RSNA PUBLICATIONS

AI Abdominal Fat Measure Predicts Heart Attack and Stroke
A study presented at RSNA's annual meeting detailed the accuracy of using deep learning artificial intelligence with CT scans for measuring abdominal fat and determining the likelihood of a heart attack or stroke within five years. The method, which earned the RSNA 2020 Trainee Research Prize, accurately localized body composition metrics from abdominal CT images. Patients with the highest visceral fat area were most likely to suffer a heart attack, while those with the lowest level of visceral fat area were protected against stroke. "These results demonstrate that precise measures of body muscle and fat compartments achieved through CT outperform traditional biomarkers for predicting risk for cardiovascular outcomes," said the University of California, San Francisco's Kirti Magudia, PhD.

From "AI Abdominal Fat Measure Predicts Heart Attack and Stroke" Azcentral.com