MCHeart: Multi-Channel-Based Heart Signal Processing Scheme for Heart Noise Detection Using Deep Learning
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....
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-09-01
|
| Series: | Biology |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2079-7737/12/10/1291 |
| _version_ | 1797574671826157568 |
|---|---|
| author | Soyul Han Woongsun Jeon Wuming Gong Il-Youp Kwak |
| author_facet | Soyul Han Woongsun Jeon Wuming Gong Il-Youp Kwak |
| author_sort | Soyul Han |
| collection | DOAJ |
| description | 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. |
| first_indexed | 2024-03-10T21:25:37Z |
| format | Article |
| id | doaj.art-91c8c9e2ddfa49119c0aebbd2bd74f0e |
| institution | Directory Open Access Journal |
| issn | 2079-7737 |
| language | English |
| last_indexed | 2024-03-10T21:25:37Z |
| publishDate | 2023-09-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Biology |
| spelling | doaj.art-91c8c9e2ddfa49119c0aebbd2bd74f0e2023-11-19T15:43:12ZengMDPI AGBiology2079-77372023-09-011210129110.3390/biology12101291MCHeart: Multi-Channel-Based Heart Signal Processing Scheme for Heart Noise Detection Using Deep LearningSoyul Han0Woongsun Jeon1Wuming Gong2Il-Youp Kwak3Department of Applied Statistics, Chung-Ang University, Seoul 06974, Republic of KoreaSchool of Electrical and Electronics Engineering, Chung-Ang University, Seoul 06974, Republic of KoreaLillehei Heart Institute, University of Minnesota, Minneapolis, MN 55455, USADepartment of Applied Statistics, Chung-Ang University, Seoul 06974, Republic of KoreaIn 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.https://www.mdpi.com/2079-7737/12/10/1291heart murmur detectionbiological signalsfeature extractionsmart healthcarelight CNNmultiple attention network |
| spellingShingle | Soyul Han Woongsun Jeon Wuming Gong Il-Youp Kwak MCHeart: Multi-Channel-Based Heart Signal Processing Scheme for Heart Noise Detection Using Deep Learning Biology heart murmur detection biological signals feature extraction smart healthcare light CNN multiple attention network |
| title | MCHeart: Multi-Channel-Based Heart Signal Processing Scheme for Heart Noise Detection Using Deep Learning |
| title_full | MCHeart: Multi-Channel-Based Heart Signal Processing Scheme for Heart Noise Detection Using Deep Learning |
| title_fullStr | MCHeart: Multi-Channel-Based Heart Signal Processing Scheme for Heart Noise Detection Using Deep Learning |
| title_full_unstemmed | MCHeart: Multi-Channel-Based Heart Signal Processing Scheme for Heart Noise Detection Using Deep Learning |
| title_short | MCHeart: Multi-Channel-Based Heart Signal Processing Scheme for Heart Noise Detection Using Deep Learning |
| title_sort | mcheart multi channel based heart signal processing scheme for heart noise detection using deep learning |
| topic | heart murmur detection biological signals feature extraction smart healthcare light CNN multiple attention network |
| url | https://www.mdpi.com/2079-7737/12/10/1291 |
| work_keys_str_mv | AT soyulhan mcheartmultichannelbasedheartsignalprocessingschemeforheartnoisedetectionusingdeeplearning AT woongsunjeon mcheartmultichannelbasedheartsignalprocessingschemeforheartnoisedetectionusingdeeplearning AT wuminggong mcheartmultichannelbasedheartsignalprocessingschemeforheartnoisedetectionusingdeeplearning AT ilyoupkwak mcheartmultichannelbasedheartsignalprocessingschemeforheartnoisedetectionusingdeeplearning |