AI can detect 5 conditions on chest x-rays

Tuesday, November 27 | 10:30 a.m.-10:40 a.m. | SSG13-01 | Room S404AB
An artificial intelligence (AI) algorithm system can be highly accurate for detecting five specific findings on chest radiography studies, according to South Korean researchers.

The group developed a deep-learning algorithm that can detect nodules, consolidation, pleural effusion, interstitial opacity, and pneumothorax from the posteroanterior view of chest radiographs. In testing on imaging data acquired from devices by multiple manufacturers, the model yielded nearly 98% sensitivity and specificity, according to the researchers, led by senior study author Namkug Kim, PhD, of the University of Ulsan and Asan Medical Center in Seoul.

How did Kim and colleagues do it? You can get more details by taking in this talk on Tuesday.

Page 1 of 372
Next Page