Heart Murmur Classification Using a Capsule Neural Network
The healthcare industry has made significant progress in the diagnosis of heart conditions due to the use of intelligent detection systems such as electrocardiograms, cardiac ultrasounds, and abnormal sound diagnostics that use artificial intelligence (AI) technology, such as convolutional neural ne...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-10-01
|
| Series: | Bioengineering |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2306-5354/10/11/1237 |
| _version_ | 1797460132514234368 |
|---|---|
| author | Yu-Ting Tsai Yu-Hsuan Liu Zi-Wei Zheng Chih-Cheng Chen Ming-Chih Lin |
| author_facet | Yu-Ting Tsai Yu-Hsuan Liu Zi-Wei Zheng Chih-Cheng Chen Ming-Chih Lin |
| author_sort | Yu-Ting Tsai |
| collection | DOAJ |
| description | The healthcare industry has made significant progress in the diagnosis of heart conditions due to the use of intelligent detection systems such as electrocardiograms, cardiac ultrasounds, and abnormal sound diagnostics that use artificial intelligence (AI) technology, such as convolutional neural networks (CNNs). Over the past few decades, methods for automated segmentation and classification of heart sounds have been widely studied. In many cases, both experimental and clinical data require electrocardiography (ECG)-labeled phonocardiograms (PCGs) or several feature extraction techniques from the mel-scale frequency cepstral coefficient (MFCC) spectrum of heart sounds to achieve better identification results with AI methods. Without good feature extraction techniques, the CNN may face challenges in classifying the MFCC spectrum of heart sounds. To overcome these limitations, we propose a capsule neural network (CapsNet), which can utilize iterative dynamic routing methods to obtain good combinations for layers in the translational equivariance of MFCC spectrum features, thereby improving the prediction accuracy of heart murmur classification. The 2016 PhysioNet heart sound database was used for training and validating the prediction performance of CapsNet and other CNNs. Then, we collected our own dataset of clinical auscultation scenarios for fine-tuning hyperparameters and testing results. CapsNet demonstrated its feasibility by achieving validation accuracies of 90.29% and 91.67% on the test dataset. |
| first_indexed | 2024-03-09T17:01:41Z |
| format | Article |
| id | doaj.art-849930bcfb32494cb49e964dc71b6d76 |
| institution | Directory Open Access Journal |
| issn | 2306-5354 |
| language | English |
| last_indexed | 2024-03-09T17:01:41Z |
| publishDate | 2023-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Bioengineering |
| spelling | doaj.art-849930bcfb32494cb49e964dc71b6d762023-11-24T14:29:34ZengMDPI AGBioengineering2306-53542023-10-011011123710.3390/bioengineering10111237Heart Murmur Classification Using a Capsule Neural NetworkYu-Ting Tsai0Yu-Hsuan Liu1Zi-Wei Zheng2Chih-Cheng Chen3Ming-Chih Lin4Master’s Program in Electro-Acoustics, Feng Chia University, Taichung 40724, TaiwanMaster’s Program in Electro-Acoustics, Feng Chia University, Taichung 40724, TaiwanHyper-Automation Laboratory, Feng Chia University, Taichung 40724, TaiwanHyper-Automation Laboratory, Feng Chia University, Taichung 40724, TaiwanDepartment of Post-Baccalaureate Medicine, College of Medicine, National Chung Hsing University, Taichung 402, TaiwanThe healthcare industry has made significant progress in the diagnosis of heart conditions due to the use of intelligent detection systems such as electrocardiograms, cardiac ultrasounds, and abnormal sound diagnostics that use artificial intelligence (AI) technology, such as convolutional neural networks (CNNs). Over the past few decades, methods for automated segmentation and classification of heart sounds have been widely studied. In many cases, both experimental and clinical data require electrocardiography (ECG)-labeled phonocardiograms (PCGs) or several feature extraction techniques from the mel-scale frequency cepstral coefficient (MFCC) spectrum of heart sounds to achieve better identification results with AI methods. Without good feature extraction techniques, the CNN may face challenges in classifying the MFCC spectrum of heart sounds. To overcome these limitations, we propose a capsule neural network (CapsNet), which can utilize iterative dynamic routing methods to obtain good combinations for layers in the translational equivariance of MFCC spectrum features, thereby improving the prediction accuracy of heart murmur classification. The 2016 PhysioNet heart sound database was used for training and validating the prediction performance of CapsNet and other CNNs. Then, we collected our own dataset of clinical auscultation scenarios for fine-tuning hyperparameters and testing results. CapsNet demonstrated its feasibility by achieving validation accuracies of 90.29% and 91.67% on the test dataset.https://www.mdpi.com/2306-5354/10/11/1237heart murmurauscultationheart sound diagnosiscardiac dysphonic diagnosiscapsule neural networkdeep learning in healthcare |
| spellingShingle | Yu-Ting Tsai Yu-Hsuan Liu Zi-Wei Zheng Chih-Cheng Chen Ming-Chih Lin Heart Murmur Classification Using a Capsule Neural Network Bioengineering heart murmur auscultation heart sound diagnosis cardiac dysphonic diagnosis capsule neural network deep learning in healthcare |
| title | Heart Murmur Classification Using a Capsule Neural Network |
| title_full | Heart Murmur Classification Using a Capsule Neural Network |
| title_fullStr | Heart Murmur Classification Using a Capsule Neural Network |
| title_full_unstemmed | Heart Murmur Classification Using a Capsule Neural Network |
| title_short | Heart Murmur Classification Using a Capsule Neural Network |
| title_sort | heart murmur classification using a capsule neural network |
| topic | heart murmur auscultation heart sound diagnosis cardiac dysphonic diagnosis capsule neural network deep learning in healthcare |
| url | https://www.mdpi.com/2306-5354/10/11/1237 |
| work_keys_str_mv | AT yutingtsai heartmurmurclassificationusingacapsuleneuralnetwork AT yuhsuanliu heartmurmurclassificationusingacapsuleneuralnetwork AT ziweizheng heartmurmurclassificationusingacapsuleneuralnetwork AT chihchengchen heartmurmurclassificationusingacapsuleneuralnetwork AT mingchihlin heartmurmurclassificationusingacapsuleneuralnetwork |