|   View web version
Radiology Today  e-Newsletter
Subscribe or Renew
Digital Edition
April 2021 Connect with us Facebook Twitter Sign up  |  Archive  |  Advertise
Editor's e-Note
AI is finding its way into all corners of radiology. This month’s e-News Exclusive details how deep learning can help researchers determine people’s risk of death by applying an algorithm to low-dose CT lung cancer screen exams. The analysis uncovered previously unknown predictors of mortality. It requires no special equipment and adds no additional time to the CT exam. See below for more about this novel algorithm.

Does your facility have a low-dose CT lung screening program? How do you determine mortality risk? Let us know on Twitter and/or Facebook.

Enjoy the newsletter, and stay safe.

— Dave Yeager, editor
e-News Exclusive
Lung Cancer Screening Predicts Risk of Death From Heart Disease

A deep learning algorithm accurately predicts the risk of death from cardiovascular disease using information from low-dose CT exams performed for lung cancer screening, according to a study published in Radiology: Cardiothoracic Imaging. Cardiovascular disease is the leading cause of mortality worldwide. It even outpaces lung cancer as the leading cause of death in heavy smokers.

Low-dose CT lung scans are used to screen for lung cancer in high-risk people such as heavy smokers. These CT scans also provide an opportunity to screen for cardiovascular disease by extracting information about calcification in the heart and aorta. The presence of calcium in these areas is linked with the buildup of plaque and is a strong predictor for cardiovascular disease mortality, heart attacks, and strokes.

Previous studies have used information extracted from CT images as well as other risk factors, such as cholesterol levels and blood pressure, and self-reported clinical data, such as history of illness. For the new study, researchers tested a faster, automated method that can predict five-year cardiovascular disease mortality with only minimal extra workload. The method draws upon the power of deep learning, an advanced type of AI in which the computer algorithm essentially learns the important features for mortality prediction from the images.

Using data from 4,451 participants, median age 61 years, who underwent low-dose CT over a two-year period in the National Lung Screening Trial, the researchers trained the method to quantify six types of vascular calcification. They then tested the method on data from 1,113 participants.

Full story »
Recently Online
A New Focus
A study published in the New England Journal of Medicine reveals a new treatment option for Parkinson’s disease symptoms: MR-guided focused ultrasound subthalamotomy. While the procedure is less invasive than other ablative options and results are promising, it comes with side effects. Read more »

Buried Treasure
Emerging research blending imaging with AI is spearheading breakthroughs in cancer treatment decisions. Using radiomics, researchers are mining archival MRI, PET, and CT scans to identify markers that can help determine the best course of action. Read more »

Moving Target
While traditional methods of reducing radiation dose to patients and technologists continue to be utilized and refined, new techniques, such as refining patient positioning and tracking health care worker exposure, are making a difference. Read more »

The Gorilla in the Room
When interpreting scans, readers of all experience levels are susceptible to confirmation bias and/or inattentional blindness—the tendency to overlook something readily apparent while on the lookout for something else. Researchers are getting to the bottom of this and offering strategies. Read more »
Advertising Opportunities
Have a product or service you want to market to radiology professionals or an open position that you need to fill quickly? Radiology Today offers many flexible advertising programs designed to maximize your results. From print advertising to e-newsletter sponsorships, website advertising to direct mail opportunities, Radiology Today helps achieve your goals. Email our experienced account executives today for more information or call 800-278-4400! is the premier online resource to recruit radiology professionals. Post your open positions, view résumés, and showcase your facility's offerings all at!

Radiology Today's Physician Recruitment Center gives physician recruiters a powerful tool to satisfy their current needs. An ideal option for recruiters looking to fill partnership opportunities, academic appointments, and hospital staff positions, the Physician Recruitment Center is visited regularly by radiologists and other imaging physicians during their frequent trips to our website for the best coverage of industry news and trends.
Gift Shop
Radiology Today's online gift shop features a wide variety of items for radiology professionals. Choose from t-shirts, journals, clocks, buttons, mouse pads, and much more! Check out our secure online shop today or call toll-free 877-809-1659 for easy and fast ordering.
In This e-Newsletter
Other Imaging News
Brain Imaging Reveals Neurological Basis for Trauma-Induced Memory Loss
Researchers from McLean Hospital in Boston analyzed the MRI data of women with histories of childhood abuse who had been diagnosed with PTSD. Their study, published in the American Journal of Psychiatry, shows that severe dissociative symptoms likely involve the connections between two specific brain networks: memory and problem-solving.

New Technique Tests Effectiveness of Cancer Treatments
Using wide-field one-photon redox imaging, a team from the Morgridge Institute for Research has developed an informative, fast, nondestructive way of measuring the responses of cancer organoids, essentially tumors-in-a-dish, to various drugs. Their findings, published in the Journal of Biomedical Optics, could help screen cancer treatment effectiveness.

Solar System–Invading Comet Detected
2I/Borisov, named after its discoverer astronomer Gennady Borisov, has now been described in a paper published in Nature Communications. Polarimetry from the European Southern Observatory’s Very Large Telescope revealed the interstellar comet to be one of the most pristine astronomers have ever seen.

Scans of Produce Could Determine Long-Term Viability
Skoltech researchers studied a Braeburn apple orchard in Germany using nondestructive sensors, such as visible and near-infrared spectroscopy, to gather data. The team developed an AI algorithm that ended up being 80% accurate in predicting internal browning of apples, the appearance of cavities on the surface, and fruit firmness, which could be adapted for other produce.
Worth Repeating
“Our study shows that screening for prostate cancer—which could save between 16% and 20% of prostate cancer deaths—might be possible with targeted screening using genetic risk and MRI as part of the diagnostic pathway. This paves the way for further clinical trials to study the real-world implementation of such a screening program.”

— Mark Emberton, MD, a professor and dean of University College London’s faculty of medical sciences, on his team’s research in predicting prostate cancer
Set up Job Alerts and create your online Résumé
to let potential employers find you today!