An intelligent computer-aided diagnosis approach for atrial fibrillation detection based on multi-scale convolution kernel and Squeeze-and-Excitation network. (July 2021)

• Record Type: Journal Article
• Authors: Guo, Xibin; Wang, Qiao; Zheng, Jinfeng
• Is Part Of: Biomedical signal processing and control. Volume 68(2021)
• Publication Date: 2021-07
• Subjects: 68Uxx -- 62P10; Atrial fibrillation -- Electrocardiogram -- Multi-scale convolution kernel -- Squeeze-and-Excitation network; Signal processing -- Periodicals; Biomedical engineering -- Periodicals; Signal Processing, Computer-Assisted -- Periodicals; Image Processing, Computer-Assisted -- Periodicals; Biomedical Engineering -- Periodicals; 610.28
• DOI: 10.1016/j.bspc.2021.102778
• Languages: English
• ISSNs: 1746-8094

Abstract

Highlights: We specially design multi-scale convolution kernel in the existing CNN for AF detection. The feature extraction and classification are not required. Subject-independent validation scheme ensures the robustness and facticity of the model. To our knowledge, this is the first time to redesign convolution kernel in traditional CNN for ECG signals analysis. Abstract: Atrial fibrillation (AF) is a most common arrhythmia with high morbidity and mortality. However, the conventional detection of AF is time-consuming and laborious because it is mainly completed by physician's visual inspection of electrocardiogram (ECG). Thus, it is essential to build the intelligent computer-aided diagnosis system strategy for AF detection. In this work, we present a novel intelligent approach based on the multi-scale convolution kernel (MCK) and Squeeze-and-Excitation network (SENet) for AF detection. The model not only is able to overcome the limitations that exist in the single-scale convolution kernel of traditional convolution neural network (CNN), but also explicitly establish the inter-dependences between the extracted feature channels and screen out the critical ECG features for AF signals recognition, thus improving the model performance. The results demonstrate that the proposed model achieves noticeable performance improvements with the accuracy of 98.3% and 97.5% using a subject-independent validation scheme on the two public databases. Besides, the corresponding ablation experiments show the effectiveness of the proposed MCK strategy. To our knowledge, this is the first time to redesign the convolution kernel in traditional CNN for AF detection, while showing its great potential as an auxiliary tool to help physicians.