Fetal electrocardiogram estimation using polynomial eigenvalue decomposition

In this paper, we propose the application of polynomial matrix eigenvalue decomposition (PEVD) to the problem of fetal electrocardiogram (ECG) extraction from real ECG recordings obtained from abdominal leads. We model the fetal ECG extraction problem as a broadband sensor array signal processing problem in order to account for the broadband nature of the ECG noise present in the recordings. An algorithm for providing an approximate PEVD is used in order to estimate the broadband noise subspace. Suppression of the broadband noise and maternal ECG is achieved by carrying out an orthonormal projection of the recordings onto the estimated fetal subspace. The proposed scheme was evaluated with multichannel synthetic ECG signals and real ECG data from the PhysioNet Challenge database and is shown to perform favorably as compared to prior-art methods. Results indicate that our method is more robust than the prior-art ones for the task of fetal ECG estimation.

PDF

___

[1] Widmark C, Jansson T, Lindecrantz K, Rosen K. ECG waveform, short term heart rate variability & plasma catecholamine concentrations in response to hypoxia in intrauterine growth related guinea-pig fetuses. J Develop Physio 1991; 15: 161-168.
[2] Solum T, Ingermarson I Nygren A. The accuracy of abdominal ECG for fetal electronic monitoring. J Perinatal Med 1980; 8: 142-149.
[3] Assaleh K, Al-Nashash H. A novel technique for the extraction of fetal ECG using polynomial networks. IEEE T Biomed Eng 2005; 52: 1148-1152.
[4] Camps G, Martinez M, Soria E. Fetal ECG extraction using an FIR neural network. In: Proceedings of Computers in Cardiology; 2001. pp. 249-252.
[5] Sameni R, Shamsollahi MB, Jutten C, Clifford GD. A nonlinear Bayesian filtering framework for ECG denoising. IEEE T Biomed Eng 2007; 54: 2172-2185.
[6] Ferrara ER, Widrow B. Fetal electrocardiogram enhancement by time sequenced adaptive filtering. IEEE T Biomed Eng 1982; 29: 458-460.
[7] Wei Z, Hongxing L, Aijun H, Xinbao N, Jianchun C. Single-lead fetal electrocardiogram estimation by means of combining R-peak detection, resampling and comb filter. Med Eng Phy 2010; 32: 708-719.
[8] Zarzoso V, Nandi AK. Noninvasive fetal electrocardiogram extraction: blind separation versus adaptive noise cancellation. IEEE T Biomed Eng 2001; 48: 12-18.
[9] De Lathauwer L, De Moor B, Vandewalle J. Fetal electrocardiogram extraction by blind source subspace separation. IEEE T Biomed Eng 2000; 47: 567-572.
[10] Salustri C, Barbati G, Porcaro C. Fetal magnetocardiographic signals extracted by signal subspace blind source separation. IEEE T Biomed Eng 2005; 52: 1140-1142.
[11] Sameni R, Jutten C, Shamsollahi MB. Multichannel electrocardiogram decomposition using periodic component analysis. IEEE T Biomed Eng 2008; 55: 1935-1940.
[12] Golub GH, Van Loan CF. Matrix Computations. 3rd ed. Baltimore, MD, USA: Johns Hopkins University Press; 1996.
[13] Clifford GD. Singular value decomposition and independent component analysis for blind signal separation. Bio Signal Image Process 2005; 44: 489-499.
[14] Cardoso JF, Souloumiac A. Blind beamforming for non-Gaussian signals. Inst Elect Eng Proc F Radar Sig Process 1993; 140: 362-370.
[15] Callaerts D, De Moor B, Vandewalle J, Sansen W, Vantrappen G, Janssens J. Comparison of SVD methods to extract the foetal electrocardiogram from cutaneous electrode signals. Med Bio Eng Comput 1990; 28: 217-224.
[16] Kanjilal PP, Palit S, Saha G. Fetal ECG extraction from single channel maternal ECG using singular value decomposition. IEEE T Biomed Eng 1997; 44: 51-59.
[17] Sameni R, Clifford GD, Jutten C, Shamsollahi MB. Multichannel ECG and noise modeling: application to maternal and fetal ECG signals. EURASIP J Adv Sig Process 2007; 2007: 43407.
[18] Sameni R, Clifford GD. A review of fetal ECG signal processing; issues and promising directions. Open Pacing Electrophysiol Ther J 2010; 3: 4-20.
[19] Mic´o P, Mora M, Cuesta-Frau D, Aboy M. Automatic segmentation of long-term ECG signals corrupted with broadband noise based on sample entropy. Comput Methods Programs Biomed 2010; 98: 118-129.
[20] Vaidyanathan PP. Theory of optimal orthonormal subband coders. IEEE T Sig Process 1998; 46: 1528-1543.
[21] Vaidyanathan PP. Multirate Systems and Filter Banks. Englewood Cliffs, NJ, USA: Prentice Hall; 1993.
[22] Lambert RH, Joho M, Mathis H. Polynomial singular values for number of wideband source estimation and principal components analysis. In: International Conference on Independent Component Analysis and Blind Signal Separation; 2001. pp. 379-383.
[23] McWhirter JG, Baxter PD, Cooper T, Redif S, Foster J. An EVD algorithm for para-Hermitian polynomial matrices. IEEE T Sig Process 2007; 55: 2158-2169.
[24] McWhirter JG. An algorithm for polynomial matrix SVD based on generalised Kogbetliantz transformations. In: Proceedings of the European Signal Processing Conference; 2010. pp. 457-461.
[25] Tkacenko A. Approximate eigenvalue decomposition of para-Hermitian systems through successive FIR paraunitary transformations. In: Proceedings of the IEEE International Conference on Acoustic Speech Signal Processing; 2010. pp. 4074-4077.
[26] Redif S, McWhirter JG, Weiss S. Design of FIR paraunitary filter banks for subband coding using a polynomial eigenvalue decomposition. IEEE T Sig Process 2011; 59: 5253-5264.
[27] Redif S, Fahrioglu U. Foetal ECG extraction using broadband signal subspace decomposition. In: IEEE Mediterranean Microwave Symposium; 2010. pp. 381-384.
[28] Liu GS, Wei CH. A new variable fractional sample delay filter with nonlinear interpolation. IEEE T Circuits-II 1992; 39: 123-126.
[29] Kailath T. Linear Systems. Englewood Cliffs, NJ, USA: Prentice Hall; 1980.
[30] Goldberger AL, Amaral LAN, Glass L, Hausdorff JM, Ivanov PC, Mark RG, Mietus JE, Moody GB, Peng CK, Stanley HE. PhysioBank, PhysioToolkit, and PhysioNet: Components of a new research resource for complex physiologic signals. Circulation 2000; 101: e215-e220.
[31] Moody GB, Mark RG. The impact of the MIT-BIH Arrhythmia Database. IEEE Eng Med Biol 2001; 20: 45-50.
[32] Moody GB, Mark RG, Goldberger AL. PhysioNet: A web-based resource for the study of physiological signals. IEEE Eng Med Biol 2001; 20: 70-75.