Efficient Anomaly Detection Algorithm for Heart Sound Signal
According to the latest report by the WHO, cardiovascular disease claims approximately 17.9 million lives annually, making it one of the leading causes of mortality. Hence, early screening and detection of cardiovascular diseases are important for their prevention. Heart sound signals contain a weal...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2024-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10685349/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841536153718620160 |
|---|---|
| author | Zhihai Liu Wen Liu Zheng Gu Feng Yang |
| author_facet | Zhihai Liu Wen Liu Zheng Gu Feng Yang |
| author_sort | Zhihai Liu |
| collection | DOAJ |
| description | According to the latest report by the WHO, cardiovascular disease claims approximately 17.9 million lives annually, making it one of the leading causes of mortality. Hence, early screening and detection of cardiovascular diseases are important for their prevention. Heart sound signals contain a wealth of information on cardiac function and health status. Researchers have recently utilized deep learning methods to detect abnormal features in heart sound signals, thereby facilitating disease diagnosis. Currently, existing heart sound datasets suffer from imbalanced data proportions, complex feature types, and low discriminative power between systolic and diastolic murmurs, resulting in the suboptimal performance of deep learning algorithms in detection. Therefore, we propose a heart sound abnormality detection algorithm based on the Swin Transformer architecture. Firstly, we enhance the ability to extract local texture features of heart sound signals by introducing a convolutional embedding module into the positional encoding layer of the backbone network. Second, we augmented the model’s capability to extract the frequency-domain features of heart-sound signals by incorporating a discrete convolutional mapping structure. This structure utilizes discrete cosine transformation in conjunction with convolutional projection to acquire feature matrices, thereby improving classification accuracy. Finally, we employed a Focal Loss function to prioritize abnormal heart-sound samples, enhancing the generalization ability of the model and evaluating the proposed algorithm using the PhysionNet/CinC 2016 public dataset. The results demonstrated an Accuracy of 93.4%, a Specificity of 90.4% and a Sensitivity of 95.7%. |
| format | Article |
| id | doaj-art-0fdef654878640d0ac20b64cff7815d2 |
| institution | Kabale University |
| issn | 2169-3536 |
| language | English |
| publishDate | 2024-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-0fdef654878640d0ac20b64cff7815d22025-01-15T00:03:37ZengIEEEIEEE Access2169-35362024-01-011213922513923610.1109/ACCESS.2024.346554010685349Efficient Anomaly Detection Algorithm for Heart Sound SignalZhihai Liu0https://orcid.org/0009-0005-7578-7842Wen Liu1https://orcid.org/0000-0001-8306-3506Zheng Gu2Feng Yang3School of Computer Science and Technology, Xinjiang Normal University, Ürümqi, ChinaSchool of Computer Science and Technology, Xinjiang Normal University, Ürümqi, ChinaArtificial Intelligence and Smart Mine Engineering Technology Center, Xinjiang Institute of Engineering, Ürümqi, ChinaComputer Information Center, Xinjiang Institute of Engineering, Ürümqi, ChinaAccording to the latest report by the WHO, cardiovascular disease claims approximately 17.9 million lives annually, making it one of the leading causes of mortality. Hence, early screening and detection of cardiovascular diseases are important for their prevention. Heart sound signals contain a wealth of information on cardiac function and health status. Researchers have recently utilized deep learning methods to detect abnormal features in heart sound signals, thereby facilitating disease diagnosis. Currently, existing heart sound datasets suffer from imbalanced data proportions, complex feature types, and low discriminative power between systolic and diastolic murmurs, resulting in the suboptimal performance of deep learning algorithms in detection. Therefore, we propose a heart sound abnormality detection algorithm based on the Swin Transformer architecture. Firstly, we enhance the ability to extract local texture features of heart sound signals by introducing a convolutional embedding module into the positional encoding layer of the backbone network. Second, we augmented the model’s capability to extract the frequency-domain features of heart-sound signals by incorporating a discrete convolutional mapping structure. This structure utilizes discrete cosine transformation in conjunction with convolutional projection to acquire feature matrices, thereby improving classification accuracy. Finally, we employed a Focal Loss function to prioritize abnormal heart-sound samples, enhancing the generalization ability of the model and evaluating the proposed algorithm using the PhysionNet/CinC 2016 public dataset. The results demonstrated an Accuracy of 93.4%, a Specificity of 90.4% and a Sensitivity of 95.7%.https://ieeexplore.ieee.org/document/10685349/Abnormality detectioncardiovascular diseaseconvolution embeddingdiscrete convolution projectionheart sound signal |
| spellingShingle | Zhihai Liu Wen Liu Zheng Gu Feng Yang Efficient Anomaly Detection Algorithm for Heart Sound Signal IEEE Access Abnormality detection cardiovascular disease convolution embedding discrete convolution projection heart sound signal |
| title | Efficient Anomaly Detection Algorithm for Heart Sound Signal |
| title_full | Efficient Anomaly Detection Algorithm for Heart Sound Signal |
| title_fullStr | Efficient Anomaly Detection Algorithm for Heart Sound Signal |
| title_full_unstemmed | Efficient Anomaly Detection Algorithm for Heart Sound Signal |
| title_short | Efficient Anomaly Detection Algorithm for Heart Sound Signal |
| title_sort | efficient anomaly detection algorithm for heart sound signal |
| topic | Abnormality detection cardiovascular disease convolution embedding discrete convolution projection heart sound signal |
| url | https://ieeexplore.ieee.org/document/10685349/ |
| work_keys_str_mv | AT zhihailiu efficientanomalydetectionalgorithmforheartsoundsignal AT wenliu efficientanomalydetectionalgorithmforheartsoundsignal AT zhenggu efficientanomalydetectionalgorithmforheartsoundsignal AT fengyang efficientanomalydetectionalgorithmforheartsoundsignal |