A self-supervised framework for computer-aided arrhythmia diagnosis

Cardiovascular diseases, including all types of arrhythmias, are the leading cause of death. Deep learning (DL)-based electrocardiography (ECG) diagnosis systems have attracted considerable attention in recent years. However, training DL-based models requires much high-quality labeled data, and labeling ECG records is time-consuming and expensive. In this paper, a high-precision deep network obtained via low-cost annotation, that is, a self-supervised residual convolutional neural network (SSRCNN), was designed. First, a convolutional neural network and residual blocks were designed to construct a deep feature extractor to automatically obtain the feature expression of ECG signals. Next, we developed time- and lead-dimension-based data augmentation methods and designed a pretraining framework based on unlabeled datasets such that the feature extractor could update the weights in the unlabeled samples. Furthermore, through interactions with clinicians, we used a few labeled data to fine-tune the pretrained model and feature classifier to automatically extract deep features and perform effective classification. Finally, we used different open-source datasets to validate the superiority of the SSRCNN. With the support of unlabeled datasets, SSRCNN can effectively reduce clinicians’ workload. Compared with existing methods, the SSRCNN achieves a better diagnostic performance in terms of average accuracy (99.0 %) and average F1-macro (86.83 %) using approximately 25 % of labeled data. Therefore, the SSRCNN has a potential for practical applications in clinical settings. • This paper presents a novel self-supervised residual convolution neural network for actual arrhythmia classification. • Convolution layers, and Residual blocks are integrated to improve model diagnostic performance. • The novel pre-training framework and data augmentation methods are introduced to obtain ECG representations. • SSRCNN improves 5.74% and 8.73% in average accuracy and average F1 macro by using approximately 25% labeled data.