Preliminary exploration of the value of pericoronary adipose tissue radiomics in identifying high-risk patients with chronic coronary syndrome: a retrospective Chinese cohort study

Vollständiger Abstract

Worum geht es in dieser Arbeit?

Background Chronic coronary syndrome (CCS) requires accurate risk stratification for optimized management. Pericoronary adipose tissue (PCAT) inflammation is closely associated with plaque progression, and coronary computed tomography angiography (CCTA)-based radiomics may provide information beyond the traditional fat attenuation index (FAI). Objective To assess the value of PCAT radiomics and its combination with one-stop CCTA parameters for identifying CCS patients who are classified as high-risk by the 2024 European Society of Cardiology (ESC) guideline-recommended risk factor-clinical (RF-CL) model. Methods We retrospectively enrolled 175 CCS patients who underwent CCTA between January 2024 and January 2026. According to the 2024 ESC guideline-recommended RF-CL model, patients were classified as high risk (>15%, n = 77) or low risk (≤15%, n = 98). PCAT radiomics features were extracted from the three major coronary arteries, and FAI, computed tomography-derived fractional flow reserve (CT-FFR), coronary artery calcium score (CACS), and the Coronary Artery Disease Reporting and Data System (CAD-RADS) were analyzed. Results Significant between-group differences were found in right coronary artery (RCA) FAI, left anterior descending (LAD) FAI, CACS, CAD-RADS, distal CT-FFR at the most stenotic plaque, and distal vessel CT-FFR, but not left circumflex (LCX) FAI. Distal vessel CT-FFR showed better discrimination than lesion-specific CT-FFR (area under the receiver operating characteristic curve [AUC] 0.782 vs. 0.698). The RCA PCAT radiomics model outperformed RCA FAI in the testing set (AUC 0.729 vs. 0.620). The integrated model achieved the best performance, with AUCs of 0.860 and 0.823 in the training and testing sets. Conclusion PCAT radiomics, especially when integrated with one-stop CCTA parameters, improves the identification of CCS patients classified as high-risk by the RF-CL model. Prospective studies with hard cardiovascular outcomes are required to validate its prognostic value and to determine whether this imaging-based strategy can guide therapeutic decision-making.