Objective:

To compare the diagnostic performance and robustness of DL-based versus CFD-based CT-FFR against invasive FFR across coronary branches, cardiac phases, clinical centers, and ischemia-positive gray-zone lesions.

Approach:

• Study Design: Retrospective analysis of 220 patients (277 vessels) who underwent coronary CTA and invasive FFR from two centers.
• CT-FFR Calculation: CT-FFR was calculated using commercial DL-based and CFD-based algorithms.
• Performance Evaluation: Diagnostic performance was evaluated using invasive FFR as the reference standard, with subgroup analyses for target vessels, reconstruction phases, imaging centers, and gray-zone lesions.

Key Findings:

• DL and CFD showed high and similar diagnostic performance with AUC of 0.90 (95% CI: 0.88-0.93) for DL and 0.89 (95% CI: 0.86-0.92) for CFD (p > 0.05).
• Both methods were strongly correlated with invasive FFR (rho = 0.71 for DL; rho = 0.68 for CFD; both p < 0.001).
• Stable performance across vessels, cardiac phases, and centers was observed (all p > 0.05).
• In gray-zone lesions, DL and CFD had comparable correct classification rates (86.4% vs. 84.6%, p = 0.690) and false-negative rates (13.6% vs. 15.4%, p = 0.690).

Interpretation:

DL-based and CFD-based CT-FFR showed similar and strong diagnostic performance for detecting hemodynamically significant stenosis.

Limitations:

• The study is retrospective and may have selection bias.
• Performance in clinical practice settings may vary due to differences in imaging protocols and patient populations.

Conclusion:

Both DL-based and CFD-based CT-FFR approaches can be considered as non-invasive functional assessment tools in selected patients.