Research on Segmentation and Classification of Heart Sound Signals Based on Deep Learning
Source abstract
Abstract
The heart sound signal is one of the signals that reflect the health of the heart. Research on the heart sound signal contributes to the early diagnosis and prevention of cardiovascular diseases. As a commonly used deep learning network, convolutional neural network (CNN) has been widely used in images. In this paper, the method of analyzing heart sound through using CNN has been studied. Firstly, the original data set was preprocessed, and then the heart sounds were segmented on U-net, based on the deep CNN. Finally, the classification of heart sounds was completed through CNN. The data from 2016 PhysioNet/CinC Challenge was utilized for algorithm validation, and the following results were obtained. When the heart sound segmented, the overall accuracy rate was 0.991, the accuracy of the first heart sound was 0.991, the accuracy of the systolic period was 0.996, the accuracy of the second heart sound was 0.996, and the accuracy of the diastolic period was 0.997, and the average accuracy rate was 0.995; While in classification, the accuracy was 0.964, the sensitivity was 0.781, and the specificity was 0.873. These results show that deep learning based on CNN shows good performance in the segmentation and classification of the heart sound signal.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Phonocardiography and Auscultation Techniques
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Key Laboratory of Biorheological Science and Technology, Ministry of Education, College of Bioengineering, Chongqing University, Chongqing 400030, China
Key Laboratory for National Defense Science and Technology of Innovation Micro-Nano Devices and System Technology, Chongqing 400030, China
Chongqing Engineering Research Center of Medical Electronics Technology, Chongqing 400030, China
Funding
the National Key Research and Development Program of China · the Chongqing Technological Innovation and Application Demonstration Project
References (40)
Show source-provided references
1. Noise detection during heart sound recording using periodicity signatures10.1088/0967-3334/32/5/008 ↗
2. Phonocardiogram signal analysis: A review
3. Dissanayake, T., and Fernando, T. (2020). Understanding the importance of heart sound segmentation for heart anomaly datec-tion. arXiv.
4. A Three-Channel Microcomputer System for Segmentation and Characterization of the Phonocardiogram10.1109/TBME.1987.326060 ↗
5. A method for accurate localization of the first heart sound and possible applications10.1088/0967-3334/29/3/011 ↗
6. Feature Extraction for Systolic Heart Murmur Classification10.1007/s10439-006-9187-4 ↗
7. Heart sound segmentation algorithm based on heart sound envelo-gram
8. Huiying, L., Sakari, L., and Iiro, H. (November, January 30). A heart sound segmentation algorithm using wavelet decomposition and recon-struction. Proceedings of the International Conference of the IEEE Engineering in Medicine & Biology Society, Chicago, IL, USA.
9. Support Vectors Machine-based identification of heart valve diseases using heart sounds10.1016/j.cmpb.2009.01.003 ↗
10. Localization of Heart Sounds Based on S-Transform and Radial Basis Function Neural Network
11. A robust heart sounds segmentation module based on S-transform10.1016/j.bspc.2012.11.008 ↗
12. Detection and boundary identification of phonocardiogram sounds using an expert frequency-energy based metric10.1007/s10439-012-0645-x ↗
13. Kumar, D., Carvalho, P., Antunes, M., Henriques, J., Eugenio, L., Schmidt, R., and Habetha, J. (September, January 30). Detection of s1 and s2 heart sounds by high frequency signatures. Proceedings of the 2006 International Conference of the IEEE Engineering in Medicine and Biology Society, New York, NY, USA.10.1109/IEMBS.2006.260735 ↗
14. Efficient heart sound segmentation and extraction using ensemble empir-ical mode decomposition and kurtosis features10.1109/JBHI.2013.2294399 ↗
15. Yin, Y., Ma, K., and Liu, M. (2020). Temporal Convolutional Network Connected with an Anti-Arrhythmia Hidden Semi-Markov Model for Heart Sound Segmentation. Appl. Sci., 10.10.3390/app10207049 ↗
16. Detection of the first heart sound using a time-delay neural network
17. Neural network classification of homomorphic segmented heart sounds10.1016/j.asoc.2005.06.006 ↗
18. Rajan, S., Budd, E., Stevenson, M., and Doraiswami, R. (September, January 30). Unsupervised and uncued segmentation of the fundamental heart sounds in phonocardiograms using a time-scale representation. Proceedings of the 2006 International Conference of the IEEE Engineering in Medicine and Biology Society, New York, NY, USA.10.1109/IEMBS.2006.260777 ↗
19. Deep convolutional neural networks for heart sound segmenta-tion10.1109/JBHI.2019.2894222 ↗
20. Heart sound segmentation—an event detection approach using deep recur-rent neural networks10.1109/TBME.2018.2843258 ↗
21. Accessing heart dynamics to estimate durations of heart sounds10.1088/0967-3334/26/6/010 ↗
22. Sedighian, P., Subudhi, A.W., Scalzo, F., and Asgari, S. (2014, January 26–30). Pediatric heart sound segmentation using Hidden Markov Model. Proceedings of the 2014 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, Chicago, IL, USA.10.1109/EMBC.2014.6944869 ↗
23. Segmentation of heart sound recordings by a duration-dependent hidden Markov model10.1088/0967-3334/31/4/004 ↗
24. Logistic Regression-HSMM-based Heart Sound Segmentation10.1109/TBME.2015.2475278 ↗
25. Potes, C., Parvaneh, S., Rahman, A., Conroy, B., and Solutions, A.C. (2016, January 11–14). Ensemble of Feature-based and Deep learn-ing-based Classifiers for Detection of Abnormal Heart Sounds. Proceedings of the 2016 Computing in Cardiology Conference (CinC), Vancouver, BC, Canada.10.22489/CinC.2016.182-399 ↗
26. Puri, C., Ukil, A., Bandyoapdhyay, S., Singh, R., Pal, A., Mukherjee, A., and Mukherjee, D. (2016, January 11–14). Classification of Normal and Abnormal Heart Sound Recordings through Robust Feature Selection. Proceedings of the 2016 Computing in Cardiology Conference (CinC), Vancouver, BC, Canada.10.22489/CinC.2016.322-363 ↗
27. Tang, H., Chen, H., Li, T., and Zhong, M. (2016, January 11–14). Classification of Normal/Abnormal Heart Sound Recordings based on Multi:Domain Features and Back Propagation Neural Network. Proceedings of the 2016 Computing in Cardiology Conference (CinC), Vancouver, BC, Canada.10.22489/CinC.2016.171-159 ↗
28. Classification of heart sound signal using curve fitting and fractal dimension10.1016/j.bspc.2017.08.002 ↗
29. Arora, V., Leekha, R., Singh, R., and Chana, I. (2019). Heart sound classification using machine learning and phonocardiogram. Mod. Phys. Lett. B, 33.10.1142/S0217984919503214 ↗
30. Son, G.-Y., and Kwon, S. (2018). Classification of Heart Sound Signal Using Multiple Features. Appl. Sci., 8.10.3390/app8122344 ↗
31. Narváez, P., Gutierrez, S., and Percybrooks, W.S. (2020). Automatic Segmentation and Classification of Heart Sounds Using Modified Empirical Wavelet Transform and Power Features. Appl. Sci., 10.10.3390/app10144791 ↗
32. A Deep Learning Approach for Valve Defect Recognition in Heart Acoustic Signal10.1007/978-3-319-67220-5_1 ↗
33. Li, F., Tang, H., Shang, S., Mathiak, K., and Cong, F. (2020). Classification of Heart Sounds Using Convolutional Neural Network. Appl. Sci., 10.10.3390/app10113956 ↗
34. An open access database for the evaluation of heart sound algorithms10.1088/0967-3334/37/12/2181 ↗
35. Automatic heart sound classification from segmented/unsegmented phono-cardiogram signals using time and frequency features10.1088/1361-6579/ab8770 ↗
36. Ronneberger, O., Fischer, P., and Brox, T. (2015, January 5–9). U-Net: Convolutional Networks for Biomedical Image Segmentation[C]. Proceedings of the International Conference on Medical Image Computing and Computer-Assisted Intervention, Munich, Germany.10.1007/978-3-319-24574-4_28 ↗
37. Feng, K., Pi, X., Liu, H., and Sun, K. (2019). Myocardial Infarction Classification Based on Convolutional Neural Network and Recurrent Neural Network. Appl. Sci., 9.10.3390/app9091879 ↗
38. Imagenet classification with deep convolutional neural net-works
39. Simonyan, K., and Zisserman, A. (2014). Very deep convolutional networks for large-scale image recognition. arXiv.
40. Keskar, N.S., and Socher, R. (2017). Improving generalization performance by switching from adam to sgd. arXiv.