhindi, M Mamdani, GS Kulkarni, A Finelli, RJ Hamilton, J Trachtenberg, et al.
The Journal of Urology 12/2014; http://dx.doi.org:/10.1016/j.juro.2014.11.096

To determine if the USPSTF recommendation against PSA screening was associated with a change in biopsy and cancer detection rates.

We conducted a time series analysis (10/2008-06/2013) of prostate biopsies performed at University Health Network (Toronto). Biopsies for active surveillance or solely targeting MRI-detected lesions were excluded. Interventional auto-regressive integrated moving average (ARIMA) models with step functions were used to examine changes in the number of biopsies performed and cancers detected per month. Low risk PC (LRPC) was defined as no Gleason pattern ≥4, ≤3 cores involved or ≤1/3 of total number of cores involved, and no core with >50% cancer involvement. Intermediate-to-high grade PC (I-HGPC) was defined as Gleason 7-10.

A total of 3408 biopsies were performed and 1601 (47.0%) PCs were detected (LRPC=563 (16.5%); I-HGPC=914 (26.8%)). The median number of biopsies per month decreased from 58.0 (IQR=54.5-63.0) before recommendations to 35.5 (IQR=27.0-41.0) afterward (p=0.003), while median number of patients undergoing their first-time biopsies decreased from 42.5 (IQR=37.5-45.5) to 24.0 (IQR=19.0-32.5, p=0.025). The median number of LRPCs detected per month decreased from 8.5 (IQR=6.5-10.5) to 5.5 (IQR=4.0-7.0, p=0.012), while the median number of I-HGPCs per month decreased from 17.5 (IQR=14.5-21.5) to 10.0 (IQR=9.0-12.0, p<0.001).

Following the USPSTF recommendation, the number of biopsies performed (total and first-time biopsies), based on referrals from our catchment area, have decreased. This is likely due to decreased use of PSA-screening. Although encouraging that fewer low risk PCs are being diagnosed, the sudden decrease in the detection rate of Gleason 7-10 PCs is concerning.

 

Tumour genomic and microenvironmental heterogeneity for integrated prediction of 5-year biochemical recurrence of prostate cancer: a retrospective cohort study.

E Lalonde, AS Ishkanian, J Sykes, M Fraser, H Ross-Adams, N Erho, et al.
The Lancet Oncology 12/2014; 15(13):1521-32.
http://dx.doi.org:/10.1016/S1470-2045(14)71021-6

Clinical prognostic groupings for localised prostate cancers are imprecise, with 30-50% of patients recurring after image-guided radiotherapy or radical prostatectomy. We aimed to test combined genomic and microenvironmental indices in prostate cancer to improve risk stratification and complement clinical prognostic factors.

We used DNA-based indices alone or in combination with intra-prostatic hypoxia measurements to develop four prognostic indices in 126 low-risk to intermediate-risk patients (Toronto cohort) who will receive image-guided radiotherapy. We validated these indices in two independent cohorts of 154 (Memorial Sloan Kettering Cancer Center cohort [MSKCC] cohort) and 117 (Cambridge cohort) radical prostatectomy specimens from low-risk to high-risk patients. We applied unsupervised and supervised machine learning techniques to the copy-number profiles of 126 pre-image-guided radiotherapy diagnostic biopsies to develop prognostic signatures. Our primary endpoint was the development of a set of prognostic measures capable of stratifying patients for risk of biochemical relapse 5 years after primary treatment.

Biochemical relapse was associated with indices of tumour hypoxia, genomic instability, and genomic subtypes based on multivariate analyses. We identified four genomic subtypes for prostate cancer, which had different 5-year biochemical relapse-free survival. Genomic instability is prognostic for relapse in both image-guided radiotherapy (multivariate analysis hazard ratio [HR] 4·5 [95% CI 2·1-9·8]; p=0·00013; area under the receiver operator curve [AUC] 0·70 [95% CI 0·65-0·76]) and radical prostatectomy (4·0 [1·6-9·7]; p=0·0024; AUC 0·57 [0·52-0·61]) patients with prostate cancer, and its effect is magnified by intratumoral hypoxia (3·8 [1·2-12]; p=0·019; AUC 0·67 [0·61-0·73]). A novel 100-loci DNA signature accurately classified treatment outcome in the MSKCC low-risk to intermediate-risk cohort (multivariate analysis HR 6·1 [95% CI 2·0-19]; p=0·0015; AUC 0·74 [95% CI 0·65-0·83]). In the independent MSKCC and Cambridge cohorts, this signature identified low-risk to high-risk patients who were most likely to fail treatment within 18 months (combined cohorts multivariate analysis HR 2·9 [95% CI 1·4-6·0]; p=0·0039; AUC 0·68 [95% CI 0·63-0·73]), and was better at predicting biochemical relapse than 23 previously published RNA signatures.

This is the first study of cancer outcome to integrate DNA-based and microenvironment-based failure indices to predict patient outcome. Patients exhibiting these aggressive features after biopsy should be entered into treatment intensification trials.
Prostate cancer: Is prostatectomy for Gleason score 6 a treatment failure?

Theodorus H van der Kwast, Monique J Roobol
Nature Reviews Urology 12/2014; http://dx.doi.org:/10.1038/nrurol.2014.335

Molecular and clinical support for a four-tiered grading system for bladder cancer based on the WHO 1973 and 2004 classifications
BWG van Rhijn, M Musquera, L Liu, AN Vis, TCM Zuiverloon, GJLH van Leenders, WJ Kirkels, EC Zwarthoff, ER Boevé, …, TH van der Kwast

Modern pathology : an official journal of the United States and Canadian Academy of Pathology, Inc 11/2014; http://dx.doi.org:/10.1038/modpathol.2014.154

Currently, the use of two classification systems for bladder cancer grade is advocated in clinical guidelines because the WHO2004 classification has not been sufficiently validated with biological markers and follow-up. The slides of 325 primary non-muscle invasive bladder cancers from three hospitals were reviewed by one uro-pathologist in two separate sessions for the WHO1973 (G1, G2 and G3) and 2004 (papillary urothelial neoplasm of low malignant potential (LMP), low-grade (LG) and high-grade (HG)) classifications. FGFR3 status was examined with PCR-SNaPshot analysis. Expression of Ki-67, P53 and P27 was analyzed by immuno-histochemistry. Clinical recurrence and progression were determined. We performed validation and cross-validation of the two systems for grade with molecular markers and clinical outcome. Multivariable analyses were done to predict prognosis and pT1 bladder cancer. Grade review resulted in 88 G1, 149 G2 and 88 G3 lesions (WHO1973) and 79 LMP, 101 LG and 145 HG lesions (WHO2004). Molecular validation of both grading systems showed that FGFR3 mutations were associated with lower grades whereas altered expression (Ki-67, P53 and P27) was found in higher grades. Clinical validation showed that the two classification systems were both significant predictors for progression but not for recurrence. Cross-validation of both WHO systems showed a significant stepwise increase in biological (molecular markers) and clinical (progression) potential along the line: G1-LG-G2-HG-G3. The LMP and G1 categories had a similar clinical and molecular profile. On the basis of molecular biology and multivariable clinical data, our results support a four-tiered grading system using the 1973 and 2004 WHO classifications with one low-grade (LMP/LG/G1) category that includes LMP, two intermediate grade (LG/G2 and HG/G2) categories and one high-grade (HG/G3) category.Modern Pathology advance online publication, 28 November 2014; doi:10.1038/modpathol.2014.154.

Read Full Post »

Imaging-guided cancer treatment

Imaging-guided cancer treatment

Writer & reporter: Dror Nir, PhD

It is estimated that the medical imaging market will exceed $30 billion in 2014 (FierceMedicalImaging). To put this amount in perspective; the global pharmaceutical market size for the same year is expected to be ~$1 trillion (IMS) while the global health care spending as a percentage of Gross Domestic Product (GDP) will average 10.5% globally in 2014 (Deloitte); it will reach ~$3 trillion in the USA.

Recent technology-advances, mainly miniaturization and improvement in electronic-processing components is driving increased introduction of innovative medical-imaging devices into critical nodes of major-diseases’ management pathways. Consequently, in contrast to it’s very small contribution to global health costs, medical imaging bears outstanding potential to reduce the future growth in spending on major segments in this market mainly: Drugs development and regulation (e.g. companion diagnostics and imaging surrogate markers); Disease management (e.g. non-invasive diagnosis, guided treatment and non-invasive follow-ups); and Monitoring aging-population (e.g. Imaging-based domestic sensors).

In; The Role of Medical Imaging in Personalized Medicine I discussed in length the role medical imaging assumes in drugs development.  Integrating imaging into drug development processes, specifically at the early stages of drug discovery, as well as for monitoring drug delivery and the response of targeted processes to the therapy is a growing trend. A nice (and short) review highlighting the processes, opportunities, and challenges of medical imaging in new drug development is: Medical imaging in new drug clinical development.

The following is dedicated to the role of imaging in guiding treatment.

Precise treatment is a major pillar of modern medicine. An important aspect to enable accurate administration of treatment is complementing the accurate identification of the organ location that needs to be treated with a system and methods that ensure application of treatment only, or mainly to, that location. Imaging is off-course, a major component in such composite systems. Amongst the available solution, functional-imaging modalities are gaining traction. Specifically, molecular imaging (e.g. PET, MRS) allows the visual representation, characterization, and quantification of biological processes at the cellular and subcellular levels within intact living organisms. In oncology, it can be used to depict the abnormal molecules as well as the aberrant interactions of altered molecules on which cancers depend. Being able to detect such fundamental finger-prints of cancer is key to improved matching between drugs-based treatment and disease. Moreover, imaging-based quantified monitoring of changes in tumor metabolism and its microenvironment could provide real-time non-invasive tool to predict the evolution and progression of primary tumors, as well as the development of tumor metastases.

A recent review-paper: Image-guided interventional therapy for cancer with radiotherapeutic nanoparticles nicely illustrates the role of imaging in treatment guidance through a comprehensive discussion of; Image-guided radiotherapeutic using intravenous nanoparticles for the delivery of localized radiation to solid cancer tumors.

 Graphical abstract

 Abstract

One of the major limitations of current cancer therapy is the inability to deliver tumoricidal agents throughout the entire tumor mass using traditional intravenous administration. Nanoparticles carrying beta-emitting therapeutic radionuclides [DN: radioactive isotops that emits electrons as part of the decay process a list of β-emitting radionuclides used in radiotherapeutic nanoparticle preparation is given in table1 of this paper.) that are delivered using advanced image-guidance have significant potential to improve solid tumor therapy. The use of image-guidance in combination with nanoparticle carriers can improve the delivery of localized radiation to tumors. Nanoparticles labeled with certain beta-emitting radionuclides are intrinsically theranostic agents that can provide information regarding distribution and regional dosimetry within the tumor and the body. Image-guided thermal therapy results in increased uptake of intravenous nanoparticles within tumors, improving therapy. In addition, nanoparticles are ideal carriers for direct intratumoral infusion of beta-emitting radionuclides by convection enhanced delivery, permitting the delivery of localized therapeutic radiation without the requirement of the radionuclide exiting from the nanoparticle. With this approach, very high doses of radiation can be delivered to solid tumors while sparing normal organs. Recent technological developments in image-guidance, convection enhanced delivery and newly developed nanoparticles carrying beta-emitting radionuclides will be reviewed. Examples will be shown describing how this new approach has promise for the treatment of brain, head and neck, and other types of solid tumors.

The challenges this review discusses

  • intravenously administered drugs are inhibited in their intratumoral penetration by high interstitial pressures which prevent diffusion of drugs from the blood circulation into the tumor tissue [1–5].
  • relatively rapid clearance of intravenously administered drugs from the blood circulation by kidneys and liver.
  • drugs that do reach the solid tumor by diffusion are inhomogeneously distributed at the micro-scale – This cannot be overcome by simply administering larger systemic doses as toxicity to normal organs is generally the dose limiting factor.
  • even nanoparticulate drugs have poor penetration from the vascular compartment into the tumor and the nanoparticles that do penetrate are most often heterogeneously distributed

How imaging could mitigate the above mentioned challenges

  • The inclusion of an imaging probe during drug development can aid in determining the clearance kinetics and tissue distribution of the drug non-invasively. Such probe can also be used to determine the likelihood of the drug reaching the tumor and to what extent.

Note: Drugs that have increased accumulation within the targeted site are likely to be more effective as compared with others. In that respect, Nanoparticle-based drugs have an additional advantage over free drugs with their potential to be multifunctional carriers capable of carrying both therapeutic and diagnostic imaging probes (theranostic) in the same nanocarrier. These multifunctional nanoparticles can serve as theranostic agents and facilitate personalized treatment planning.

  • Imaging can also be used for localization of the tumor to improve the placement of a catheter or external device within tumors to cause cell death through thermal ablation or oxidative stress secondary to reactive oxygen species.

See the example of Vintfolide in The Role of Medical Imaging in Personalized Medicine

vinta

Note: Image guided thermal ablation methods include radiofrequency (RF) ablation, microwave ablation or high intensity focused ultrasound (HIFU). Photodynamic therapy methods using external light devices to activate photosensitizing agents can also be used to treat superficial tumors or deeper tumors when used with endoscopic catheters.

  • Quality control during and post treatment

For example: The use of high intensity focused ultrasound (HIFU) combined with nanoparticle therapeutics: HIFU is applied to improve drug delivery and to trigger drug release from nanoparticles. Gas-bubbles are playing the role of the drug’s nano-carrier. These are used both to increase the drug transport into the cell and as ultrasound-imaging contrast material. The ultrasound is also used for processes of drug-release and ablation.

 HIFU

Additional example; Multifunctional nanoparticles for tracking CED (convection enhanced delivery)  distribution within tumors: Nanoparticle that could serve as a carrier not only for the therapeutic radionuclides but simultaneously also for a therapeutic drug and 4 different types of imaging contrast agents including an MRI contrast agent, PET and SPECT nuclear diagnostic imaging agents and optical contrast agents as shown below. The ability to perform multiple types of imaging on the same nanoparticles will allow studies investigating the distribution and retention of nanoparticles initially in vivo using non-invasive imaging and later at the histological level using optical imaging.

 multi

Conclusions

Image-guided radiotherapeutic nanoparticles have significant potential for solid tumor cancer therapy. The current success of this therapy in animals is most likely due to the improved accumulation, retention and dispersion of nanoparticles within solid tumor following image-guided therapies as well as the micro-field of the β-particle which reduces the requirement of perfectly homogeneous tumor coverage. It is also possible that the intratumoral distribution of nanoparticles may benefit from their uptake by intratumoral macrophages although more research is required to determine the importance of this aspect of intratumoral radionuclide nanoparticle therapy. This new approach to cancer therapy is a fertile ground for many new technological developments as well as for new understandings in the basic biology of cancer therapy. The clinical success of this approach will depend on progress in many areas of interdisciplinary research including imaging technology, nanoparticle technology, computer and robot assisted image-guided application of therapies, radiation physics and oncology. Close collaboration of a wide variety of scientists and physicians including chemists, nanotechnologists, drug delivery experts, radiation physicists, robotics and software experts, toxicologists, surgeons, imaging physicians, and oncologists will best facilitate the implementation of this novel approach to the treatment of cancer in the clinical environment. Image-guided nanoparticle therapies including those with β-emission radionuclide nanoparticles have excellent promise to significantly impact clinical cancer therapy and advance the field of drug delivery.

Read Full Post »

Multiple Lung Cancer Genomic Projects Suggest New Targets, Research Directions for Non-Small Cell Lung Cancer

Curator, Writer: Stephen J. Williams, Ph.D.

UPDATED 08/11/2025

Human Curation vs. AI tools: ChatGPT & Knowledge Graphs [KG] Output: A case study for the following original curation:

  • Multiple Lung Cancer Genomic Projects Suggest New Targets, Research Directions for Non-Small Cell Lung Cancer

https://pharmaceuticalintelligence.com/2014/09/05/multiple-lung-cancer-genomic-projects-suggest-new-targets-research-directions-for-non-small-cell-lung-cancer/

 

This update was performed by the following methods:
A. GPT 5 Text analysis and Reasoning
B. Insertion of Knowledge Graph on topic Curation of Genomic Analysis from Non Small Cell Lung Cancer Studies  from Nodus Labs using InfraNodus software
C. Domain Knowledge Expert evaluation of the Update outcomes
This article has the following Structure:
Part A: Introduction to LLM, Knowledge Graph software InfraNodus, ChatGPT5 and Background Information on curated material for Test Case
Part B: InfraNodus Analysis of manual curation and Knowledge Graph Creation
Part C: Chat GPT 5 Analysis of Manually Curated Material
Part D: Curation entitled Multiple Lung Cancer Genomic Projects Suggest New Targets, Research Directions for Non-Small Cell Lung Cancer originally published on 09/05/2014
Results of Article Update with GPT 5
1. GPT5 alone was not able to understand the goal of the article, namely to determine knowledge gaps in a particular research area involving 5 genomic studies on lung cancer patients
2. GPT5 alone was not able to group concepts or comonalities between biological pathways unless supplied with a manually curated list of KEGG pathways from a list of mutated genes.  However this precluded any effect that fusion proteins had on the analysis and so GPT5 would only concentrate on mutated genes commonly found in literature
3. GPT was not able to access some of the open Access databases like NCBI Gene Ontology database
Results of Article Update with KnowledgeGraph presentation to GPT 5
4. As the Knowledge Graph understood the importance of fusion proteins and transversions, the knowledgegraph augmented the GPT analysis and so enriched the known pathways as well as could correctly identify the less represented pathways in the knowledge graph
5.  This led to the identification of many novel signaling pathways not identified in the original analysis, and was able to perform this task with ease and speed

6. GPT with InfraNodus Analysis was able to propose pertinent questions for future research (the goal of the original curation) such as:

  • How does the interaction between [[EGFR]] mutations and sex-specific gene alterations, including [[RBM10]], influence treatment outcomes in lung adenocarcinoma?
  • How does the intersection of mutational patterns from smoking influence pathway activation in NSCLC, and can identifying these interactions improve targeted therapy development?
Novelty in comparison to Original article published on 09/05/2014
7. it appears that manual curation is necessary to assist in the building of relevant knowledge graphs in the biomedical fields to augment generative AI analysis
8. by itself, generative AI is not optimized for inference of higher concepts from biomedical text, and therefore, at this point, requires the input from human curators developing domain-specific knowledge graphs
9.  The combination of ChatGPT5 and Knowledge graphs of this manually curated biomedical text added a further layer of complexity of gaps of knowledge not seen in the original curations including the need to study noncanonical signaling pathways like WNT and Hedgehog in smoker versus nonsmoker cohorts of lung cancer patients

A Comparison of Manual Expert-Curative and an LLM-based analysis of Knowledge Gaps  in Non Small Lung Cancer Whole Exome Sequencing Studies and a Use Case Example of Chat GPT 5

Part A: Introduction to LLM, Knowledge Graph software InfraNodus, ChatGPT5 and Background Information on curated material for Test Case

The development of Large Language Models (LLMs), together with development of knowledge graphs, have facilitated the ability to analyze text and determine the relationships among the various concepts contained within series of texts.  These concepts and relationships can be visualized, and new insights inferred from these visualizations.  As a result, this type of analysis suggests new directions and lines of research.

 

Alternatively,  these types of visualizations can also reveal gaps in knowledge which should be addressed. A new type of LLM and visualization tools have been developed to understand the gaps in knowledge in biomedical text.

Nodus Labs InfrNodus AI Knowledge Graph Software Tools Allow Text Relationship Visualization and Integrated AI Functionality

 

Infranodus makes knowlegde graphs from text and then is able to visualize the relationships between concepts (or nodes).  In doing so, the tool also highlights the various knowledge gaps (or large differences between nodes) which can be used to investigate new hypotheses and research directions of previously univestigated relationships between concepts.  This generates new research questions, in which these gaps can be used as prompts in the software’s integrated AI tool.  The AI tool, much like a GPT, returns recommendations for research to be conducted in the area.

https://infranodus.com/

In addition, the InfraNodus software can detect if text is too biased on a particular concept or conclusion, and using a GPT3 or GPT4, can determine if the nodes are too dispersed and will recommend which gaps should be focused on.

The software can upload any biomedical text in various formats

A full demonstration is on their website but a good summary is found on their Youtube site at

https://www.youtube.com/watch?v=wCEhiIJsmrg

A couple of use cases include

 

 

Previously we had manually curated and analyzed the knowledge gaps from a series of publications on whole exome sequencing  of biopsied tumors from cohorts of non small lung cancer patients. This curation (from 2016) is seen in the lower half of this updated link below and I separated with a bar and highlighted in Yellow as Text for AI Analysis.

https://pharmaceuticalintelligence.com/2014/09/05/multiple-lung-cancer-genomic-projects-suggest-new-targets-research-directions-for-non-small-cell-lung-cancer/

A literature analysis of the driver mutations found in five NSLC exome sequencing projects:

  1. Comprehensive genomic characterization of squamous cell lung cancersNature 2012, 489(7417):519-525.
  2. A genomics-based classification of human lung tumorsScience translational medicine 2013, 5(209):209ra153.
  3. Govindan R, Ding L, Griffith M, Subramanian J, Dees ND, Kanchi KL, Maher CA, Fulton R, Fulton L, Wallis J et alGenomic landscape of non-small cell lung cancer in smokers and never-smokersCell 2012, 150(6):1121-1134.
  4. Imielinski M, Berger AH, Hammerman PS, Hernandez B, Pugh TJ, Hodis E, Cho J, Suh J, Capelletti M, Sivachenko A et alMapping the hallmarks of lung adenocarcinoma with massively parallel sequencingCell 2012, 150(6):1107-1120.
  5. Peifer M, Fernandez-Cuesta L, Sos ML, George J, Seidel D, Kasper LH, Plenker D, Leenders F, Sun R, Zander T et alIntegrative genome analyses identify key somatic driver mutations of small-cell lung cancerNature genetics 2012, 44(10):1104-1110.

 

were performed.

The purpose of this analysis was to uncover biological functions related to the sets of mutated genes with limited research publications in the area of  non small cell lung cancer.  The identification of such biological functions would represent a gap in knowledge in this disease.  In addition, this analysis attempted to find new lines of research or potential new biotargets to investigate for lung cancer therapy.

 

 

 

However this manual method is time consuming and may miss relationships not defined in a GO ontology or gene knowledgebases.

Therefore we turned to an AI-driven approach:

  1. Using InfraNodus ability to develop a knowledge graph based on our curation and determine if the AI platform could infer knowledge gaps
  2. Utilize Chat GPT5 to analyze the same curated set to determine if OpenAI analysis would lead to the similar analysis from curated material
  3. Determine if combining a knowledge graph within GPT would lead to a higher level of analysis

See below (Part D) of this update for the curated studies which were included in this analysis and the text which was entered into both InfraNodus and Chat GPT5. 

As a summary, it seems that manual curation is necessary to assist in the building of relevant knowledge graphs in the biomedical fields to augment generative AI analysis.  In addition, it appears that , by itself, generative AI is not optimized for inference of higher concepts from biomedical text, and therefore, at this point, requires the input from human curators developing domain-specific knowledge graphs.

 

Part B. InfraNodus Analysis of manual curation and Knowledge Graph Creation

Methods: 

Text of the curation was copied and directly pasted into the text analysis module of InfraNodus.  There was no editing of words however genes in the curation were linked to their GeneCard entry. GeneCards is a database run by the Weizmann Institute.  InfraNodus utilizes a combination of LLMs and its own GraphRAG system to provide insights from text analysis. While it leverages various models, including those from OpenAI and Anthropic, it’s not limited to a single LLM. Instead, InfraNodus integrates these models within its GraphRAG framework, which enhances their capabilities by adding a relational understanding of the context through a knowledge graph.

InfraNodus then autogenerates a knowledge graph and returns entities and relationships between entities.  InfraNodus offers the opportunity to modify the knowledge graph however for this analysis we used the first graph InfraNodus generated.  Inspection of this graph (as shown below) was deemed reasonable.

 

Results

The knowledge graph of the input text is shown below:

InfraNodus generated Knowledge Graph of 5 WES Non Smal Cell Lung Cancer studies involving smokers and non smokers

 

Four main concepts were returned: tumors, genes, literature, and mutations.

A snapshot of the Analysis window is given below.  It should be noted that InfraNodus felt there needed to be more connections between Pathway and Mutational Patterns.

An InfraNodus reposrt with Knowlege Graph on Whole Exome Sequencing studies in NSCLC to determine mutational spectrum in smokers versus non smokers

Auto generated summary report

Context name: text_250808T0144

Created on: aug 7, 2025 9:47 pm

Last updated on: aug 7, 2025 10:10 pm

Main concepts:

[[tumors]], analysis, [[mutations]], identify, [[lung]], [[genes]]

Main topics:

  1. Tumor Genomics: [[tumors]] [[lung]] reveal
  2. Genetic Alterations: identify [[genes]] study
  3. Pathway Analysis: analysis pathway literature
  4. Mutation Patterns: [[mutations]] [[egfr]] [[rbm10]]

Structural gap (topics to connect):

  1. Pathway Analysis: analysis pathway
  2. Smoking Influence: mutational [[smoking]]

Topical connectors:

alk clinical [[egfr]] mutational pathway [[paper]] found key literature study [[genomic]] reveal [[transversion]]

 

Top relations / ngrams:

1) [[lung]] [[tumors]]

2) alk fusion

3) link function

4) eml alk

5) function [[gene_ontology]]

Modulary: 0.47

Relations:

InfraNodus identified 744 relations between entities (nodes)

A list of some of the more frequent are given here:

source target occurrences weight betweenness
[[lung]] [[tumors]] 8 24 0.4676
analysis pathway 5 12 0.2291
significantly [[genes]] 5 9 0.1074
significantly [[mutated]] 4 12 0.0281
[[mutated]] [[genes]] 4 12 0.0847
[[transversion]] high 3 12 0.0329
[[smoking]] history 3 10 0.0352
study identify 3 9 0.2051
mutational pattern 3 9 0.0921
[[rbm10]] [[mutations]] 3 8 0.1776
literature analysis 3 7 0.2218
[[egfr]] [[mutations]] 3 7 0.2139
[[transversion]] group 3 7 0.0259
enriched cohort 3 6 0.0219
[[whole_exome_sequencing]] [[tumors]] 3 6 0.3485
identify [[genes]] 3 6 0.2268
including analysis 3 5 0.1985
alteration [[genes]] 3 4 0.1298
[[tumors]] analysis 3 4 0.5192
alk fusion 2 15 0.0671
link function 2 14 0.0269
function [[gene_ontology]] 2 13 0.0054

 

Notice how the betweenness or importance of connection of disparate concepts vary but are high between concepts like tumors and analysis, or lung and tumor, however many important linked concepts like alk and fusion may have low betweenness but are mentioned frequently and have a much higher weight or closeness to each other. Gene-mutations-transversions-smoking seem to have a high correspondence to each other

For a full list please see the file

InfraNodus relations five WES studies on NSCLC and smoking

sjwilliams_text_250808T0144_nodedataon NSCLCWESstudies

Generated the following responses using AI to bridge the gap between

  1. Mutation Patterns: [[mutations]][[egfr]][[rbm10]]and
  2. Genetic Alterations: identify[[genes]]study:The recent comprehensive studies on lung adenocarcinoma have significantly advanced our understanding of the genetic landscape by identifying key mutations and their intricate interactions. Notably, EGFR and RBM10 exhibit distinct mutational patterns, with RBM10 inactivations being notably enriched in male cohorts. This gender-linked enrichment underscores a potential differential oncogenic pathway involving ERBB2 and RB1 alterations.Moreover, these projects emphasize the quest to map significant gene alterations within lung adenocarcinoma. The identification of such genes not only corroborates prior reports but also expands upon them by highlighting new connections between mutation signatures and clinical factors like smoking history. These findings are crucial as they can inform future therapeutic targeting strategies, ensuring that personalized treatment approaches consider both gender-specific genomic enrichments and mutation-driven tumorigenesis pathways elucidated through rigorous analyses.elaborate

 

<MainTopics>

  1. Tumor Genomics: [[tumors]], [[lung]], reveal, base, [[genomic]], [[data]], classification, subtype,
  2. Genetic Alterations: identify, [[genes]], study, alteration, reported, significantly, [[lung_adenocarcinoma]], key,
  3. Pathway Analysis: analysis, pathway, literature, including, activation, target, [[nsclc]], [[patients]],
  4. Mutation Patterns: [[mutations]], [[egfr]], [[rbm10]], male, enriched, cohort, [[erbb2]], noted,
  5. Smoking Influence: mutational, [[smoking]], [[transversion]], pattern, high, notably, [[smokers]], show,
  6. Research Strategies: found, [[paper]], [[omics]], unique, profile, result, multus, characterization,
  7. Targeted Therapy: alk, [[lung_cancer]], fusion, [[therapy]], ro, eml, include, targeted,
  8. Mutation Signatures: clinical, [[tumor]], approach, mutation, sample, signature, gender, specific,
  9. Gene Function: link, [[gene]], note, function, author, [[gene_ontology]],

</MainTopics>

 

<TopicalGap>:

  1. Genetic Alterations: identify [[genes]]
  2. Mutation Patterns: [[mutations]] [[egfr]]

</TopicalGap>

 

 

questions generated using AI to help you explore “alk, clinical, [[egfr]], mutational, pathway, [[paper]], found, key, literature, study, [[genomic]], reveal, [[transversion]]…”:How do mutational patterns, specifically EGFR mutations and transversions related to smoking history, influence the effectiveness of targeted therapies in NSCLC patients?elaborate

 

ideas generated using AI to help you explore “alk, clinical, [[egfr]], mutational, pathway, [[paper]], found, key, literature, study, [[genomic]], reveal, [[transversion]]…”:Develop a predictive model that utilizes genomic data and smoking history to forecast patient response to targeted therapies. This model would identify key mutational signatures linked to EGFR and other genes, highlighting the impact of smoking-induced transversions on drug efficacy.elaborate

 

Project Notes

 

The recent comprehensive studies on lung adenocarcinoma have significantly advanced our understanding of the genetic landscape by identifying key mutations and their intricate interactions. Notably, EGFR and RBM10 exhibit distinct mutational patterns, with RBM10 inactivations being notably enriched in male cohorts. This gender-linked enrichment underscores a potential differential oncogenic pathway involving ERBB2 and RB1 alterations.

 

Moreover, these projects emphasize the quest to map significant gene alterations within lung adenocarcinoma. The identification of such genes not only corroborates prior reports but also expands upon them by highlighting new connections between mutation signatures and clinical factors like smoking history. These findings are crucial as they can inform future therapeutic targeting strategies, ensuring that personalized treatment approaches consider both gender-specific genomic enrichments and mutation-driven tumorigenesis pathways elucidated through rigorous analyses.”

 

<ConceptualGateways>

alk

clinical

[[egfr]]

mutational

pathway

[[paper]]

found

key

literature

study

[[genomic]]

reveal

[[transversion]]

</ConceptualGateways>

 

 

How do mutational patterns, specifically EGFR mutations and transversions related to smoking history, influence the effectiveness of targeted therapies in NSCLC patients?

 

The report from the NCI Bulletin outlines significant advancements in understanding lung cancer through genome sequencing projects. These studies have revealed a plethora of genetic and epigenetic alterations across various forms of lung tumors, including adenocarcinomas, squamous cell carcinomas, and small cell lung cancers. Notably, some identified alterations could be targeted by existing therapies, providing potential new avenues for treatment.Dr. Meyerson emphasizes the complexity of these genetic changes, highlighting that distinct mechanisms inactivating genes can vary between tumors. The report also notes gaps in knowledge regarding non-coding DNA alterations, which comprise a major part of the human genome.Key findings include:1. Comprehensive genomic analyses revealing unique driver mutations in lung adenocarcinoma, such as those affecting MET and ERBB2, alongside significant mutations in known cancer drivers like TP53 and KRAS.2. A classification system based on genomic data enabling more accurate patient stratification—achieving a 75% classification rate of lung cancer subtypes.3. Smoking history is shown to influence mutational patterns significantly, with smokers exhibiting a higher incidence of point mutations compared to never-smokers.Moreover, the integration of genomic data and pathway analysis highlighted recurrent mutations across various pathways related to tumorigenesis, suggesting new therapeutic targets and underscoring the importance of personalized medicine approaches that factor in gender-specific mutation distributions.This synthesis of findings not only corroborates earlier studies but also extends our understanding of the interplay between genomic alterations, smoking habits, and clinical outcomes in lung cancer. Future research is needed to explore the implications of these findings further and to develop targeted therapies that leverage the identified genetic alterations.

 

  1. Tumor Genomics
  2. Genetic Alterations
  3. Pathway Analysis
  4. Mutation Patterns

 

Main Ideas Summary from Infranodus:

 

The report from the NCI Bulletin highlights significant developments in lung cancer genomics through five genome sequencing projects. These studies have uncovered various genetic and epigenetic alterations across multiple forms of lung cancer, including adenocarcinomas, squamous cell cancers, and small cell lung cancers. Notably, these alterations may correspond to existing drugs, offering new avenues for targeted therapy.

Key findings include the identification of unique mutations in genes like NF1, MET, and ERBB2, with particular attention to smoking’s role in mutational patterns. The analysis shows that smokers exhibit a higher incidence of specific point mutations, marking a distinct divergence in mutation profiles compared to never-smokers.

The research also emphasizes the need for continued exploration of the data to link mutation signatures with clinical outcomes, particularly regarding gender-specific differences in mutation prevalence. Emerging insights suggest that pathways involving MYC and alterations in splicing factors could be vital targets for future therapeutic strategies.

Overall, the studies collectively underscore an urgent need for integrating genomic data into clinical practice, which can lead to more personalized treatment approaches for lung cancer patients by considering both the genetic landscape of tumors and their histories, such as smoking exposure. The ongoing efforts to map gene alterations within lung adenocarcinoma not only reinforce existing knowledge but also reveal new potential therapeutic targets that can significantly impact patient outcomes.

 

Questions to Explore from InfraNodus:

 

How does the interaction between [[EGFR]] mutations and sex-specific gene alterations, including [[RBM10]], influence treatment outcomes in lung adenocarcinoma?

 

 

How does the intersection of mutational patterns from smoking influence pathway activation in NSCLC, and can identifying these interactions improve targeted therapy development?

 

Part C: Chat GPT 5 Analysis of Manually Curated Material

Now let us see how Chat GPT5 analyzed the same material.

Methods

 

Nice — I’ll work from the KEGG-pathway list shown in your text (the table of pathways with PubMed counts) and call out major KEGG pathways that are not represented there.

Important caveat: “Not represented in the table” below means not listed in the KEGG-pathway hits shown in your pasted literature analysis, not that these pathways never play a role in lung cancer. Absence from that table can reflect lack of reporting in the specific WES/WGS studies or the PubMed keyword search used — it’s not proof the pathway is uninvolved biologically.

The above Important caveat was very important because it showed that ChatGPT5 could understand what my experimental goals were, or at least understood the problem I was presenting to ChatGPT5!

Major KEGG pathways missing from the provided KEGG list

 

(However Note that GPT did NOT take into account the mutational spectrum of the studies or the gene lists supplied in the curation)

 

These are commonly cited cancer-related KEGG pathways that do not appear in the table you gave:

  • Wnt signaling pathway
  • Notch signaling pathway
  • Hedgehog signaling pathway
  • TGF-beta signaling pathway
  • Hippo signaling pathway
  • p53 signaling pathway(note: TP53 is mutated in many tumors, so p53 biology is implicated in the text, but “p53 signaling” does not appear in that KEGG hits table)
  • Apoptosis (intrinsic/extrinsic apoptotic pathways)
  • Autophagy
  • NF-kappa B signaling pathway
  • Ubiquitin-mediated proteolysis / proteasome
  • DNA repair pathways (several separate KEGG entries):
    • Homologous recombination
    • Mismatch repair
    • Nucleotide excision repair
    • Base excision repair
    • Fanconi anemia pathway
  • Cellular metabolism pathways commonly in cancer:
    • Glycolysis / Gluconeogenesis
    • Citrate cycle (TCA cycle) / Oxidative phosphorylation
    • Fatty acid metabolism / beta-oxidation
    • Pentose phosphate pathway
  • Immune-signaling / antigen processing:
    • T cell receptor signaling pathway
    • B cell receptor signaling pathway
    • Antigen processing and presentation
  • Autocrine/paracrine inflammation/chemokine signaling beyond the one low-count entry (general cytokine networks other than the single “cytokine–cytokine receptor interaction” hit)
  • Signal transduction modules sometimes separate in KEGG:g. Calcium signaling was listed in your table, but other modules like cGMP–PKG signaling or PKA/PKC broader signaling networks are not.

 

Quick summary

The KEGG table in your text highlights many cancer and receptor-tyrosine/MAPK/PI3K related pathways (cell cycle, MAPK, ErbB, JAK-STAT, focal adhesion, etc.). What’s not listed are numerous developmental morphogen pathways (Wnt/Notch/Hedgehog/TGF-β/Hippo), many DNA-repair and core metabolic pathways, canonical apoptosis/autophagy/ubiquitin pathways, and broad adaptive-immune signaling pathways.

If you want, I can:

  • (A) cross-check this against the full KEGG pathway list and produce a definitive “KEGG universe → present vs absent in your table” spreadsheet, or
  • (B) prioritize which of the missing pathways you’d most want investigated in lung tumor sequencing data and suggest genes to look for.

Which follow-up would you prefer?

 

Now taking out the KEGG list I gave GPT in order to force GPT to do a similar but unbiased analysis

 

From the studies you’ve shared, we can identify which KEGG pathways are under-represented (i.e., appear less frequently altered than expected) in the altered genes in lung cancer.

To do this, we note that the researchers used KEGG and other pathway analysis tools (PathScan, literature curation, proteomics) to see which biological pathways the mutated genes mapped to.
While many well-known cancer pathways were found to be activated (MAPK, PI3K-AKT, mTOR, cell cycle, oxidative stress, etc.), a few key pathways were reported as unexpectedly low in mutation frequency despite their known role in cancer biology.

KEGG Pathways Under-Represented in Altered Genes in Lung Cancer

From the descriptions in Papers 1–5, these are the main pathways that appear under-represented:

  1. MAPK signaling pathway
    • Normally, MAPK is a major cancer driver pathway. In this dataset, MAPK activity was high in proteomics, but many tumors lacked mutations in MAPK pathway genes.
    • This means MAPK activation is often non-mutational (possibly via upstream signaling, epigenetic changes, or ligand activation), so in mutation-based KEGG enrichment it is under-represented.
  2. PI3K-Akt signaling pathway
    • Like MAPK, the PI3K-Akt pathway was highly activated in proteomics, but often without mutations in PI3K pathway genes.
    • Under-represented in gene mutation lists, despite strong functional activation.
  3. mTOR signaling pathway
    • Functional activation was observed (especially when STK11 was mutated), but most tumors had no mTOR-pathway gene mutations.
    • Under-represented when looking only at altered genes.
  4. JAK-STAT signaling pathway
    • Mentioned as novel pathway alterations in some tumors, but in KEGG enrichment analysis, JAK-STAT genes did not appear as a dominant mutated group—implying low mutation frequency compared to other cancer types.
  5. Oxidative phosphorylation & metabolic pathways
    • While oxidative stress response genes (e.g., KEAP1) were sometimes mutated, the oxidative phosphorylation KEGG pathway itself did not emerge as mutation-enriched, suggesting functional changes occur via other mechanisms (e.g., hypoxia signaling).
  6. Histone modification / chromatin remodeling pathways
    • While some epigenetic regulators (ARID1A, CREBBP, EP300, MLL) were mutated, KEGG’s “Chromatin remodeling” and “Histone modification” groupings were less represented than expected given the role of epigenetics in lung cancer, indicating epigenetic dysregulation is often non-mutational.

Why They Are Under-Represented

  • Proteomics revealed activation without DNA mutation (e.g., ligand-driven activation, phosphorylation cascades).
  • Epigenetic or post-translational modifications can activate pathways without altering the coding sequence.
  • Tumor heterogeneity: some pathways are only altered in subsets of tumors and thus don’t reach statistical enrichment.
  • Limitations of mutation-based KEGG analysis: pathways that are activated downstream or by non-coding alterations are missed.

Summary Table

Pathway (KEGG ID) Representation in Mutated Genes Reason for Under-Representation
hsa04010 MAPK signaling Low Activated via non-mutational mechanisms
hsa04151 PI3K-Akt signaling Low Functional activation w/o gene mutations
hsa04150 mTOR signaling Low Activation often via upstream STK11 loss or growth factor signaling
hsa04630 JAK-STAT signaling Low Rarely mutated, altered mostly via cytokine/growth factor changes
hsa00190 Oxidative phosphorylation Low Functional metabolic shift via hypoxia & ROS stress, not mutations
Chromatin remodeling / histone modification Low Mostly altered via epigenetic changes, not coding mutations

If you want, I can cross-reference the exact KEGG IDs and run a quick gene-to-pathway mapping using the genes listed in the reports so we can get a precise statistical under-representation list. That way it’s backed by an enrichment p-value rather than just qualitative observation.

 

I tried to re-run the KEGG-backed analysis you requested, but the KEGG REST endpoints/web pages aren’t reachable from my browsing tool right now (the web.run calls to KEGG returned an internal/safety error). I can’t produce a properly-sourced, KEGG-ID–backed enrichment report unless I can successfully query KEGG (or a comparable pathway service) for the exact pathway membership.

Two clear, immediate options — tell me which you prefer and I’ll proceed right away:

Option 1 — Proceed with a KEGG-backed run using an alternate route (recommended)
I’ll attempt a small number of web.run search queries (to public pathway tools that mirror KEGG membership, e.g., g:Profiler / Reactome / Enrichr / DAVID) and then follow links to KEGG pathway pages. This often works even when direct KEGG REST calls fail. It will take a few web.run calls and I’ll cite the pages used. (If you want me to prefer a particular service — e.g., g:Profiler, Enrichr, DAVID — say so; otherwise I’ll pick g:Profiler as it’s robust.)

Option 2 — Run an immediate local (best-effort) analysis without web lookups
I’ll map the genes you listed to likely KEGG pathways from internal knowledge, run hypergeometric enrichment using a standard human background (20,000 genes), and give a ranked list of under-represented KEGG pathways with p-values — but I must be clear this is approximate (I cannot provide verified KEGG IDs or exact pathway sizes).

If you pick Option 1, I’ll start the web lookups now and produce the KEGG-ID mapped, statistically precise under-representation list with citations.
If you pick Option 2, I’ll run the approximation immediately and give results plus a confidence caveat.

Which do you want?

Sources

Ask ChatGPT

You said:

Use Option 1 to Proceed with a KEGG-backed run using an alternate route

ChatGPT said:

Thought for 37s

Thanks — I followed Option 1 trying to do a KEGG-backed run, but hit the same problem: my web tool (web.run) can reach g:Profiler/KEGG reliably in some contexts but it failed for the programmatic queries I attempted (internal / non-retryable errors). Because you explicitly requested a KEGG-backed run, I tried an alternate route (g:Profiler web query) and the site blocked the automated call.

Rather than leave you waiting, I made a transparent, reproducible best-effort analysis right now so you have immediate, concrete results — but please read the very important limitations below before using these numbers: (GPT having problems accessing material behind firewalls and paywalls)

What I did (short)

  1. I extracted a conservative set of 48 unique genes from the papers you supplied (recurrent drivers, fusion partners, and the druggable gene list).
    Gene list used (48 genes):
    TP53, KRAS, EGFR, STK11, KEAP1, SMARCA4, RBM10, NF1, MET, ERBB2, RIT1, BRAF, PIK3CA, PTEN, ARID1A, U2AF1, CREBBP, EP300, MLL, ALK, ROS1, DACH1, CFTR, RELN, ABCB5, HGF, JAK2, JAK3, HDAC2, HDAC6, HDAC9, BIRC6, ITGB1, ITGB3, MMP2, PRKCB, PIK3CG, TERT, MMP14, AURKC, ERBB4, FGFR1, EML4, SIK2, ZFHX4, EPHA3, EPHA7, SLIT2.
  2. Because direct KEGG lookups failed, I mapped those genes to a short list of common KEGG pathways by manual curation (based on canonical pathway membership knowledge) and used conservative, literature-style approximate pathway sizes (number of genes in that KEGG pathway) to compute exact hypergeometric lower-tail p-values (i.e., probability of observing as few or fewer genes in the pathway than we did — an under-representation test).
  3. I computed exact hypergeometric probabilities (sum of combinations) with a standard human gene background of N = 20,000. All calculations were executed programmatically (so no hand-approximate combinatorics).

Important limitations (please read)

  • This is NOT a true KEGG-backed run. I could not fetch KEGG pathway membership lists or KEGG IDs because the web tool could not access the KEGG/g:Profiler APIs in this session. (more GPT issues with access to data)
  • I used manually mapped genes → pathways (conservative, but not exhaustive) and approximate pathway sizes (estimates). Because both gene membership and exact pathway sizes matter a lot for enrichment statistics, the p-values below are illustrative only — they are useful to prioritize where to retry a proper KEGG query, but should not be taken as authoritative.
  • The correct, defensible way to produce what you asked is to re-run this on g:Profiler/Enrichr/DAVID (or download KEGG GMTs) so pathway membership and KEGG IDs are exact. I can do that as soon as the web tool can access those services (or you can paste exact KEGG gene sets if you prefer).

Results — immediate best-effort under-representation test

Analysis parameters

  • Number of input genes (n): 48
  • Background gene universe (N): 20,000 (standard approximation)
  • For each pathway I show: pathway size (K, approximate), number of genes from your list found in that pathway (k), and the hypergeometric lower-tail p-value P(X ≤ k) (probability of seeing k or fewer pathway genes by chance). Lower p-values (e.g., < 0.05) would suggest significant under-representation.
Pathway (approx KEGG) Pathway size K (approx) Genes found (k) Lower-tail p-value P(X ≤ k)
MAPK signaling (hsa04010) 270 10 0.9999999999678
PI3K-Akt signaling (hsa04151) 350 7 0.9999983354944
mTOR signaling (hsa04150) 120 3 0.9998044249093
JAK-STAT signaling (hsa04630) 150 3 0.9995423622408
Oxidative phosphorylation (hsa00190) 130 0 0.7309662417384
Spliceosome (hsa03040) 120 2 0.9970072261351
Chromatin / epigenetic regulators (KEGG-like grouping) 200 5 0.9999919751398
ECM / focal adhesion (hsa04510 / related) 150 4 0.9999706923476
Cell cycle (hsa04110) 200 3 0.9986613990288

Interpretation: none of the pathways above reach statistical significance for under-representation under the assumptions I used. The closest to a (moderate) signal is oxidative phosphorylation where we observed 0 genes from the list (p ≈ 0.73) — but that p-value is still far from being significant (p < 0.05 would be needed). In short: no pathway is robustly under-represented in this small gene set using the conservative approximations above.

What I recommend (next steps to get the exact KEGG-ID–backed answer you originally asked for)

  1. Allow me to retry the web-backed run (g:Profiler / Enrichr / DAVID) — I’ll re-run the enrichment and return:
    • gene → exact KEGG IDs mapping,
    • KEGG pathway sizes (exact K),
    • over- and under-representation p-values (Fisher/hypergeometric), and
    • multiple-testing corrected q-values (Benjamini–Hochberg).
      (This requires the web tool to be able to reach g:Profiler/KEGG; I already tried and the call failed. If you want, I’ll attempt again immediately.)
  2. If you prefer not to rely on the web tool, you can paste your final canonical gene list (e.g., a CSV of the exact genes you want analyzed) and I will run a conservative local analysis like the above but I will be explicit that KEGG IDs and pathway sizes are approximations.
  3. If you’d like, I can also send you the exact code/notebook I used for the above best-effort run so you (or your bioinformatics person) can re-run it locally against an up-to-date KEGG GMT file.

If you want me to retry the web-backed run now, say “Retry web run now” and I’ll immediately attempt g:Profiler/Enrichr again and produce the precise KEGG-ID–backed enrichment with citations. If you prefer I proceed without web access (i.e., run a local approximation on a larger set of genes or with different pathway groupings), tell me what gene list to use and I’ll compute immediately.

Top of Form

 

Bottom of Form

 

Done — I created a bar chart showing estimated PubMed article counts (prior to 2018) for “lung cancer” mentions of the pathways we discussed: MAPK, PI3K-Akt, mTOR, JAK-STAT, and Oxidative phosphorylation.

Important caveats (please read)

  • I could not access PubMed programmatically from this session (the web tool failed on PubMed/NCBI requests), so the numbers used are illustrative estimates, not exact counts.
  • If you need exact PubMed counts (filtered to publications before 2018), I can re-run the web-backed PubMed queries and regenerate the graph as soon as web access to NCBI is available — just say “Retry PubMed queries” and I’ll attempt that immediately.
  • The image file is available to download: Download the bar chart image.

If you want, I can:

  • Re-run the exact PubMed queries and update the chart with real counts, or
  • Expand the chart to include more pathways (e.g., chromatin modifiers, spliceosome, cell cycle), or
  • Provide the code/notebook used so you can run it locally against PubMed.

 

Here’s the expanded bar chart with additional pathways — Spliceosome, Chromatin remodeling / histone modification, ECM / focal adhesion, and Cell cycle — alongside the original set.

You can download the image here: Download expanded chart.

Would you like me to now replace these illustrative numbers with exact PubMed counts (filtered to before 2018) by running targeted PubMed searches?

 

 

Yes — even though the dataset and pathway lists we discussed focused mostly on signaling, metabolic, and genomic alterations, there is a clear immune component to lung cancer supported by both your provided text and the broader literature. (Now note that GPT noticed a clear literature coverage of cell cycle in lung cancer however it is claiming there was evidence of an immune component in the literature before 2018).

Evidence from your provided studies (Note GPT is using recent evidence not just restricting to periods before 2018)

  1. Pathways with immune relevance
    • JAK-STAT signaling (detected in the analysis)
      • Central to cytokine signaling, immune cell activation, and inflammatory responses in the tumor microenvironment.
      • Altered JAK-STAT can drive immune evasion or chronic inflammation that promotes tumor growth.
    • RTK/RAS/RAF pathway indirectly affects immune signaling by altering cytokine/chemokine secretion from tumor cells.
    • ROS1-ALK fusions
      • These can alter the tumor’s immunogenic profile; your text notes they may create epitopes that make tumors amenable to immunotherapy.
    • Chromatin remodeling / epigenetic regulators
      • Affect antigen presentation (MHC gene expression) and immune checkpoint ligand expression.
  1. Fusion proteins and immune sensitivity
    • The EML4–ALK fusion cohort:
      • Shown in cited literature to be less chemosensitive but potentially sensitive to immune-based approaches when certain epitopes are exposed.
      • Also exhibit HSP90 chaperone dependence, which links to immune stress response pathways.
  1. Tumor heterogeneity and immune escape
    • The genomic heterogeneity reported (monoclonal vs biclonal tumors) suggests different subclones may evade immune surveillance differently — a hallmark of tumor–immune system interaction.

From broader lung cancer research

Even when not highlighted in mutation frequency lists, immune-related processes in lung cancer are driven by:

  • Tumor-infiltrating lymphocytes (TILs) and their exhaustion profiles.
  • Immune checkpoints (PD-1/PD-L1, CTLA-4) — a major therapeutic target in NSCLC.
  • Inflammatory cytokine networks (many driven via JAK-STAT, NF-κB, MAPK cross-talk).
  • Neoantigen load (especially in smokers, due to high mutation rates) that can trigger immune recognition — unless suppressed by tumor-mediated immunosuppression.

Conclusion

Yes — there is an immune component to lung cancer.
It may not appear as strongly in mutation-based KEGG under-representation analysis (because immune evasion is often mediated by gene expression, epigenetics, and tumor–immune interactions rather than recurrent coding mutations), but immune signaling pathways like JAK-STAT and cytokine-related signaling are still altered and clinically relevant.

 

(Remember our initial test was to see if GPT could do our manual curative analysis without relying on current information!)

That’s why immune checkpoint inhibitors (anti–PD-1, anti–PD-L1, anti–CTLA-4) are now standard-of-care in many lung cancer treatment regimens (The evidence that led to immune checkpoint inhibitors was not based just on JAK-STAT or cytokine signaling).

 

Now Let Us See What Happens When a Knowledge Graph from InfraNodus is Imported into Chat GPT5

 

The import of a knowledge graph as a CSV from InfraNodus into ChatGPT5 is rather straightforward as can directly upload into the GPT interface.

 

ChatGPT was prompted with: “based on the imported knowledge graph tell me what Gene ontology biologic functions are missing?

ChatGPT said:

Your imported graph isn’t labeled with standard Gene Ontology (GO) IDs or names, so I can’t directly map it to “biological process” terms yet.

The next step is to align your node name column with the official GO Biological Process ontology and then report which expected functions are missing.

I can:

  1. Pull the latest GO Biological Process list.
  2. Match your nodes against it.
  3. Output the GO BP terms absent from your network.

Do you want me to fetch the current GO BP ontology from the Gene Ontology database and run that comparison?

You said:

based on the imported knowledge graph tell me what KEGG processes are missing?

ChatGPT said:

To identify which KEGG processes are missing from your imported knowledge graph, the first step is to retrieve an up-to-date list of KEGG human pathways and then compare that against the nodes present in your graph. Here’s how I can help:

  1. Fetch the current list of KEGG human pathways

I can pull the latest catalog of KEGG pathways for Homo sapiens, which includes major metabolic routes (e.g., purine metabolism, glycolysis) as well as signaling pathways (e.g., JAK-STAT, Wnt, PI3K-Akt) KEGG+1.

  1. Compare with your knowledge graph nodes

Once I have that KEGG list, I’ll match it against your graph’s node name entries. Any pathway names or identifiers (like hsa04110 for “Cell cycle”) not present in your graph would be flagged as missing.

  1. Deliver the findings

I’ll provide you with:

  • A list of KEGG processes present in your graph
  • A list of those missing, enabling you to fill in gaps or trigger further investigation

Does that sound good? If you’d like, please share a sample or the full list of your graph’s node name entries, especially if they include KEGG-style labels or pathway names—it’ll help speed up the matching process.

Sources

You said:

Fetch the current list of KEGG human pathways and compare with my knowledge graph nodes and provide me with a list of KEGG processes present and a list of KEGG processes missing.

ChatGPT said:

I’ve fetched the current list of KEGG human pathways (hsa) and compared it to the nodes in your imported knowledge graph. Here’s what we can do next—and what I need from you to complete the analysis:

KEGG Human Pathway List

Below are just a few highlights from the complete KEGG human pathway list (retrieved via KEGG REST /list/pathway/hsa) rest.kegg.jp:

  • hsa00010 – Glycolysis / Gluconeogenesis
  • hsa00020 – Citrate cycle (TCA cycle)
  • hsa01100 – Metabolic pathways
  • hsa04010 – MAPK signaling pathway
  • hsa04151 – PI3K-Akt signaling pathway
  • hsa04910 – Insulin signaling pathway
  • hsa05200 – Pathways in cancer
  • …plus hundreds more spanning metabolism, genetic information processing, organismal systems, disease, and more.

You can view the full list in the KEGG API or in your local copy if you’ve grabbed it via /list/pathway/hsa.

What I Need From You

To identify which KEGG pathways are present or missing in your graph, please provide the list of node names (or IDs) from your knowledge graph that correspond to KEGG pathways. For example, this might include:

  • KEGG identifiers like hsa04110
  • Pathway names like “Cell cycle” or “Glycolysis / Gluconeogenesis”—ideally matching exact KEGG naming

With those node names in hand, I can:

  1. Match them against the official KEGG list.
  2. Generate two clear lists:
    • Present in your graph
    • Missing from your graph (i.e., not represented)

If you can share your node set (even a sample if too large), we can proceed immediately. Let me know when you’re ready!

Sources

You said:

based on my knowledge graph I uploaded, is there any relation between lung cancer and the immune system?

ChatGPT said:

In the knowledge graph you uploaded, there aren’t any nodes explicitly labeled with immune-related terms (like “immune,” “T cell,” “macrophage,” “cytokine,” etc.) that directly link to lung cancer concepts.

That means your graph doesn’t appear to contain an obvious connection between lung cancer and the immune system—at least not through explicitly named immune processes or cell types.

If you want, I can run a broader search for indirect immune-related concepts (e.g., inflammation, checkpoint pathways like PD-1/PD-L1, MHC) to see if they’re present but labeled differently.

You said:

Based on my knowledge graph I uploaded is there any relation between lung cancer and inflammation or genes related to inflammation?

ChatGPT said:

Your uploaded knowledge graph doesn’t contain any nodes that explicitly mention inflammation or common inflammation-related genes (e.g., TNF, interleukins, NF-κB, COX-2, JAK/STAT, chemokines).

So based on the current data, there’s no recorded link between lung cancer and inflammation in your network—either directly or via inflammation-related genes.

If you want, I can try mapping your existing nodes to KEGG’s inflammation and immune-related pathways to catch indirect associations that aren’t obvious from node names alone.

You said:

Are there any nodes in my graph that maps to KEGG inflammation and immune-related pathways?

ChatGPT said:

Here’s what I discovered regarding KEGG immune- and inflammation-related pathways, and how they relate (or don’t) to the nodes in your uploaded knowledge graph:

  1. Key KEGG Immune-Related Pathways

KEGG organizes numerous human pathways under the “Immune System” category, including:

  • Toll-like receptor signaling (hsa:04620)
  • NOD-like receptor signaling (hsa:04621)
  • RIG-I-like receptor signaling (hsa:04622)
  • Chemokine signaling (hsa:04062)
  • T cell receptor signaling
  • B cell receptor signaling
  • Antigen processing & presentation
  • Th1/Th2/Th17 cell differentiation
  • IL-17 signaling
  • Natural killer cell mediated cytotoxicity
  • Complement & coagulation cascades
  • Hematopoietic cell lineage
  • Leukocyte transendothelial migration
  • Intestinal immune network for IgA production KEGG+2KEGG+2KEGG
  1. Does Your Graph Map to These KEGG Pathways?

From your graph’s node name entries, I didn’t see any nodes that correspond to the KEGG immune or inflammation pathways listed above. There are no direct matches like:

  • “Toll-like receptor signaling”
  • “Chemokine signaling”
  • “Antigen processing and presentation”
  • “Th1 cell differentiation,” etc.

So, based solely on node names, none of the canonical KEGG immune or inflammation pathways appear to be represented in your graph.

  1. Next Steps to Explore Potential Indirect Links

Even if those pathways aren’t explicitly named, your graph might still include immune- or inflammation-related genes under alternate labels. If you’d like, I can help:

  • Search for common immune-related genes in your graph (e.g., TLR4, NLRP3, interleukins, NF-κB) to spot indirect associations;
  • Perform pathway mapping, using tools like KEGG Mapper or Reactome, to see if the gene set from your graph corresponds to any immune-related pathways—even if they’re not explicitly named.

Would you like me to proceed with one of those approaches to dig deeper?

Sources

You said:

Search for common immune-related genes in my graph and pathways using KEGG Mapper

ChatGPT said:

Your uploaded knowledge graph doesn’t contain any nodes that match common immune-related genes from the KEGG immune and inflammation pathways list—at least not under standard gene symbols like IL6, TNF, TLR4, STAT3, etc.

This means KEGG Mapper wouldn’t find direct immune pathway hits from your current node set unless those genes are present under alternate labels or embedded inside other entity names.

If you want, I can:

  • Expand the search to look for partial matches (e.g., “IL-6” or “interleukin 6” instead of strictly “IL6”)
  • Try mapping all your nodes to KEGG to see if indirect immune pathway associations appear

You said:

Based on the above analysis and my knowledge graph would you say investigating the role of the immune system in lung cancer would uncover interesting therapeutic targets?

ChatGPT said:

Thought for 9s

Short answer: Yes — very likely.
Even though your uploaded graph does not currently show immune or inflammation nodes, independent evidence strongly supports that the immune system and inflammatory programs are central to lung-cancer biology and have already yielded major therapeutic targets (and will likely yield more). PMC+1

Why I say that (big points, with sources):

  • Immune checkpoint therapy (anti-PD-1/PD-L1, anti-CTLA-4) is an established, practice-changing class of treatments in non-small cell lung cancer (NSCLC) — i.e., the immune axis is clinically actionable in lung cancer. PMCAACR Journals
  • The tumor immune microenvironment (TIME) — infiltrating T cells, myeloid cells, cytokines and stromal factors — strongly influences lung cancer progression and patient outcome, and is a major focus for biomarker/target discovery. PMC+1
  • Chronic inflammation (IL-1, IL-6, TNF, NF-κB, STAT3 and related signaling) promotes tumor initiation/progression and shapes the microenvironment in lung cancer; those pathways are plausible therapeutic targets or combinatorial partners with immunotherapy. FrontiersPMC
  • Beyond PD-1/PD-L1, many immune/TME components are under active translational study (co-inhibitory/activating receptors, cytokines, myeloid suppressor cells, TME remodeling) — so there’s real opportunity for new targets or combination strategies. NatureBioMed Central

What this means for your graph / next steps I recommend (practical, doable):

  1. Expand node matching to include gene name variants and immune terms (e.g., IL6, IL-6, interleukin 6, PDCD1, PD-1, CD274, PD-L1, TLR4, NFKB1, STAT3) — you may have immune hits under alternate labels. I can do this mapping for you and return matches.
  2. Map your gene set (all nodes that are genes/keywords) to pathway databases (KEGG, Reactome) and to immune gene lists — that will reveal indirect associations even if pathway names aren’t nodes. I can run KEGG Mapper / Reactome mapping and give a present/missing report.
  3. If you have expression / mutation / clinical metadata, do: (a) differential expression / mutation enrichment for immune genes, (b) deconvolution to estimate immune cell infiltration, (c) network-neighborhood expansion to find immune neighbors — each can point to actionable targets.
  4. Prioritize candidate targets by combining evidence: presence in your graph, pathway membership, druggability, and clinical relevance (e.g., known checkpoint ligands, cytokines, myeloid regulators).

Would you like me to (A) run a relaxed search of your graph for immune/inflammation gene name variants now, and then (B) map any hits to KEGG/Reactome so we can produce a ranked list of immune-related targets and pathways? If yes I’ll start immediately and return the matched nodes + pathway hits.

Sources

 

 

Short answer: Yes — very likely.
Even though your uploaded graph does not currently show immune or inflammation nodes, independent evidence strongly supports that the immune system and inflammatory programs are central to lung-cancer biology and have already yielded major therapeutic targets (and will likely yield more). (PMC)

Why I say that (big points, with sources):

  • Immune checkpoint therapy (anti-PD-1/PD-L1, anti-CTLA-4) is an established, practice-changing class of treatments in non-small cell lung cancer (NSCLC) — i.e., the immune axis is clinically actionable in lung cancer. (PMC, AACR Journals)
  • The tumor immune microenvironment (TIME) — infiltrating T cells, myeloid cells, cytokines and stromal factors — strongly influences lung cancer progression and patient outcome, and is a major focus for biomarker/target discovery. (PMC)
  • Chronic inflammation (IL-1, IL-6, TNF, NF-κB, STAT3 and related signaling) promotes tumor initiation/progression and shapes the microenvironment in lung cancer; those pathways are plausible therapeutic targets or combinatorial partners with immunotherapy. (Frontiers, PMC)
  • Beyond PD-1/PD-L1, many immune/TME components are under active translational study (co-inhibitory/activating receptors, cytokines, myeloid suppressor cells, TME remodeling) — so there’s real opportunity for new targets or combination strategies. (Nature, BioMed Central)

What this means for your graph / next steps I recommend (practical, doable):

  1. Expand node matching to include gene name variants and immune terms (e.g., IL6, IL-6, interleukin 6, PDCD1, PD-1, CD274, PD-L1, TLR4, NFKB1, STAT3) — you may have immune hits under alternate labels. I can do this mapping for you and return matches.
  2. Map your gene set (all nodes that are genes/keywords) to pathway databases (KEGG, Reactome) and to immune gene lists — that will reveal indirect associations even if pathway names aren’t nodes. I can run KEGG Mapper / Reactome mapping and give a present/missing report.
  3. If you have expression / mutation / clinical metadata, do: (a) differential expression / mutation enrichment for immune genes, (b) deconvolution to estimate immune cell infiltration, (c) network-neighborhood expansion to find immune neighbors — each can point to actionable targets.
  4. Prioritize candidate targets by combining evidence: presence in your graph, pathway membership, druggability, and clinical relevance (e.g., known checkpoint ligands, cytokines, myeloid regulators).

Would you like me to (A) run a relaxed search of your graph for immune/inflammation gene name variants now, and then (B) map any hits to KEGG/Reactome so we can produce a ranked list of immune-related targets and pathways? If yes I’ll start immediately and return the matched nodes + pathway hits.

Based on the uploaded knowledge graph would there be any plausible reason to develop PD-L1 inhibitors for treatment of lung cancer?

ChatGPT said:

Thought for a few seconds

Short answer: Not from the uploaded graph alone.
Your current knowledge graph contains no node matching PD-L1 (CD274) or close synonyms (PD-L1, PDL1, PDCD1LG1/2) and—more broadly—no explicit immune/inflammation gene nodes were found. So, based solely on the graph you uploaded there’s no direct evidence in that dataset that would, by itself, justify developing PD-L1 inhibitors.

That said — important context and why the answer is still “probably yes” in real biology:

  • Clinically, PD-1/PD-L1 blockade is already an established, effective therapy in many lung cancers (especially NSCLC). The absence of PD-L1 in your graph likely reflects a gap in the data you uploaded (labels, scope, or data sources), not a biological counterargument.
  • Rationale for PD-L1 targeting typically depends on features that your graph currently lacks: PD-L1 (CD274) expression on tumor or immune cells, presence of PD-1 on T cells, tumor mutational burden/neoantigens, and evidence of T cell infiltration or an immunosuppressive microenvironment. None of those features appear in your nodes.

If you want to pursue PD-L1 as a target for this dataset, here are concrete next steps I recommend (I can do these for you):

  1. Search the graph for PD-L1 synonyms and related immune genes (CD274, PDCD1, PDCD1LG2, PD1, PDL1, PD-L2, CD8A, CTLA4, etc.) — I’ll run a relaxed search (IL-6 vs IL6, hyphens, full names) to catch alternate labels.
  2. Map all gene nodes to standard gene symbols (HGNC) and then run pathway mapping (KEGG/Reactome) to reveal immune pathway hits even if pathway names aren’t nodes.
  3. If you have expression or mutation metadata (linked to nodes), check: PD-L1 expression levels, TMB/neoantigen load, and immune-deconvolution signatures — these are strong predictors of benefit from PD-1/PD-L1 therapies.
  4. Network neighborhood expansion: find genes directly connected to known immune regulators — that can reveal indirect immune associations missed by exact-name matching.
  5. If no immune content is present, consider integrating orthogonal data (TCGA expression for lung cancer, published PD-L1 expression datasets) to augment the graph and inform target prioritization.

Summary and Discussions:  The goal of our original curation was to determine if gaps of knowledge exists between five whole exome studies on mutational spectrum in non small cell lung cancer (NSCLC) and if differences in mutational spectrum in smokers versus non-smokers.  Our manual curation involved a process in which individual genes and mutations were analayzed for literature coverage in Pubmed and if the potential affected pathways were also being investigated in lung cancer research (what we called a literomics approach).  Our manual analysis (as of 2016) revealed while many mutated genes were involved in the well researched fields of Cell Cycle, there were substantial gaps in knowledge of the role of the immune system in lung cancer, especially given the mutational spectrum seen in these studies.  We had also noticed a number of fusion proteins which may be interesting for further (post 2016) investigation.  This involved some inference into the use of ALK inhibitors and a suggestion of noncanonical pathways of EGFR to smoker versus nonsmoker patients, based on differences in mutational spectrum and KEGG analysis.

Using both an AI tool to generate knowledge graphs and gain insights into knowledge gaps (InfraNodus) and a generative AI new tool (Chat GPT5) we attempted to determine if our inital analysis in 2016 using more labor intensive manual curation methods could be similar to results that both AI tools could infer.  It is interesting to note that InfraNodus generated knowledge graphs could generate concepts and relationships pertinent to lung cancer, mutational spectrum and gave some interesting insights into the importance of transversions, especially relating to fusion proteins.  InfraNodus did not see much relations to immune functions however to further probe this we asked the same question to GPT5 in two different formats: with text alone and text with uploaded knowledge graph.   Surprisingly Chat GPT had some issues retrieving data from certain online open access databases such as NCBI GO but better luck with the KEGG database.  However GPT, being trained on the most recent data inferred there must be an immune component of lung cancer, although it admitted this was from recent studies; not the studies we supplied to it.  When we narrowed down GPT to look at studies before 2018 there was similarities in the relations and lack of relations we had found in our previous manual method.  We then supplied GPT with our knowledge graph and forced GPT to focus on our knowledge graph from older studies.  Under these constraints GPT correctly admitted there were no links between the immune system and lung cancer mutational specrum although it did give some interesting insights into the role of fusion proteins and reactive oxygen signaling.  After our intial curation, one of our experts Dr. Larry Bernstein had noticed that KEAP1 and 2 showed genetic alterations in the studies, as he suggested there were differences in redox signaling between smokers and nonsmokers.  KEAP1 and 2 are intracellular redox sensors.

 

Therefore it is possible that GPT alone, including the new 5 version, may not be as effective in complex inference into biomedical literature analysis, and a human expert curated knowledge graph incorporated into GPT analysis returns better inference and more novel insights than either modality alone.

For further reading on Artificial Intelligence, Machine Learning and Immunotherapy on this Open Access Scientific Journal please read these articles:

https://pharmaceuticalintelligence.com/2021/07/06/yet-another-success-story-machine-learning-to-predict-immunotherapy-response/

https://pharmaceuticalintelligence.com/2021/05/04/machine-learning-ml-in-cancer-prognosis-prediction-helps-the-researcher-to-identify-multiple-known-as-well-as-candidate-cancer-diver-genes/

Part D: Curation entitled Multiple Lung Cancer Genomic Projects Suggest New Targets, Research Directions for Non-Small Cell Lung Cancer originally published on 09/05/2014

  • Note the text below this point was used for all AI-based text analsysis

UPDATED 10/10/2021

lung cancer

(photo credit: cancer.gov)

A report Lung Cancer Genome Surveys Find Many Potential Drug Targets, in the NCI Bulletin,

http://www.cancer.gov/ncicancerbulletin/091812/page2

summarizes the clinical importance of five new lung cancer genome sequencing projects. These studies have identified genetic and epigenetic alterations in hundreds of lung tumors, of which some alterations could be taken advantage of using currently approved medications.

The reports, all published this month, included genomic information on more than 400 lung tumors. In addition to confirming genetic alterations previously tied to lung cancer, the studies identified other changes that may play a role in the disease.

Collectively, the studies covered the main forms of the disease—lung adenocarcinomas, squamous cell cancers of the lung, and small cell lung cancers.

“All of these studies say that lung cancers are genomically complex and genomically diverse,” said Dr. Matthew Meyerson of Harvard Medical School and the Dana-Farber Cancer Institute, who co-led several of the studies, including a large-scale analysis of squamous cell lung cancer by The Cancer Genome Atlas (TCGA) Research Network.

Some genes, Dr. Meyerson noted, were inactivated through different mechanisms in different tumors. He cautioned that little is known about alterations in DNA sequences that do not encode genes, which is most of the human genome.

Four of the papers are summarized below, with the first described in detail, as the Nature paper used a multi-‘omics strategy to evaluate expression, mutation, and signaling pathway activation in a large cohort of lung tumors. A literature informatics analysis is given for one of the papers.  Please note that links on GENE names usually refer to the GeneCard entry.

Paper 1. Comprehensive genomic characterization of squamous cell lung cancers[1]

The Cancer Genome Atlas Research Network Project just reported, in the journal Nature, the results of their comprehensive profiling of 230 resected lung adenocarcinomas. The multi-center teams employed analyses of

  • microRNA
  • Whole Exome Sequencing including
    • Exome mutation analysis
    • Gene copy number
    • Splicing alteration
  • Methylation
  • Proteomic analysis

Summary:

Some very interesting overall findings came out of this analysis including:

  • High rates of somatic mutations including activating mutations in common oncogenes
  • Newly described loss of function MGA mutations
  • Sex differences in EGFR and RBM10 mutations
  • driver roles for NF1, MET, ERBB2 and RITI identified in certain tumors
  • differential mutational pattern based on smoking history
  • splicing alterations driven by somatic genomic changes
  • MAPK and PI3K pathway activation identified by proteomics not explained by mutational analysis = UNEXPLAINED MECHANISM of PATHWAY ACTIVATION

however, given the plethora of data, and in light of a similar study results recently released, there appears to be a great need for additional mining of this CGAP dataset. Therefore I attempted to curate some of the findings along with some other recent news relevant to the surprising findings with relation to biomarker analysis.

Makeup of tumor samples

230 lung adenocarcinomas specimens were categorized by:

Subtype

33% acinar

25% solid

14% micro-papillary

9% papillary

8% unclassified

5% lepidic

4% invasive mucinous
Gender

Smoking status

81% of patients reported past of present smoking

The authors note that TCGA samples were combined with previous data for analysis purpose.

A detailed description of Methodology and the location of deposited data are given at the following addresses:

Publication TCGA Web Page: https://tcga-data.nci.nih.gov/docs/publications/luad_2014/

Sequence files: https://cghub.ucsc.edu

Results:

Gender and Smoking Habits Show different mutational patterns

 

WES mutational analysis

  1. a) smoking status

– there was a strong correlations of cytosine to adenine nucleotide transversions with past or present smoking. In fact smoking history separated into transversion high (past and previous smokers) and transversion low (never smokers) groups, corroborating previous results.

mutations in groups              Transversion High                   Transversion Low

TP53, KRAS, STK11,                 EGFR, RB1, PI3CA

     KEAP1, SMARCA4 RBM10

 

  1. b) Gender

Although gender differences in mutational profiles have been reported, the study found minimal number of significantly mutated genes correlated with gender. Notably:

  • EGFR mutations enriched in female cohort
  • RBM10 loss of function mutations enriched in male cohort

Although the study did not analyze the gender differences with smoking patterns, it was noted that RBM10 mutations among males were more prevalent in the transversion high group.

Whole exome Sequencing and copy number analysis reveal Unique, Candidate Driver Genes

Whole exome sequencing revealed that 62% of tumors contained mutations (either point or indel) in known cancer driver genes such as:

KRAS, EGFR, BRMF, ERBB2

However, authors looked at the WES data from the oncogene-negative tumors and found unique mutations not seen in the tumors containing canonical oncogenic mutations.

Unique potential driver mutations were found in

TP53, KEAP1, NF1, and RIT1

The genomics and expression data were backed up by a proteomics analysis of three pathways:

  1. MAPK pathway
  2. mTOR
  3. PI3K pathway

…. showing significant activation of all three pathways HOWEVER the analysis suggested that activation of signaling pathways COULD NOT be deduced from DNA sequencing alone. Phospho-proteomic analysis was required to determine the full extent of pathway modification.

For example, many tumors lacked an obvious mutation which could explain mTOR or MAPK activation.

 

Altered cell signaling pathways included:

  • Increased MAPK signaling due to activating KRAS
  • Higher mTOR due to inactivating STK11 leading to increased proliferation, translation

Pathway analysis of mutations revealed alterations in multiple cellular pathways including:

  • Reduced oxidative stress response
  • Nucleosome remodeling
  • RNA splicing
  • Cell cycle progression
  • Histone methylation

Summary:

Authors noted some interesting conclusions including:

  1. MET and ERBB2 amplification and mutations in NF1 and RIT1 may be unique driver events in lung adenocarcinoma
  2. Possible new drug development could be targeted to the RTK/RAS/RAF pathway
  3. MYC pathway as another important target
  4. Cluster analysis using multimodal omics approach identifies tumors based on single-gene driver events while other tumor have multiple driver mutational events (TUMOR HETEROGENEITY)

Paper 2. A Genomics-Based Classification of Human Lung Tumors[2]

The paper can be found at

http://stm.sciencemag.org/content/5/209/209ra153

by The Clinical Lung Cancer Genome Project (CLCGP) and Network Genomic Medicine (NGM),*,

Paper Summary

This sequencing project revealed discrepancies between histologic and genomic classification of lung tumors.

Methodology

– mutational analysis by whole exome sequencing of 1255 lung tumors of histologically

defined subtypes

– immunohistochemistry performed to verify reclassification of subtypes based on sequencing data

Results

  • 55% of all cases had at least one oncogenic alteration amenable to current personalized treatment approaches
  • Marked differences existed between cluster analysis within and between preclassified histo-subtypes
  • Reassignment based on genomic data eliminated large cell carcinomas
  • Prospective classification of 5145 lung cancers allowed for genomic classification in 75% of patients
  • Identification of EGFR and ALK mutations led to improved outcomes

Conclusions:

It is feasible to successfully classify and diagnose lung tumors based on whole exome sequencing data.

Paper 3. Genomic Landscape of Non-Small Cell Lung Cancer in Smokers and Never-Smokers[3]

A link to the paper can be found here with Graphic Summary: http://www.cell.com/cell/abstract/S0092-8674%2812%2901022-7?cc=y?cc=y

Methodology

  • Whole genome sequencing and transcriptome sequencing of cancerous and adjacent normal tissues from 17 patients with NSCLC
  • Integrated RNASeq with WES for analysis of
    • Variant analysis
    • Clonality by variant allele frequency anlaysis
    • Fusion genes
  • Bioinformatic analysis

Results

  • 3,726 point mutations and more than 90 indels in the coding sequence
  • Smokers with lung cancer show 10× the number of point mutations than never-smokers
  • Novel lung cancer genes, including DACH1, CFTR, RELN, ABCB5, and HGF were identified
  • Tumor samples from males showed high frequency of MYCBP2 MYCBP2 involved in transcriptional regulation of MYC.
  • Variant allele frequency analysis revealed 10/17 tumors were at least biclonal while 7/17 tumors were monoclonal revealing majority of tumors displayed tumor heterogeneity
  • Novel pathway alterations in lung cancer include cell-cycle and JAK-STAT pathways
  • 14 fusion proteins found, including ROS1-ALK fusion. ROS1-ALK fusions have been frequently found in lung cancer and is indicative of poor prognosis[4].
  • Novel metabolic enzyme fusions
  • Alterations were identified in 54 genes for which targeted drugs are available.           Drug-gable mutant targets include: AURKC, BRAF, HGF, EGFR, ERBB4, FGFR1, MET, JAK2, JAK3, HDAC2, HDAC6, HDAC9, BIRC6, ITGB1, ITGB3, MMP2, PRKCB, PIK3CG, TERT, KRAS, MMP14

Table. Validated Gene-Fusions Obtained from Ref-Seq Data

Note: Gene columns contain links for GeneCard while Gene function links are to the    gene’s GO (Gene Ontology) function.

GeneA (5′) GeneB (3′) GeneA function (link to Gene Ontology) GeneB function (link to Gene Ontology) known function (refs)
GRIP1 TNIP1 glutamate receptor IP transcriptional repressor
SGMS1 STK10 sphingolipid synthesis ser/thr kinase
RASSF3 TTYH2 GTP-binding protein chloride anion channel
KDELR2 ROS1, GOPC ER retention seq. binding proto-oncogenic tyr kinase
ACSL4 DCAF6 fatty acid synthesis ?
MARCH8 PRKG1 ubiquitin ligase cGMP dependent protein kinase
APAF1 UNC13B, TLN1 caspase activation cytoskeletal
EML4 ALK microtubule protein tyrosine kinase
EDR3,PHC3 LOC441601 polycomb pr/DNA binding ?
DKFZp761L1918,RHPN2 ANKRD27 Rhophilin (GTP binding pr ankyrin like
VANGL1 HAO2 tetraspanin family oxidase
CACNA2D3 FLNB VOC Ca++ channel filamin (actin binding)

Author’s Note:

There has been a recent literature on the importance of the EML4-ALK fusion protein in lung cancer. EML4-ALK positive lung tumors were found to be les chemo sensitive to cytotoxic therapy[5] and these tumor cells may exhibit an epitope rendering these tumors amenable to immunotherapy[6]. In addition, inhibition of the PI3K pathway has sensitized EMl4-ALK fusion positive tumors to ALK-targeted therapy[7]. EML4-ALK fusion positive tumors show dependence on the HSP90 chaperone, suggesting this cohort of patients might benefit from the new HSP90 inhibitors recently being developed[8].

Table. Significantly mutated genes (point mutations, insertions/deletions) with associated function.

Gene Function
TP53 tumor suppressor
KRAS oncogene
ZFHX4 zinc finger DNA binding
DACH1 transcription factor
EGFR epidermal growth factor receptor
EPHA3 receptor tyrosine kinase
ENSG00000205044
RELN cell matrix protein
ABCB5 ABC Drug Transporter

Table. Literature Analysis of pathways containing significantly altered genes in NSCLC reveal putative targets and risk factors, linkage between other tumor types, and research areas for further investigation.

Note: Significantly mutated genes, obtained from WES, were subjected to pathway analysis (KEGG Pathway Analysis) in order to see which pathways contained signicantly altered gene networks. This pathway term was then used for PubMed literature search together with terms “lung cancer”, “gene”, and “NOT review” to determine frequency of literature coverage for each pathway in lung cancer. Links are to the PubMEd search results.

KEGG pathway Name # of PUBMed entries containing Pathway Name, Gene ANDLung Cancer
Cell cycle 1237
Cell adhesion molecules (CAMs) 372
Glioma 294
Melanoma 219
Colorectal cancer 207
Calcium signaling pathway 175
Prostate cancer 166
MAPK signaling pathway 162
Pancreatic cancer 88
Bladder cancer 74
Renal cell carcinoma 68
Focal adhesion 63
Regulation of actin cytoskeleton 34
Thyroid cancer 32
Salivary secretion 19
Jak-STAT signaling pathway 16
Natural killer cell mediated cytotoxicity 11
Gap junction 11
Endometrial cancer 11
Long-term depression 9
Axon guidance 8
Cytokine-cytokine receptor interaction 8
Chronic myeloid leukemia 7
ErbB signaling pathway 7
Arginine and proline metabolism 6
Maturity onset diabetes of the young 6
Neuroactive ligand-receptor interaction 4
Aldosterone-regulated sodium reabsorption 2
Systemic lupus erythematosus 2
Olfactory transduction 1
Huntington’s disease 1
Chemokine signaling pathway 1
Cardiac muscle contraction 1
Amyotrophic lateral sclerosis (ALS) 1

A few interesting genetic risk factors and possible additional targets for NSCLC were deduced from analysis of the above table of literature including HIF1-α, mIR-31, UBQLN1, ACE, mIR-193a, SRSF1. In addition, glioma, melanoma, colorectal, and prostate and lung cancer share many validated mutations, and possibly similar tumor driver mutations.

KEGGinliteroanalysislungcancer

 please click on graph for larger view

Paper 4. Mapping the Hallmarks of Lung Adenocarcinoma with Massively Parallel Sequencing[9]

For full paper and graphical summary please follow the link: http://www.cell.com/cell/abstract/S0092-8674%2812%2901061-6

Highlights

  • Exome and genome characterization of somatic alterations in 183 lung adenocarcinomas
  • 12 somatic mutations/megabase
  • U2AF1, RBM10, and ARID1A are among newly identified recurrently mutated genes
  • Structural variants include activating in-frame fusion of EGFR
  • Epigenetic and RNA deregulation proposed as a potential lung adenocarcinoma hallmark

Summary

Lung adenocarcinoma, the most common subtype of non-small cell lung cancer, is responsible for more than 500,000 deaths per year worldwide. Here, we report exome and genome sequences of 183 lung adenocarcinoma tumor/normal DNA pairs. These analyses revealed a mean exonic somatic mutation rate of 12.0 events/megabase and identified the majority of genes previously reported as significantly mutated in lung adenocarcinoma. In addition, we identified statistically recurrent somatic mutations in the splicing factor gene U2AF1 and truncating mutations affecting RBM10 and ARID1A. Analysis of nucleotide context-specific mutation signatures grouped the sample set into distinct clusters that correlated with smoking history and alterations of reported lung adenocarcinoma genes. Whole-genome sequence analysis revealed frequent structural rearrangements, including in-frame exonic alterations within EGFR and SIK2 kinases. The candidate genes identified in this study are attractive targets for biological characterization and therapeutic targeting of lung adenocarcinoma.

Paper 5. Integrative genome analyses identify key somatic driver mutations of small-cell lung cancer[10]

Highlights

  • Whole exome and transcriptome (RNASeq) sequencing 29 small-cell lung carcinomas
  • High mutation rate 7.4 protein-changing mutations/million base pairs
  • Inactivating mutations in TP53 and RB1
  • Functional mutations in CREBBP, EP300, MLL, PTEN, SLIT2, EPHA7, FGFR1 (determined by literature and database mining)
  • The mutational spectrum seen in human data also present in a Tp53-/- Rb1-/- mouse lung tumor model

 

Curator Graphical Summary of Interesting Findings From the Above Studies

DGRAPHICSUMMARYNSLCSEQPOST

The above figure (please click on figure) represents themes and findings resulting from the aforementioned studies including

questions which will be addressed in Future Posts on this site.

UPDATED 10/10/2021

The following article uses RNASeq to screen lung adenocarcinomas for fusion proteins in patients with either low or high tumor mutational burden. Findings included presence of MET fusion proteins in addition to other fusion proteins irrespective if tumors were driver negative by DNASeq screening.

High Yield of RNA Sequencing for Targetable Kinase Fusions in Lung Adenocarcinomas with No Mitogenic Driver Alteration Detected by DNA Sequencing and Low Tumor Mutation Burden

Source:

High Yield of RNA Sequencing for Targetable Kinase Fusions in Lung Adenocarcinomas with No Mitogenic Driver Alteration Detected by DNA Sequencing and Low Tumor Mutation Burden
Ryma BenayedMichael OffinKerry MullaneyPurvil SukhadiaKelly RiosPatrice DesmeulesRyan PtashkinHelen WonJason ChangDarragh HalpennyAlison M. SchramCharles M. RudinDavid M. HymanMaria E. ArcilaMichael F. BergerAhmet ZehirMark G. KrisAlexander Drilon and Marc Ladanyi

Abstract

Purpose: Targeted next-generation sequencing of DNA has become more widely used in the management of patients with lung adenocarcinoma; however, no clear mitogenic driver alteration is found in some cases. We evaluated the incremental benefit of targeted RNA sequencing (RNAseq) in the identification of gene fusions and MET exon 14 (METex14) alterations in DNA sequencing (DNAseq) driver–negative lung cancers.

Experimental Design: Lung cancers driver negative by MSK-IMPACT underwent further analysis using a custom RNAseq panel (MSK-Fusion). Tumor mutation burden (TMB) was assessed as a potential prioritization criterion for targeted RNAseq.

Results: As part of prospective clinical genomic testing, we profiled 2,522 lung adenocarcinomas using MSK-IMPACT, which identified 195 (7.7%) fusions and 119 (4.7%) METex14 alterations. Among 275 driver-negative cases with available tissue, 254 (92%) had sufficient material for RNAseq. A previously undetected alteration was identified in 14% (36/254) of cases, 33 of which were actionable (27 in-frame fusions, 6 METex14). Of these 33 patients, 10 then received matched targeted therapy, which achieved clinical benefit in 8 (80%). In the 32% (81/254) of DNAseq driver–negative cases with low TMB [0–5 mutations/Megabase (mut/Mb)], 25 (31%) were positive for previously undetected gene fusions on RNAseq, whereas, in 151 cases with TMB >5 mut/Mb, only 7% were positive for fusions (P < 0.0001).

Conclusions: Targeted RNAseq assays should be used in all cases that appear driver negative by DNAseq assays to ensure comprehensive detection of actionable gene rearrangements. Furthermore, we observed a significant enrichment for fusions in DNAseq driver–negative samples with low TMB, supporting the prioritization of such cases for additional RNAseq.

Translational Relevance

Inhibitors targeting kinase fusions have shown dramatic and durable responses in lung cancer patients, making their comprehensive detection critical. Here, we evaluated the incremental benefit of targeted RNA sequencing (RNAseq) in the identification of gene fusions in patients where no clear mitogenic driver alteration is found by DNA sequencing (DNAseq)–based panel testing. We found actionable alterations (kinase fusions or MET exon 14 skipping) in 13% of cases apparently driver negative by previous DNAseq testing. Among the driver-negative samples tested by RNAseq, those with low tumor mutation burden (TMB) were significantly enriched for gene fusions when compared with the ones with higher TMB. In a clinical setting, such patients should be prioritized for RNAseq. Thus, a rational, algorithmic approach to the use of targeted RNA-based next-generation sequencing (NGS) to complement large panel DNA-based NGS testing can be highly effective in comprehensively uncovering targetable gene fusions or oncogenic isoforms not just in lung cancer but also more generally across different tumor types.

A Commentary is in the same issue at https://clincancerres.aacrjournals.org/content/25/15/4586?iss=15

Wake Up and Smell the Fusions: Single-Modality Molecular Testing Misses Drivers

by Kurtis D. Davies and Dara L. Aisner

Abstract

Multitarget assays have become common in clinical molecular diagnostic laboratories. However, all assays, no matter how well designed, have inherent gaps due to technical and biological limitations. In some clinical cases, testing by multiple methodologies is needed to address these gaps and ensure the most accurate molecular diagnoses.

See related article by Benayed et al., p. 4712

In this issue of Clinical Cancer Research, Benayed and colleagues illustrate the growing need to consider multiple molecular testing methodologies for certain clinical specimens (1). The rapidly expanding list of actionable molecular alterations across cancer types has resulted in the wide adoption of multitarget testing approaches, particularly those based on next-generation sequencing (NGS). NGS-based assays are commonly viewed as “one-stop shops” to detect a vast array of molecular variants. However, as Benayed and colleagues discuss, even well-designed and highly vetted NGS assays have inherent gaps that, under certain circumstances, are ideally addressed by analyzing the sample using an alternative approach.

In the article, the authors examined a cohort of lung adenocarcinoma patient samples that had been deemed “driver- negative” via MSK-IMPACT, an FDA-cleared test that is widely considered by experts in the field to be one of the best examples of a DNA-based large gene panel NGS assay (2). Of 589 driver-negative cases, 254 had additional material amenable for a different approach: RNA-based NGS designed specifically for gene fusion and oncogenic gene isoform detection. After accounting for quality control failures, 232 samples were successfully sequenced, and, among these, 36 samples (representing an astonishing 15.5% of tested cases) were found to be positive for a driver gene fusion or oncogenic isoform that had not been detected by DNA-based NGS. The real-world value derived from this orthogonal testing schema was more than theoretical, with 8 of 10 (80%) patients demonstrating clinical benefit when treated according to the alteration identified via the RNA-based approach.

To detect gene rearrangements that lead to oncogenic gene fusions (and to detect mutations and insertions/deletions that lead to MET exon 14 skipping), MSK-IMPACT employs hybrid capture-based enrichment of selected intronic regions from genomic DNA. While this approach has proven to be successful in a variety of settings, there are associated limitations that were determined in this study to underlie the discrepancies between MSK-IMPACT and the RNA-based assay. First, some introns that are involved in clinically actionable rearrangement events are very large, thus requiring substantial sequencing capital that can represent a disproportionate fraction of the assay. Despite the ability via NGS to perform sequencing at a large scale, this sequencing capacity is still finite, and thus decisions must be made to sacrifice coverage of certain large genomic regions to ensure sufficient sequencing depth for other desired genomic targets. In the case of MSK-IMPACT (and most other DNA-based NGS assays), certain important introns in NTRK3 and NRG1 are not included in covered content, simply because they are too large (>90 Kb each). The second primary problem with DNA-based analysis of introns is that they often contain highly repetitive elements that are extremely difficult to assess via NGS due to their recurring presence across the genome. Attempts to sequence these regions are largely unfruitful because any sequencing data obtained cannot be specifically aligned/mapped to the desired targeted region of the genome (3). This is particularly true for intron 31 of ROS1, because it contains two repetitive long interspersed nuclear elements, and many DNA-based assays, including MSK-IMPACT, poorly cover this intron (4). In this study by Benayed and colleagues, the most common discrepant alteration was fusion involving ROS1, which accounted for 10 of 36 (28%) cases. At least six of these, those that demonstrated fusion to ROS1 exon 32, were likely directly explained by incomplete intron 31 sequencing. RNA-based analysis is able to overcome the above described limitations owing to the simple fact that sequencing is focused on exons post-splicing and the need to sequence introns is entirely avoided (Fig. 1).

Figure 1.

Schematic representation of underlying genomic complexities that can lead to false-negative gene fusion results in DNA-based NGS analysis. In some cases, RNA-based approaches may overcome the limitations of DNA-based testing.

Lack of sufficient intronic coverage could not account for all of the discrepancies between DNA-based and RNA-based analysis however. Six samples in the cohort were found to be positive for MET exon 14 skipping based on RNA. In five of these, genomic alterations in MET introns 13 or 14 were observed, however they did not conform to canonical splice site alterations and thus were not initially called (although this was addressed by bioinformatics updates). In RNA-based testing, however, determination of exon skipping is simplified such that, regardless of the specific genomic alteration that interferes with splicing, absence of the exon in the transcript is directly observed (5). In another two of the discrepant cases, tumor purity was observed to be low in the sample, meaning that the expected variant allele frequency (VAF) for a genomic event would also likely be low, potentially below detectable levels. However, overexpression of the fusions at the transcript level was theorized to compensate for low VAF (Fig. 1). Additional explanations for discordant findings between the assays included sample-specific poor sequencing in selected introns and complex rearrangements that hindered proper capture (Fig. 1).

The take home message from Benayed and colleagues is simply this: there is no perfect assay that will detect 100% of the potential actionable alterations in patient samples. Even an extremely well designed, thoroughly vetted, and FDA-cleared assay such as MSK-IMPACT will have inherent and unavoidable “holes” due to intrinsic limitations. The solution to this dilemma, as adeptly described by Benayed and colleagues, is additional testing using a different approach. While in an ideal world every clinical tumor sample would be tested by multiple modalities to ensure the most comprehensive clinical assessment, the reality is that these samples are often scant and testing is fiscally burdensome (and often not reimbursed). Therefore, algorithms to determine which samples should be reflexed to secondary assays after testing with a primary assay are critical for maximizing benefit. In this study, the first algorithmic step was lack of an identified driver (because activated oncogenic drivers tend to exist exclusively of each other), which amounted to 23% of samples tested with the primary assay. In addition, the authors found a significantly higher rate of actionable gene fusions in samples with a low (<5 mut/Mb) tumor mutational burden, meaning that this metric, which was derived from the primary assay, could also be used to help inform decision making regarding additional testing. While this scenario is somewhat specific to lung cancer, similar approaches could be prescribed on a cancer type–specific basis.

These findings should be considered a “wake-up call” for oncologists in regard to the ordering and interpretation of molecular testing. It is clear from these and other published findings that advanced molecular analysis has limitations that require nuanced technical understanding. As this arena evolves, it is critical for oncologists (and trainees) to gain an increased comprehension of how to identify when the “gaps” in a test might be most clinically relevant. This requires a level of technical cognizance that has been previously unexpected of clinical practitioners, yet is underscored by the reality that opportunities for effective targeted therapy can and will be missed if the treating oncologist is unaware of how to best identify patients for whom additional testing is warranted. This study also highlights the mantra of “no test is perfect” regardless of prestige of the testing institution, number of past tests performed, or regulatory status. NGS, despite its benefits, does not mean all-encompassing. It is only through the adaptability of laboratories to utilize knowledge such as is provided by Benayed and colleagues that advances in laboratory medicine can be quickly deployed to maximize benefits for oncology patients.

References:

  1. Comprehensive genomic characterization of squamous cell lung cancers. Nature 2012, 489(7417):519-525.
  2. A genomics-based classification of human lung tumors. Science translational medicine 2013, 5(209):209ra153.
  3. Govindan R, Ding L, Griffith M, Subramanian J, Dees ND, Kanchi KL, Maher CA, Fulton R, Fulton L, Wallis J et al: Genomic landscape of non-small cell lung cancer in smokers and never-smokers. Cell 2012, 150(6):1121-1134.
  4. Takeuchi K, Soda M, Togashi Y, Suzuki R, Sakata S, Hatano S, Asaka R, Hamanaka W, Ninomiya H, Uehara H et al: RET, ROS1 and ALK fusions in lung cancer. Nature medicine 2012, 18(3):378-381.
  5. Morodomi Y, Takenoyama M, Inamasu E, Toyozawa R, Kojo M, Toyokawa G, Shiraishi Y, Takenaka T, Hirai F, Yamaguchi M et al: Non-small cell lung cancer patients with EML4-ALK fusion gene are insensitive to cytotoxic chemotherapy. Anticancer research 2014, 34(7):3825-3830.
  6. Yoshimura M, Tada Y, Ofuzi K, Yamamoto M, Nakatsura T: Identification of a novel HLA-A 02:01-restricted cytotoxic T lymphocyte epitope derived from the EML4-ALK fusion gene. Oncology reports 2014, 32(1):33-39.
  7. Yang L, Li G, Zhao L, Pan F, Qiang J, Han S: Blocking the PI3K pathway enhances the efficacy of ALK-targeted therapy in EML4-ALK-positive nonsmall-cell lung cancer. Tumour biology : the journal of the International Society for Oncodevelopmental Biology and Medicine 2014.
  8. Workman P, van Montfort R: EML4-ALK fusions: propelling cancer but creating exploitable chaperone dependence. Cancer discovery 2014, 4(6):642-645.
  9. Imielinski M, Berger AH, Hammerman PS, Hernandez B, Pugh TJ, Hodis E, Cho J, Suh J, Capelletti M, Sivachenko A et al: Mapping the hallmarks of lung adenocarcinoma with massively parallel sequencing. Cell 2012, 150(6):1107-1120.
  10. Peifer M, Fernandez-Cuesta L, Sos ML, George J, Seidel D, Kasper LH, Plenker D, Leenders F, Sun R, Zander T et al: Integrative genome analyses identify key somatic driver mutations of small-cell lung cancer. Nature genetics 2012, 44(10):1104-1110.

Other posts on this site which refer to Lung Cancer and Cancer Genome Sequencing include:

Multi-drug, Multi-arm, Biomarker-driven Clinical Trial for patients with Squamous Cell Carcinoma called the Lung Cancer Master Protocol, or Lung-MAP launched by NCI, Foundation Medicine, and Five Pharma Firms

US Personalized Cancer Genome Sequencing Market Outlook 2018 –

Comprehensive Genomic Characterization of Squamous Cell Lung Cancers

International Cancer Genome Consortium Website has 71 Committed Cancer Genome Projects Ongoing

Non-small Cell Lung Cancer drugs – where does the Future lie?

Lung cancer breathalyzer trialed in the UK

Diagnosing Lung Cancer in Exhaled Breath using Gold Nanoparticles

Multi-drug, Multi-arm, Biomarker-driven Clinical Trial for patients with Squamous Cell Carcinoma called the Lung Cancer Master Protocol, or Lung-MAP launched by NCI, Foundation Medicine, and Five Pharma Firms

Read Full Post »

Good and Bad News Reported for Ovarian Cancer Therapy

Reporter, Curator: Stephen J. Williams, Ph.D.

 

In a recent Fierce Biotech report

FDA review red-flags AstraZeneca’s case for ovarian cancer drug olaparib”,

John Carroll reports on a disappointing ruling by the FDA on AstraZeneca’s PARP1 inhibitor olaparib for maintenance therapy in women with cisplatin refractory ovarian cancer with BRCA mutation.   Early clinical investigations had pointed to efficacy of PARP inhibitors in ovarian tumors carrying the BRCA mutation. The scientific rationale for using PARP1 inhibitors in BRCA1/2 deficiency was quite clear:

  1. DNA damage can result in

1. double strand breaks (DSB)

  1.  DSB can be repaired by efficient homologous recombination (HR) or less efficient non-homologous end joining (NHEJ)

b. BRCA1 involved in RAD51 dependent HR at DSB sites

  1. In BRCA1 deficiency DSB repaired by less efficient NHEJ

 

 

2. single strand breaks, damage (SSB)

  1. PARP1 is activated by DNA damage and poly-ADP ribosylates histones and other proteins marking DNA for SSB repair
  2. SSB repair usually base excision (BER) or sometimes nucleotide excision repair (NER)

B. if PARP inhibited then SSB gets converted to DSB

C. in BRCA1/2 deficient background repair is forced to less efficient NHEJ thereby perpetuating some DNA damage pon exposure to DNA damaging agent

 

A good review explaining the pharmacology behind the rationale of PARP inhibitors in BRCA deficient breast and ovarian cancer is given by Drs. Christina Annunziata and Susan E. Bates in PARP inhibitors in BRCA1/BRCA2 germline mutation carriers with ovarian and breast cancer

(http://f1000.com/prime/reports/b/2/10/) and below a nice figure from their paper:

 

parpbrcadnadamage

 

 

 

 

 

 

 

(from Christina M Annunziata and Susan E Bates. PARP inhibitors in BRCA1/BRCA2 germline mutation carriers with ovarian and breast cancer.  F1000 Biol Reports, 2010; 2:10.)  Creative Commons

Dr. Sudipta Saha’s post BRCA1 a tumour suppressor in breast and ovarian cancer – functions in transcription, ubiquitination and DNA repair discusses how BRCA1 affects the double strand DNA repair process, augments histone modification, as well as affecting expression of DNA repair genes.

Dana Farber’s Dr. Ralph Scully, Ph.D., in Exploiting DNA Repair Targets in Breast Cancer (http://www.dfhcc.harvard.edu/news/news/article/5402/), explains his research investigating why multiple DNA repair pathways may have to be targeted with PARP therapy concurrent with BRCA1 deficiency.

 

However FDA investigators voiced their skepticism of AstraZeneca’s clinical results, namely

  • Small number of patients enrolled
  • BRCA1/2 cohort were identified retrospectively
  • results skewed by false benefit from “underperforming” control arm
  • possible inadvertent selection bias
  • hazard ratio suggesting improvement in progression free survival but higher risk/benefit

The FDA investigators released their report two days before an expert panel would be releasing their own report (reported in the link below from FierceBiotech)

UPDATED: FDA experts spurn AstraZeneca’s pitch for ovarian cancer drug olaparib

in which the expert panel reiterated the findings of the FDA investigators.   The expert panel’s job was to find if there was any clinical benefit for continuing consideration of olaparib, basically stating

“This trial has problems,” noted FDA cancer chief Richard Pazdur during the panel discussion. If investigators had “pristine evidence of a 7-month advantage in PFS, we wouldn’t be here.”

The expert panel was concerned for the above reasons as well as the reported handful of lethal cases of myelodysplastic syndrome and acute myeloid leukemia in the study, although the panel noted these patients had advanced disease before entering the trial, raising the possibility that prior drugs may have triggered their deaths.

 

This was certainly a disappointment as ….

it was at last year’s ASCO (2013) that investigators at Perelman School of Medicine at the University of Pennsylvania and Sheba Medical Center in Tel Hashomer, Israel presented data showing that in 193 cisplatin-refractory ovarian cancer patients carrying a BRCA1/2 mutation, 31% had a partial or complete tumor regression. In addition the study also showed good response in pancreatic and prostate cancer with tolerable side effects.

 

See here for study details: http://www.uphs.upenn.edu/news/News_Releases/2013/05/domchek/

 

As John Carrol from FierceBiotech notes, the decision may spark renewed interest by Pfizer of a bid for AstraZeneca as the potential FDA rejection would certainly dampen AstraZeneca’s future growth and profit plans. Last month AstraZeneca’s CEO made the case to shareholders to reject the Pfizer offer by pointing to AstraZeneca’s potential beefed-up pipeline. AstraZeneca had projected olaparib as a potential $2 billion-a-year seller, although some industry analysts see sales at less than half that amount.

A company spokeswoman said the monotherapy use of olaparib for ovarian cancer assessed by the U.S. expert panel this week was only one element of a broad development program.

 

 

Please see a table of current oncology clinical trials with PARP1 inhibitors

at end of this post

 

However, on the same day, FierceBiotechreports some great news (at least in Europe) on the ovarian cancer front:

 

EU backs Roche’s Avastin for hard-to-treat ovarian cancer

As Arlene Weintraub   of FierceBiotech reports:

EU Committee for Medicinal Products for Human Use (CHMP) handed down a positive ruling on Avastin, recommending that the European Commission approve the drug for use in women with ovarian cancer that’s resistant to platinum-based chemotherapy. It’s the first biologic to receive a positive opinion from the CHMP for this hard-to-treat form of the disease.

Please see here for official press release: CHMP recommends EU approval of Roche’s Avastin for platinum-resistant recurrent ovarian cancer

 

EU had been getting pressure from British doctors to approve Avastin based on clinical trial results although it may be important to note that the EU zone seems to have an ability to recruit more numbers for clinical trials than in US. For instance an EU women’s breast cancer prevention trial had heavy recruitment in what would be considered a short time frame compared to recruitment times for the US.

 

Below is a table on PARP1 inhibitors in current clinical trials (obtained from NewMedicine’s Oncology KnowledgeBase™). nm|OK is a relational knowledgeBASE covering all major aspects of product development in oncolology. The database comprises 6 modules each dedicated in a specific sector within the oncology field.

 

PARP1 Inhibitors Currently in Clinical Trials for Ovarian Cancer

 

Developer and

Drug Name

Development Status & Location
– Indications
AbbVie

Current as of: March 27, 2014

PARP inhibitor: ABT-767

Phase I (begin 5/11, ongoing 2/14) Europe (Netherlands) – solid tumors with BRCA1 or BRCA2 mutations, locally advanced or metastatic • ovarian cancer, advanced or metastatic • fallopian tube cancer, advanced or metastatic • peritoneal cancer, advanced or metastatic
AstraZeneca
Affiliate(s):
· Myriad GeneticsCurrent as of: June 26, 2014Generic Name: Olaparib
Brand Name: Lynparza
Other Designation: AZD2281, KU59436, KU-0059436, NSC 747856
Phase I (begin 7/05, closed 9/08) Europe (Netherlands, UK, Poland); phase II (begin 6/07, closed 2/08, completed 5/09) USA, Australia, Europe (Germany, Spain, Sweden, UK), phase II (begin 7/08, closed 2/09) USA, Australia, Europe (Belgium, Germany, Poland, Spain, UK), Israel, phase II (begin 8/08, closed 12/09, completed 3/13) USA, Australia, Canada, Europe (Belgium, France, Germany, Poland, Romania, Spain, Ukraine, UK), Israel, Russia; phase II (begin 2/10, closed 7/10) USA, Australia, Canada, Europe (Belgium, Czech Republic, Germany, Italy, Netherlands, Spain, UK), Japan, Panama, Peru (combination); MAA (accepted 9/13) EU, NDA (filed 2/14) USA – ovarian cancer, advanced or metastatic, BRCA positive • ovarian cancer, recurrent, platinum sensitive • ovarian cancer, advanced, refractory, BRCA1 or BRCA2-associatedPhase I (begin 5/08, ongoing 5/12) USA; phase II (begin 7/08, closed 10/09) Canada – breast cancer, locally advanced, BRCA1/BRCA2-associated or hereditary metastatic or inoperable • ovarian cancer, locally advanced, BRCA1/BRCA2-associated or hereditary metastatic or inoperable • breast cancer, triple-negative, BRCA-positive • ovarian cancer, high-grade serous and/or undifferentiated, BRCA-positive

Phase I (begin 10/10, ongoing 1/13) USA (combination) – ovarian cancer, inoperable or metastatic, refractory • breast cancer, inoperable or metastatic, refractory

Phase III (begin 8/13) USA, Australia, Brazil, Canada, Europe (France, Italy, Netherlands, Poland, Russia, Spain, UK), Israel, South Korea, phase III (begin 9/13) USA, Australia, Brazil, Canada, Europe (France, Germany, Italy, Netherlands, Poland, Russia, Spain, UK), Israel – ovarian cancer, serous, high grade, BRCA mutated, platinum-sensitive, relapsed, third line, maintenance • ovarian cancer, serous or endometrioid, high grade, BRCA mutated, platinum responsive (PR or CR), maintenance, first line • primary peritoneal cancer, high grade, BRCA mutated, platinum responsive (PR or CR), maintenance • fallopian tube cancer, high grade, BRCA mutated, platinum responsive (PR or

BioMarin Pharmaceutical

Current as of: June 14, 2014

PARP inhibitor:

BMN-673, BMN673, LT-673

Phase I/II (begin 1/11, ongoing 3/14) USA – solid tumors, advanced, recurrent

Phase I (begin 2/13, closed 4/13, completed 5/14) USA – healthy volunteers

Phase I/II (begin 11/13) USA – solid tumors, relapsed or refractory, BRCA mutated, second line

BiPar Sciences

Current as of: April 16, 2009

Parp inhibitor:

BSI-401

Preclin (ongoing 4/09) – solid tumors
Clovis Oncology
Affiliate(s):
· University of Newcastle Upon Tyne
· Cancer Research Campaign Technology
· PfizerCurrent as of: June 21, 2014Generic Name: Rucaparib
Brand Name: Rucapanc
Other Designation: AG140699, AG014699, AG-14,699, AG-14669, AG14699, AG140361, AG-14361, AG-014699, CO-338, PF-01367338
Phase I (begin 03, completed 05) Europe (UK) (combination), phase I (begin 2/10, closed 11/13) Europe (France, UK) (combination) – solid tumors, advanced

Phase II (begin 12/07, closed 10/13) Europe (UK) – breast cancer, advanced or metastatic, in patients carrying BRCA1 or BRCA2 mutations • ovarian cancer, advanced or metastatic, in patients carrying BRCA1 or BRCA2 mutations

Phase I/II (begin 11/11, ongoing 6/14) USA, Europe (UK) – solid tumors, metastatic, with mutated BRCA • breast cancer, metastatic, HEr2 negative, with mutated BRCA

Sanofi

Current as of: June 03, 2013

Generic Name: Iniparib
Brand Name: Tivolza
Other Designation: BSI-201, NSC 746045, SAR240550

Phase I/Ib (begin 3/06, closed 3/10) USA (combination), phase I (begin 7/10, closed 11/10) USA, phase I (begin 9/10, ongoing 2/11) Japan (combination); phase Ib (begin 1/07, ongoing 1/11) USA (combination) – solid tumors, advanced, refractory
Phase II (begin 5/08, closed 1/09) USA – ovarian cancer, advanced, refractory, BRCA-1 or BRCA-2 associated • fallopian tube cancer, advanced, refractory, BRCA-1 or BRCA-2 associated • peritoneal cancer, advanced, refractory, BRCA-1 or BRCA-2 associated
Tesaro
Affiliate(s):
· MerckCurrent as of: May 18, 2014Generic Name: Niraparib
Other Designation: MK-4827, MK4827
Phase I (begin 9/08, closed 2/11) USA, Europe (UK) – solid tumors, locally advanced or metastatic • ovarian cancer, locally advanced or metastatic, BRCA mutant • chronic lymphocytic leukemia (CLL), relapsed or refractory • prolymphocytic leukemia, T cell, relapsed or refractory
Phase Ib (begin 11/10, closed 3/11, terminated 10/12) USA (combination) – solid tumors, locally advanced or metastatic • ovarian cancer, serous, high grade, platinum resistant or refractoryPhase III (begin 5/13, ongoing 5/14) USA – ovarian cancer, platinum-sensitive, high grade serous or BRCA mutant, chemotherapy responsive • fallopian tube cancer • primary peritoneal cancer
Teva Pharmaceutical Industries

Current as of: May 04, 2013

Designation:

CEP-9722

Phase I (begin 5/11, closed 11/12, terminated 10/13) USA, phase I (begin 6/09, closed 7/12, completed 1/12) Europe (France and UK) (combination) – solid tumors, advanced, third line
Phase I (begin 5/11, completed 1/13) Europe (France) (combination) – solid tumors, advanced • mantle cell lymphoma (MCL), advanced

 

 

Summary of Combination Ovarian Cancer Trials with Avastin (current and closed)

 

Indication in Development ovarian cancer, advanced, recurrent, persistent • ovarian cancer, progressive, platinum resistant, second line • fallopian tube cancer, progressive, platinum resistant, second line • primary peritoneal cancer, progressive, platinum resistant, second line
Latest Status Phase II (begin 4/02, closed 8/04) USA, phase II (begin 11/04, closed 10/05) USA; phase III (begin 10/09) Europe (Belgium, Bosnia and Herzegovina, Denmark, Finland, France, Germany, Greece, Italy, Netherlands, Norway, Portugal, Spain, Sweden), Turkey
Clinical History Refer to the Combination Trial Module for trials of Avastin in combination with various chemotherapeutic regimens.According to results from the AURELIA clinical trial (protocol ID: MO22224; 2009-011400-33; NCT00976911), the median PFS in women with progressive platinum resistant ovarian, fallopian tube or primary peritoneal cancer treated with Avastin in combination with chemotherapy, was 6.7 months compared to 3.4 months in those treated with chemotherapy alone for an HR of 0.48 (range =0.38–0.60).. In addition, the objective response rate was 30.9% in women treated with Avastin compared to 12.6% in those on chemotherapy (p=0.001). Certain AE (Grade 2 to 5) that occurred more often in the Avastin arm compared to the chemotherapy alone arm were high blood pressure (20% versus 7%) and an excess of protein in the urine (11% versus 1%). Gastrointestinal perforations and fistulas occurred in 2% of women in the Avastin arm compared to no events in the chemotherapy arm (Pujade-Lauraine E, etal, ASCO12, Abs. LBA5002).A multicenter (n=124), randomized, open label, 2-arm, phase III clinical trial (protocol ID: MO22224; 2009-011400-33; NCT00976911; http://clinicaltrials.gov/ct2/results?term=NCT00976911 ), dubbed AURELIA, was initiated in October 2009, in Europe (Belgium, Bosnia and Herzegovina, Denmark, Finland, France, Germany, Greece, Italy, Netherlands, Norway, Portugal, Spain, and Sweden), and Turkey, to evaluate the efficacy and safety of Avastin added to chemotherapy versus chemotherapy alone in patients with epithelial ovarian, fallopian tube or primary peritoneal cancer with disease progression within 6 months of platinum therapy in the first line setting. The trials primary outcome measure is PFS. Secondary outcome measures include objective response rate, biological PFS interval, OS, QoL, and safety and tolerability. According to the protocol, all patients are treated with standard chemotherapy with IV paclitaxel (80 mg/m²) on days 1, 8, 15 and 22 of each 4-week cycle; or IV topotecan at a dose of 4 mg/m² on days 1, 8 and 15 of each 4-week cycle, or 1.25 mg/kg on days 1-5 of each 3-week cycle; or IV liposomal doxorubicin (40 mg/m²) every 4 weeks. Patients (n=179) randomized to arm 2 of the trial are treated with IV Avastin at a dose of 10 mg/kg twice weekly or 15 mg/kg thrice weekly concomitantly with the chemotherapy choice. Treatment continues until disease progression. Subsequently, patients are treated with the standard of care. Patients in arm 1 (n=182), on chemotherapy only may opt to be treated with IV Avastin (15 mg/kg) three times weekly. The trial was set up in cooperation with the Group d’Investigateurs Nationaux pour l’Etude des Cancers Ovariens (GINECO) and was conducted by the international network of the Gynecologic Cancer Intergroup (GCIG) and the pan-European Network of Gynaecological Oncological Trial Groups (ENGOT), under PI Eric Pujade-Lauraine, MD, Hopitaux Universitaires, Paris Centre, Hôpital Hôtel-Dieu (Paris, France). The trial enrolled 361 patients and was closed as of May 2012..Results were presented from a phase II clinical trial (protocol ID: CDR0000068839; GOG-0170D; NCT00022659) of bevacizumab in patients with persistent or recurrent epithelial ovarian cancer or primary peritoneal cancer that was performed by the Gynecologic Oncology Group to determine the ORR, PFS, and toxicity for this treatment. Patients must have been administered 1-2 prior cytotoxic regimens. Treatment consisted of bevacizumab (15 mg/kg) IV every 3 weeks until disease progression or prohibitive toxicity. Between April 2002 and August 2004, 64 patients were enrolled, of which 2 were excluded for wrong primary and borderline histology and 62 were evaluable (1 previous regimen=23, 2 previous regimens=39). The median disease free interval from completion of primary cytotoxic chemotherapy to first recurrence was 6.5 months. Early results demonstrated that some patients had confirmed objective responses and PFS in some was at least 6 months. Observed Grade 3 or 4 toxicities included allergy (Grade 3=1), cardiovascular (Grade 3=4; Grade 4=1), gastrointestinal (Grade 3=3), hepatic (Grade 3=1), pain (Grade 3=2), and pulmonary (Grade 4=1). As of 11/04, 36 patients were removed from the trial, including 29 for disease progression and 1 for toxicity in 33 cases reported. Preliminary evidence exists for objective responses to bevacizumab (Burger R, et al, ASCO05, Abs. 5009).An open label, single arm, 2-stage, phase II clinical trial (protocol ID: AVF2949g, NCT00097019) of bevacizumab in patients with platinum resistant, advanced (Stage III or IV), ovarian cancer or primary peritoneal cancer for whom subsequent doxorubicin or topotecan therapy also has failed was initiated in November 2004 at multiple locations in the USA to determine the safety and efficacy for this treatment.A multicenter phase II clinical trial was initiated in April 2002 to determine the 6-month PFS of patients with persistent or recurrent ovarian epithelial or primary peritoneal cancer treated with bevacizumab (protocol ID: GOG-0170D, CDR0000068839, NCT00022659). IV bevacizumab is administered over 30-90 minutes on day 1. Treatment is repeated every 21 days in the absence of disease progression or unacceptable toxicity. Patients are followed every 3 months for 2 years, every 6 months for 3 years, and then annually thereafter. A total of 22-60 patients will be accrued within 12-30 months. Robert A. Burger, MD, of Chao Family Comprehensive Cancer Center is Trial Chair.This trial was closed in August 2004.

 

 

Sources

http://www.fiercebiotech.com/story/fda-review-red-flags-astrazenecas-case-ovarian-cancer-drug-olaparib/2014-06-23

 

http://www.fiercebiotech.com/story/fda-experts-spurn-astrazenecas-pitch-ovarian-cancer-drug-olaparib/2014-06-25

 

http://www.fiercepharma.com/story/eu-backs-roches-avastin-hard-treat-ovarian-cancer/2014-06-27

 

In a followup to this original posting A Report From the Institute of Medicine of the National Academies of Sciences, Engineering, and Medicine entitled

Evolving Approaches in Research and Care for Ovarian Cancers

was generated in a ViewPoint piece in JAMA which discussed their Congressional mandated report on the State of the Science in Ovarian Cancer Research, titled

Ovarian Cancers: Evolving Paradigms in Research and Care 

highlights some of the research gaps felt by the committee in the current state of ovarian cancer research including:

  • consideration in research protocols of the multitude of histologic and morphologic subtypes of ovarian cancer, including the feeling of the committee that high grade serous OVCA originates from the distal end of the fallopian tube (espoused by Dr. Doubeau and Dr. Christopher Crum) versus originating from the ovarian surface epithelium
  • a call for expanded screening and prevention research with mutimodal screening including CA125 with secondary transvaginal screen
  • better patient education of the risk/benefit of genetic testing including BRCA1/2 as well as in consideration for PARP inhibitor therapy
  • treatments should be standardized and disseminated including more research in health outcomes and decision support for personalized therapy

This Perspective article can be found here: jvp160038

Some other posts relating to OVARIAN CANCER on this site include

Efficacy of Ovariectomy in Presence of BRCA1 vs BRCA2 and the Risk for Ovarian Cancer

Testing for Multiple Genetic Mutations via NGS for Patients: Very Strong Family History of Breast & Ovarian Cancer, Diagnosed at Young Ages, & Negative on BRCA Test

Ultrasound-based Screening for Ovarian Cancer

Dasatinib in Combination With Other Drugs for Advanced, Recurrent Ovarian Cancer

BRCA1 a tumour suppressor in breast and ovarian cancer – functions in transcription, ubiquitination and DNA repair

 

Read Full Post »

Current Advanced Research Topics in MRI-based Management of Cancer Patients

 Author: Dror Nir, PhD

Step forward towards quantitative and reproducible MRI of cancer patients is the combination of structure and morphology based imaging with expressions of typical bio-chemical processes using imaging contrast materials. The following list brings the latest publications on this subject in Radiology magazine.

 The Effects of Applying Breast Compression in Dynamic Contrast Material–enhanced MR Imaging

Abstract

 Purpose: To evaluate the effects of breast compression on breast cancer masses, contrast material enhancement of glandular tissue, and quality of magnetic resonance (MR) images in the identification and characterization of breast lesions.

Materials and Methods: This was a HIPAA-compliant, institutional review board–approved retrospective study, with waiver of informed consent. Images from 300 MR imaging examinations in 149 women (mean age ± standard deviation, 51.5 years ± 10.9; age range, 22–76 years) were evaluated. The women underwent diagnostic MR imaging (no compression) and MR-guided biopsy (with compression) between June 2008 and February 2013. Breast compression was expressed as a percentage relative to the noncompressed breast. Percentage enhancement difference was calculated between noncompressed- and compressed-breast images obtained in early and delayed contrast-enhanced phases. Breast density, lesion type (mass vs non-masslike enhancement [NMLE]), lesion size, percentage compression, and kinetic curve type were evaluated. Linear regression, receiver operating characteristic (ROC) curve analysis, and κ test were performed.

Conclusion: Breast compression during biopsy affected breast lesion detection, lesion size, and dynamic contrast-enhanced MR imaging interpretation and performance. Limiting the application of breast compression is recommended, except when clinically necessary.

 Localized Prostate Cancer Detection with 18F FACBC PET/CT: Comparison with MR Imaging and Histopathologic Analysis

Abstract

 Purpose: To characterize uptake of 1-amino-3-fluorine 18-fluorocyclobutane-1-carboxylic acid (18F FACBC) in patients with localized prostate cancer, benign prostatic hyperplasia (BPH), and normal prostate tissue and to evaluate its potential utility in delineation of intraprostatic cancers in histopathologically confirmed localized prostate cancer in comparison with magnetic resonance (MR) imaging.

Materials and Methods: Institutional review board approval and written informed consent were obtained for this HIPAA-compliant prospective study. Twenty-one men underwent dynamic and static abdominopelvic 18F FACBC combined positron emission tomography (PET) and computed tomography (CT) and multiparametric (MP) 3-T endorectal MR imaging before robotic-assisted prostatectomy. PET/CT and MR images were coregistered by using pelvic bones as fiducial markers; this was followed by manual adjustments. Whole-mount histopathologic specimens were sliced with an MR-based patient-specific mold. 18F FACBC PET standardized uptake values (SUVs) were compared with those at MR imaging and histopathologic analysis for lesion- and sector-based (20 sectors per patient) analysis. Positive and negative predictive values for each modality were estimated by using generalized estimating equations with logit link function and working independence correlation structure.

Conclusion: 18F FACBC PET/CT shows higher uptake in intraprostatic tumor foci than in normal prostate tissue; however, 18F FACBC uptake in tumors is similar to that in BPH nodules. Thus, it is not specific for prostate cancer. Nevertheless, combined 18F FACBC PET/CT and T2-weighted MR imaging enable more accurate localization of prostate cancer lesions than either modality alone.

Illuminating Radiogenomic Characteristics of Glioblastoma Multiforme through Integration of MR Imaging, Messenger RNA Expression, and DNA Copy Number Variation

 Abstract

Purpose: To perform a multilevel radiogenomics study to elucidate the glioblastoma multiforme (GBM) magnetic resonance (MR) imaging radiogenomic signatures resulting from changes in messenger RNA (mRNA) expression and DNA copy number variation (CNV).

Materials and Methods: Radiogenomic analysis was performed at MR imaging in 23 patients with GBM in this retrospective institutional review board–approved HIPAA-compliant study. Six MR imaging features—contrast enhancement, necrosis, contrast-to-necrosis ratio, infiltrative versus edematous T2 abnormality, mass effect, and subventricular zone (SVZ) involvement—were independently evaluated and correlated with matched genomic profiles (global mRNA expression and DNA copy number profiles) in a significant manner that also accounted for multiple hypothesis testing by using gene set enrichment analysis (GSEA), resampling statistics, and analysis of variance to gain further insight into the radiogenomic signatures in patients with GBM

Conclusion: Construction of an MR imaging, mRNA, and CNV radiogenomic association map has led to identification of MR traits that are associated with some known high-grade glioma biomarkers and association with genomic biomarkers that have been identified for other malignancies but not GBM. Thus, the traits and genes identified on this map highlight new candidate radiogenomic biomarkers for further evaluation in future studies.

PET/MR Imaging: Technical Aspects and Potential Clinical Applications

Abstract

Instruments that combine positron emission tomography (PET) and magnetic resonance (MR) imaging have recently been assembled for use in humans, and may have diagnostic performance superior to that of PET/computed tomography (CT) for particular clinical and research applications. MR imaging has major strengths compared with CT, including superior soft-tissue contrast resolution, multiplanar image acquisition, and functional imaging capability through specialized techniques such as diffusion-tensor imaging, diffusion-weighted (DW) imaging, functional MR imaging, MR elastography, MR spectroscopy, perfusion-weighted imaging, MR imaging with very short echo times, and the availability of some targeted MR imaging contrast agents. Furthermore, the lack of ionizing radiation from MR imaging is highly appealing, particularly when pediatric, young adult, or pregnant patients are to be imaged, and the safety profile of MR imaging contrast agents compares very favorably with iodinated CT contrast agents. MR imaging also can be used to guide PET image reconstruction, partial volume correction, and motion compensation for more accurate disease quantification and can improve anatomic localization of sites of radiotracer uptake, improve diagnostic performance, and provide for comprehensive regional and global structural, functional, and molecular assessment of various clinical disorders. In this review, we discuss the historical development, software-based registration, instrumentation and design, quantification issues, potential clinical applications, potential clinical roles of image segmentation and global disease assessment, and challenges related to PET/MR imaging.

Read Full Post »

« Newer Posts - Older Posts »