Lesion-Level Association Between Artificial Intelligence-Derived Coronary Calcium Volume and Plaque Vulnerability

Extensively calcified lesions are typically at low risk for lesion-level acute events, which may be related to less vulnerable plaques.

This study sought to evaluate the lesion-level association between total calcification volume and plaque vulnerability.

Data were derived from the prospective, observational PECTUS-obs study, in which patients with myocardial infarction underwent intracoronary optical coherence tomography (OCT) imaging of all fractional flow reserve-negative nonculprit lesions. OCT images were analyzed by a core laboratory for plaque vulnerability features (lipid-rich plaque, thin-cap fibroatheroma, layered plaque, macrophage accumulation, microvessel, and cholesterol crystal) and by a validated artificial intelligence algorithm (OCT-AID) for automated volumetric calcium quantification. Total calcium volume was indexed for lesion length and stratified by quartiles (Q1-Q4), from lowest to highest.

Among 488 lesions from 414 patients, calcium plaques were identified in 470 (96.3%) lesions. The lesion-level median indexed total calcium volume ranged from 0.004 mm³/mm (IQR: 0.001-0.011) in Q1 to 0.83 mm³/mm (IQR: 0.63-1.18) in Q4. The lower quartiles demonstrated the highest prevalence of lipid-rich plaques, macrophage accumulation, and microvessels. Thin-cap fibroatheroma and layered plaques accumulated predominantly in the middle quartiles (Q2-Q3). Cholesterol crystals showed no significant differences between quartiles. Overall, Q1-Q3 lesions demonstrated a greater mean number of plaque vulnerability features than Q4 lesions (P < 0.001 for all).

Most severely calcified nonculprit lesions demonstrate a significantly lower prevalence of plaque vulnerability features as compared to less calcified, more lipid-rich lesions, which may contribute to the lower lesion-level acute event rate observed in heavily calcified lesions.