Vascular inflammation inhibits local adipogenesis in pericoronary adipose tissue (PCAT) and this can be detected on coronary computed tomography angiography (CCTA) as an increase in CT attenuation of PCAT surrounding the proximal right coronary artery (RCA). In this cross-sectional study, we assessed the utility of PCAT CT attenuation as an imaging biomarker of coronary inflammation in distinguishing different stages of coronary artery disease (CAD). Sixty patients with acute myocardial infarction (MI) were prospectively recruited to undergo CCTA within 48 h of admission, prior to invasive angiography. These participants were matched to patients with stable CAD (n = 60) and controls with no CAD (n = 60) by age, gender, BMI, risk factors, medications, and CT tube voltage. PCAT attenuation around the proximal RCA was quantified per-patient using semi-automated software. Patients with MI had a higher PCAT attenuation (−82.3 ± 5.5 HU) compared with patients with stable CAD (−90.6 ± 5.7 HU, P < 0.001) and controls (−95.8 ± 6.2 HU, P < 0.001). PCAT attenuation was significantly increased in stable CAD patients over controls (P = 0.01). The association of PCAT attenuation with stage of CAD was independent of age, gender, cardiovascular risk factors, epicardial adipose tissue volume, and CCTA-derived quantitative plaque burden. No interaction was observed for clinical presentation (MI vs. stable CAD) and plaque burden on PCAT attenuation. PCAT CT attenuation as a quantitative measure of global coronary inflammation independently distinguishes patients with MI vs. stable CAD vs. no CAD. Future studies should assess whether this imaging biomarker can track patient responses to therapies in different stages of CAD.

This review covers state-of-the-art artificial intelligence applications across various noninvasive imaging modalities for the quantification of cardiovascular risk in coronary artery disease. Artificial intelligence (AI) describes the use of computational techniques to perform tasks that normally require human cognition. Machine learning and deep learning are subfields of AI that are in...