Physiology and Anatomy Aware Inverse Inference of Myocardial Infarction for Cardiac Digital Twin

2026-05-21

AI Summary

Current methods for inferring myocardial infarction suffer from insufficient sensitivity to subtle electrocardiographic changes and poor interpretability, primarily due to their neglect of realistic scar morphology and cardiac repolarization dynamics. To address this, this work proposes a non-invasive localization framework grounded in a cardiac digital twin, which integrates cine MRI and multi-lead ECG data. The approach employs an anatomy-aware stochastic infarction synthesis strategy to generate realistic, irregular scars incorporating border zones, and introduces a Physiology- and Anatomy-Aware Network (PAA-Net) that jointly encodes three-dimensional myocardial geometry and QRS-T waveform dynamics to infer infarcted regions. The method achieves Dice scores of 0.7391 and 0.5503 for scar and border zone segmentation, respectively, significantly outperforming existing techniques.

Abstract

Accurate localization of myocardial infarction is essential for risk stratification. While LGE-MRI remains the gold standard, it is resource-intensive. Integrating cine MRI with ECG enables a more detailed representation of infarct properties. Existing inverse MI inference methods overlook realistic scar morphology and cardiac repolarization, reducing sensitivity to subtle ECG variations and interpretability of infarct-induced electrophysiological changes. In this paper, we propose a novel framework for noninvasive MI localization using cardiac digital twins. To bridge the domain gap between simulation and reality, we introduce an anatomy-aware stochastic infarct synthesis strategy to synthesize realistic, irregular scars with border zones, mimicking ischemic transmural progression. We then construct a virtual cohort to simulate QRS-T waveforms, capturing both depolarization and repolarization dynamics. Furthermore, we design a Physiology and Anatomy Aware Network (PAA-Net) that jointly encodes 3D myocardial geometry and multi-lead ECGs to infer infarct areas with varying localizations, sizes, spatial extents, and transmuralities. Experimental results demonstrate that our framework significantly outperforms existing methods in inverse inference, achieving Dice scores of 0.7391 and 0.5503 for scar and border zone segmentation, respectively, while further enhancing the interpretability of the ECG-infarct relationship. Our code will be released upon acceptance.

Problem

• myocardial infarction
• inverse inference
• scar morphology
• cardiac repolarization
• ECG interpretability

Innovation

• cardiac digital twin
• myocardial infarction localization
• anatomy-aware scar synthesis
• physiology-aware ECG modeling
• PAA-Net