Wavelet-based fundamental heart sound recognition method using morphological and interval features

V. Nivitha Varghees; K.I. Ramachandran; K.P. Soman

Wavelet-based fundamental heart sound recognition method using morphological and interval features

View Fulltext

Author(s): V. Nivitha Varghees¹ ; K.I. Ramachandran¹ ; K.P. Soman¹
- Affiliations: 1: Center for Computational Engineering and Networking (CEN), Amrita School of Engineering , Amrita University , Amrita Vishwa Vidyapeetham, Coimbatore , India
Source: Volume 5, Issue 3, June 2018, p. 81 – 87
DOI: 10.1049/htl.2016.0109 , Online ISSN 2053-3713

« Previous Article
Table of contents
Next Article »

This is an open access article published by the IET under the Creative Commons Attribution-NoDerivs License (http://creativecommons.org/licenses/by-nd/3.0/)

Received 21/12/2016, Accepted 28/06/2017, Revised 21/06/2017, Published 25/04/2018

Accurate and reliable recognition of fundamental heart sounds (FHSs) plays a significant role in automated analysis of heart sound (HS) patterns. This Letter presents an automated wavelet-based FHS recognition (WFHSR) method using morphological and interval features. The proposed method first performs the decomposition of phonocardiogram (PCG) signal using a synchrosqueezing wavelet transform to extract the HSs and suppresses the murmurs, low-frequency and high-frequency noises. The HS delineation (HSD) is presented using Shannnon energy envelope and amplitude-dependent thresholding rule. The FHS recognition (FHSR) is presented using interval, HS duration and envelope area features with a decision-rule algorithm. The performance of the method is evaluated on PASCAL HSs Challenge, PhysioNet/CinC HS Challenge, eGeneralMedical databases and real-time recorded PCG signals. Results show that the HSD approach achieves an average sensitivity (Se) of 98.87%, positive predictivity (Pp) of 97.50% with detection error rate of 3.67% for PCG signals with signal-to-noise ratio of 10 dB, and outperforms the existing HSD methods. The proposed FHSR method achieves a Se of 99.00%, Sp of 99.08% and overall accuracy of 99.04% on both normal and abnormal PCG signals. Evaluation results show that the proposed WFHSR method is able to accurately recognise the S1/S2 HSs in noisy real-world PCG recordings with murmurs and other abnormal sounds.

References

1. 1)
  - 25. Daubechies, I., et al: ‘Synchrosqueezed wavelet transforms: an empirical mode decomposition-like tool’, Appl. Comput. Harmon. Anal., 2011, 30, (2), pp. 243–261 (doi: 10.1016/j.acha.2010.08.002).
2. 2)
  - 15. Hedayioglu, F., et al: ‘Denoising and segmentation of the second heart sound using matching pursuit’. Proc. IEEE 34th Annual Int. Conf. Engineering in Medicine and Biology Society, 2012, pp. 3440–3443.
3. 3)
  - 21. Gamero, L., Watrous, R.: ‘Detection of the first and second heart sound using probabilistic models’. Proc. IEEE 25th Annual Int. Conf. Engineering in Medicine and Biology Society, September 2003, pp. 2877–2880.
4. 4)
  - 26. Herrera, R.H., et al: ‘Applications of the synchrosqueezing transform in seismic time–frequency analysis’, Geophysics, 2014, 79, (3), pp. v55–v64 (doi: 10.1190/geo2013-0204.1).
5. 5)
  - 2. Herzig, J., et al: ‘Monitoring cardiac stress using features extracted from S1 heart sounds’, IEEE Trans. Biomed. Eng., 2015, 62, (4), pp. 1169–1178 (doi: 10.1109/TBME.2014.2377695).
6. 6)
  - 8. Tschannen, M., et al: ‘Heart sound classification using deep structured features’. Proc. Computing in Cardiology, September 2016.
7. 7)
  - 28. Bentley, P., et al: ‘Classifying heart sounds challenge’. Available at http://www.peterjbentley.com/heartchallenge/.
8. 8)
  - 17. Wang, X., et al: ‘Detection of the first and second heart sound using heart sound energy’. Proc. Int. Conf. Biomedical Engineering and Informatics, 2009, pp. 1–4.
9. 9)
  - 29. Classification of Normal/Abnormal Heart Sound Recordings: the PhysioNet/Computing in Cardiology Challenge, 2016. Available at https://www.physionet.org/challenge/2016/.
10. 10)
  - 29. Naseri, H., Homaeinezhad, M.R.: ‘Detection and boundary identification of phonocardiogram sounds using an expert frequency-energy based metrice’, Ann. Biomed. Eng., 2013, 41, (2), pp. 279–292 (doi: 10.1007/s10439-012-0645-x).
11. 11)
  - 12. Sun, H., et al: ‘An improved empirical mode decomposition-wavelet algorithm for phonocardiogram signal denoising and its application in the first and second heart sound extraction’. Proc. 6th Int. Conf. Biomedical Engineering and Informatics, December 2013, pp. 187–191.
12. 12)
  - 22. Oskiper, T., Watrous, R.: ‘Detection of the first heart sound using a time-delay neural network’. Proc. Computers in Cardiology, September 2002, pp. 537–540.
13. 13)
  - 16. Schmidt, S.E., et al: ‘Segmentation of heart sound recordings by a duration-dependent hidden Markov model’, Physiol. Meas., 2010, 31, (4), pp. 513–529 (doi: 10.1088/0967-3334/31/4/004).
14. 14)
  - 3. Zhang, X.-Y., et al: ‘Relations between the timing of the second heart sound and aortic blood pressure’, IEEE Trans. Biomed. Eng., 2008, 55, (04), pp. 1291–1297 (doi: 10.1109/TBME.2007.912422).
15. 15)
  - 17. Nivitha Varghees, V., Ramachandran, K.I.: ‘A novel heart sound activity detection framework for automated heart sound analysis’, Biomed. Signal Process. Control, 2014, 13, pp. 174–188 (doi: 10.1016/j.bspc.2014.05.002).
16. 16)
  - 7. Thomas, R., et al: ‘Heart sound segmentation using fractal decomposition’. Proc. IEEE 38th Annual Int. Conf. Engineering in Medicine and Biology Society, August 2016, pp. 6234–6236.
17. 17)
  - 27. Nivitha Varghees, V., Ramachandran, K.I.: ‘Effective heart sound segmentation and murmur classification using empirical wavelet transform and instantaneous phase for electronic stethoscope’, IEEE Sens. J., 2017, 17, (12), pp. 3861–3872 (doi: 10.1109/JSEN.2017.2694970).
18. 18)
  - 5. Beritelli, F., Serrano, S.: ‘Biometric identification based on frequency analysis of cardiac sounds’, IEEE Trans. Inf. Forensics Sec., 2007, 2, (3), pp. 596–604 (doi: 10.1109/TIFS.2007.902922).
19. 19)
  - 6. Chen, T.-E., et al: ‘S1 and S2 heart sound recognition using deep neural networks’, IEEE Trans. Biomed. Eng., 2017, 64, (2), pp. 372–380 (doi: 10.1109/TBME.2016.2559800).
20. 20)
  - 11. Sabarimalai Manikandan, M., Soman, K.P.: ‘Robust heart sound activity detection in noisy environments’, Electron. Lett., 2010, 46, (16), pp. 1100–1102 (doi: 10.1049/el.2010.1201).
21. 21)
  - 19. Gill, D., et al: ‘Detection and identification of heart sounds using homomorphic envelogram and self-organizing probabilistic model’. Proc. Computers in Cardiology, September 2005, pp. 957–960.
22. 22)
  - 1. Barma, S., et al: ‘Measurement of duration, energy of instantaneous frequencies, and splits of subcomponents of the second heart sound’, IEEE Trans. Instrum. Meas., 2015, 64, (7), pp. 1958–1967 (doi: 10.1109/TIM.2014.2383071).
23. 23)
  - 4. Springer, D.B., et al: ‘Logistic regression-HSMM-based heart sound segmentation’, IEEE Trans. Biomed. Eng., 2016, 63, (4), pp. 822–832.
24. 24)
  - 11. Moukadem, A., et al: ‘A robust heart sounds segmentation module based on S-transform’, Biomed. Signal Process. Control, 2013, 8, (3), pp. 273–281 (doi: 10.1016/j.bspc.2012.11.008).
25. 25)
  - 20. Wang, P., et al: ‘First heart sound detection for phonocardiogram segmentation’. Proc. IEEE 27th Annual Conf. Engineering in Medicine and Biology Society, January 2005, pp. 5519–5522.
26. 26)
  - 23. Hebden, J.E., Torry, I.N.: ‘Neural network and conventional classifiers to distinguish between first and second heart sound’. Proc. IEE Colloquium Artificial Intelligence Methods for Biomedical Data Processing, April 1996, vol. 3, pp. 1–6.
27. 27)
  - 18. Kumar, D., et al: ‘Detection of S1 and S2 heart sounds by high frequency signatures’. Proc. IEEE 28th Annual Int. Conf. Engineering in Medicine and Biology Society, vol. 1, August/September 2006, pp. 1410–1416.
28. 28)
  - 13. Mondal, A., et al: ‘Boundary estimation of cardiac events S1 and S2 based on Hilbert transform and adaptive thresholding approach’. Proc. Indian Conf. Medical Informatics and Telemedicine, March 2013, pp. 43–47.
29. 29)
  - 12. Iwata, A., Ishii, N., Suzumura, N., et al: ‘Algorithm for detecting the first and the second heart sounds by spectral tracking’, Med. Biol. Eng. Comput., 1980, 18, (1), pp. 19–26 (doi: 10.1007/BF02442475).
30. 30)
  - 4. Papadaniil, C., Hadjileontiadis, L.: ‘Efficient heart sound segmentation and extraction using ensemble empirical mode decomposition and kurtosis features’, IEEE J. Biomed. Health Inf., 2014, 18, (4), pp. 1138–1152 (doi: 10.1109/JBHI.2013.2294399).

Login

Not registered yet?

Share

Tools

Login to add to favourites

Key

Wavelet-based fundamental heart sound recognition method using morphological and interval features

References

Related content