Bing Pingping, Liu Yang, Liu Wei, Zhou Jun, Zhu Lemei
Academician Workstation, Changsha Medical University, Changsha, China.
College of Mechanical and Electrical Engineering, Beijing University of Chemical Technology, Beijing, China.
Front Cardiovasc Med. 2022 Oct 10;9:983543. doi: 10.3389/fcvm.2022.983543. eCollection 2022.
As an important auxiliary tool of arrhythmia diagnosis, Electrocardiogram (ECG) is frequently utilized to detect a variety of cardiovascular diseases caused by arrhythmia, such as cardiac mechanical infarction. In the past few years, the classification of ECG has always been a challenging problem. This paper presents a novel deep learning model called convolutional vision transformer (ConViT), which combines vision transformer (ViT) with convolutional neural network (CNN), for ECG arrhythmia classification, in which the unique soft convolutional inductive bias of gated positional self-attention (GPSA) layers integrates the superiorities of attention mechanism and convolutional architecture. Moreover, the time-reassigned synchrosqueezing transform (TSST), a newly developed time-frequency analysis (TFA) method where the time-frequency coefficients are reassigned in the time direction, is employed to sharpen pulse traits for feature extraction. Aiming at the class imbalance phenomena in the traditional ECG database, the smote algorithm and focal loss (FL) are used for data augmentation and minority-class weighting, respectively. The experiment using MIT-BIH arrhythmia database indicates that the overall accuracy of the proposed model is as high as 99.5%. Furthermore, the specificity (Spe), F1-Score and positive Matthews Correlation Coefficient (MCC) of supra ventricular ectopic beat (S) and ventricular ectopic beat (V) are all more than 94%. These results demonstrate that the proposed method is superior to most of the existing methods.
作为心律失常诊断的重要辅助工具，心电图（ECG）常被用于检测由心律失常引起的各种心血管疾病，如心肌梗死。在过去几年中，心电图分类一直是一个具有挑战性的问题。本文提出了一种名为卷积视觉Transformer（ConViT）的新型深度学习模型，该模型将视觉Transformer（ViT）与卷积神经网络（CNN）相结合，用于心电图心律失常分类，其中门控位置自注意力（GPSA）层独特的软卷积归纳偏差整合了注意力机制和卷积架构的优势。此外，时间重分配同步挤压变换（TSST）是一种新开发的时频分析（TFA）方法，它在时间方向上重新分配时频系数，用于锐化脉搏特征以进行特征提取。针对传统心电图数据库中的类别不平衡现象，分别使用SMOTE算法和焦点损失（FL）进行数据增强和少数类加权。使用麻省理工学院-比哈尔心律失常数据库进行的实验表明，所提出模型的总体准确率高达99.5%。此外，室上性早搏（S）和室性早搏（V）的特异性（Spe）、F1分数和阳性马修斯相关系数（MCC）均超过94%。这些结果表明，所提出的方法优于大多数现有方法。
