A lead-aware hierarchical convolutional neural network for arrhythmia detection in electrocardiogram

• Published in: Signal, image and video processing Vol. 19; no. 2; p. 139
• Main Authors: Li, Tong, Wang, Nan, Yang, Hongxiao, Dou, Mengfei, Yang, Xinwu
• Format: Journal Article
• Language: English
• Published: London Springer London 01.02.2025; Springer Nature B.V
• Subjects: Algorithms; Arrhythmia; Artificial neural networks; Cardiac arrhythmia; Classification; Computer Imaging; Computer Science; Data collection; Datasets; Diagnosis; Electrocardiography; Feature extraction; Image Processing and Computer Vision; Multimedia Information Systems; Neural networks; Original Paper; Pattern Recognition and Graphics; Physiology; Signal,Image and Speech Processing; Vision; Wavelet transforms; Arrhythmia detection; Attention mechanism; Multi-lead ECG signal; Recurrent neural network; Convolutional neural network
• ISSN: 1863-1703; 1863-1711
• DOI: 10.1007/s11760-024-03686-0

Automatic arrhythmia detection in electrocardiogram (ECG) aims to enable computer to recognize different types of arrhythmia to assist doctors in diagnosis. In medical conclusion, there is lead specificity in different types of arrhythmias, and doctors mainly identify different arrhythmias according to these specific manifestations in clinical diagnosis. However, most of the existing methods focus on the temporal dimension of ECG signals, ignoring the dependence of ECG signal leads. This work aims to develop a general method for multi-lead ECG arrhythmia recognization through exploring lead feature extraction and fusion. For the first time, we propose a novel Lead-aware hierarchical convolutional neural network (LAH-CNN) that capture time and lead features hierarchically with a lead-leval attention module mining the interdependence between lead feature mappings, and then obtain Ngram features of leads for final arrhythmia classification. Our proposed approach achieved F1 score of 78.86%, 99.2% and 99.1% on 12-lead databases CPCS, INCART and 2-lead database MIT-BIH Respectively. Our experiments show that N-gram lead-leval features are an important factor affecting prediction performance. Our proposed method is competitive and achieves good robustness for arrhythmias recognization.