Detection and Localization of Myocardial Infarction Based on Multi-Scale ResNet and Attention Mechanism

Yang Cao; Wenyan Liu; Shuang Zhang; Lisheng Xu; Baofeng Zhu; Huiying Cui; Ning Geng; Hongguang Han; Stephen E Greenwald

doi:10.3389/fphys.2022.783184

Detection and Localization of Myocardial Infarction Based on Multi-Scale ResNet and Attention Mechanism

Front Physiol. 2022 Jan 28:13:783184. doi: 10.3389/fphys.2022.783184. eCollection 2022.

Authors

Yang Cao¹, Wenyan Liu², Shuang Zhang², Lisheng Xu^{2

3

4}, Baofeng Zhu⁴, Huiying Cui², Ning Geng⁵, Hongguang Han⁶, Stephen E Greenwald⁷

Affiliations

¹ School of Intelligent Medicine, China Medical University, Shenyang, China.
² College of Medicine and Biological Information Engineering, Northeastern University, Shenyang, China.
³ Key Laboratory of Medical Image Computing, Ministry of Education, Shenyang, China.
⁴ Neusoft Research of Intelligent Healthcare Technology, Co., Ltd., Shenyang, China.
⁵ Department of Cardiology, Shengjing Hospital of China Medical University, Shenyang, China.
⁶ Department of Cardiac Surgery, General Hospital of Northern Theater Command, Shenyang, China.
⁷ Barts and the London School of Medicine and Dentistry, Blizard Institute, Queen Mary University of London, London, United Kingdom.

Abstract

Purpose: Myocardial infarction (MI) is one of the most common cardiovascular diseases, frequently resulting in death. Early and accurate diagnosis is therefore important, and the electrocardiogram (ECG) is a simple and effective method for achieving this. However, it requires assessment by a specialist; so many recent works have focused on the automatic assessment of ECG signals.

Methods: For the detection and localization of MI, deep learning models have been proposed, but the diagnostic accuracy of this approaches still need to be improved. Moreover, with deep learning methods the way in which a given result was achieved lacks interpretability. In this study, ECG data was obtained from the PhysioBank open access database, and was analyzed as follows. Firstly, the 12-lead ECG signal was preprocessed to identify each beat and obtain each heart interval. Secondly, a multi-scale deep learning model combined with a residual network and attention mechanism was proposed, where the input was the 12-lead ECG recording. Through the SENet model and the Grad-CAM algorithm, the weighting of each lead was calculated and visualized. Using existing knowledge of the way in which different types of MI gave characteristic patterns in specific ECG leads, the model was used to provisionally diagnose the type of MI according to the characteristics of each of the 12 ECG leads.

Results: Ten types of MI anterior, anterior lateral, anterior septal, inferior, inferior lateral, inferior posterior, inferior posterior lateral, lateral, posterior, and posterior lateral were diagnosed. The average accuracy, sensitivity, and specificity for MI detection of all lesion types was 99.98, 99.94, and 99.98%, respectively; and the average accuracy, sensitivity, and specificity for MI localization was 99.79, 99.88, and 99.98%, respectively.

Conclusion: When compared to existing models based on traditional machine learning methods, convolutional neural networks and recurrent neural networks, the results showed that the proposed model had better diagnostic performance, being superior in accuracy, sensitivity, and specificity.

Keywords: attention mechanism; gradient class activation mapping; multi-lead ECG; myocardial infarction; residual network.