MSAIC-Net: A Multi-Scale Attention and Imbalance-Aware Contrastive Network for ECG-Based Myocardial Substrate Abnormality Detection

2026-06-04

AI Summary

This study addresses the challenges in electrocardiogram (ECG)-based detection of myocardial substrate abnormalities—such as myocardial scar and infarction—including lead dependency, high-dimensional signal complexity, class imbalance, and limited model interpretability. To overcome these issues, the authors propose MSAIC-Net, a novel deep learning framework that employs parallel multi-scale dilated convolutions to capture temporal features, integrates channel attention to adaptively weight both leads and feature channels, incorporates an imbalance-aware supervised contrastive learning strategy to enhance inter-class separability, and leverages lead permutation importance to improve model interpretability. Evaluated on the UVA low-data cohort and the PTB-XL dataset, MSAIC-Net consistently outperforms baseline methods, demonstrating particularly strong performance in data-scarce scenarios while enabling efficient and interpretable detection of myocardial abnormalities.

Abstract

Myocardial substrate abnormalities, such as myocardial scar and myocardial infarction (MI), are associated with adverse cardiovascular outcomes. Electrocardiography (ECG) provides a low-cost and widely available tool for detecting these abnormalities, but ECG-based detection remains challenging due to heterogeneous lead-dependent manifestations, high-dimensional multi-lead signals, class imbalance, and the limited interpretability of deep learning models. We propose a multi-scale attention-enhanced convolutional network (MSAIC-Net) for ECG-based myocardial substrate abnormality detection. MSAIC-Net employs parallel atrous convolutional branches to extract ECG features across multiple temporal receptive fields. %, enabling the model to capture both local and longer-range temporal patterns. Channel attention is then used to adaptively reweight informative lead-wise and feature-channel representations. To address class imbalance and improve feature separability, we introduce a novel imbalance-aware supervised contrastive learning strategy that encourages samples from the same class to form compact representations while increasing separation between abnormal and normal samples. Lead-wise permutation importance is further incorporated to quantify the contribution of each ECG lead and improve model interpretability. The proposed method was evaluated on two complementary datasets: a low-data institutional cohort from the University of Virginia (UVA) Health System for myocardial scar classification and the large-scale public PTB-XL dataset from PhysioNet for MI identification. Experimental results show that MSAIC-Net outperforms baseline models, with particularly pronounced improvements in the low-data UVA cohort. Overall, the proposed framework provides an effective and interpretable approach for ECG-based detection of myocardial substrate abnormalities.

Problem

• myocardial substrate abnormality
• ECG-based detection
• class imbalance
• multi-lead signals
• interpretability

Innovation

• multi-scale attention
• imbalance-aware contrastive learning
• atrious convolution
• ECG interpretability
• myocardial substrate abnormality