DAMAL: Data Augmentation Aided Multi-channel Attention Fusion Network for Multi-label Myocardial Infarction Localization

Myocardial infarction (MI) has the highest mortality of all cardiovascular diseases (CVDs). 12-lead electrocardiogram (ECG) is regarded as an effective noninvasive method for localization of MI. Considering the clinical reality that sometimes patients with heart disease often have multiple MI, and that real-world data faces an imbalance problem for each class of MI. In this study, we propose a data augmentation aided multichannel attention fusion network for multi-label MI localization (DAMAL), fusing both lead correlation and label correlation in a framework to localize MI. Specifically, DAMAL constructs separate channels for each of 12-lead ECG, and builds a matrix channel attention (MCA), to enhance the representativeness of the input features. A spatial & channel fusion module is proposed which includes a channel attention (CA) module to capture the attention levels of different leads, and a spatial attention (SA) module to capture the spatial relationships among the leads. Additionally, data augmentation is performed for multi-label datasets with minority classes to capture the optimal classification thresholds for each class of labels and improve the model performance. Furthermore, DAMAL exhibits good interpretability by the Grad-CAM-based visualization. Experimental results show that DAMAL performs better than other state-of-the-art methods in classifying multi-label MI across various metrics, including F1 score, AUROC, and Hamming Loss.