Heart sound classification based on equal scale frequency cepstral coefficients and deep learning
-
Xiaoqing Chen
,
Youhe Huang
Abstract
Heart diseases represent a serious medical condition that can be fatal. Therefore, it is critical to investigate the measures of its early prevention. The Mel-scale frequency cepstral coefficients (MFCC) feature has been widely used in the early diagnosis of heart abnormity and achieved promising results. During feature extraction, the Mel-scale triangular overlapping filter set is applied, which makes the frequency response more in line with the human auditory property. However, the frequency of the heart sound signals has no specific relationship with the human auditory system, which may not be suitable for processing of heart sound signals. To overcome this issue and obtain a more objective feature that can better adapt to practical use, in this work, we propose an equal scale frequency cepstral coefficients (EFCC) feature based on replacing the Mel-scale filter set with a set of equally spaced triangular overlapping filters. We further designed classifiers combining convolutional neural network (CNN), recurrent neural network (RNN) and random forest (RF) layers, which can extract both the spatial and temporal information of the input features. We evaluated the proposed algorithm on our database and the PhysioNet Computational Cardiology (CinC) 2016 Challenge Database. Results from ten-fold cross-validation reveal that the EFCC-based features show considerably better performance and robustness than the MFCC-based features on the task of classifying heart sounds from novel patients. Our algorithm can be further used in wearable medical devices to monitor the heart status of patients in real time with high precision, which is of great clinical importance.
Funding source: National Natural Science Foundation of China
Award Identifier / Grant number: 61903071
Award Identifier / Grant number: 61973067
-
Research funding: This work was supported by the National Natural Science Foundation of China (61973067, 61903071).
-
Author contributions: Authors (Xiaoqing Chen, and Youhe Huang) have made an important contribution to the conception and drafting of the article. Authors (Hongru Li, and Xia Yu) have made an important contribution to the content design and critical revision of the article. Authors (Weiwei Han, Pengfei Zhang, and Rui Tao) have made an important contribution to the data analysis, interpretation and critical revision of the article. The version to be published has been approved by all authors. And all authors agree to be accountable for all aspects of the work to ensure the accuracy or completeness of any part of the work properly investigated and resolved.
-
Competing interests: We declare that we have no financial and personal relationships with other people or organizations that can inappropriately influence our work, there is no professional or other personal interest of any nature or kind in any product, service and/or company that could be construed as influencing the position presented in, or the review of, the manuscript entitled “ Heart sound classification based on equal scale frequency cepstral coefficients and deep learning ”.
-
Ethical approval: This study was approved by the ethics committee of Shijiazhuang first people’s hospital (NO. 039).
-
Informed consent: Complete informed consents, including written permission, were obtained for this study.
References
1. Virani, SS, Alonso, A, Benjamin, EJ, Bittencourt, MS, Callaway, CW, Carson, AP, et al.. Heart disease and stroke statistics-2020 update: a report from the American heart association: a report from the American heart association. Circulation 2020;141:e139–596. https://doi.org/10.1161/CIR.0000000000000757.Suche in Google Scholar PubMed
2. Ruffo, M, Cesarelli, M, Romano, M, Bifulco, P, Fratini, A. An algorithm for FHR estimation from foetal phonocardiographic signals. Biomed Signal Process Control 2010;5:131–41. https://doi.org/10.1016/j.bspc.2010.02.002.Suche in Google Scholar
3. Ghosh, SK, Ponnalagu, RN, Tripathy, RK, Acharya, UR. Automated detection of heart valve diseases using chirplet transform and multiclass composite classifier with PCG signals. Comput Biol Med 2020;118:103632. https://doi.org/10.1016/j.compbiomed.2020.103632.Suche in Google Scholar PubMed
4. Deng, M, Meng, T, Cao, J, Wang, S, Zhang, J, Fan, H. Heart sound classification based on improved MFCC features and convolutional recurrent neural networks. Neural Network 2020;130:22–32. https://doi.org/10.1016/j.neunet.2020.06.015.Suche in Google Scholar PubMed
5. Al-Naami, B, Fraihat, H, Gharaibeh, NY, Al-Hinnawi, ARM. A framework classification of heart sound signals in PhysioNet challenge 2016 using high order statistics and adaptive neuro-fuzzy inference system. IEEE Access 2020;8:224852–9. https://doi.org/10.1109/access.2020.3043290.Suche in Google Scholar
6. Singh, SA, Majumder, S. Classification of unsegmented heart sound recording using knn classifier. J Mech Med Biol 2019;19:1950025. https://doi.org/10.1142/s0219519419500258.Suche in Google Scholar
7. Ibrahim, EA, Awar, SA, Balayah, ZH, Hadjileontiadis, LJ, Khandoker, AH. A comparative study on fetal heart rates estimated from fetal phonography and cardiotocography. Front Physiol 2017;8:764. https://doi.org/10.3389/fphys.2017.00764.Suche in Google Scholar PubMed PubMed Central
8. Mubarak, QUA, Akram, MU, Shaukat, A, Hussain, F, Khawaja, SG, Butt, WH. Analysis of PCG signals using quality assessment and homomorphic filters for localization and classification of heart sounds. Comput Methods Progr Biomed 2018;164:143–57. https://doi.org/10.1016/j.cmpb.2018.07.006.Suche in Google Scholar PubMed
9. Babu, KA, Ramkumar, B, Manikandan, MS. Automatic identification of S1 and S2 heart sounds using simultaneous PCG and PPG recordings. IEEE Sensor J 2018;18:9430–40. https://doi.org/10.1109/jsen.2018.2869416.Suche in Google Scholar
10. Das, S, Pal, S, Mitra, M. Supervised model for cochleagram feature based fundamental heart sound identification. Biomed Signal Process Control 2019;52:32–40. https://doi.org/10.1016/j.bspc.2019.01.028.Suche in Google Scholar
11. Langley, P, Murray, A. Heart sound classification from unsegmented phonocardiograms. Physiol Meas 2017;38:1658–70. https://doi.org/10.1088/1361-6579/aa724c.Suche in Google Scholar PubMed
12. Chen, TE, Yang, SI, Ho, LT, Tsai, KH, Chen, YH, Chang, YF, et al.. S1 and S2 heart sound recognition using deep neural networks. IEEE Trans Biomed Eng 2016;64:372–80. https://doi.org/10.1109/TBME.2016.2559800.Suche in Google Scholar PubMed
13. Fernando, T, Ghaemmaghami, H, Denman, S, Sridharan, S, Hussain, N, Fookes, C. Heart sound segmentation using bidirectional LSTMs with attention. IEEE J Biomed Health Inform 2020;24:1601–9. https://doi.org/10.1109/jbhi.2019.2949516.Suche in Google Scholar PubMed
14. Mishra, M, Menon, H, Mukherjee, A. Characterization of S_1 and S_2 heart sounds using stacked autoencoder and convolutional neural network. IEEE Trans Instrum Meas 2019;68:3211–20. https://doi.org/10.1109/tim.2018.2872387.Suche in Google Scholar
15. Khan, FA, Abid, A, Khan, MS. Automatic heart sound classification from segmented/unsegmented phonocardiogram signals using time and frequency features. Physiol Meas 2020;41:055006. https://doi.org/10.1088/1361-6579/ab8770.Suche in Google Scholar PubMed
16. Noman, F, Salleh, SH, Ting, CM, Samdin, SB, Ombao, H, Hussain, H. A Markov-switching model approach to heart sound segmentation and classification. IEEE J Biomed Health Inform 2020;24:705–16. https://doi.org/10.1109/jbhi.2019.2925036.Suche in Google Scholar
17. Kambhampati, AB, Ramkumar, B. Automatic detection and classification of systolic and diastolic profiles of PCG corrupted due to limitations of electronic stethoscope recording. IEEE Sensor J 2021;21:5292–302. https://doi.org/10.1109/jsen.2020.3028373.Suche in Google Scholar
18. Yang, L, Li, S, Zhang, Z, Yang, X. Classification of phonocardiogram signals based on envelope optimization model and support vector machine. J Mech Med Biol 2020;20:1950062. https://doi.org/10.1142/s0219519419500623.Suche in Google Scholar
19. Li, P, Hu, Y, Liu, ZP. Prediction of cardiovascular diseases by integrating multi-modal features with machine learning methods. Biomed Signal Process Control 2021;66:102474. https://doi.org/10.1016/j.bspc.2021.102474.Suche in Google Scholar
20. Khan, MU, Aziz, S, Iqtidar, K, Zaher, GF, Alghamdi, S, Gull, M. A two-stage classification model integrating feature fusion for coronary artery disease detection and classification. Multimed Tool Appl 2021;81:1–30. https://doi.org/10.1007/s11042-021-10805-3.Suche in Google Scholar
21. Baydoun, M, Safatly, L, Ghaziri, H, El Hajj, A. Analysis of heart sound anomalies using ensemble learning. Biomed Signal Process Control 2020;62:102019. https://doi.org/10.1016/j.bspc.2020.102019.Suche in Google Scholar
22. Noman, F, Ting, CM, Salleh, SH, Ombao, H. Short-segment heart sound classification using an ensemble of deep convolutional neural networks. In: ICASSP 2019 – 2019 IEEE international conference on acoustics, speech and signal processing (ICASSP). IEEE; 2019.10.1109/ICASSP.2019.8682668Suche in Google Scholar
23. Kiranyaz, S, Zabihi, M, Rad, AB, Ince, T, Hamila, R, Gabbouj, M. Real-time phonocardiogram anomaly detection by adaptive 1D Convolutional neural networks. Neurocomputing 2020;411:291–301. https://doi.org/10.1016/j.neucom.2020.05.063.Suche in Google Scholar
24. Humayun, AI, Ghaffarzadegan, S, Ansari, MI, Feng, Z, Hasan, T. Towards domain invariant heart sound abnormality detection using learnable filterbanks. IEEE J Biomed Health Inform 2020;24:2189–98. https://doi.org/10.1109/jbhi.2020.2970252.Suche in Google Scholar
25. Erol, B, Gurbuz, SZ. Hyperbolically-warped cepstral coefficients for improved micro-Doppler classification. In: 2016 IEEE radar conference (RadarConf). IEEE; 2016.10.1109/RADAR.2016.7485204Suche in Google Scholar
26. Wang, P, Kim, Y, Soh, CB. Feature extraction based on mel-scaled wavelet transform for heart sound analysis. In: Annual international conference of the IEEE engineering in medicine and biology – proceedings, Shanghai; 2005:7572–5 pp.10.1109/IEMBS.2005.1616264Suche in Google Scholar PubMed
27. Wang, N, He, M, Sun, J, Wang, H, Zhou, L, Chu, C, et al.. Ia-PNCC: noise processing method for underwater target recognition convolutional neural network. Comput Mater Continua (CMC) 2019;58:169–81. https://doi.org/10.32604/cmc.2019.03709.Suche in Google Scholar
28. Abdulaziz, Y, Ahmad, S. Infant cry recognition system: A comparison of system performance based on mel frequency and linear prediction cepstral coefficients. In: International conference on information retrieval & knowledge management. IEEE; 2010.10.1109/INFRKM.2010.5466907Suche in Google Scholar
29. Pham, DH, Meignen, S, Dia, N, Fontecave-Jallon, J, Rivet, B. Phonocardiogram signal denoising based on nonnegative matrix factorization and adaptive contour representation computation. IEEE Signal Process Lett 2018;25:1475–9. https://doi.org/10.1109/lsp.2018.2865253.Suche in Google Scholar
30. Ai, OC, Hariharan, M, Yaacob, S, Chee, LS. Classification of speech dysfluencies with MFCC and LPCC features. Expert Syst Appl 2012;39:2157–65. https://doi.org/10.1016/j.eswa.2011.07.065.Suche in Google Scholar
31. Sahidullah, M, Saha, G. Design, analysis and experimental evaluation of block based transformation in MFCC computation for speaker recognition. Speech Commun 2012;54:543–65. https://doi.org/10.1016/j.specom.2011.11.004.Suche in Google Scholar
32. Picone, JW. Signal modeling techniques in speech recognition. Proc IEEE Inst Electr Electron Eng 1993;81:1215–47. https://doi.org/10.1109/5.237532.Suche in Google Scholar
33. Nuttall, A. Some windows with very good sidelobe behavior. IEEE Trans Acoust 1981;29:84–91. https://doi.org/10.1109/tassp.1981.1163506.Suche in Google Scholar
34. Lee, DK. Data transformation: a focus on the interpretation. Korean J Anesthesiol 2020;73:503–8. https://doi.org/10.4097/kja.20137.Suche in Google Scholar PubMed PubMed Central
35. Kumar, K, Kim, C, Stern, RM. Delta-spectral cepstral coefficients for robust speech recognition. In: 2011 IEEE international conference on acoustics, speech and signal processing (ICASSP). IEEE; 2011.10.1109/ICASSP.2011.5947425Suche in Google Scholar
36. Cuan, K, Zhang, T, Huang, J, Fang, C, Guan, Y. Detection of avian influenza-infected chickens based on a chicken sound convolutional neural network. Comput Electron Agric 2020;178:105688. https://doi.org/10.1016/j.compag.2020.105688.Suche in Google Scholar
37. Wu, JMT, Tsai, MH, Huang, YZ, Islam, SKH, Hassan, MM, Alelaiwi, A, et al.. Applying an ensemble convolutional neural network with Savitzky–Golay filter to construct a phonocardiogram prediction model. Appl Soft Comput 2019;78:29–40. https://doi.org/10.1016/j.asoc.2019.01.019.Suche in Google Scholar
38. Chen, Y, Kang, Y, Chen, Y, Wang, Z. Probabilistic forecasting with temporal convolutional neural network. Neurocomputing 2020;399:491–501. https://doi.org/10.1016/j.neucom.2020.03.011.Suche in Google Scholar
39. Shuvo, SB, Ali, SN, Swapnil, SI, Al-Rakhami, MS, Gumaei, A. CardioXNet: a novel lightweight deep learning framework for cardiovascular disease classification using heart sound recordings. IEEE Access 2021;9:36955–67. https://doi.org/10.1109/access.2021.3063129.Suche in Google Scholar
40. Hochreiter, S, Schmidhuber, J. Long short-term memory. Neural Comput 1997;9:1735–80. https://doi.org/10.1162/neco.1997.9.8.1735.Suche in Google Scholar PubMed
41. Brocki, Ł, Marasek, K. Deep belief neural networks and bidirectional long-short term memory hybrid for speech recognition. Arch Acoust Q 2015;40:191–5. https://doi.org/10.1515/aoa-2015-0021.Suche in Google Scholar
42. Piryonesi, SM, El-Diraby, TE. Using machine learning to examine impact of type of performance indicator on flexible pavement deterioration modeling. J Infrastruct Syst 2021;27:04021005. https://doi.org/10.1061/(asce)is.1943-555x.0000602.Suche in Google Scholar
43. Alkhodari, M, Fraiwan, L. Convolutional and recurrent neural networks for the detection of valvular heart diseases in phonocardiogram recordings. Comput Methods Progr Biomed 2021;200:105940. https://doi.org/10.1016/j.cmpb.2021.105940.Suche in Google Scholar PubMed
44. Xiao, B, Xu, Y, Bi, X, Zhang, J, Ma, X. Heart sounds classification using a novel 1-D convolutional neural network with extremely low parameter consumption. Neurocomputing 2020;392:153–9. https://doi.org/10.1016/j.neucom.2018.09.101.Suche in Google Scholar
45. Li, F, Tang, H, Shang, S, Mathiak, K, Cong, F. Classification of heart sounds using convolutional neural network. Appl Sci 2020;10:3956. https://doi.org/10.3390/app10113956.Suche in Google Scholar
Supplementary Material
This article contains supplementary material (https://doi.org/10.1515/bmt-2021-0254).
© 2023 Walter de Gruyter GmbH, Berlin/Boston
Artikel in diesem Heft
- Frontmatter
- Review
- A review: strategies to reduce infection in tantalum and its derivative applied to implants
- Research Articles
- Biomechanical analysis of different fixed dental restorations on short implants: a finite element study
- Highly sensitive temperature sensor using one-dimensional Bragg Reflector for biomedical applications
- Synchronisation of wearable inertial measurement units based on magnetometer data
- Multiple ECG segments denoising autoencoder model
- Heart sound classification based on equal scale frequency cepstral coefficients and deep learning
- Towards a versatile mental workload modeling using neurometric indices
- An improved multi-source domain adaptation network for inter-subject mental fatigue detection based on DANN
Artikel in diesem Heft
- Frontmatter
- Review
- A review: strategies to reduce infection in tantalum and its derivative applied to implants
- Research Articles
- Biomechanical analysis of different fixed dental restorations on short implants: a finite element study
- Highly sensitive temperature sensor using one-dimensional Bragg Reflector for biomedical applications
- Synchronisation of wearable inertial measurement units based on magnetometer data
- Multiple ECG segments denoising autoencoder model
- Heart sound classification based on equal scale frequency cepstral coefficients and deep learning
- Towards a versatile mental workload modeling using neurometric indices
- An improved multi-source domain adaptation network for inter-subject mental fatigue detection based on DANN
