MCHeart: Multi-Channel-Based Heart Signal Processing Scheme for Heart Noise Detection Using Deep Learningopen access
- Authors
- Han, Soyul; Jeon, Woongsun; Gong, Wuming; Kwak, Il-Youp
- Issue Date
- Oct-2023
- Publisher
- MDPI
- Keywords
- heart murmur detection; biological signals; feature extraction; smart healthcare; light CNN; multiple attention network; deep learning
- Citation
- BIOLOGY-BASEL, v.12, no.10
- Journal Title
- BIOLOGY-BASEL
- Volume
- 12
- Number
- 10
- URI
- https://scholarworks.bwise.kr/cau/handle/2019.sw.cau/70220
- DOI
- 10.3390/biology12101291
- ISSN
- 2079-7737
- Abstract
- Simple Summary Cardiovascular disease is a major global health concern. Early detection is vital, with phonocardiograms (PCGs) offering valuable heart sound data, including murmurs. Research automating PCG analysis is growing, addressing challenges like the 2022 PhysioNet Challenge. Our innovation, the MCHeart system, focuses on irregular heart murmurs, combining S1/S2 features, smoothing, and a residual LCNN architecture with multi-head self-attention for enhanced feature extraction.Abstract In this study, we constructed a model to predict abnormal cardiac sounds using a diverse set of auscultation data collected from various auscultation positions. Abnormal heart sounds were identified by extracting features such as peak intervals and noise characteristics during systole and diastole. Instead of using raw signal data, we transformed them into log-mel 2D spectrograms, which were employed as input variables for the CNN model. The advancement of our model involves integrating a deep learning architecture with feature extraction techniques based on existing knowledge of cardiac data. Specifically, we propose a multi-channel-based heart signal processing (MCHeart) scheme, which incorporates our proposed features into the deep learning model. Additionally, we introduce the ReLCNN model by applying residual blocks and MHA mechanisms to the LCNN architecture. By adding murmur features with a smoothing function and training the ReLCNN model, the weighted accuracy of the model increased from 79.6% to 83.6%, showing a performance improvement of approximately 4% point compared to the LCNN baseline model.
- Files in This Item
-
- Appears in
Collections - College of ICT Engineering > School of Electrical and Electronics Engineering > 1. Journal Articles
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.