Skip to main content

Fetal ECG Extraction from Sparse Representation of Multichannel Abdominal Recordings

Abstract

Noninvasive extraction of fetal electrocardiogram (ECG) from maternal abdominal recordings is quite challenging as such signals are often corrupted by signals from other sources, with maternal heart activities being the most distorting one. In this paper, a modified compressive sensing (CS)-based approach for extracting fetal ECG signals from multichannel abdominal recordings is proposed. Sparse representations of the acquired abdominal recordings allows for the effective compression rate of 75% for the recorded data. The scheme deploys two BSS algorithms, namely fast independent component analysis (fICA) and time–frequency BSS (TF–BSS), to estimate the source signals from the recordings and extract the fetal ECG. The performance of the proposed method is evaluated using the publicly available 2013 PhysioNet Challenge database and compared with that of the best performing existing ones. The experimental results show that the proposed framework outperforms the existing methods with a mean minimum square error of 98.59 and exhibits computational complexity comparable with the best existing methods. The results also show that the discrete wavelet transform dictionary performs well as sparsifying basis for abdominal recordings in a CS-based fetal ECG extraction framework. The proposed method can therefore be used for noninvasive and reliable extraction of fetal ECG from abdominal recordings and for developing wireless body sensor networks for ECG tele-monitoring.

This is a preview of subscription content, access via your institution.

Fig. 1
Fig. 2

Source signals after CS recovery. d Source signals after removing maternal QRS complexes

Fig. 3

Data availability

The data that support the findings of this study are available from “https://archive.physionet.org/challenge/2013/#data-sets.” For more details, see Sect. 2.1 and references therein.

Notes

  1. 1.

    https://archive.physionet.org/tutorials/hrv/

  2. 2.

    https://booksite.elsevier.com/9780123984999/supplementary.php

References

  1. 1.

    M.M. Abo-Zahhad, A.I. Hussein, A.M. Mohamed, Compression of ECG signal based on compressive sensing and the extraction of significant features. Int. J. Commun. Netw. Syst. Sci. 8(5), 97–117 (2015)

    Google Scholar 

  2. 2.

    M.H. Aghababaei, G. Azemi, A modified row-sparse multiple measurement vector recovery algorithm for reconstructing multichannel EEG signals from compressive measurements. Biomed. Signal Process. Control. 60, 101956 (2020)

    Article  Google Scholar 

  3. 3.

    Y. Alshebly, M. Nafea, Isolation of fetal ECG signals from abdominal ECG using wavelet analysis. IRBM. 261, 1–9 (2019)

    Google Scholar 

  4. 4.

    Baldazzi, G., et al.: Wavelet denoising as a post-processing enhancement method for non-invasive foetal electrocardiography. Comput. Methods Programs Biomed. 105558 (2020)

  5. 5.

    J. Behar et al., An echo state neural network for foetal ECG extraction optimised by random search. Proc. Adv. Neural Inf. Process. Syst. 36, 1629–1644 (2013)

    Google Scholar 

  6. 6.

    J. Behar, J. Oster, G.D. Clifford, Combining and benchmarking methods of foetal ECG extraction without maternal or scalp electrode data. Physiol. Meas. 35(8), 1569 (2014)

    Article  Google Scholar 

  7. 7.

    Belouchrani, A., et al.: Joint anti-diagonalization for blind source separation, in 2001 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings (Cat. No. 01CH37221). (2001. IEEE), pp. 2789–2792

  8. 8.

    A. Belouchrani, M.G. Amin, Blind source separation based on time-frequency signal representations. IEEE Trans. Signal Process. 46(11), 2888–2897 (1998)

    Article  Google Scholar 

  9. 9.

    A. Belouchrani et al., Source separation and localization using time-frequency distributions: an overview. IEEE Signal Process. Mag. 30(6), 97–107 (2013)

    Article  Google Scholar 

  10. 10.

    Boashash, B.: Time-frequency signal analysis and processing: a comprehensive reference: Academic Press (2015)

  11. 11.

    B. Boashash, A. Aïssa-El-Bey, Robust multisensor time–frequency signal processing: A tutorial review with illustrations of performance enhancement in selected application areas. Digit. Signal Process. 77, 153–186 (2018)

    MathSciNet  Article  Google Scholar 

  12. 12.

    E.J. Candès, J. Romberg, T. Tao, Robust uncertainty principles: Exact signal reconstruction from highly incomplete frequency information. IEEE Trans. Inf. Theory 52(2), 489–509 (2006)

    MathSciNet  Article  Google Scholar 

  13. 13.

    G. Chabriel et al., Joint matrices decompositions and blind source separation: A survey of methods, identification, and applications. IEEE Signal Process. Mag. 31(3), 34–43 (2014)

    Article  Google Scholar 

  14. 14.

    G.-H. Chen et al., Time-resolved interventional cardiac C-arm cone-beam CT: An application of the PICCS algorithm. IEEE Trans. Med. Imaging 31(4), 907–923 (2012)

    Article  Google Scholar 

  15. 15.

    G. Da Poian, R. Bernardini, R. Rinaldo, Separation and analysis of fetal-ECG signals from compressed sensed abdominal ECG recordings. IEEE Trans. Biomed. Eng. 63(6), 1269–1279 (2015)

    Article  Google Scholar 

  16. 16.

    Dessì, A., D. Pani, and L. Raffo: Identification of fetal QRS complexes in low density non-invasive biopotential recordings, in Computing in Cardiology. (2013. IEEE), pp. 321–324

  17. 17.

    Di Marco, L.Y., A. Marzo, and A. Frangi: Multichannel foetal heartbeat detection by combining source cancellation with expectation-weighted estimation of fiducial points, in Computing in Cardiology. (2013. IEEE), pp. 329–332

  18. 18.

    S. Dong et al., Automated detection of perinatal hypoxia using time–frequency-based heart rate variability features. Med. Biol. Eng. Compu. 52(2), 183–191 (2014)

    Article  Google Scholar 

  19. 19.

    Eldar, Y.C. and G. Kutyniok: Compressed sensing: theory and applications: Cambridge University Press (2012)

  20. 20.

    E. Fotiadou et al., Enhancement of low-quality fetal electrocardiogram based on time-sequenced adaptive filtering. Med. Biol. Eng. Compu. 56(12), 2313–2323 (2018)

    Article  Google Scholar 

  21. 21.

    A. Hyvärinen, E. Oja, Independent component analysis: algorithms and applications. Neural Netw. 13(4), 411–430 (2000)

    Article  Google Scholar 

  22. 22.

    D. Jagannath, D.R.J. Dolly, J.D. Peter, Composite Deep Belief Network approach for enhanced Antepartum foetal electrocardiogram signal. Cogn. Syst. Res. 59, 198–203 (2020)

    Article  Google Scholar 

  23. 23.

    A. Jiménez-González, N. Castañeda-Villa, Blind extraction of fetal and maternal components from the abdominal electrocardiogram: an ICA implementation for low-dimensional recordings. Biomed. Signal Process. Control. 58, 101836 (2020)

    Article  Google Scholar 

  24. 24.

    R.G. John, K. Ramachandran, Extraction of foetal ECG from abdominal ECG by nonlinear transformation and estimations. Comput. Methods Programs Biomed. 175, 193–204 (2019)

    Article  Google Scholar 

  25. 25.

    Kuzilek, J. and L. Lhotska: Advanced signal processing techniques for fetal ECG analysis, in Computing in Cardiology. (2013. IEEE), pp. 177–180

  26. 26.

    Lee, J.S., et al.: Fetal QRS detection based on convolutional neural networks in noninvasive fetal electrocardiogram, in 2018 4th International Conference on Frontiers of Signal Processing (ICFSP). (2018. IEEE), pp. 75–78

  27. 27.

    C. Liu et al., A multi-step method with signal quality assessment and fine-tuning procedure to locate maternal and fetal QRS complexes from abdominal ECG recordings. Physiol. Meas. 35(8), 1665–1683 (2014)

    Article  Google Scholar 

  28. 28.

    G. Liu, Y. Luan, An adaptive integrated algorithm for noninvasive fetal ECG separation and noise reduction based on ICA-EEMD-WS. Med. Biol. Eng. Comput. 53(11), 1113–1127 (2015)

    Article  Google Scholar 

  29. 29.

    M. Lustig et al., Compressed sensing MRI. IEEE Signal Process. Mag. 25(2), 72–82 (2008)

    Article  Google Scholar 

  30. 30.

    R. Martinek et al., Comparative effectiveness of ICA and PCA in extraction of fetal ECG from abdominal signals: toward non-invasive fetal monitoring. Front. Physiol. 9, 1–25 (2018)

    Article  Google Scholar 

  31. 31.

    A. Mirza, S.M. Kabir, S. Ayub, Impulsive noise cancellation of ECG signal based on SSRLS. Proc. Comput. Sci. 62, 196–202 (2015)

    Article  Google Scholar 

  32. 32.

    H. Mohimani, M. Babaie-Zadeh, C. Jutten, A fast approach for overcomplete sparse decomposition based on smoothed L0 norm. IEEE Trans. Signal Process. 57(1), 289–301 (2008)

    Article  Google Scholar 

  33. 33.

    B. Onaral, H.H. Sun, H.P. Schwan, Electrical properties of bioelectrodes. IEEE Trans. Biomed. Eng. 31(12), 827–832 (1984)

    Article  Google Scholar 

  34. 34.

    Podziemski, P. and J. Gieraltowski: Fetal heart rate discovery: algorithm for detection of fetal heart rate from noisy, noninvasive fetal ECG recordings, in Computing in Cardiology. (2013. IEEE), pp. 333–336

  35. 35.

    K. Prasanth, B. Paul, A.A. Balakrishnan, Fetal ECG extraction using adaptive filters. Int. J. Adv. Res. Electric. Electron. Instrum. Eng. 2(4), 1483–1487 (2013)

    Google Scholar 

  36. 36.

    Quinsac, C., et al.: Compressed sensing of ultrasound images: Sampling of spatial and frequency domains, in 2010 IEEE Workshop On Signal Processing Systems. (2010. IEEE), pp. 231–236

  37. 37.

    A.K. Rahmati, S. Setarehdan, B. Araabi, A PCA/ICA based fetal ECG extraction from mother abdominal recordings by means of a novel data-driven approach to fetal ECG quality assessment. J. Biomed. Phys. Eng. 7(1), 37–50 (2017)

    Google Scholar 

  38. 38.

    R. Sameni, G.D. Clifford, A review of fetal ECG signal processing; issues and promising directions. Open Pacing Electrophys. Therapy J. 3(1), 4–20 (2010)

    Google Scholar 

  39. 39.

    R. Sameni et al., A nonlinear bayesian filtering framework for ECG denoising. IEEE Trans. Biomed. Eng. 54(12), 2172–2185 (2007)

    Article  Google Scholar 

  40. 40.

    Silva, I., et al.: Noninvasive fetal ECG: the PhysioNet/computing in cardiology challenge 2013, in Computing in Cardiology. (2013. IEEE), pp. 149-152

  41. 41.

    Sugumar, D., P. Vanathi, and S. Mohan: Joint blind source separation algorithms in the separation of non-invasive maternal and fetal ECG, in 2014 International Conference on Electronics and Communication Systems (ICECS). (2014. IEEE), pp. 1–6

  42. 42.

    Varanini, M., et al.: A multi-step approach for non-invasive fetal ECG analysis, in Computing in Cardiology. (2013. IEEE), pp. 281–284

  43. 43.

    S. Wu et al., Research of fetal ECG extraction using wavelet analysis and adaptive filtering. Comput. Biol. Med. 43(10), 1622–1627 (2013)

    Article  Google Scholar 

  44. 44.

    V. Zarzoso, A.K. Nandi, Noninvasive fetal electrocardiogram extraction: blind separation versus adaptive noise cancellation. IEEE Trans. Biomed. Eng. 48(1), 12–18 (2001)

    Article  Google Scholar 

  45. 45.

    Y. Zhang, S. Yu, Single-lead noninvasive fetal ECG extraction by means of combining clustering and principal components analysis. Med. Biol. Eng. Comput. 58(2), 419–432 (2020)

    Article  Google Scholar 

Download references

Author information

Affiliations

Authors

Corresponding author

Correspondence to Ghasem Azemi.

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

Verify currency and authenticity via CrossMark

Cite this article

Tavoosi, P., Haghi, F., Zarjam, P. et al. Fetal ECG Extraction from Sparse Representation of Multichannel Abdominal Recordings. Circuits Syst Signal Process (2021). https://doi.org/10.1007/s00034-021-01870-y

Download citation

Keyword

  • Fetal ECG
  • Blind source separation
  • Compressive sensing
  • ICA
  • Time–frequency analysis