Medical & Biological Engineering & Computing

, Volume 53, Issue 11, pp 1113–1127 | Cite as

An adaptive integrated algorithm for noninvasive fetal ECG separation and noise reduction based on ICA-EEMD-WS

Original Article
First Online:
Received:
Accepted:

Abstract

High-resolution fetal electrocardiogram (FECG) plays an important role in assisting physicians to detect fetal changes in the womb and to make clinical decisions. However, in real situations, clear FECG is difficult to extract because it is usually overwhelmed by the dominant maternal ECG and other contaminated noise such as baseline wander, high-frequency noise. In this paper, we proposed a novel integrated adaptive algorithm based on independent component analysis (ICA), ensemble empirical mode decomposition (EEMD), and wavelet shrinkage (WS) denoising, denoted as ICA-EEMD-WS, for FECG separation and noise reduction. First, ICA algorithm was used to separate the mixed abdominal ECG signal and to obtain the noisy FECG. Second, the noise in FECG was reduced by a three-step integrated algorithm comprised of EEMD, useful subcomponents statistical inference and WS processing, and partial reconstruction for baseline wander reduction. Finally, we evaluate the proposed algorithm using simulated data sets. The results indicated that the proposed ICA-EEMD-WS outperformed the conventional algorithms in signal denoising.

Keywords

Fetal electrocardiogram Independent component analysis Ensemble empirical mode decomposition Wavelet shrinkage denoising Adaptive noise reduction 
This is a preview of subscription content, log in to check access.

Notes

Acknowledgments

The authors thank Professor Fengzhu Sun from the University of Southern California deeply for introducing the Hilbert–Huang transform (HHT) algorithm (including EMD) to us and critically reading the manuscript. The authors also thank Mr. Ang Shan, Mr. Arvis Sulovari, Mr. Kees-Jan Kan and Ms. Kari Ann Tremblay for their helpful discussions and suggestions. This work was supported by Natural Science Foundation of China Grants 11371227 and 11221061, and Graduate Independent Innovation Foundation of Shandong University (GIIFSDU) yzc12098.

References

  1. 1.
    Andreotti F, Riedl M, Himmelsbach T, Wedekind D, Zaunseder S, Wessel N, Malberg H (2013) Maternal signal estimation by Kalman filtering and template adaptation for fetal heart rate extraction. Comput Cardiol 40:193–196Google Scholar
  2. 2.
    Blanco-Velasco M, Weng BW, Barner KE (2008) ECG signal denoising and baseline wander correction based on the empirical mode decomposition. Comput Biol Med 38:1–13CrossRefPubMedGoogle Scholar
  3. 3.
    Behar J, Oster J, Clifford GD (2013) Non-invasive FECG extraction from a set of abdominal sensors. Comput Cardiol 40:297–300Google Scholar
  4. 4.
    Behar J, Johnson A, Clifford GD, Oster J (2014) A comparison of single channel fetal ECG extraction methods. Ann Biomed Eng 42(6):1340–1353CrossRefPubMedGoogle Scholar
  5. 5.
    Behar J, Andreotti F, Zaunseder S, Li Q, Oster J, Clifford GD (2014) An ECG model for simulating maternal-foetal activity mixtures on abdominal ECG recordings. Physiol Meas 35:1537–50CrossRefPubMedGoogle Scholar
  6. 6.
    Chang KM (2010) Ensemble empirical mode decomposition for high frequency ECG noise reduction. Biomed Tech 55:193–201CrossRefGoogle Scholar
  7. 7.
    Clifford GD, Silva I, Behar J, Moody GB (2014) Non-invasive fetal ECG analysis. Physiol Meas 35:1521–1536PubMedCentralCrossRefPubMedGoogle Scholar
  8. 8.
    De Lathauwer L, De Moor B, Vandewalle J (1995) Fetal electrocardiogram extraction by source subspace separation. In: Proceedings of IEEE SP/ATHOS workshop on HOS, Girona, Spain, pp 134–138Google Scholar
  9. 9.
    Donoho DL, Johnstone IM (1994) Ideal spatial adaptation by wavelet shrinkage. Biometrika 81:425–455CrossRefGoogle Scholar
  10. 10.
    Donoho DL (1995) De-noising by soft-thresholding. IEEE Trans Inf Theory 41(3):613–627CrossRefGoogle Scholar
  11. 11.
    Flandrin P, Rilling G, Goncalves P (2004) Empirical mode decomposition as a filter bank. IEEE Signal Process Lett 11(2):112–114CrossRefGoogle Scholar
  12. 12.
    Freeman RK, Garite TJ, Nageotte MP (2003) Fetal heart rate monitoring, 3rd edn. Lippincoot Williams & Wilkins, PhiladelphiaGoogle Scholar
  13. 13.
    Goldberger AL, Amaral LAN, Glass L, Hausdorff JM, Ivanov PC, Mark RG, Mietus JE, Moody GB, Peng C-K, Stanley HE (2000) Physiobank, physiotoolkit, and physionet: components of a new research resource for complex physiologic signals. Circulation 101(23):e215–e220CrossRefPubMedGoogle Scholar
  14. 14.
    Goodlin RC (1979) History of fetal monitoring. Am J Obstet Gynecol 133(3):323–352PubMedGoogle Scholar
  15. 15.
    Hasan MA, Reaz MBI, Ibrahimy MI, Hussain MS, Uddin J (2009) Detection and processing techniques of FECG signal for fetal monitoring. Biol Proced Online 11(1):263–295PubMedCentralCrossRefPubMedGoogle Scholar
  16. 16.
    Huang E, Shen Z, Long SR, Wu ZH, Shin HH, Zheng Q, Yen NC, Tung CC, Liu HH (1998) The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis. Proc R Soc Lond A 454(1971):903–995CrossRefGoogle Scholar
  17. 17.
    Hyvarinen A (1999) Fast and robust fixed-point algorithm for independent component analysis. IEEE Trans Neural Netw 10(3):626–634CrossRefPubMedGoogle Scholar
  18. 18.
    Immanuel JRJ, Prabhu V, Chrstopheraj JV, Sugumar D, Vanathi PT (2012) Separation of maternal and fetal ECG signal from the mixed source signal using FASTICA. Procedia Eng 30:356–363CrossRefGoogle Scholar
  19. 19.
    Jafari MG, Chambers JA (2005) Fetal electrocardiogram extraction by sequential source separation in the wavelet domain. IEEE Trans Biomed Eng 52(3):390–400CrossRefPubMedGoogle Scholar
  20. 20.
    Jezewski J, Wrobel J, Horoba K (2006) Comparison of Doppler ultrasound and direct electrocardiography acquisition techniques for quantification of fetal heart rate variability. IEEE Trans Biomed Eng 53(5):855–864CrossRefPubMedGoogle Scholar
  21. 21.
    Jezewski J, Matonia A, Kupka T, Roj D, Czabanski R (2012) Determination of the fetal heart rate from abdominal signals: evaluation of beat-to-beat accuracy in relation to the direct fetal electrocardiogram. Biomed Tech 57(5):383–394CrossRefGoogle Scholar
  22. 22.
    Kanjilal PP, Palit S, Saha G (1997) Fetal ECG extraction from single-channel maternal ECG using singular value decomposition. IEEE Trans Biomed Eng 44(1):51–59CrossRefPubMedGoogle Scholar
  23. 23.
    Khamene A, Negahdaripour S (2000) A new method for the extraction of fetal ECG from the composite abdominal signal. IEEE Trans Biomed Eng 47(4):507–516CrossRefPubMedGoogle Scholar
  24. 24.
    Outram NJ, Ifeachor EC, Eetvelt PWJV, Curnow JSH (1995) Techniques for optimal enhancement and feature extraction of fetal electrocardiogram. IEE Proc Sci Meas Technol 142(6):482–489CrossRefGoogle Scholar
  25. 25.
    Maria CD, Liu CY, Zheng DC, Murray A, Langley P (2014) Extracting fetal heart beats from maternal abdominal recordings:selection of the optimal principal components. Physiol Meas 35:1649–1664CrossRefPubMedGoogle Scholar
  26. 26.
    McSharry PE, Clifford GD, Tarassenko L, Smith LA (2003) A dynamical model for generating synthetic electrocardiogram signals. IEEE Trans Biomed Eng 50(3):289–294CrossRefPubMedGoogle Scholar
  27. 27.
    Martin-Clemente R, Camargo-Olivares JL, Hornillo-Mellado S, Elena M, Roman I (2011) Fast technique for noninvasive fetal ECG extraction. IEEE Trans Biomed Eng 58(2):227–230CrossRefPubMedGoogle Scholar
  28. 28.
    Ni YM, Yang NH (2011) Speech denoising application based on Hilbert–Huang transform. Comput Simulink 28(4):408–412Google Scholar
  29. 29.
    Niknazar M, River B, Christian J (2013) Fetal QRS complex detection based on three-way tensor decomposition. Comput Cardiol 40:185–188Google Scholar
  30. 30.
    Salmanpour A, Nikjoo SM, Tehrani AS, Moghadas SMA (2007) Extraction of fetal electrocardiogram from maternal skin electrodes using affine projection algorithm (APA), recursive least square (RLS), and QR-RLS algorithm. In: Proceedings of the 2007 IEEE international symposium on signal processing and information technology, pp 1149–1154Google Scholar
  31. 31.
    Sameni R, Clifford GD, Jutten C, Shamsollahi MB (2007) Multichannel ECG and noise modeling: application to maternal and fetal ECG signals. EURASIP J Adv Signal Process 2007(1):94CrossRefGoogle Scholar
  32. 32.
    Sameni R, Clifford GD (2010) A review of fetal ECG signal processing: issues and promising directions. Open Pacing Electrophysiol Ther J 3:4–20PubMedCentralPubMedGoogle Scholar
  33. 33.
    Taswell C (2000) The what, how, and why of wavelet shrinkage denoising. Comput Sci Eng 2(3):12–19CrossRefGoogle Scholar
  34. 34.
    Varanini M, Tartarisco G, Billeci L, Macerata A, Piggia G, Balocchi R (2013) A multi-step approach for non-invasive fetal ECG analysis. Comput Cardiol 40:281–284Google Scholar
  35. 35.
    Vigneron V, Paraschiv-Ionescu A, Azancot A, Slbony O, Jutten C (2003) Fetal electrocardiogram extraction based on non-stationary ICA and wavelet denoising. In: Seventh international symposium on signal processing and its applications 2003 proceedings, vol 2, pp 69-72Google Scholar
  36. 36.
    Vulling R, Peters C, Mischi M, Ochi G, Bergman J (2006) Maternal ECG removal from non-invasive fetal ECG recording. In: Proceedings of the 28th IEEE EMBS annual international conference, pp 1394–1397Google Scholar
  37. 37.
    Wang YH, Yeh CH, Young HWV, Hu K, Lo MT (2014) On the computational complexity of the empirical mode decomposition algorithm. Phys A Stat Mech Appl 400(15):159–167CrossRefGoogle Scholar
  38. 38.
    Widrow B, Glover JR, McCool JM, Kaunitz J, Williams CS, Hearn RH, Zeidler JR, Dong E Jr, Goodlin RC (1975) Adaptive noise cancelling: principles. Proc IEEE 63(12):1692–1716CrossRefGoogle Scholar
  39. 39.
    Wu ZH, Huang NE (2004) A study of the characteristics of white noise using the empirical mode decomposition. Proc R Soc Lond A 460(2046):1597–1611CrossRefGoogle Scholar
  40. 40.
    Wu ZH, Huang NE (2009) Ensemble empirical mode decomposition: a noise-assisted data analysis method. Adv Adapt Data Anal 01(1):1–41CrossRefGoogle Scholar
  41. 41.
    Xing HY, Huang MS (2009) Research on the QRS complex detection algorithm based on Hilbert–Huang transform. Chin J Sci Instrum 30(7):1469–1475Google Scholar
  42. 42.
    Zarzoso V, Nandi AK, Bacharakis E (1997) Maternal and fetal ECG separation using blind source separation methods. IMA J Math Appl Med Biol 14:207–255 (for Signal Processing 1/1-1/6)CrossRefPubMedGoogle Scholar
  43. 43.
    Zeng yj, Liu SJ, Zhang JH (2008) Extraction of fetal ECG signal via adaptive noise cancellation approach. In: Proceedings of 2nd international conference on bioinformatics and biomedical engineering, pp 2270–2273Google Scholar
  44. 44.
    Zhao ZD, Pan M, Guo XS, Chen YQ (2002) Denoising of electrocardiogram signal using wavelet packet shrinkage. Comput Eng Appl 38(20):19–26Google Scholar
  45. 45.
    Zhao ZD, Luo Y, Lu Q (2011) Adaptive noise removal of ECG signal based on ensemble empirical mode decomposition. In: Garcia L (ed) Adaptive filtering applications. InTech, pp 123–140. doi: 10.5772/16263. ISBN: 978-953-307-306-4

Copyright information

© International Federation for Medical and Biological Engineering 2015

Authors and Affiliations

  1. 1.School of MathematicsShandong UniversityJinanPeople’s Republic of China

Personalised recommendations