To explore the associations of AI-derived CCTA features with coronary flow reserve (CFR) and CT-derived fractional flow reserve (FFR-CT) in patients with suspected or known coronary artery disease (CAD).
Key Findings:
Poor agreement between CFR and FFR-CT for ischemia (Kappa = 0.084).
CFR <2.0 associated with perivascular fat attenuation index and calcified plaque burden.
FFR-CT ≤0.8 predicted by low attenuation plaque and lipid plaque burden.
Adjusted AUC for FFR-CT-defined ischemia was 0.892; for CFR-defined ischemia, it was 0.615.
Interpretation:
CFR and FFR-CT reflect different pathophysiological dimensions of myocardial ischemia, with CFR linked to microvascular dysfunction and FFR-CT to obstructive ischemia from high-risk plaques.
Limitations:
Findings are hypothesis-generating and need confirmation through studies with invasive physiological assessments.
CCTA features alone are insufficient to predict abnormal CFR.
Conclusion:
CCTA is valuable for assessing obstructive coronary lesions, but further research is needed to clarify the relationship between CFR and FFR-CT.