Advertisement

A Robust Algorithm for Segmentation of Phonocardiography Signal Using Tunable Quality Wavelet Transform

  • Puneet Kumar Jain
  • Anil Kumar Tiwari
Original Article
  • 71 Downloads

Abstract

Segmentation of the phonocardiography (PCG) signal is of importance for diagnosis of heart health and the same is recently reported to be done with tunable quality Wavelet transform (TQWT). In the reported method, parameters of TQWT are tuned to vary the frequency range of the approximation level such that its kurtosis gets maximized. Kurtosis will be larger for the fundamental heart sounds (FHS) as compared to the murmur because probability distribution of FHS is super-Gaussian and murmur is sub-Gaussian. However, this is observed in some pathological cases with sharp peak murmurs, murmur and FHS are indistinguishable using kurtosis. Since Fano factor gives a measure of relative variability, we propose to use Fano-factor for selection of the sub-band, in place of Kurtosis. The proposed method decomposes the signal up to twenty levels only once as compared to approximately 55 times in the reported method and then selects a sub-band considering the detailed levels only. This result into 25 times reduction in computational cost. Moreover, exclusion of the approximation level also helps in reduction of the real-life noise. Another contribution of the paper is the adaptive thresholding method used to suppress the noise level from the selected level that improves the segmentation accuracy in the presence of noise. Experiments are performed on PCG signals of various normal and pathological cases, with and without simulated noise using white Gaussian, pink, and red noise models, separately. The obtained results show the efficiency of the proposed method to segment the PCG signal in the presence of noise, murmurs, and both.

Keywords

Heart sound segmentation Phonocardiography Tunable quality Wavelet transform Wavelet denoising Fano factor 

References

  1. 1.
    Vuyisile, N., Julius, G., Thomas, S., John, S. G., Christopher, G. S., & Maurice, E. (2006). Burden of valvular heart diseases: A population-based study. The Lancet, 368, 1005–1011. doi: 10.1016/S0140-6736(06)69208-8.CrossRefGoogle Scholar
  2. 2.
    Enriquez-Sarano, M., Akins, C. W., & Vahanian, A. (2009). Mitral regurgitation. The Lancet, 373(9672), 1382–1394. doi: 10.1016/S0140-6736(09)60692-9.CrossRefGoogle Scholar
  3. 3.
    Bach, D. S., Siao, D., Girard, S. E., Duvernoy, C., McCallister, B. D., & Gualano, S. K. (2009). Evaluation of patients with severe symptomatic aortic stenosis who do not undergo aortic valve replacement: The potential role of subjectively overestimated operative risk. Circulation: Cardiovascular Quality and Outcomes, 2(6), 533–539. doi: 10.1161/CIRCOUTCOMES.109.848259.Google Scholar
  4. 4.
    Kao, W.-C., & Wei, C.-C. (2011). Automatic phonocardiograph signal analysis for detecting heart valve disorders. Expert Systems with Applications, 38(6), 6458–6468. doi: 10.1016/j.eswa.2010.11.100.CrossRefGoogle Scholar
  5. 5.
    Yuenyong, S., Nishihara, A., Kongprawechnon, W., & Tungpimolrut, K. (2011). A framework for automatic heart sound analysis without segmentation. Biomedical Engineering Online, 10(1), 13. doi: 10.1186/1475-925X-10-13.CrossRefGoogle Scholar
  6. 6.
    Moukadem, A., Dieterlen, A., Hueber, N., & Brandt, C. (2013). A robust heart sounds segmentation module based on s-transform. Biomedical Signal Processing and Control, 8(3), 273–281. doi: 10.1016/j.bspc.2012.11.008.CrossRefGoogle Scholar
  7. 7.
    Jain, P. K., & Tiwari, A. K. (2014). Heart monitoring systems-a review. Computers in Biology and Medicine, 54, 1–13. doi: 10.1016/j.compbiomed.2014.08.014.CrossRefGoogle Scholar
  8. 8.
    Sanei, S., Ghodsi, M., & Hassani, H. (2011). An adaptive singular spectrum analysis approach to murmur detection from heart sounds. Medical Engineering & Physics, 33(3), 362–367. doi: 10.1016/j.medengphy.2010.11.004.CrossRefGoogle Scholar
  9. 9.
    Dokur, Z., & Imez, T. (2008). Heart sound classification using wavelet transform and incremental self-organizing map. Digital Signal Processing, 18(6), 951–959. doi: 10.1016/j.dsp.2008.06.001.CrossRefGoogle Scholar
  10. 10.
    Patidar, S., & Pachori, R. B. (2013). Segmentation of cardiac sound signals by removing murmurs using constrained tunable-q wavelet transform. Biomedical Signal Processing and Control, 8(6), 559–567. doi: 10.1016/j.bspc.2013.05.004.CrossRefGoogle Scholar
  11. 11.
    Oliveira, J., Castro, A., Coimbra, M. (2014). Exploring embedding matrices and the entropy gradient for the segmentation of heart sounds in real noisy environments. In 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, pp. 3244–3247. doi: 10.1109/EMBC.2014.6944314.
  12. 12.
    Jiang, Z., & Choi, S. (2006). A cardiac sound characteristic waveform method for in-home heart disorder monitoring with electric stethoscope. Expert Systems with Applications, 31(2), 286–298.CrossRefGoogle Scholar
  13. 13.
    Tang, H., Li, T., Qiu, T., & Park, Y. (2012). Segmentation of heart sounds based on dynamic clustering. Biomedical Signal Processing and Control, 7(5), 509–516. doi: 10.1016/j.bspc.2011.09.002.CrossRefGoogle Scholar
  14. 14.
    Yadollahi, A., & Moussavi, Z. M. K. (2006). A robust method for heart sounds localization using lung sounds entropy. IEEE Transactions on Biomedical Engineering, 53(3), 497–502. doi: 10.1109/TBME.2005.869789.CrossRefGoogle Scholar
  15. 15.
    Gavrovska, A., Bogdanovi, V., Reljin, I., & Reljin, B. (2014). Automatic heart sound detection in pediatric patients without electrocardiogram reference via pseudo-affine wignerville distribution and haar wavelet lifting. Computer Methods and Programs in Biomedicine, 113(2), 515–528. doi: 10.1016/j.cmpb.2013.11.018.CrossRefGoogle Scholar
  16. 16.
    Ramos, J. P., Carvalho, P., Coimbra, M. (2013). Towards a time-feature independent phonocardiogram segmentation. In 35th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), pp. 2116–2119. doi: 10.1109/EMBC.2013.6609951.
  17. 17.
    Atbi, A., Debbal, S. M., Meziani, F., & Meziane, A. (2013). Separation of heart sounds and heart murmurs by hilbert transform envelogram. Journal of Medical Engineering and Technology, 37(6), 375–387. doi: 10.3109/03091902.2013.816379.CrossRefGoogle Scholar
  18. 18.
    Gupta, C. N., Palaniappan, R., Swaminathan, S., & Krishnan, S. M. (2007). Neural network classification of homomorphic segmented heart sounds. Applied Soft Computing., 7(1), 286–297. doi: 10.1016/j.asoc.2005.06.006.CrossRefGoogle Scholar
  19. 19.
    Zia, M. K., Griffel, B., Semmlow, J. L. (2011). Robust detection of background noise in phonocardiograms. In 1st Middle East Conference on Biomedical Engineering, pp. 130–133. doi: 10.1109/MECBME.2011.5752082.
  20. 20.
    Boutana, D., Benidir, M., & Barkat, B. (2011). Segmentation and identification of some pathological phonocardiogram signals using time-frequency analysis. Signal Processing, IET, 5(6), 527–537. doi: 10.1049/iet-spr.2010.0013.MathSciNetCrossRefGoogle Scholar
  21. 21.
    Paska, M. P., Gavrovska, A. M., Reljin, N. B. (2014). Identification of fundamental heart sounds from PCG using blanket fractal dimension. In: Cardiovascular Oscillations (ESGCO), 8th Conference of the European Study Group on, pp. 123–124. doi: 10.1109/ESGCO.2014.6847550.
  22. 22.
    Choi, S., & Jiang, Z. (2008). Comparison of envelope extraction algorithms for cardiac sound signal segmentation. Expert Systems with Applications, 34(2), 1056–1069.CrossRefGoogle Scholar
  23. 23.
    Kumar, D., Carvalho, P., Antunes, M., Henriques, J., Eugenio, L., Schmidt, R., Habetha, J. (2006). Detection of s1 and s2 heart sounds by high frequency signatures. In Engineering in Medicine and Biology Society, EMBS ‘06. 28th Annual International Conference of the IEEE, pp. 1410–1416. doi: 10.1109/IEMBS.2006.260735.
  24. 24.
    Safara, F., Doraisamy, S., Azman, A., Jantan, A. (2012). Heart sounds clustering using a combination of temporal, spectral and geometric features. Computing in Cardiology, 217–220.Google Scholar
  25. 25.
    Sun, S., Jiang, Z., Wang, H., & Fang, Y. (2014). Automatic moment segmentation and peak detection analysis of heart sound pattern via short-time modified Hilbert transform. Computer Methods and Programs in Biomedicine, 114(3), 219–230. doi: 10.1016/j.cmpb.2014.02.004.CrossRefGoogle Scholar
  26. 26.
    Ahlstrom, C. (2008). Nonlinear phonocardiographic signal processing. PhD thesis, Linkoping University.Google Scholar
  27. 27.
    Kudriavtsev, V., Polyshchuk, V., & Roy, D. L. (2007). Heart energy signature spectrogram for cardiovascular diagnosis. Biomedical Engineering Online, 6(1), 1–22. doi: 10.1186/1475-925X-6-16.CrossRefGoogle Scholar
  28. 28.
    Bajelani, K., Navidbakhsh, M., Behnam, H., Doyle, J. D., & Hassani, K. (2013). Detection and identification of first and second heart sounds using empirical mode decomposition. Proceedings of the Institution of Mechanical Engineers. Part H. Journal of Engineering in Medicine, 227(9), 976–987. doi: 10.1177/0954411913493734.CrossRefGoogle Scholar
  29. 29.
    Rajan, S., Budd, E., Stevenson, M., Doraiswami, R. (2006). Unsupervised and uncued segmentation of the fundamental heart sounds in phonocardiograms using a time-scale representation. In Engineering in Medicine and Biology Society. EMBS ‘06. 28th Annual International Conference of the IEEE, pp. 3732–3735. doi: 10.1109/IEMBS.2006.260777.
  30. 30.
    Vaisman, S., Salem, S. Y., Holcberg, G., & Geva, A. B. (2012). Passive fetal monitoring by adaptive wavelet denoising method. Computers in Biology and Medicine, 42(2), 171–179. doi: 10.1016/j.compbiomed.2011.11.005.CrossRefGoogle Scholar
  31. 31.
    Song, D., Jia, L., Lu, Y., Tao, L. (2012). Heart sounds monitor and analysis in noisy environments. In Systems and Informatics (ICSAI), International Conference on, pp. 1677–1681. doi: 10.1109/ICSAI.2012.6223364.
  32. 32.
    Kumar, D., Carvalho, P., Antunes, M., Henriques, J., Melo, A. S. E., Schmidt, R., Habetha, J. (2007). Third heart sound detection using wavelet transform-simplicity filter. In 29th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, pp. 1277–1281. doi: 10.1109/IEMBS.2007.4352530.
  33. 33.
    Selesnick, I. W. (2011). Wavelet transform with tunable q-factor. IEEE Transactions on Signal Processing, 59(8), 3560–3575. doi: 10.1109/TSP.2011.2143711.MathSciNetCrossRefGoogle Scholar
  34. 34.
    Gradolewski, D., & Redlarski, G. (2014). Wavelet-based denoising method for real phonocardiography signal recorded by mobile devices in noisy environment. Computers in Biology and Medicine, 52, 119–129. doi: 10.1016/j.compbiomed.2014.06.011.CrossRefGoogle Scholar
  35. 35.
    Fano, U. (1947). Ionization yield of radiations. II. The fluctuations of the number of ions. Physical Review, 72, 26–29. doi: 10.1103/PhysRev.72.26.CrossRefGoogle Scholar
  36. 36.
    Singh, J., & Anand, R. S. (2007). Computer aided analysis of phonocardiogram. Journal of Medical Engineering & Technology, 31(5), 319–323. doi: 10.1080/03091900500282772.CrossRefGoogle Scholar
  37. 37.
    Otsu, N. (1979). A threshold selection method from gray-level histograms. Systems, Man and Cybernetics, IEEE Transactions on, 9(1), 62–66.MathSciNetCrossRefGoogle Scholar
  38. 38.
    Meziani, F., Debbal, S. M., & Atbi, A. (2012). Analysis of phonocardiogram signals using wavelet transform. Journal of Medical Engineering & Technology, 36(6), 283–302. doi: 10.3109/03091902.2012.684830.CrossRefGoogle Scholar
  39. 39.
    Man, K. F., Tang, K. S., & Kwong, S. (1996). Genetic algorithms: Concepts and applications [in engineering design]. IEEE Transactions on Industrial Electronics, 43(5), 519–534. doi: 10.1109/41.538609.CrossRefGoogle Scholar
  40. 40.
    Pearson, K. (1905). Das fehlergesetz und seine verallgemeinerungen durch fechner und pearson. a rejoinder. biometrika, Biometrika, 4(1–2), 169–212. arXiv:http://biomet.oxfordjournals.org/content/4/1-2/169.full.pdf+html,
  41. 41.
    Westfall, P. (2014). Kurtosis as peakedness, 1905. 2014. r.i.p. The American Statistician, 68(3), 191–195. doi: 10.1080/00031305.2014.917055.MathSciNetCrossRefGoogle Scholar
  42. 42.
    Cox, D. R., & Lewis, P. W. (1966). The statistical analysis of series of events. London: Methuen.CrossRefzbMATHGoogle Scholar
  43. 43.
    Naseri, H., & Homaeinezhad, M. (2013). Detection and boundary identification of phonocardiogram sounds using an expert frequency-energy based metric. Annals of Biomedical Engineering, 41(2), 279–292. doi: 10.1007/s10439-012-0645-x.CrossRefGoogle Scholar
  44. 44.
    Luo, G., Zhang, D. (2012). Wavelet denoising, advances in wavelet theory and their applications in engineering, physics and technology, Dr. Dumitru Baleanu, intechopen.Google Scholar
  45. 45.
    Messer, S. R., Agzarian, J., & Abbott, D. (2001). Optimal wavelet denoising for phonocardiograms. Microelectronics Journal, 32(12), 931–941. doi: 10.1016/S0026-2692(01)00095-7.CrossRefGoogle Scholar
  46. 46.
    Liang, H., Lukkarinen, S., & Hartimo, I. (1997). Heart sound segmentation algorithm based on heart sound envelogram. Computers in Cardiology, 1997, 105–108. doi: 10.1109/CIC.1997.647841.Google Scholar
  47. 47.
    Institute, T. H. Heart sounds podcast series. Retrieved from June 19, 2016, www.texasheart.org/Education/CME/explore/events/eventdetail_6456.cfm.
  48. 48.
    Zhivomirov, H. Pink, red, blue and violet noise generation with matlab implementation. Retrieved from April 19, 2016, http://www.mathworks.com/matlabcentral/profile/authors/3571337-hristo-zhivomirov.
  49. 49.
    Toole, J. O., Mesbah, M., Boashash, B. (2005). A discrete time and frequency wignerville distribution: Properties and implementation. In 8th International Symposium on DSP and Communication Systems, DSPCS’2005, pp. 19–21.Google Scholar

Copyright information

© Taiwanese Society of Biomedical Engineering 2017

Authors and Affiliations

  1. 1.Center for Information and Communication TechnologyIndian Institute of Technology JodhpurJodhpurIndia
  2. 2.Department of Electrical EngineeringIndian Institute of Technology JodhpurJodhpurIndia

Personalised recommendations