Monday, December 1 | 9:50 a.m.-10:00 a.m. | M3-SSCH03-3 | Room S501
Dynamic chest radiography (DCR) can improve the detection of lung cancer lesions, particularly in cases where conventional chest x-ray is limited by anatomical overlap, according to a study in this session.
The study will be presented by Koji Takumi, MD, PhD, of Kagoshima University in Kagoshima, Japan, and is from a trial in which 100 patients underwent both scans prior to surgery for lung cancer lesions.
The diagnostic confidence in the two techniques for detecting lesions was evaluated by three chest radiologists on a 3-point scale (2: definite presence, 1: probable presence, 0: difficult to identify), with a score of 1 or higher defined as a detectable lesion. The researchers also evaluated the performance of an AI model approved in Japan for detecting abnormalities on conventional chest x-rays.
Based on the radiologists’ consensus, DCR received scores of 81%, which was significantly higher than scores for CCRs interpreted by radiologists (71%; p = 0.002) and by the AI-based software (64%; p < 0.001). Further, among 29 lesions that were difficult for radiologists to identify on CCR, 10 were successfully detected using DCR, all of which overlapped with normal anatomical structures on CCR, the group reported. For almost all lesions (98.6%) that were initially diagnosed with a confidence level of 1 on CCR by radiologists, the confidence level improved on DCR.
DCR could serve as a valuable complement to both conventional interpretation and AI-assisted analysis in clinical practice, according to the group.
Take in this Monday morning presentation to learn more.