A heart sound segmentation method based on multi-feature fusion network_Chinese Journal of Clinical Thoracic and Cardiovascular Surgery

Authors：

TIAN Pian ¹ , HE Peiyu ¹ , CAI Jie ² , ZHAO Qijun ³ , LI Li ⁴ ,  QIAN Yongjun ² ,  PAN Fan ¹

1. School of Electronic Information, Sichuan University, Chengdu, 610065, P. R. China;
2. Department of Cardiovascular Surgery, West China Hospital, Sichuan University, Chengdu, 610041, P. R. China;
3. School of Computer Science, Sichuan University, Chengdu, 610065, P. R. China;
4. Department of Pediatric Cardiology, West China Second University Hospital, Sichuan University, Chengdu, 610041, P. R. China;

Corresponding author：

QIAN Yongjun, Email: qianyongjun@scu.edu.cn; PAN Fan, Email: panfan@scu.edu.cn

Keywords：

Heart sound segmentation; BiGRU network; principal component analysis; feature selection; multi-feature fusion

DOI：

10.7507/1007-4848.202310060

Video：

Export PDF Favorites Scan Get Citation

Abstract Full text Figures/Tables Video References Cited by

Objective To propose a heart sound segmentation method based on multi-feature fusion network. Methods Data were obtained from the CinC/PhysioNet 2016 Challenge dataset (a total of 3 153 recordings from 764 patients, about 91.93% of whom were male, with an average age of 30.36 years). Firstly the features were extracted in time domain and time-frequency domain respectively, and reduced redundant features by feature dimensionality reduction. Then, we selected optimal features separately from the two feature spaces that performed best through feature selection. Next, the multi-feature fusion was completed through multi-scale dilated convolution, cooperative fusion, and channel attention mechanism. Finally, the fused features were fed into a bidirectional gated recurrent unit (BiGRU) network to heart sound segmentation results. Results The proposed method achieved precision, recall and F1 score of 96.70%, 96.99%, and 96.84% respectively. Conclusion The multi-feature fusion network proposed in this study has better heart sound segmentation performance, which can provide high-accuracy heart sound segmentation technology support for the design of automatic analysis of heart diseases based on heart sounds.

Citation： TIAN Pian, HE Peiyu, CAI Jie, ZHAO Qijun, LI Li, QIAN Yongjun, PAN Fan. A heart sound segmentation method based on multi-feature fusion network. Chinese Journal of Clinical Thoracic and Cardiovascular Surgery, 2024, 31(5): 672-681. doi: 10.7507/1007-4848.202310060 Copy

1.	马丽媛, 王增武, 樊静, 等. 《中国心血管健康与疾病报告2021》关于中国高血压流行和防治现状. 中国全科医学, 2022, 25(30): 3715-3720.
2.	程显声. 胸部(心肺)听诊的技巧(下). 中国民康医学, 2006, 18(4): 81-83.
3.	Chen Y, Lv JC, Sun YN, et al. Heart sound segmentation via duration long–short term memory neural network. Appl Soft Comput, 2020, 95: 106540.
4.	曾劲云, 何培宇, 潘帆. 基于自适应阈值的心音分段算法研究. 四川大学学报(自然科学版), 2019, 56(5): 867-874.
5.	Belmecheri MZ, Ahfir M, Kale I. Automatic heart sounds segmentation based on the correlation coefficients matrix for similar cardiac cycles identification. Biomed Signal Process Control, 2018, 43: 300-310.
6.	Liu Q, Wu X, Ma X. An automatic segmentation method for heart sounds. Biomed Eng Online, 2018, 17(1): 106.
7.	Babu KA, Ramkumar B, Manikandan MS. S1 and S2 heart sound segmentation using variational mode decomposition. TENCON 2017-2017 IEEE Region 10 Conference. Penang: IEEE, 2017: 1629-1634.
8.	Varghees VN, Ramachandran KI. Effective heart sound segmentation and murmur classification using empirical wavelet transform and instantaneous phase for electronic stethoscope. IEEE Sens J, 2017, 17(12): 3861-3872.
9.	Alexander B, Nallathambi G, Selvaraj N. Screening of heart sounds using hidden markov and gammatone filterbank models. 2018 17th IEEE International Conference on Machine Learning and Applications (ICMLA). Orlando, FL: IEEE, 2018: 1460-1465.
10.	Shukla S, Singh SK, Mitra D. An efficient heart sound segmentation approach using kurtosis and zero frequency filter features. Biomed Signal Process Control, 2020, 57: 101762.
11.	Springer DB, Tarassenko L, Clifford GD. Logistic regression-hsmm-based heart sound segmentation. IEEE Trans Biomed Eng, 2016, 63(4): 822-832.
12.	Liu C, Springer D, Clifford GD. Performance of an open-source heart sound segmentation algorithm on eight independent databases. Physiol Meas, 2017, 38(8): 1730-1745.
13.	Kamson AP, Sharma LN, Dandapat S. Multi-centroid diastolic duration distribution based HSMM for heart sound segmentation. Biomed Signal Process Control, 2019, 48: 265-272.
14.	Oliveira J, Renna F, Coimbra M. A subject-driven unsupervised hidden Semi-Markov model and gaussian mixture model for heart sound segmentation. IEEE J Sel Top Signal Process, 2019, 13(2): 323-331.
15.	Oliveira J, Renna F, Mantadelis T, et al. Adaptive sojourn time HSMM for heart sound segmentation. IEEE J Biomed Health Inform, 2019, 23(2): 642-649.
16.	Messner E, Zohrer M, Pernkopf F. Heart sound segmentation-An event detection approach using deep recurrent neural networks. IEEE Trans Biomed Eng, 2018, 65(9): 1964-1974.
17.	Xu XC, Geng XG, Gao ZX, et al. Optimal heart sound segmentation algorithm based on K-mean clustering and wavelet transform. Appl Sci-Basel, 2023, 13(2): 1170.
18.	Renna F, Oliveira J, Coimbra MT. Deep convolutional neural networks for heart sound segmentation. IEEE J Biomed Health Inform, 2019, 23(6): 2435-2445.
19.	Chen TE, Yang SI, Ho LT, et al. S1 and S2 heart sound recognition using deep neural networks. IEEE Trans Biomed Eng, 2017, 64(2): 372-380.
20.	Fernando T, Ghaemmaghami H, Denman S, et al. Heart sound segmentation using bidirectional LSTMs with attention. IEEE J Biomed Health Inform, 2020, 24(6): 1601-1609.
21.	Oliveira J, Carvalho M, Nogueira D M, et al. Segmentation and optimal region selection of physiological signals using deep neural networks and combinatorial optimization. 2020, arXiv: 2003.07981.
22.	Chen Y, Sun YA, Lv JC, et al. End-to-end heart sound segmentation using deep convolutional recurrent network. Complex Intell Syst, 2021, 7(4): 2103-2117.
23.	Wang X, Liu C, Li Y, et al. Temporal-framing adaptive network for heart sound segmentation without prior knowledge of state duration. IEEE Trans Biomed Eng, 2021, 68(2): 650-663.
24.	Guo Y, Yang H, Guo T, et al. A novel heart sound segmentation algorithm via multi-feature input and neural network with attention mechanism. Biomed Phys Eng Express, 2022, 9(1): 1.
25.	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.
26.	Lee WS, Roh YW, Kim DJ, et al. Speech emotion recognition using spectral entropy. 1st International Conference on Intelligent Robotics and Applications, Wuhan: Springer-Verlag, 2008: 45-54.
27.	Deepa P, Thilagavathi K. Data reduction techniques of hyperspectral images: A comparative study. 2015 3rd International Conference on Signal Processing, Communication and Networking (ICSCN). Chennai, India: IEEE, 2015: 1-6.
28.	陆莉霞, 邹俊忠, 郭玉成, 等. 多模态融合的膝关节损伤预测. 计算机工程与应用, 2021, 57(9): 225-232.
29.	Yu F, Koltun V. Multi-scale context aggregation by dilated convolutions. ICLR, 2016, arXiv: 1511.07122.
30.	Fu K, Fan DP, Ji GP, et al. Siamese network for RGB-D salient object detection and beyond. IEEE Trans Pattern Anal Mach Intell, 2021. Epub ahead of print.
31.	Hu J, Shen L, Albanie S, et al. Squeeze-and-excitation networks. IEEE Trans Pattern Anal Mach Intell, 2020, 42(8): 2011-2023.
32.	Chung J, Gulcehre C, Cho K, et al. Empirical evaluation of gated recurrent neural networks on sequence modeling. 2014, arXiv: 1412.3555v1.
33.	Schmidt SE, Holst-Hansen C, Graff C, et al. Segmentation of heart sound recordings by a duration-dependent hidden Markov model. Physiol Meas, 2010, 31(4): 513-529.
34.	Chen W, Sun Q, Chen X, et al. Deep learning methods for heart sounds classification: A systematic review. Entropy (Basel), 2021, 23(6): 667.

1. 马丽媛, 王增武, 樊静, 等. 《中国心血管健康与疾病报告2021》关于中国高血压流行和防治现状. 中国全科医学, 2022, 25(30): 3715-3720.
2. 程显声. 胸部(心肺)听诊的技巧(下). 中国民康医学, 2006, 18(4): 81-83.
3. Chen Y, Lv JC, Sun YN, et al. Heart sound segmentation via duration long–short term memory neural network. Appl Soft Comput, 2020, 95: 106540.
4. 曾劲云, 何培宇, 潘帆. 基于自适应阈值的心音分段算法研究. 四川大学学报(自然科学版), 2019, 56(5): 867-874.
5. Belmecheri MZ, Ahfir M, Kale I. Automatic heart sounds segmentation based on the correlation coefficients matrix for similar cardiac cycles identification. Biomed Signal Process Control, 2018, 43: 300-310.
6. Liu Q, Wu X, Ma X. An automatic segmentation method for heart sounds. Biomed Eng Online, 2018, 17(1): 106.
7. Babu KA, Ramkumar B, Manikandan MS. S1 and S2 heart sound segmentation using variational mode decomposition. TENCON 2017-2017 IEEE Region 10 Conference. Penang: IEEE, 2017: 1629-1634.
8. Varghees VN, Ramachandran KI. Effective heart sound segmentation and murmur classification using empirical wavelet transform and instantaneous phase for electronic stethoscope. IEEE Sens J, 2017, 17(12): 3861-3872.
9. Alexander B, Nallathambi G, Selvaraj N. Screening of heart sounds using hidden markov and gammatone filterbank models. 2018 17th IEEE International Conference on Machine Learning and Applications (ICMLA). Orlando, FL: IEEE, 2018: 1460-1465.
10. Shukla S, Singh SK, Mitra D. An efficient heart sound segmentation approach using kurtosis and zero frequency filter features. Biomed Signal Process Control, 2020, 57: 101762.
11. Springer DB, Tarassenko L, Clifford GD. Logistic regression-hsmm-based heart sound segmentation. IEEE Trans Biomed Eng, 2016, 63(4): 822-832.
12. Liu C, Springer D, Clifford GD. Performance of an open-source heart sound segmentation algorithm on eight independent databases. Physiol Meas, 2017, 38(8): 1730-1745.
13. Kamson AP, Sharma LN, Dandapat S. Multi-centroid diastolic duration distribution based HSMM for heart sound segmentation. Biomed Signal Process Control, 2019, 48: 265-272.
14. Oliveira J, Renna F, Coimbra M. A subject-driven unsupervised hidden Semi-Markov model and gaussian mixture model for heart sound segmentation. IEEE J Sel Top Signal Process, 2019, 13(2): 323-331.
15. Oliveira J, Renna F, Mantadelis T, et al. Adaptive sojourn time HSMM for heart sound segmentation. IEEE J Biomed Health Inform, 2019, 23(2): 642-649.
16. Messner E, Zohrer M, Pernkopf F. Heart sound segmentation-An event detection approach using deep recurrent neural networks. IEEE Trans Biomed Eng, 2018, 65(9): 1964-1974.
17. Xu XC, Geng XG, Gao ZX, et al. Optimal heart sound segmentation algorithm based on K-mean clustering and wavelet transform. Appl Sci-Basel, 2023, 13(2): 1170.
18. Renna F, Oliveira J, Coimbra MT. Deep convolutional neural networks for heart sound segmentation. IEEE J Biomed Health Inform, 2019, 23(6): 2435-2445.
19. Chen TE, Yang SI, Ho LT, et al. S1 and S2 heart sound recognition using deep neural networks. IEEE Trans Biomed Eng, 2017, 64(2): 372-380.
20. Fernando T, Ghaemmaghami H, Denman S, et al. Heart sound segmentation using bidirectional LSTMs with attention. IEEE J Biomed Health Inform, 2020, 24(6): 1601-1609.
21. Oliveira J, Carvalho M, Nogueira D M, et al. Segmentation and optimal region selection of physiological signals using deep neural networks and combinatorial optimization. 2020, arXiv: 2003.07981.
22. Chen Y, Sun YA, Lv JC, et al. End-to-end heart sound segmentation using deep convolutional recurrent network. Complex Intell Syst, 2021, 7(4): 2103-2117.
23. Wang X, Liu C, Li Y, et al. Temporal-framing adaptive network for heart sound segmentation without prior knowledge of state duration. IEEE Trans Biomed Eng, 2021, 68(2): 650-663.
24. Guo Y, Yang H, Guo T, et al. A novel heart sound segmentation algorithm via multi-feature input and neural network with attention mechanism. Biomed Phys Eng Express, 2022, 9(1): 1.
25. 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.
26. Lee WS, Roh YW, Kim DJ, et al. Speech emotion recognition using spectral entropy. 1st International Conference on Intelligent Robotics and Applications, Wuhan: Springer-Verlag, 2008: 45-54.
27. Deepa P, Thilagavathi K. Data reduction techniques of hyperspectral images: A comparative study. 2015 3rd International Conference on Signal Processing, Communication and Networking (ICSCN). Chennai, India: IEEE, 2015: 1-6.
28. 陆莉霞, 邹俊忠, 郭玉成, 等. 多模态融合的膝关节损伤预测. 计算机工程与应用, 2021, 57(9): 225-232.
29. Yu F, Koltun V. Multi-scale context aggregation by dilated convolutions. ICLR, 2016, arXiv: 1511.07122.
30. Fu K, Fan DP, Ji GP, et al. Siamese network for RGB-D salient object detection and beyond. IEEE Trans Pattern Anal Mach Intell, 2021. Epub ahead of print.
31. Hu J, Shen L, Albanie S, et al. Squeeze-and-excitation networks. IEEE Trans Pattern Anal Mach Intell, 2020, 42(8): 2011-2023.
32. Chung J, Gulcehre C, Cho K, et al. Empirical evaluation of gated recurrent neural networks on sequence modeling. 2014, arXiv: 1412.3555v1.
33. Schmidt SE, Holst-Hansen C, Graff C, et al. Segmentation of heart sound recordings by a duration-dependent hidden Markov model. Physiol Meas, 2010, 31(4): 513-529.
34. Chen W, Sun Q, Chen X, et al. Deep learning methods for heart sounds classification: A systematic review. Entropy (Basel), 2021, 23(6): 667.

Chinese Journal of Clinical Thoracic and Cardiovascular Surgery

A heart sound segmentation method based on multi-feature fusion network

Abstract Full text Figures/Tables Video References Cited by

Previous Article

Next Article

Format

Content