Heart sound classification based on sub-band envelope and convolution neural network_Journal of Biomedical Engineering

Authors：

WANG Xingzhi ¹ , YANG Hongbo ² , ZONG Rong ¹ , PAN Jiahua ² ,  WANG Weilian ¹

1. School of Information Science and Engineering, Yunnan University, Kunming 650504, P.R.China;
2. Fuwai Cardiovascular Hospital of Yunnan Province, Kunming 650102, P.R.China;

Corresponding author：

WANG Weilian, Email: wlwang_47@126.com

Keywords：

heart sound classification; sub-band envelope; convolution neural network; gammatone filter bank; Hilbert transform

DOI：

10.7507/1001-5515.202012024

Video：

Export PDF Favorites Scan Get Citation

Abstract Full text Figures/Tables Video References Cited by

Automatic classification of heart sounds plays an important role in the early diagnosis of congenital heart disease. A kind of heart sound classification algorithms based on sub-band envelope feature and convolution neural network was proposed in this paper, which did not need to segment the heart sounds according to cardiac cycle accurately. Firstly, the heart sound signal was divided into some frames. Then, the frame level heart sound signal was filtered with Gammatone filter bank to obtain the sub-band signals. Next, the sub-band envelope was extracted by Hilbert transform. After that, the sub-band envelope was stacked into a feature map. Finally, type Ⅰ and type Ⅱ convolution neural network were selected as classifier. The result shown that the sub-band envelope feature was better in type Ⅰ than type Ⅱ. The algorithm is tested with 1 000 heart sound samples. The test results show that the overall performance of the algorithm proposed in this paper is significantly improved compared with other similar algorithms, which provides a new method for automatic classification of congenital heart disease, and speeds up the process of automatic classification of heart sounds applied to the actual screening.

Citation： WANG Xingzhi, YANG Hongbo, ZONG Rong, PAN Jiahua, WANG Weilian. Heart sound classification based on sub-band envelope and convolution neural network. Journal of Biomedical Engineering, 2021, 38(5): 969-978. doi: 10.7507/1001-5515.202012024 Copy

1.	Zimmerman M S, Smith A, Sable C, et al. Global, regional, and national burden of congenital heart disease. a systematic analysis for the global burden of disease study 2017. Lancet Child & Adolescent Health, 2020, 4(3): 185-200.
2.	Deng S, Han J. Adaptive overlapping-group sparse denoising for heart sound signals. Biomedical Signal Processing and Control, 2018, 40: 49-57.
3.	Liu C, Springer D, Li Q, et al. An open access database for the evaluation of heart sound algorithms. Physiol Meas, 2016, 37(12): 2181-2213.
4.	Schmidt S E, Holst-Hansen C, Hansen J, et al. Acoustic features for the identification of coronary artery disease. IEEE Trans Biomed Eng, 2015, 62(11): 2611-2619.
5.	Chen Qiyu, Zhang Weibin, Tian Xiang, et al. Automatic heart and lung sounds classification using convolutional neural networks//2016 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA), Jeju: Asia-Pacific Signal and Information Processing Association, 2016: 1-4.
6.	Zabihi M, Rad A B, Kiranyaz S, et al. Heart sound anomaly and quality detection using ensemble of neural networks without segmentation//2016 Computing in Cardiology Conference (CinC), Vancouver: Computing in Cardiology, 2016: 613-616.
7.	Rubin J, Abreu R, Ganguli A, et al. Classifying heart sound recordings using deep convolutional neural networks and Mel-frequency cepstral coefficients//2016 Computing in Cardiology Conference (CinC), Vancouver: Computing in Cardiology, 2016: 813-816.
8.	Maknickas V, Maknickas A. Recognition of normal-abnormal phonocardiographic signals using deep convolutional neural networks and mel-frequency spectral coefficients. Physiol Meas, 2017, 38(8): 1671-1684.
9.	Kay E, Agarwal A. DropConnected neural networks trained on time-frequency and inter-beat features for classifying heart sounds. Physiol Meas, 2017, 38(8): 1645-1657.
10.	Hamidi M, Ghassemian H, Imani M. Classification of heart sound signal using curve fitting and fractal dimension. Biomedical Signal Processing and Control, 2018, 39: 351-359.
11.	Zhang W, Han J, Deng S. Heart sound classification based on scaled spectrogram and partial least squares regression. Biomedical Signal Processing and Control, 2017, 32: 20-28.
12.	Sepehri A A, Gharehbaghi A, Dutoit T, et al. A novel method for pediatric heart sound segmentation without using the ECG. Comput Methods Programs Biomed, 2010, 99(1): 43-48.
13.	Lubaib P, Muneer K. The heart defect analysis based on PCG signals using pattern recognition techniques. Procedia Technology, 2016, 24: 1024-1031.
14.	Zhang W, Han J, Deng S. Heart sound classification based on scaled spectrogram and tensor decomposition. Expert Systems with Applications, 2017, 84: 220-231.
15.	Picone J W. Signal modeling techniques in speech recognition. Proceedings of the IEEE, 1993, 81(9): 1215-1247.
16.	Sharma L N. Multiscale analysis of heart sound for segmentation using multiscale Hilbert envelope//2015 13th International Conference on ICT and Knowledge Engineering (ICT & Knowledge Engineering 2015), IEEE, 2015: 33-37.
17.	Deng S, Han J. Towards heart sound classification without segmentation via autocorrelation feature and diffusion maps. Future Generation Computer Systems, 2016, 60: 13-21.
18.	Das S, Pal S, Mitra M. Supervised model for cochleagram feature based fundamental heart sound identification. Biomedical Signal Processing and Control, 2019, 52: 32-40.
19.	Liu F, Tong X, Zhang C, et al. Multi-peak detection algorithm based on the Hilbert transform for optical FBG sensing. Optical Fiber Technology, 2018, 45: 47-52.
20.	Nilanon T, Yao Jiayu, Hao Junheng, et al. Normal/abnormal heart sound recordings classification using convolutional neural network//2016 Computing in Cardiology Conference (CinC), Vancouver: Computing in Cardiology , 2016: 585.
21.	Zhang W, Han J, Deng S. Abnormal heart sound detection using temporal quasi-periodic features and long short-term memory without segmentation. Biomedical Signal Processing and Control, 2019, 53: 101560.
22.	Chinchor N. MUC-4 evaluation metrics//4th Message Understanding Conference(MUC-4), Mclean: Morgan Kaufmann, 1992: 22-29.
23.	Fan J, Upadhye S, Worster A. Understanding receiver operating characteristic (ROC) curves. CJEM, 2006, 8(1): 19-20.

1. Zimmerman M S, Smith A, Sable C, et al. Global, regional, and national burden of congenital heart disease. a systematic analysis for the global burden of disease study 2017. Lancet Child & Adolescent Health, 2020, 4(3): 185-200.
2. Deng S, Han J. Adaptive overlapping-group sparse denoising for heart sound signals. Biomedical Signal Processing and Control, 2018, 40: 49-57.
3. Liu C, Springer D, Li Q, et al. An open access database for the evaluation of heart sound algorithms. Physiol Meas, 2016, 37(12): 2181-2213.
4. Schmidt S E, Holst-Hansen C, Hansen J, et al. Acoustic features for the identification of coronary artery disease. IEEE Trans Biomed Eng, 2015, 62(11): 2611-2619.
5. Chen Qiyu, Zhang Weibin, Tian Xiang, et al. Automatic heart and lung sounds classification using convolutional neural networks//2016 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA), Jeju: Asia-Pacific Signal and Information Processing Association, 2016: 1-4.
6. Zabihi M, Rad A B, Kiranyaz S, et al. Heart sound anomaly and quality detection using ensemble of neural networks without segmentation//2016 Computing in Cardiology Conference (CinC), Vancouver: Computing in Cardiology, 2016: 613-616.
7. Rubin J, Abreu R, Ganguli A, et al. Classifying heart sound recordings using deep convolutional neural networks and Mel-frequency cepstral coefficients//2016 Computing in Cardiology Conference (CinC), Vancouver: Computing in Cardiology, 2016: 813-816.
8. Maknickas V, Maknickas A. Recognition of normal-abnormal phonocardiographic signals using deep convolutional neural networks and mel-frequency spectral coefficients. Physiol Meas, 2017, 38(8): 1671-1684.
9. Kay E, Agarwal A. DropConnected neural networks trained on time-frequency and inter-beat features for classifying heart sounds. Physiol Meas, 2017, 38(8): 1645-1657.
10. Hamidi M, Ghassemian H, Imani M. Classification of heart sound signal using curve fitting and fractal dimension. Biomedical Signal Processing and Control, 2018, 39: 351-359.
11. Zhang W, Han J, Deng S. Heart sound classification based on scaled spectrogram and partial least squares regression. Biomedical Signal Processing and Control, 2017, 32: 20-28.
12. Sepehri A A, Gharehbaghi A, Dutoit T, et al. A novel method for pediatric heart sound segmentation without using the ECG. Comput Methods Programs Biomed, 2010, 99(1): 43-48.
13. Lubaib P, Muneer K. The heart defect analysis based on PCG signals using pattern recognition techniques. Procedia Technology, 2016, 24: 1024-1031.
14. Zhang W, Han J, Deng S. Heart sound classification based on scaled spectrogram and tensor decomposition. Expert Systems with Applications, 2017, 84: 220-231.
15. Picone J W. Signal modeling techniques in speech recognition. Proceedings of the IEEE, 1993, 81(9): 1215-1247.
16. Sharma L N. Multiscale analysis of heart sound for segmentation using multiscale Hilbert envelope//2015 13th International Conference on ICT and Knowledge Engineering (ICT & Knowledge Engineering 2015), IEEE, 2015: 33-37.
17. Deng S, Han J. Towards heart sound classification without segmentation via autocorrelation feature and diffusion maps. Future Generation Computer Systems, 2016, 60: 13-21.
18. Das S, Pal S, Mitra M. Supervised model for cochleagram feature based fundamental heart sound identification. Biomedical Signal Processing and Control, 2019, 52: 32-40.
19. Liu F, Tong X, Zhang C, et al. Multi-peak detection algorithm based on the Hilbert transform for optical FBG sensing. Optical Fiber Technology, 2018, 45: 47-52.
20. Nilanon T, Yao Jiayu, Hao Junheng, et al. Normal/abnormal heart sound recordings classification using convolutional neural network//2016 Computing in Cardiology Conference (CinC), Vancouver: Computing in Cardiology , 2016: 585.
21. Zhang W, Han J, Deng S. Abnormal heart sound detection using temporal quasi-periodic features and long short-term memory without segmentation. Biomedical Signal Processing and Control, 2019, 53: 101560.
22. Chinchor N. MUC-4 evaluation metrics//4th Message Understanding Conference(MUC-4), Mclean: Morgan Kaufmann, 1992: 22-29.
23. Fan J, Upadhye S, Worster A. Understanding receiver operating characteristic (ROC) curves. CJEM, 2006, 8(1): 19-20.

Journal of Biomedical Engineering

Heart sound classification based on sub-band envelope and convolution neural network

Abstract Full text Figures/Tables Video References Cited by

Previous Article

Next Article

Format

Content