Correlation of AI-Generated Coronary CT Angiography Characteristics with CZT-SPECT Coronary Flow Reserve

Overview

This study investigates the relationship between AI-derived coronary CT angiography features and coronary flow reserve (CFR) as well as fractional flow reserve (FFR-CT) in patients with suspected coronary artery disease. The findings indicate that CFR and FFR-CT reflect different pathophysiological aspects of myocardial ischemia.

Background

Coronary artery disease (CAD) is a leading cause of mortality globally, necessitating accurate diagnosis and assessment of myocardial ischemia. Non-invasive imaging techniques like CFR and FFR-CT are critical for evaluating CAD, yet discrepancies between these methods are common. Understanding their relationship can enhance diagnostic accuracy and treatment strategies.

Data Highlights

Key Findings

• The agreement between CFR and FFR-CT for ischemia was poor (Kappa = 0.084).
• CFR <2.0 was associated with perivascular fat attenuation index and calcified plaque burden.
• FFR-CT ≤0.8 was predicted by low attenuation plaque and lipid plaque burden.
• Distinct plaque feature patterns were observed among discordant CFR/FFR-CT statuses.
• CCTA alone is insufficient to predict abnormal CFR.

Clinical Implications

Clinicians should be aware that CFR and FFR-CT provide different insights into myocardial ischemia, with CFR reflecting microvascular dysfunction and FFR-CT indicating focal obstructive ischemia. These findings underscore the importance of integrating multiple imaging modalities for comprehensive CAD assessment.

Conclusion

The study highlights the need for further research to validate the associations between AI-derived CCTA features and physiological measures of ischemia. Understanding these relationships may improve diagnostic strategies in CAD management.

References

1. European Radiology, 2025 -- Evaluation of a Deep Learning Model Utilizing Coronary CT Angiography for Predicting Ischemia in Specific Vessels
2. npj Digital Medicine, 2026 -- Assessment of Interpretable Artificial Intelligence for Diagnosing Coronary Artery Disease Using PET Biomarkers Across Multiple Centers
3. European Radiology, 2023 -- Influence of Vessel Structure on CT-Based Fractional Flow Reserve in Non-Obstructive Coronary Artery Disease of the Right Coronary Artery
4. European Radiology, 2023 -- Enhanced CT Evaluation of Coronary Artery Disease in Patients with Severe Aortic Valve Stenosis and Intermediate Stenosis
5. 2024 ESC Guidelines for the management of chronic coronary syndromes | European Heart Journal | Oxford Academic
6. Diagnostic Performance of Fractional Flow Reserve Derived From Coronary CT Angiography: The ACCURATE-CT Study - ScienceDirect
7. Diagnostic and prognostic value of myocardial flow reserve quantification with single photon emission computed tomography - a systematic review and meta-analysis - PubMed
8. 2024 ESC Chronic Coronary Syndromes guideline
9. Diagnostic Performance of Fractional Flow Reserve Derived From Coronary CT Angiography: The ACCURATE-CT Study - ScienceDirect
10. Diagnostic and prognostic value of myocardial flow reserve quantification with single photon emission computed tomography - a systematic review and meta-analysis - PubMed