Key result
DSC-Net using 2D-VCG tensors achieves ~100% accuracy in localizing MI categories and normal cases.
Why the study?
Existing algorithms only extract pathological information from three-lead VCG signals without fully considering the correlation information between different orthogonal planes for MI localization.
Does a depthwise separable convolution network (DSC-Net) using 2D-VCG tensors accurately localize myocardial infarction?
Does a depthwise separable convolution network (DSC-Net) using 2D-VCG tensors accurately localize myocardial infarction?
A novel depthwise separable convolution network using 2D-VCG tensors demonstrated >99.92% accuracy in localizing myocardial infarction.
Supports AI integration for MI localization in ECG practice; extends RCT evidence for deep learning in vectorcardiography.
Myocardial infarction (MI) can cause acute and permanent damage to the myocardial muscle. Vectorcardiogram (VCG) is formed by the time varying coordinates of cardiac electrical activity in space. According to different infarct locations, the ring of VCG in the three orthogonal planes has pathological morphological changes. Yet the existing algorithms only extract the pathological information of three lead VCG signals, but they do not fully consider the correlation information between different orthogonal planes. We proposed a depthwise separable convolution network (DSC-Net) for automatic MI localization from 2-dimensional (2D)-VCG tensor. Utilizing the orthogonality between the lead axes, we first combine the 3 leads in pairs to form a 2D-VCG, and then construct a 2D-VCG tensor that captures the correlation information between leads. DSC-Net extracts spatial features related to MI obtained in 2D-VCG before Softmax is applied to classify MIs. The proposed method was validated on the benchmark Physikalisch Technische-Bundesanstalt dataset, which includes VCG of 11 types of MI. We demonstrated, with the cardiac electrical activity spatial features obtained from the 2D-VCG tensor, that the accuracy of 11 categories of MI and normal are higher than 99.92%. The proposed model effectively realized the localization of MI with competitively high accuracy for all 11 categories.
No takes yet. Share an insight, caveat, or question.
Xiong et al. (2023) studied Myocardial infarction. Depthwise separable convolution network (DSC-Net) using 2D-VCG tensor was evaluated on Accuracy of classifying 11 categories of MI and normal. A depthwise separable convolution network (DSC-Net) using 2D-VCG tensors achieved an accuracy higher than 99.92% for localizing 11 categories of myocardial infarction and normal cases.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: