AI-derived CCTA features revealed that FFR-CT-defined ischemia is strongly predicted by low attenuation plaque (OR 3.527), whereas CFR-defined ischemia is associated with diffuse inflammatory markers like perivascular fat attenuation index.
Observational (n=251)
No
Do AI-derived CCTA plaque features differentially predict myocardial ischemia as defined by CZT-SPECT CFR versus FFR-CT in patients with suspected or known CAD?
AI-derived CCTA plaque features strongly predict FFR-CT-defined focal obstructive ischemia but are insufficient to predict CFR-defined microvascular/diffuse ischemia, highlighting that CFR and FFR-CT reflect distinct pathophysiological dimensions.
Odds Ratio: 3.527 (95% CI 1.716–7.247)
p-value: p=<0.001
Objective This study aims to explore the associations of artificial intelligence (AI)-derived coronary CT angiography (CCTA) features with coronary flow reserve (CFR) measured by cardiac-cadmium zinc-telluride single-photon emission computed tomography (CZT-SPECT) and CT-derived fractional flow reserve (FFR-CT), and to investigate their intrinsic relationships. Methods This retrospective study included 251 patients (753 vessels) with suspected or known coronary artery disease (CAD), who underwent CZT-SPECT and concurrent CCTA. Myocardial ischemia was defined as CFR 2.0 or FFR-CT ≤0.8. Generalized estimating equations (GEE) were used to analyze the associations between CCTA coronary parameters and the two ischemia definitions. Results Among the 753 vessels, the agreement analysis between CFR and FFR-CT for ischemia was poor (Kappa = 0.084). Multivariate analysis demonstrated that CFR 2.0 was only associated with perivascular fat attenuation index (FAI) and calcified plaque burden, whereas FFR-CT ≤0.8 was additionally predicted by low attenuation plaque and lipid plaque burden (all p 0.05). Subgroup analysis revealed distinct plaque feature patterns among discordant CFR/FFR-CT statuses. The same set of coronary features achieved an adjusted AUC of 0.892 for FFR-CT-defined ischemia and 0.615 for CFR-defined ischemia. Conclusions CFR and FFR-CT reflect different pathophysiological dimensions: CFR reduction is more associated with microvascular dysfunction in the context of inflammation and diffuse lesions, whereas FFR-CT mainly reflects focal, obstructive ischemia caused by high-risk plaques (such as low attenuation plaque). CCTA is an important tool for assessing obstructive coronary lesions, but coronary features alone are insufficient to predict whether CFR is abnormal or not. However, in the absence of invasive reference standards (invasive FFR and index of microcirculatory resistance), these findings should be considered hypothesis-generating and require confirmation in future studies incorporating invasive physiological assessment.
Ni et al. (Tue,) conducted a observational in Coronary artery disease (n=251). AI-derived coronary CT angiography features vs. Normal CFR or FFR-CT was evaluated on Ischemia defined by FFR-CT ≤ 0.8 associated with low attenuation plaque (OR 3.527, 95% CI 1.716-7.247, p=<0.001). AI-derived CCTA features revealed that FFR-CT-defined ischemia is strongly predicted by low attenuation plaque (OR 3.527), whereas CFR-defined ischemia is associated with diffuse inflammatory markers like perivascular fat attenuation index.