Skip to main content

Advertisement

SpringerLink
Log in

Detection and Boundary Identification of Phonocardiogram Sounds Using an Expert Frequency-Energy Based Metric

  • Published:
Annals of Biomedical Engineering Aims and scope Submit manuscript

Abstract

This paper presents a new method to detect and to delineate phonocardiogram (PCG) sounds. Toward this objective, after preprocessing the PCG signal, two windows were moved on the preprocessed signal, and in each analysis window, two frequency-and amplitude-based features were calculated from the excerpted segment. Then, a synthetic decision making basis was devised by combining these two features for being used as an efficient detection-delineation decision statistic, (DS). Next, local extremums and locations of minimum slopes of the DS were determined by conducting forward–backward local investigations with the purpose of detecting sound incidences and their boundaries. In order to recognize the delineated PCG sounds, first, S1 and S2 were detected. Then, a new DS was regenerated from the signal whose S1 and S2 were eliminated to detect occasional S3 and S4 sounds. Finally, probable murmurs and souffles were spotted. The proposed algorithm was applied to 52 min PCG signals gathered from patients with different valve diseases. The provided database was annotated by some cardiology experts equipped by echocardiography and appropriate computer interfaces. The acquisition landmarks were in 2R (aortic), 2L (pulmonic), 4R (apex) and 4L (tricuspid) positions. The acquisition sensor was an electronic stethoscope (3 M Littmann® 3200, 4 kHz sampling frequency). The operating characteristics of the proposed method have an average sensitivity Se = 99.00% and positive predictive value PPV = 98.60% for sound type recognition (i.e., S1, S2, S3 or S4).

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Figure 1
Figure 2
Figure 3
Figure 4
Figure 5
Figure 6
Figure 7
Figure 8
Figure 9
Figure 10
Figure 11

Similar content being viewed by others

Notes

  1. The envelope of a signal is the “apparent” signal seen by tracking successive local peak values and pretending that they are connected.

Abbreviations

ASF:

Adaptive Smoothing Filtering

PCG:

Phonocardiogram

GSF:

Gaussian Smoothing Filtering

DS:

Decision Statistic

s.t.:

Subject to

TF:

Time-Frequency

STFA:

Short-Time Frequency Amplifier

IPWT:

Inverse Packet Wavelet Transform

PWT:

Packet Wavelet Transform

AS:

Aortic Stenosis

AR:

Aortic Regurgitation

MR:

Mitral Regurgitation

MS:

Mitral Stenosis

Acc:

Accuracy

f f :

Frequency amplifier feature

f e :

Amplitude-based feature (envelope)

f ef :

Frequency-amplitude-based feature

l :

Window length

\( \tau_{\text{s}} \) :

Segmentation threshold

S(t):

A generic PCG signal

S n(t):

Normalized PCG signal

\( \tau_{\text{c}} \) :

Wavelet denoising threshold

σ:

Smoothing parameter

T p :

Periodicity time

References

  1. Ari, S., K. Hembram, and G. Saha. Detection of cardiac abnormality from PCG signal using LMS based least square SVM classifier. Expert Syst. Appl. 37(12):8019–8026, 2010.

    Article  Google Scholar 

  2. Ari, S., P. Kumar, and G. Saha. On an algorithm for boundary estimation of commonly occurring heart valve diseases in time domain. Paper presented at the 2006 Annual India Conference, INDICON, 2006.

  3. Chebil, J., and J. Al-Nabulsi. Classification of heart sound signals using discrete wavelet analysis. Int. J. Soft Comput. 2:37–41, 2007.

    Google Scholar 

  4. Cherif, L. H., S. M. Debbal, and F. Bereksi-Reguig. Choice of the wavelet analyzing in the phonocardiogram signal analysis using the discrete and the packet wavelet transform. Expert Syst. Appl. 37(2):913–918, 2010.

    Article  Google Scholar 

  5. Choi, S. Detection of valvular heart disorders using wavelet packet decomposition and support vector machine. Expert Syst. Appl. 35(4):1679–1687, 2008.

    Article  Google Scholar 

  6. Choi, S., and Z. Jiang. Comparison of envelope extraction algorithms for cardiac sound signal segmentation. Expert Syst. Appl. 34(2):1056–1069, 2008.

    Article  Google Scholar 

  7. Choi, S., and Z. Jiang. Cardiac sound murmurs classification with autoregressive spectral analysis and multi-support vector machine technique. Comput. Biol. Med. 40(1):8–20, 2010.

    Article  PubMed  Google Scholar 

  8. Ciaccio, E. J., A. B. Biviano, W. Whang, J. Coromilas, and H. Garan. A new transform for the analysis of complex fractionated atrial electrograms. BioMed. Eng. OnLine 12(10):35, 2011.

    Article  Google Scholar 

  9. Ciaccio, E. J., A. B. Biviano, W. Whang, A. L. Wit, J. Coromilas, and H. Garan. Optimized measurement of activation rate at left atrial sites with complex fractionated electrograms during atrial fibrillation. J. Cardiovasc. Electrophysiol. 21(2):133–143, 2010.

    Article  PubMed  Google Scholar 

  10. Ciaccio, E. J., A. B. Biviano, W. Whang, A. L. Wit, H. Garan, and J. Coromilas. New methods for estimating local electrical activation rate during atrial fibrillation. Heart Rhythm 6(1):21–32, 2009.

    Article  PubMed  Google Scholar 

  11. Debbal, S. M., and F. Bereksi-Reguig. Time-frequency analysis of the first and the second heartbeat sounds. Appl. Math. Comput. 184(2):1041–1052, 2007.

    Article  Google Scholar 

  12. Dokur, Z., and T. Ölmez. Heart sound classification using wavelet transform and incremental self-organizing map. Digit. Signal Process. Rev. J. 18(6):951–959, 2008.

    Article  Google Scholar 

  13. Dokur, Z., and T. Ölmez. Feature determination for heart sounds based on divergence analysis. Digit. Signal Process. Rev. J. 19(3):521–531, 2009.

    Article  Google Scholar 

  14. Erçelebi, E. Second generation wavelet transform-based pitch period estimation and voiced/unvoiced decision for speech signals. Appl. Acoust. 64(1):25–41, 2003.

    Article  Google Scholar 

  15. Gamero, L. G., and R. Watrous. Detection of the first and second heart sound using probabilistic models. Paper presented at the Annual International Conference of the IEEE Engineering in Medicine and Biology—Proceedings, vol. 3, pp. 2877–2880, 2003.

  16. Gill, D., N. Gavrieli, and N. Intrator. Detection and identification of heart sounds using homomorphic envelogram and self-organizing probabilistic model. Paper presented at the Computers in Cardiology, Vol. 32, pp. 957–960, 2005.

  17. González, G., R. E. Badra, R. Medina, and J. Regidor. Period estimation using minimum entropy deconvolution (MED). Signal Process. 41(1):91–100, 1995.

    Article  Google Scholar 

  18. Gupta, C. N., R. Palaniappan, S. Swaminathan, and S. M. Krishnan. Neural network classification of homomorphic segmented heart sounds. Appl. Soft Comput. J. 7(1):286–297, 2007.

    Article  Google Scholar 

  19. Homaeinezhad, M. R., M. Aghaee, H. N. Toosi, A. Ghaffari, and R. Rahmani. Aapplication of the discrete wavelet transform for the robust detection of the impulsive incidences: application to arterial blood pressure characteristic events detectiondelineation. Int. J. Wavelets Multires. Inf. Process. 9(5):813–842, 2011.

    Article  Google Scholar 

  20. Homaeinezhad, M. R., P. Sabetian, A. Feizollahi, A. Ghaffari, and R. Rahmani. Parametric modelling of cardiac system multiple measurement signals: An open-source computer framework for performance evaluation of ECG, PCG and ABP event detectors. J. Med. Eng. Technol. 36(2):117–134, 2012.

    Article  PubMed  CAS  Google Scholar 

  21. http://www.rhc.ac.ir/en/index.htm.

  22. Jiang, Z., and S. Choi. A cardiac sound characteristic waveform method for in-home heart disorder monitoring with electric stethoscope. Expert Syst. Appl. 31(2):286–298, 2006.

    Article  Google Scholar 

  23. Kumar, D., P. Carvalho, M. Antunes, R. P. Paiva, and J. Henriques. Noise detection during heart sound recording using periodicity signatures. Physiol. Measurement 32(5):599–618, 2011.

    Article  CAS  Google Scholar 

  24. Kumar, D., P. Carvalho, M. Antunes, J. Henriques, A. Sá e Melo, R. Schmidt, and J. Habetha. Third heart sound detection using wavelet transform-simplicity filter. Conference Proceedings: Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society Conference, 2007, pp. 1277–1281.

  25. Naseri, H., and M. R. Homaeinezhad. Computerized quality assessment of phonocardiogram signal measurement-acquisition parameters. J. Med. Eng. Technol. 36(6):308–318, 2012.

    Google Scholar 

  26. Nazeran, H. Wavelet-based segmentation and feature extraction of heart sounds for intelligent PDA-based phonocardiography. Methods Inf. Med. 46(2):135–141, 2007.

    PubMed  CAS  Google Scholar 

  27. Schmidt, S. E., C. Holst-Hansen, C. Graff, E. Toft, and J. J. Struijk. Segmentation of heart sound recordings by a duration-dependent hidden markov model. Physiol. Measurement 31(4):513–529, 2010.

    Article  CAS  Google Scholar 

  28. Tseng et al. Detection of the third and fourth heart sounds using Hilbert-Huang transform. BioMed. Eng. OnLine 11:8, 2012.

  29. Oskiper, T., and R. Watrous. Detection of the first heart sound using a time-delay neural network. Paper presented at the Computers in Cardiology, Vol. 29, pp. 537–540.

  30. Yan, Z., Z. Jiang, A. Miyamoto, and Y. Wei. The moment segmentation analysis of heart sound pattern. Comput. Methods Progr. Biomed. 98(2):140–150, 2010.

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Department of Mechanical Engineering, Faculty of Mechanical Engineering, K. N. Toosi University of Technology, P.O. Box 19395-1999, Tehran, Iran

    H. Naseri & M. R. Homaeinezhad

  2. CardioVascular Research Group (CVRG), K. N. Toosi University of Technology, Tehran, Iran

    H. Naseri & M. R. Homaeinezhad

Authors
  1. H. Naseri
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. M. R. Homaeinezhad
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to H. Naseri.

Additional information

Associate Editor Tingrui Pan oversaw the review of this article.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Naseri, H., Homaeinezhad, M.R. Detection and Boundary Identification of Phonocardiogram Sounds Using an Expert Frequency-Energy Based Metric. Ann Biomed Eng 41, 279–292 (2013). https://doi.org/10.1007/s10439-012-0645-x

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10439-012-0645-x

Keywords

Search

Navigation