Location via proxy:   [ UP ]  
[Report a bug]   [Manage cookies]                
Skip to main content
Springer Nature Link
Log in

Classification of heart sounds based on the combination of the modified frequency wavelet transform and convolutional neural network

  • Original Article
  • Published:
Medical & Biological Engineering & Computing Aims and scope Submit manuscript

Abstract

We purpose a novel method that combines modified frequency slice wavelet transform (MFSWT) and convolutional neural network (CNN) for classifying normal and abnormal heart sounds. A hidden Markov model is used to find the position of each cardiac cycle in the heart sound signal and determine the exact position of the four periods of S1, S2, systole, and diastole. Then the one-dimensional cardiac cycle signal was converted into a two-dimensional time-frequency picture using the MFSWT. Finally, two CNN models are trained using the aforementioned pictures. We combine two CNN models using sample entropy (SampEn) to determine which model is used to classify the heart sound signal. We evaluated our model on the heart sound public dataset provided by the PhysioNet Computing in Cardiology Challenge 2016. Experimental classification performance from a 10-fold cross-validation indicated that sensitivity (Se), specificity (Sp) and mean accuracy (MAcc) were 0.95, 0.93, and 0.94, respectively. The results showed the proposed method can classify normal and abnormal heart sounds with efficiency and high accuracy.

Block diagram of heart sound classification.

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

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

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

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6

Similar content being viewed by others

References

  1. Potes C, Parvaneh S, Rahman A, Conroy B Ensemble of feature-based and deep learning-based classifiers for detection of abnormal heart sounds. In: Computing in Cardiology Conference, 11–14 Sept. 2016. IEEE, pp 621–624

  2. Whitaker BM, Suresha PB, Liu C, Clifford G, Anderson D (2017) Combining sparse coding and time-domain features for heart sound classification. Physiol Meas 38:1701–1713

    Article  Google Scholar 

  3. Langley P, Murray A (2017) Heart sound classification from unsegmented phonocardiograms. Physiol Meas 38:1658–1670

    Article  Google Scholar 

  4. Bobillo ID A Tensor approach to heart sound classification. In: Computing in Cardiology Conference, Vancouver, 2016. IEEE, pp 629–632

  5. Homsi MN, Medina N, Quintero N, Perpiñan G, Quintana A, Warrick P (2016) Automatic heart sound recording classification using a nested set of ensemble algorithms. In: Computing in Cardiology Conference. IEEE, pp 817–820

  6. Abdollahpur M, Ghaffari A, Ghiasi S, Mollakazemi MJ (2017) Detection of pathological heart sounds. Physiol Meas 38:1616–1630

    Article  Google Scholar 

  7. Safara F (2015) Cumulant-based trapezoidal basis selection for heart sound classification. Med Biol Eng Comput 53:1153–1164. https://doi.org/10.1007/s11517-015-1394-4

    Article  PubMed  Google Scholar 

  8. Wenjie Z, Jiqing H, Shiwen D (2017) Heart sound classification based on scaled spectrogram and partial least squares regression. Biomed Signal Process Control 32:20–28

  9. Baris B, Ioannis G, Yannis S (2018) A study of time-frequency features for CNN-based automatic heart sound classification for pathology detection. Comput Biol Med 100:132–143

    Article  Google Scholar 

  10. Rubin J, Rui A, Ganguli A, Nelaturi S, Sricharan K Classifying heart sound recordings using deep convolutional neural networks and mel-frequency cepstral coefficients. In: Computing in Cardiology Conference, 2016. IEEE, pp 813–816

  11. Han W, Yang Z, Lu J (2018) Supervised threshold-based heart sound classification algorithm. Physiol Meas 39:115011

    Article  Google Scholar 

  12. Cheng XF, Huang JZ, Li Y, Gui G (2019) Design and application of a laconic heart sound neural network. IEEE Access 7:124417–124425

    Article  Google Scholar 

  13. Montesinos L, Castaldo R, Pecchia L (2018) On the use of approximate entropy and sample entropy with centre of pressure time-series. J NeuroEng Rehabil 15:116

  14. Richman JS, Moorman JR (2000) Physiological time-series analysis using approximate entropy and sample entropy. Am J Phys Heart Circ Phys 278:H2039–H2049. https://doi.org/10.1152/ajpheart.2000.278.6.H2039

    Article  CAS  Google Scholar 

  15. Liu C, Springer D, Li Q, Moody B, Juan RA, Chorro FJ, Castells F, Roig JM, Silva I, Johnson AEW (2016) An open access database for the evaluation of heart sound algorithms. Physiol Meas 37:2181–2213

    Article  Google Scholar 

  16. Springer D, Tarassenko L, Clifford G (2016) Logistic regression-HSMM-based heart sound segmentation. IEEE Trans Biomed Eng 63:822–832. https://doi.org/10.1109/TBME.2015.2475278

    Article  PubMed  Google Scholar 

  17. Oki T, Tabata T, Yamada H, Manabe K, Fukuda K, Abe M, Onose Y, Iuchi A, Fukuda N, Ito S (1998) Difference in systolic motion velocity of the left ventricular posterior wall in patients with asymmetric septal hypertrophy and prior anteroseptal myocardial infarction. Evaluation by pulsed tissue Doppler imaging. Jpn Heart J 39:163–172

    Article  CAS  Google Scholar 

  18. Cuschieri A, Luo K, Li J, Wang Z (2017) Patient-specific deep architectural model for ECG classification. J Healthc Eng 2017:05–13. https://doi.org/10.1155/2017/4108720

  19. Kan L, Du K, Cai Z, Li J, Wang Z, Cuschieri A A (2018) modified frequency slice wavelet transform for physiological signal time-frequency analysis. In: Chinese Automation Congress. IEEE, pp 3441–3444. doi:https://doi.org/10.1109/CAC.2017.8243375

  20. Xu X, Wei S, Ma C, Kan L, Li Z, Liu C (2018) Atrial fibrillation beat identification using the combination of modified frequency slice wavelet transform and convolutional neural networks. J Healthc Eng 2018:1–8

  21. Yan Z, Miyamoto A, Jiang Z (2011) Frequency slice algorithm for modal signal separation and damping identification. Comput Struct 89:14–26

    Article  Google Scholar 

  22. Lecun Y, Bottou L, Bengio Y, Haffner P (1998) Gradient-based learning applied to document recognition. Proc IEEE 86:2278–2324. https://doi.org/10.1109/5.726791

    Article  Google Scholar 

  23. Clifford GD, Liu C, Moody B, Springer D, Silva I, Qiao L, Mark RG (2016) Classification of normal/abnormal heart sound recordings: the PhysioNet/Computing in Cardiology Challenge 2016. In: Computing in Cardiology Conference. IEEE, pp 609–612

  24. Zabihi M, Rad AB, Kiranyaz S, Gabbouj M, Katsaggelos AK (2016) Heart sound anomaly and quality detection using ensemble of neural networks without segmentation. In: Computing in Cardiology Conference. IEEE, pp 613–616

  25. Antink CH, Becker J, Leonhardt S, Walter M (2016) Nonnegative matrix factorization and random forest for classification of heart sound recordings in the spectral domain. In: Computing in Cardiology Conference. IEEE, pp 809–812

  26. Goda MA, Hajas P (2016) Morphological determination of pathological pcg signals by time and frequency domain analysis. In: Computing in Cardiology Conference. IEEE, pp 1133–1136

  27. Leal A, Nunes D, Couceiro R, Henriques J, Carvalho P, Quintal I, Teixeira C (2018) Noise detection in phonocardiograms by exploring similarities in spectral features. Biomed Signal Process Control 44:154–167

Download references

Funding

This work was supported by Shandong Province Key Research and Development Plan (2018GSF118133); China Postdoctoral Science Foundation (2018M642144); and the China Postdoctoral Science Foundation under Grant (2017M612280).

Author information

Authors and Affiliations

  1. School of Control Science and Engineering, Shandong University, Jinan, China

    Yongchao Chen, Shoushui Wei & Yatao Zhang

  2. School of Mechanical, Electrical & Information Engineering, Shandong University, Weihai, China

    Yatao Zhang

Authors
  1. Yongchao Chen
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Shoushui Wei
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Yatao Zhang
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding authors

Correspondence to Shoushui Wei or Yatao Zhang.

Ethics declarations

Conflict of interest

The authors declare that they have no conflict of interest.

Additional information

Publisher’s note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Chen, Y., Wei, S. & Zhang, Y. Classification of heart sounds based on the combination of the modified frequency wavelet transform and convolutional neural network. Med Biol Eng Comput 58, 2039–2047 (2020). https://doi.org/10.1007/s11517-020-02218-5

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11517-020-02218-5

Keywords

Search

Navigation