Diagnosis of Coronavirus Infection by Medical Imaging and ALL other Cardiovascular Impacts of Viral Infection
- Lead Curator – e–mail Contact: avivalev-ari@alum.berkeley.edu
UPDATED on 11/25/2020
AI can detect COVID-19 quickly, accurately on x-rays
By Erik L. Ridley, AuntMinnie staff writer
A team of researchers from Northwestern University led by senior author Aggelos Katsaggelos, PhD, and cardiologist Dr. Ramsey Wehbe trained their algorithm — called DeepCOVID-XR — on nearly 15,000 chest x-rays acquired earlier this year. In testing on an independent dataset, the algorithm performed comparably to the consensus interpretations by five experienced radiologists and was also 10 times faster.
“We feel that this algorithm has the potential to benefit healthcare systems in mitigating unnecessary exposure to the virus by serving as an automated tool to rapidly flag patients with suspicious chest imaging for isolation and further testing,” the authors wrote.
DeepCOVID-XR is an ensemble of 24 individually trained deep convolutional neural networks (CNNs). First, the algorithm was pretrained using a dataset of over 100,000 chest x-ray images from the U.S. National Institutes of Health (NIH).
Next, DeepCOVID-XR was trained and validated on 14,788 images — including 4,253 COVID-19-positive images — gathered from 20 sites across the Northwestern Memorial Healthcare System between February and April 2020.
After analyzing the images, DeepCOVID-XR yields a final binary prediction of either positive or negative for COVID-19 based on the weighted average of the predictions by the individual CNNs that make up the ensemble. The algorithm also uses a gradient class activation mapping technique to provide “heat maps” on the images. This allows users to see the image features that were most important in arriving at the algorithm’s predictions of a positive COVID-19 result.
SOURCE
https://www.auntminnie.com/index.aspx?sec=sup&sub=aic&pag=dis&ItemID=130926
UPDATED on 11/3/2020
What new imaging data tells us about COVID-19 and heart damageCardiac structural abnormalities are common among hospitalized COVID-19 patients who undergo a transthoracic echocardiogram (TTE), according to new findings published in the Journal of the American College of Cardiology.
Prior studies focused on myocardial injury had not included much, if any, insight into medical imaging data, making the results less helpful to clinicians. The team behind this analysis hoped to address that shortcoming by taking a thorough look at the TTE findings of hospitalized COVID-19 patients.
The study included data from 305 patients who were treated in one of seven hospitals from March 5 to May 2, 2020. All patients had a confirmed COVID-19 diagnosis and underwent a TTE. The mean patient age was 63 years old and more than 67% were male. While
Overall, 62.6% of patients showed biomarker evidence of myocardial injury. While 61% of those patients showed signs of myocardial injury when they were initially admitted to the hospital, the other patients developed myocardial injury during the hospitalization.
“Patients with cardiac injury had a substantially greater prevalence of left ventricular, right ventricular and pericardial abnormalities,” wrote lead author Gennaro Giustino, MD, of the Icahn School of Medicine at Mount Sinai in New York City, and colleagues. “Higher degrees of diastolic dysfunction were also more frequent in patients with myocardial injury, possibly reflecting the higher prevalence of hypertension and chronic kidney disease among these patients. ST-segment changes on the 12-lead electrocardiogram appeared to identify two different patterns of myocardial injury, with diffuse ST-segment changes associated with global biventricular dysfunction (possibly reflecting a diffuse myocardial inflammatory damage) and regional ST-segment changes associated with regional wall motion abnormalities (possibly reflecting regional ischemic damage of the myocardium due to macro- or microvascular thrombosis). Therefore, ECG and echocardiographic abnormalities in the context of the appropriate clinical scenario may help differentiate across the different etiologies of myocardial injury in COVID-19.”
Patients with myocardial injury, the authors added, tended to be older and were more likely to have hypertension, diabetes or chronic kidney disease.
Among patients without myocardial injury, the in-hospital mortality rate was 5.2%. For patients with myocardial injury and no TTE-detected cardiac structural abnormalities, that rate increased to 18.6%. And for patients with myocardial injury and TTE-detected abnormalities, it jumped all the way to 31.7%.
After adjusting for certain variables and running numerous calculations, the team concluded that myocardial injury with TTE-detected abnormalities was associated with an increased risk of in-hospital mortality. Myocardial injury and no TTE-detected abnormalities, however, was not associated with such a risk.
SOURCE
UPDATED on 10/11/2020
Tiny biologic drug to fight COVID-19 show promise in animal models
Reporters: Irina Robu, PhD
UPDATED on 10/11/2020
Llama-inspired “AeroNabs” to strangle COVID-19 with an inhaler
Reporters: Irina Robu, PhD
UPDATED on 9/29/2020
Precision Cardiology to Benefit from New Atlas of Cells of the Adult Human Heart
Reporters: Justin D. Pearlman, MD, PhD, FACC and Aviva Lev-Ari, PhD, RN
The Impact of COVID-19 on the Human Heart
Reporters: Justin D. Pearlman, MD, PhD, FACC and Aviva Lev-Ari, PhD, RN
https://pharmaceuticalintelligence.com/2020/09/29/the-impact-of-covid-19-on-the-human-heart/
UPDATED on 9/2/2020
First Randomized Trial Reassures on ACEIs, ARBs in COVID-19
Editor’s note: Find the latest COVID-19 news and guidance in Medscape’s Coronavirus Resource Center.
The first randomized study to compare continuing vs stopping angiotensin-converting enzyme (ACE) inhibitors or angiotensin receptor blockers (ARBs) for patients with COVID-19 has shown no difference in key outcomes between the two approaches.
The BRACE CORONA trial ― conducted in patients had been taking an ACE inhibitor or an ARB on a long-term basis and who were subsequently hospitalized with COVID-19 ― showed no difference in the primary endpoint of number of days alive and out of hospital among those whose medication was suspended for 30 days and those who continued undergoing treatment with these agents.
Dr Renato Lopes
“Because these data indicate that there is no clinical benefit from routinely interrupting these medications in hospitalized patients with mild to moderate COVID-19, they should generally be continued for those with an indication,” principal investigator Renato Lopes, MD, of Duke Clinical Research Institute, Durham, North Carolina, concluded.
The BRACE CORONA trial was presented at the European Society of Cardiology (ESC) Congress 2020 on September 1.
Lopes explained that there are two conflicting hypotheses about the role of ACE inhibitors and ARBs in COVID-19.
One hypothesis suggests that use of these drugs could be harmful by increasing the expression of ACE2 receptors (which the SARS-CoV-2 virus uses to gain entry into cells), thus potentially enhancing viral binding and viral entry.
The other suggests that ACE inhibitors and ARBs could be protective by reducing production of angiotensin II and enhancing the generation of angiotensin 1–7, which attenuates inflammation and fibrosis and therefore could attenuate lung injury.
SOURCE
UPDATED on 7/12/2020
Combining PCR and CT testing for COVID Chen Shen∗ , Ron Mark MD DABR† , Nolan J. Kagetsu MD DABR‡ , Anton S. Becker MD PhD, Yaneer Bar-Yam∗
∗New England Complex Systems Institute,
†Mark Medical Care PLLC, ‡Mt. Sinai Hospital May 26, 2020
http://pharmaceuticalintelligence.com/wp-content/uploads/2020/03/7b0a4-ct_and_pcr_f1.pdf
UPDATED on 5/18/2020
TOP STORIES
Use CTA to evaluate obese COVID-19 patients for PE risk
Ultrasound scoring aids COVID-19 decisions
CT angio images show stroke in COVID-19 patient
ISMRM annual meeting goes virtual CT COMMUNITY
Sponsored by Canon Medical Systems
Use CTA to evaluate obese COVID-19 patients for PE risk
CT angio images show stroke in COVID-19 patient
SOURCE
From: AuntMinnie’s Letter from the Editor <letters@auntminnie.com>
Reply-To: <do-not-reply@auntminnie.com>
Date: Monday, May 18, 2020 at 7:50 AM
To: Aviva Lev-Ari <AvivaLev-Ari@alum.berkeley.edu>
Subject: Use CTA to evaluate obese COVID-19 patients for PE risk
UPDATED on 5/6/2020
|
SOURCE
From: Science News from the American Heart Association <email@heartemail.org>
Reply-To: American Heart Association <reply-71896937-7991033_HTML-1648404797-10171707-0@heartemail.org>
Date: Wednesday, May 6, 2020 at 12:32 PM
To: Aviva Lev-Ari <AvivaLev-Ari@alum.berkeley.edu>
Subject: Family caregiving and SDOH in HF care; CVD during pregnancy; COVID-19 health disparities
UPDATED ON 4/2/2020
VIDEO: 9 Cardiologists Share COVID-19 Takeaways From Across the U.S. End of Title |
|
DAIC Editor Dave Fornell has conducted numerous video interviews remotely from his home office in March and April 2020 with nine cardiologists from around the United States. After each interview he asked how COVID-19 has impacted their hospital and them personally. This video offers a candid overview of their thoughts in the fight against the novel coronavirus… |
|
SOURCE
From: Diagnostic and Interventional Cardiology <mail@sgc-editorial.com>
Reply-To: Diagnostic and Interventional Cardiology <DoNotReply@sgc-editorial.com>
Date: Tuesday, April 21, 2020 at 3:46 PM
To: Aviva Lev-Ari <AvivaLev-Ari@alum.berkeley.edu>
Subject: VIDEO: 9 Cardiologists share COVID-19 takeaways from across the U.S.
UPDATED ON 4/16/2020
Covid-19 testing issues could sink plans to re-open the country. Might CT scans help?
“Every ER physician I know recognizes the power of these scans,” said Joseph Fraiman, an emergency medicine physician at hospitals in the New Orleans area who does two or three chest CTs on suspected Covid-19 patients every shift. “Aggressive disease identification would involve both [swab tests] and CT to ensure the highest sensitivity, missing the fewest cases possible.”
But despite China’s experience, the use of chest CT to diagnose Covid-19 in the U.S. remains very limited (no one has data on how many have been done). That’s due in large part of the CDC and the American College of Radiology recommendations.
One of their objections is that CT scanners will become contaminated with the coronavirus. China, whose fever clinics routinely scanned 200 patients per day per machine, managed to clean the machines between patients well enough to avoid infecting health care workers or subsequent patients, however. Researchers there reported last month that CT scanning is far safer for health care workers than the swabs that reach the throat via the nose, and often trigger explosive coughing that can spew virus particles into the air. Thanks to staff training and between-patient scanner cleaning, after 3,340 CT scans for suspected Covid-19, another group of physicians in China reported, “none of the staff of the radiology department was infected with Covid-19.”
“It’s not like China has a monopoly on the technology to clean CT scanners,” said the Louisiana emergency medicine physician who asked not to be identified, so as not to anger colleagues. “Are you really going to say that your cleaning protocol is why you’re willing to kill 1 million people?” if the test/isolate/trace strategy fails because of faulty swab tests.
Fraiman said he is able to do chest CTs for his suspected Covid-19 cases by getting the technicians and cleaning crews on board: “I tell them, you are the guys who are going to save us!”
Another objection is that CT scans cannot easily distinguish between Covid-19, SARS, MERS, and other viral pneumonias, including from influenza. “They’re not specific enough,” said Sanjat Kanjilal, an infectious disease physician at Brigham and Women’s Hospital in Boston.
Although SARS, which is caused by a coronavirus related to the one causing Covid-19, was eliminated, and MERS (also from a coronavirus) is extremely rare outside the Middle East, viral pneumonia looks a lot like Covid-19 in a chest CT. “That makes me skeptical that it can have a big role to play,” Kanjilal said.
The rate of false positives from misidentifying other viral pneumonias as Covid-19 might be as high as 30%, said radiologist Paras Lakhani of Thomas Jefferson University Hospital in Philadelphia. But it would be much lower outside of flu season, which is ending. Reading scans during a time of year when flu and therefore pneumonia is rare, he said, “would give us more confidence in interpreting a scan.”
To be sure, chest CTs are no panacea. They, too, can miss Covid-19 cases; just two-fifths of the Diamond Princess passengers who had positive swab tests had lung opacities, researchers reported last month.
“There is evidence that a large fraction of Covid-19 patients have normal CTs,” said radiologist Mark Hammer of Brigham and Women’s Hospital in Boston. “Using CT to screen patients would let a lot of people go who may be infectious.”
Absent more accurate Covid-19 tests of any kind, whether swabs or CT or a combination, states’ tentative “re-opening” plans will be inefficient at best and failures at worst. The many Covid-19 cases that swab tests miss, said BU’s Galea, “is why the proposed Massachusetts contact tracing plan I have seen will quarantine people for 14 days even if they test negative” — a fortnight that someone could have been safely back at work and in the community if only a negative result on the molecular tests were more credible.
SOURCE
UPDATED ON 3/27/2020
VIDEO: What Cardiologists Need to Know about COVID-19
Interview with Thomas Maddox, M.D., MSc, FACC, the chairman of the American College of Cardiology (ACC) Science and Quality Committee, which recently created the ACC document on novel coronavirus (COVID-19) clinical guidance for the cardiovascular care team. He explains the document and what cardiologists and the cardiac care team needs to know about caring for COVID-19 patients. The document points out COVID-19 combined with the comorbidity of cardiovascular disease has the mortality of any comorbidity, as high as 10.5 percent.
He explains the need for more serious attention to protective equipment, cardiovascular complications seen in COVID-19 (SARS‐CoV‐2) patients, suggestions on how to mitigate exposure if an echo or cath is required, and other considerations for the CV care team. He said the document will be updated on a regular bases and the committee is drafting other sets of related COVID-19 guidelines for cardiology departments.
Updates regarding COVID-19 and cardiology will be posted on the ACC COVID-19 Hub page.
Maddox is also the executive director of the Healthcare Innovation Lab of BJC Healthcare and Washington University School of Medicine, St. Louis. He is also an assistant professor of cardiology at Washington University.
Read more on ACC COVID-19 recommendations for the cardiovascular care team.
ADDITIONAL COVID-19 RESOURCES FOR CLINICIANS:
World Health Organization (WHO) COVID-19 situation reports
World Health Organization (WHO) coronavirus information page
U.S. Food and Drug Administration (FDA) COVID-19 information page
Centers for Disease Control (CDC) COVID-19 information page
RELATED COVID-19 CONTENT:
The Cardiac Implications of Novel Coronavirus
ESC Council on Hypertension Says ACE-I and ARBs Do Not Increase COVID-19 Mortality
CT Provides Best Diagnosis for Novel Coronavirus (COVID-19)
Radiology Lessons for Coronavirus From the SARS and MERS Epidemics
Deployment of Health IT in China’s Fight Against the COVID-19 Epidemic
Emerging Technologies Proving Value in Chinese Coronavirus Fight
Radiologists Describe Coronavirus CT Imaging Features
Coronavirus Update from the FDA
CT Imaging of the 2019 Novel Coronavirus (2019-nCoV) Pneumonia
CT Imaging Features of 2019 Novel Coronavirus (2019-nCoV)
Chest CT Findings of Patients Infected With Novel Coronavirus 2019-nCoV Pneumonia
Radiologists distinguish COVID-19 pneumonia on CTBy Abraham Kim, AuntMinnie.com staff writer
CT findings for COVID-19 vs. non-COVID-19 pneumonia Non-COVID-19COVID-19Ground-glass opacity68%91%Peripheral distribution57%80%Vascular thickening22%59%Fine reticular opacity22%56%Reverse halo sign1%5% |
https://www.auntminnie.com/index.aspx?sec=sup&sub=cto&pag=dis&ItemID=128422 |
Hypertension ‘a key dangerous factor’ in COVID-19 mortality | https://www.cardiovascularbusiness.com/topics/hypertension/hypertension-key-dangerous-factor-covid-19-death?utm_source=newsletter&utm_medium=cvb_news |
ACC issues COVID-19 guidance for cardiologists | https://www.cardiovascularbusiness.com/topics/healthcare-economics/acc-issues-covid-19-guidance-cardiologists?utm_source=newsletter&utm_medium=cvb_news |