AG-STDF: Anatomy-Guided ECG Spatiotemporal Dynamical Fusion for Screening Coronary Microvascular Dysfunction.

OBJECTIVE

Coronary slow flow (CSF), present in 1-7% of coronary angiograms, occurs in patients with angiographically normal epicardial arteries and is associated with acute coronary syndrome, representing an unmet need in coronary microvascular dysfunction (CMD) management. This study proposes an anatomy-guided spatiotemporal dynamical fusion (AG-STDF) framework for CSF screening.

METHODS

AG-STDF integrates anatomical electrophysiological territory mapping with 12-lead electrocardiogram (ECG) dynamics. ECG signals are decomposed into coronary territories-left anterior descending (LAD), left circumflex (LCX), and right coronary artery (RCA)-and static morphology is fused with intrinsic dynamics (derived from dynamic modeling) using joint recurrence quantification and multi-scale decomposition.

RESULTS

AG-STDF achieves an AUROC of 0.9467 $\pm$ 0.0272 for CSF detection. At the vessel level, where therapeutic decisions are made per 2024 European Society of Cardiology guidelines, AG-STDF predicts corrected thrombolysis in myocardial infarction frame counts (CTFC) with an $\text{R}^{\text{2}}$ = 0.5951 $\pm$ 0.0666 (AUROC: 0.8428). Notably, AG-STDF performs steadily in right-dominant coronary patients, with favorable results in LAD ($\text{R}^{\text{2}}$ = 0.6753) and mild fluctuations in LCX ($\text{R}^{\text{2}}$ = 0.5673) and RCA ($\text{R}^{\text{2}}$ = 0.5296) due to anatomical variations and competitive perfusion. Anatomical constraints and spatiotemporal fusion improve AUROC by 3.5% (p $< $ 0.01) and 9.47% (p $< $ 0.05). When equipped with an Intel Core i5-10500 and NVIDIA GTX 1660S, AG-STDF processes a 10-second ECG segment in 19.37 s.

CONCLUSION

AG-STDF allows accurate, non-invasive CSF detection and vessel-level assessment in right-dominant populations.

SIGNIFICANCE: It serves as a cost-effective CMD screening tool that may reduce invasive testing and support early diagnosis.