Coronary Artery Calcification on Low-Dose Lung Cancer Screening CT in South Korea: Visual and Artificial Intelligence–Based Assessment and Association With Cardiovascular Events
Authors
Chan Park, MD, Byung Chan Lee, MD, PhD, Won Gi Jeong, MD, PhD, Won-Ju Park, MD, PhD, Gong Yong Jin, MD, PhD, Yun-Hyeon Kim, MD, PhD
This study evaluates coronary artery calcification (CAC) prevalence and severity using visual and artificial intelligence (AI) methods in South Korea's national lung cancer screening program. Including 1002 patients (mean age 62.4 years, predominantly male), CAC was assessed by two radiologists and AI software (aview CAC by Corelinesoft and syngo Calcium Scoring by Siemens Healthineers). Interreader agreement for CAC presence and severity was high (kappa 0.793 and 0.671, respectively). CAC prevalence was 53.4% visually, 60.1% by aview CAC, and 56.6% by syngo Calcium Scoring. CAC severity was mild, moderate, and severe, with significant associations between higher CAC severity and increased major adverse cardiovascular events (MACEs). MACE rates increased with CAC severity, notably 1.1% to 8.6% visually and 1.3% to 11.3% by aview CAC. This highlights the importance of routine CAC evaluation in lung cancer screening programs, despite the study's sex imbalance.