Classification of heart sound signals in congenital heart disease based on convolutional neural network_Journal of Biomedical Engineering

Authors：

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

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

Corresponding author：

WANG Weilian, Email: wlwang_47@126.com

Keywords：

congenital heart disease; classification; machine aided auscultation; Mel coefficient; convolutional neural network

DOI：

10.7507/1001-5515.201806031

Video：

Export PDF Favorites Scan Get Citation

Abstract Full text Figures/Tables Video References Cited by

Cardiac auscultation is the basic way for primary diagnosis and screening of congenital heart disease(CHD). A new classification algorithm of CHD based on convolution neural network was proposed for analysis and classification of CHD heart sounds in this work. The algorithm was based on the clinically collected diagnosed CHD heart sound signal. Firstly the heart sound signal preprocessing algorithm was used to extract and organize the Mel Cepstral Coefficient (MFSC) of the heart sound signal in the one-dimensional time domain and turn it into a two-dimensional feature sample. Secondly, 1 000 feature samples were used to train and optimize the convolutional neural network, and the training results with the accuracy of 0.896 and the loss value of 0.25 were obtained by using the Adam optimizer. Finally, 200 samples were tested with convolution neural network, and the results showed that the accuracy was up to 0.895, the sensitivity was 0.910, and the specificity was 0.880. Compared with other algorithms, the proposed algorithm has improved accuracy and specificity. It proves that the proposed method effectively improves the robustness and accuracy of heart sound classification and is expected to be applied to machine-assisted auscultation.

Citation： TAN Zhaowen, WANG Weilian, ZONG Rong, PAN Jiahua, YANG Hongbo. Classification of heart sound signals in congenital heart disease based on convolutional neural network. Journal of Biomedical Engineering, 2019, 36(5): 728-736, 744. doi: 10.7507/1001-5515.201806031 Copy

1.	Tang Hong, Li Ting, Park Y, et al. Separation of heart sound signal from noise in joint cycle frequency-time-frequency domains based on fuzzy detection. IEEE Trans Biomed Eng, 2010, 57(10): 2438-2447.
2.	Gavrovska A, Bogdanovic V, Reljin I, et al. Automatic heart sound detection in pediatric patients without electrocardiogram reference via pseudo-affine Wigner-Ville distribution and Haar wavelet lifting. Comput Methods Programs Biomed, 2014, 113(2): 515-528.
3.	Abbas A, Bassam R. Phonocardiography signal processing. New York: Morgan and Claypool, 2009: 29-37.
4.	Safara F, Doraisamy S, Azman A, et al. Multi-level basis selection of wavelet packet de-composition tree for heart sound classification. Comput Biol Med, 2013, 43(10): 1407-1414.
5.	Ortiz P M, Drugalski C, Miranda V E, et al. Modelos acústicos HMM multimodales para sonidos cardiacos y pulmonares. Revista mexicana de ingeniería biomédica, 2014, 35(3): 197-209.
6.	Ortiz J J G, Phoo C P, Wiens J. Heart sound classification based on temporal alignment techniques// Computing in Cardiology Conference (CINC). Vancouver: IEEE, 2016, 43: 589-592.
7.	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.
8.	Nabih-Ali M. El-Dahshan E A. Yahia A S. A review of intelligent systems for heart sound signal analysis. J Med Eng Technol, 2017, 41(7): 553-563.
9.	Papadaniil C D, Hadjileontiadis L J. Efficient heart sound segmentation and extraction using ensemble empirical mode decomposition and kurtosis features. IEEE J Biomed Health Inform, 2014, 18(4): 1138-1152.
10.	Sh-Hussain H, Mohamad M M, Zahilah R, et al. Classification of heart sound signals using autoregressive model and hidden markov model. Journal of Medical Imaging and Health Informatics, 2017, 7(4): 755-763.
11.	马莉. 基于小波包分解的复杂心音信号分段定位与特征提取研究. 昆明: 云南大学, 2015.
12.	Krizhevsky A, Sutskever I, Hinton G E. ImageNet classification with deep convolutional neural networks. Commun ACM, 2017, 60(6): 84-90.
13.	Frigieri E P, Brito T G, Ynoguti C A, et al. Pattern recognition in audible sound energy emissions of AISI 52100 hardened steel turning: a MFCC-based approach. International Journal of Advanced Manufacturing Technology, 2017, 88(5-8): 1383-1392.
14.	Mohamed A. Deep neural network acoustic models for asr. Toronto: University of Toronto, 2014.
15.	Hu Zheng, Li Yongping, Yang Zhiyong. Improving convolutional neural network using pseudo derivative ReLU//5th International Conference On Systems And Informatics (ICSAI), Nanjing: IEEE, 2018: 283-287.
16.	Poernomo A, Kang D K. Biased dropout and crossmap dropout: learning towards effective dropout regularization in convolutional neural network. Neural Networks, 2018, 104: 60-67.
17.	Kingma D P, Ba J. Adam: a method for stochastic optimization// 3rd International Conference for Learning Representations, San Diego, 2015. arXiv: 1412.6980.
18.	Bobillo I J D. A tensor approach to heart sound classification//2016 Computing in Cardiology Conference (CinC), IEEE, 2016: 629-632.

1. Tang Hong, Li Ting, Park Y, et al. Separation of heart sound signal from noise in joint cycle frequency-time-frequency domains based on fuzzy detection. IEEE Trans Biomed Eng, 2010, 57(10): 2438-2447.
2. Gavrovska A, Bogdanovic V, Reljin I, et al. Automatic heart sound detection in pediatric patients without electrocardiogram reference via pseudo-affine Wigner-Ville distribution and Haar wavelet lifting. Comput Methods Programs Biomed, 2014, 113(2): 515-528.
3. Abbas A, Bassam R. Phonocardiography signal processing. New York: Morgan and Claypool, 2009: 29-37.
4. Safara F, Doraisamy S, Azman A, et al. Multi-level basis selection of wavelet packet de-composition tree for heart sound classification. Comput Biol Med, 2013, 43(10): 1407-1414.
5. Ortiz P M, Drugalski C, Miranda V E, et al. Modelos acústicos HMM multimodales para sonidos cardiacos y pulmonares. Revista mexicana de ingeniería biomédica, 2014, 35(3): 197-209.
6. Ortiz J J G, Phoo C P, Wiens J. Heart sound classification based on temporal alignment techniques// Computing in Cardiology Conference (CINC). Vancouver: IEEE, 2016, 43: 589-592.
7. 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.
8. Nabih-Ali M. El-Dahshan E A. Yahia A S. A review of intelligent systems for heart sound signal analysis. J Med Eng Technol, 2017, 41(7): 553-563.
9. Papadaniil C D, Hadjileontiadis L J. Efficient heart sound segmentation and extraction using ensemble empirical mode decomposition and kurtosis features. IEEE J Biomed Health Inform, 2014, 18(4): 1138-1152.
10. Sh-Hussain H, Mohamad M M, Zahilah R, et al. Classification of heart sound signals using autoregressive model and hidden markov model. Journal of Medical Imaging and Health Informatics, 2017, 7(4): 755-763.
11. 马莉. 基于小波包分解的复杂心音信号分段定位与特征提取研究. 昆明: 云南大学, 2015.
12. Krizhevsky A, Sutskever I, Hinton G E. ImageNet classification with deep convolutional neural networks. Commun ACM, 2017, 60(6): 84-90.
13. Frigieri E P, Brito T G, Ynoguti C A, et al. Pattern recognition in audible sound energy emissions of AISI 52100 hardened steel turning: a MFCC-based approach. International Journal of Advanced Manufacturing Technology, 2017, 88(5-8): 1383-1392.
14. Mohamed A. Deep neural network acoustic models for asr. Toronto: University of Toronto, 2014.
15. Hu Zheng, Li Yongping, Yang Zhiyong. Improving convolutional neural network using pseudo derivative ReLU//5th International Conference On Systems And Informatics (ICSAI), Nanjing: IEEE, 2018: 283-287.
16. Poernomo A, Kang D K. Biased dropout and crossmap dropout: learning towards effective dropout regularization in convolutional neural network. Neural Networks, 2018, 104: 60-67.
17. Kingma D P, Ba J. Adam: a method for stochastic optimization// 3rd International Conference for Learning Representations, San Diego, 2015. arXiv: 1412.6980.
18. Bobillo I J D. A tensor approach to heart sound classification//2016 Computing in Cardiology Conference (CinC), IEEE, 2016: 629-632.

Journal of Biomedical Engineering

Classification of heart sound signals in congenital heart disease based on convolutional neural network

Abstract Full text Figures/Tables Video References Cited by

Previous Article

Next Article

Format

Content