Download PDF
Methods Inf Med 2007; 46(02): 135-141
DOI: 10.1055/s-0038-1625394
Original Article
Schattauer GmbH

Wavelet-based Segmentation and Feature Extraction of Heart Sounds for Intelligent PDA-based Phonocardiography

H. Nazeran
1   Electrical and Computer Engineering, The University of Texas at El Paso, El Paso, Texas, USA
› Author Affiliations
Further Information

Publication History

Publication Date:
11 January 2018 (online)

    Permissions and Reprints

Summary

Objectives : Many pathological conditions of the cardiovascular system cause murmurs and aberrations in heart sounds. Phonocardiography provides the clinician with a complementary tool to record the heart sounds heard during auscultation. The advancement of intracardiac phonocardiography combined with modern digital signal processing techniques has strongly renewed researchers' interest in studying heart sounds and murmurs.

The aim of this work is to investigate the applicability of different spectral analysis methods to heart sound signals and explore their suitability for PDA-based implementation.

Methods : Fourier transform (FT), short-time Fourier transform (STFT) and wavelet transform (WT) are used to perform spectral analysis on heart sounds. A segmentation algorithm based on Shannon energy is used to differentiate between first and second heartsounds. Then wavelet transform is deployed again to extract 64 features of heart sounds.

Results : The FT provides valuable frequency information but the timing information is lost during the transformation process. The STFT or spectrogram provides valuable time-frequency information but there is a trade-off between time and frequency resolution. Waveletanalysis, however, does not suffer from limitations of the STFT and provides adequate time and frequency resolution to accurately characterize the normal and pathological heartsounds.

Conclusions : The results show that the wavelet-based segmentation algorithm is quite effective in localizing the important components of both normal and abnormal heart sounds. They also demonstrate that wavelet-based feature extraction provides suitable feature vectors which are clearly differentiable and useful for automatic classification of heart sounds.

Keywords

Advanced biomedical signal processing - feature extraction - heart sound analysis - intelligent phonocardiography - wavelet decomposition
 

  • References

  • 1. Rangayyan RM, Lehner RJ. Phonocardiogram signal analysis: A review. Critical Reviews in Biomedical Engineering 1988; 15: 211-236.
    PubMedSearch in Google Scholar
  • 2. Durand LG, Pibarot P. Digital signal processing of the phonocardiogram: Review of the most recent advancements. Critical Review™ in Biomedical Engineering 1995; 23: 116-219.
    PubMedSearch in Google Scholar
  • 3. Liang H, Lukkarinen S, Hartimo I. Heart sound segmentation algorithm based on heart sound envelogram. Computer in Cardiology 1997; 24: 105-108.
    PubMedSearch in Google Scholar
  • 4. Liang H, Lukkarinen S, Hartimo I. A heart sound segmentation algorithm using wavelet decomposition and reconstruction. Proceedings of the IEEE EMBS, 19th Annual International Conference 1997: 1630-1633.
    PubMedSearch in Google Scholar
  • 5. Say O, Dokur Z, Ölmez T. Classification of heart sounds by using wavelet transforms. Proceedings of the Second Joint EMBS/BMES Conference 2002; 128-129.
    PubMedSearch in Google Scholar
  • 6. Obaidat MS, Matalgah MM. Performance of the short time Fourier transform and wavelet transform to phonocardiogram signal analysis. Symposium on applied computing: technological challenges of the 1990’s 1992; 856-862.
    PubMedSearch in Google Scholar
  • 7. Doyle JD, Gopakumaran B, Smith WA. Color spectrographic analysis of the phonocardiogram: A future noninvasive cardiac monitoring technology?. Proceedings of the IEEE EMBS, 25th Annual International Conference 2003: 2251-2554.
    PubMedSearch in Google Scholar
  • 8. El-Asir B, Kahadra L, Al-Abbasi AH, Mohamed MM. Time-frequency analysis of heart sounds. IEEE TENCON - Digital Signal Processing Applications 1996; 553-558.
    PubMedSearch in Google Scholar
  • 9. Lee JJ, Lee SM, Young K, Min HK, Hong SH. Comparison between short time Fourier and wavelet transform for feature extraction of heart sounds. IEEE TENCON 1999; 1547-1550.
    PubMedSearch in Google Scholar
  • 10. Buthan E, Yetkin T. Optimal continuous wavelet analysis of phonocardiogram signals. Proceedings of the International Conference on Signal Processing 2003; 1 (02) 188-192.
    PubMedSearch in Google Scholar
  • 11. Durand LG, Blanchard M, Cloutier G, Sabbah HN, Stein PD. Comparison of pattern recognition methods for computer-assisted classification of spectra of heart sounds in patients with a porcine bioprosthetic valve implanted in the mitral position IEEE Trans. BME 1990; 37 (12) 1121-1129.
    CrossrefPubMedSearch in Google Scholar
  • 12. Brusco M, Nazeran H. Digital phonocardiography: A PDA-based approach. Proceedings of the IEEE EMBS, 26th Annual International Conference 2004: 2299-2302.
    PubMedSearch in Google Scholar
  • 13. Mason D. Listening to Heart Sounds and Murmurs. 2nd edition. Philadelphia: Davis Publishers; 2000. Audio CDs
    PubMed
  • 14. Brusco M. Development of a PDA-based Digital Phonocardiograph. MS Thesis. The University of Texas at El Paso, 2005
    PubMedSearch in Google Scholar