Efficient Fetal-Maternal ECG Signal Separation from Two Channel Maternal Abdominal ECG via Diffusion-Based Channel Selection

Ruilin Li, Martin G Frasch, Hau-Tieng Wu, Ruilin Li, Martin G Frasch, Hau-Tieng Wu

Abstract

There is a need for affordable, widely deployable maternal-fetal ECG monitors to improve maternal and fetal health during pregnancy and delivery. Based on the diffusion-based channel selection, here we present the mathematical formalism and clinical validation of an algorithm capable of accurate separation of maternal and fetal ECG from a two channel signal acquired over maternal abdomen. The proposed algorithm is the first algorithm, to the best of the authors' knowledge, focusing on the fetal ECG analysis based on two channel maternal abdominal ECG signal, and we apply it to two publicly available databases, the PhysioNet non-invasive fECG database (adfecgdb) and the 2013 PhysioNet/Computing in Cardiology Challenge (CinC2013), to validate the algorithm. The state-of-the-art results are achieved when compared with other available algorithms. Particularly, the F1 score for the R peak detection achieves 99.3% for the adfecgdb and 87.93% for the CinC2013, and the mean absolute error for the estimated R peak locations is 4.53 ms for the adfecgdb and 6.21 ms for the CinC2013. The method has the potential to be applied to other fetal cardiogenic signals, including cardiac doppler signals.

Keywords: de-shape short time Fourier transform; diffusion maps; fetal electrocardiogram; maternal abdominal electrocardiogram; nonlocal median.

Figures

Figure 1
Figure 1
The flow chart of the proposed two-channel fECG algorithm, SAVER. The x-axis of all figures are of the unit second. The data is the a2 recording from the database used in the 2013 PhysioNet/Computing in Cardiology Challenge, and channel 1 and channel 4 are shown in this illustration. Only three linear combinations are shown for the illustration purpose. The signal quality index for the channel selection is shown on the third block.
Figure 2
Figure 2
The lead placement for the adfecgdb.

References

    1. Akbari H., Shamsollahi M. B., Phlypo R. (2015). Fetal ECG extraction using πTucker decomposition, in International Conference on Systems, Signals and Image Processing (London: IEEE; ).
    1. Akhbari M., Niknazar M., Jutten C., Shamsollahi M. B., Rivet B. (2013). Fetal electrocardiogram R-peak detection using robust tensor decomposition and extended Kalman filtering. Comput. Cardiol. 40, 189–192. Available online at:
    1. Amer-Wåhlin I., Hellsten C., Norén H., Hagberg H., Herbst A., Kjellmer I., et al. . (2001). Cardiotocography only versus cardiotocography plus st analysis of fetal electrocardiogram for intrapartum fetal monitoring: a swedish randomised controlled trial. Lancet 358, 534–538. 10.1016/S0140-6736(01)05703-8
    1. Anblagan D., Pataky R., Evans M. J., Telford E. J., Serag A., Sparrow S., et al. . (2016). Association between preterm brain injury and exposure to chorioamnionitis during fetal life. Sci. Rep. 6:37932. 10.1038/srep37932
    1. Andreotti F., Behar J., Zaunseder S., Oster J., Clifford G. D. (2016). An open-source framework for stress-testing non-invasive foetal ECG extraction algorithms. Physiol. Meas. 37, 627–648. 10.1088/0967-3334/37/5/627
    1. Andreotti F., Riedl M., Himmelsbach T., Wedekind D., Wessel N., Stepan H., et al. . (2014). Robust fetal ECG extraction and detection from abdominal leads. Physiol. Meas. 35, 1551–1567. 10.1088/0967-3334/35/8/1551
    1. Behar J., Andreotti F., Zaunseder S., Oster J., Clifford G. D. (2016). A practical guide to non-invasive foetal electrocardiogram extraction and analysis. Physiol. Meas. 37:R1. 10.1088/0967-3334/37/5/R1
    1. Behar J., Johnson A., Clifford G. D., Oster J. (2014a). A comparison of single channel fetal ECG extraction methods. Ann. Biomed. Eng. 42, 1340–1353. 10.1007/s10439-014-0993-9
    1. Behar J., Oster J., Clifford G. D. (2014b). Combining and benchmarking methods of foetal ECG extraction without maternal or scalp electrode data. Physiol. Meas. 35, 1569–1589. 10.1088/0967-3334/35/8/1569
    1. Belfort M. A., Saade G. R., Thom E., Blackwell S. C., Reddy U. M., Thorp J. M., Jr., et al. . (2015). A randomized trial of intrapartum fetal ECG ST-segment analysis. N. Engl. J. Med. 373, 632–641. 10.1056/NEJMoa1500600
    1. Bravi A., Green G., Herry C., Wright H., Longtin A., Kenny G., et al. . (2013). Do physiological and pathological stresses produce different changes in heart rate variability? Front. Physiol. 4:197. 10.3389/fphys.2013.00197
    1. Castillo E., Morales D. P., Botella G., Garcia A., Parrilla L., Palma A. J. (2013). Efficient wavelet-based ECG processing for single-lead FHR extraction. Digital Signal Process. 23, 1897–1909. 10.1016/j.dsp.2013.07.010
    1. Coifman R. R., Lafon S. (2006). Diffusion maps. Appl. Comput. Harmon. Anal. 21, 5–30. 10.1016/j.acha.2006.04.006
    1. Daubechies I., Wang Y. G., Wu H.-t. (2016). ConceFT: concentration of frequency and time via a multitapered synchrosqueezed transform. Philos. Trans. A Math. Phys. Eng. Sci. 374:20150193. 10.1098/rsta.2015.0193
    1. De Lathauwer L., De Moor B., Vandewalle J. (2000). Fetal electrocardiogram extraction by blind source subspace separation. IEEE Trans. Biomed. Eng. 47, 567–572. 10.1109/10.841326
    1. Di Maria C., Liu C., Zheng D., Murray A., Langley P. (2014). Extracting fetal heart beats from maternal abdominal recordings: selection of the optimal principal components. Physiol. Meas. 35, 1649–1664. 10.1088/0967-3334/35/8/1649
    1. Durosier L. D., Herry C. L., Cortes M., Cao M., Burns P., Desrochers A., et al. . (2015). Does heart rate variability reflect the systemic inflammatory response in a fetal sheep model of lipopolysaccharide-induced sepsis? Physiol. Meas. 36:2089. 10.1088/0967-3334/36/10/2089
    1. Durosier L. D., Green G., Batkin I., Seely A. J., Ross M. G., Richardson B. S., et al. . (2014). Sampling rate of heart rate variability impacts the ability to detect acidemia in ovine fetuses near-term. Front. Pediatr. 2:38. 10.3389/fped.2014.00038
    1. El Karoui N. (2010). On information plus noise kernel random matrices. Ann. Stat. 38, 3191–3216. 10.1214/10-AOS801
    1. El Karoui N., Wu H.-T. (2016). Connection graph Laplacian methods can be made robust to noise. Ann. Stat. 44, 346–372. 10.1214/14-AOS1275
    1. Fairchild K. D., Sinkin R. A., Davalian F., Blackman A. E., Swanson J. R., Matsumoto J. A., et al. . (2014). Abnormal heart rate characteristics are associated with abnormal neuroimaging and outcomes in extremely low birth weight infants. J. Perinatol. 34, 375–379. 10.1038/jp.2014.18
    1. Fairchild K. D., Srinivasan V., Randall Moorman J., Gaykema R. P. A., Goehler L. E. (2011). Pathogen-induced heart rate changes associated with cholinergic nervous system activation. Am. J. Physiol. 300, R330–R339. 10.1152/ajpregu.00487.2010
    1. Garzoni L., Faure C., Frasch M. (2013). Fetal cholinergic anti-inflammatory pathway and necrotizing enterocolitis: the brain-gut connection begins in utero. Front. Integr. Neurosci. 7:57. 10.3389/fnint.2013.00057
    1. Ghaffari A., Mollakazemi M. J., Atyabi S. A., Niknazar M. (2015). Robust fetal QRS detection from noninvasive abdominal electrocardiogram based on channel selection and simultaneous multichannel processing. Australas Phys. Eng. Sci. Med. 38, 581–592. 10.1007/s13246-015-0381-2
    1. Goldberger A., Amaral L., Glass L., Hausdorff J., Ivanov P., Mark R., et al. . (2000). Physiobank, physiotoolkit, and physionet: components of a new research resource for complex physiologic signals. Circulation 101, e215–e220. 10.1161/01.CIR.101.23.e215
    1. Graupe D., Graupe M. H., Zhong Y., Jackson R. K. (2008). Blind adaptive filtering for non-invasive extraction of the fetal electrocardiogram and its non-stationarities. Proc. Inst. Mech. Eng. H J. Eng. Med. 222, 1221–1234. 10.1243/09544119JEIM417
    1. Guerrero-Martinez J. F., Martinez-Sober M., Bataller-Mompean M., Magdalena-Benedito J. R. (2006). New algorithm for fetal QRS detection in surface abdominal records, in Computers in Cardiology (IEEE: ), 441–444.
    1. Hagberg H., Mallard C., Ferriero D. M., Vannucci S. J., Levison S. W., Vexler Z. S., et al. . (2015). The role of inflammation in perinatal brain injury. Nat. Rev. Neurol. 11, 192–208. 10.1038/nrneurol.2015.13
    1. Haghpanahi M., Borkholder D. A. (2013). Fetal ECG extraction from abdominal recordings using array signal processing, in Computing in Cardiology, Vol. 40 (IEEE; ), 173–176.
    1. Jenkins H. M. (1989). Thirty years of electronic intrapartum fetal heart rate monitoring: discussion paper. J. R. Soc. Med. 82, 210–214. 10.1177/014107688908200410
    1. Kanjilal P. P., Palit S., Saha G. (1997). Fetal ECG extraction from single-channel maternal ECG using singular value decomposition. IEEE Trans. Biomed. Eng. 44, 51–59. 10.1109/10.553712
    1. Keener J. (1998). Mathematical Physiology. Springer; Available online at:
    1. Keller Y., Coifman R. R., Lafon S., Zucker S. W. (2010). Audio-visual group recognition using diffusion maps. IEEE Trans. Signal Process. 58, 403–413. 10.1109/TSP.2009.2030861
    1. Kotas M., Jezewski J., Matonia A., Kupka T. (2010). Towards noise immune detection of fetal QRS complexes. Comput. Methods Prog. Biomed. 97, 241–256. 10.1016/j.cmpb.2009.09.005
    1. Laguna P., Sörnmo L. (2000). Sampling rate and the estimation of ensemble variability for repetitive signals. Med. Biol. Eng. Comput. 38, 540–546. 10.1007/BF02345750
    1. Lederman R. R., Talmon R. (in press). Learning the geometry of common latent variables using alternating-diffusion. Appl. Comp. Harmon. Anal. 10.1016/j.acha.2015.09.002
    1. Lee K., Lee B. (2016). Sequential total variation denoising for the extraction of fetal ECG from single-channel maternal abdominal ECG. Sensors 16:1020. 10.3390/s16071020
    1. Li X., Dunn J., Salins D., Zhou G., Zhou W., Schüssler-Fiorenza Rose S. M., et al. . (2017). Digital health: tracking physiomes and activity using wearable biosensors reveals useful health-related information. PLoS Biol. 15:e2001402. 10.1371/journal.pbio.2001402
    1. Li X., Xu Y., Herry C., Durosier L. D., Casati D., Stampalija T., et al. (2015). Sampling frequency of fetal heart rate impacts the ability to predict pH and BE at birth: a retrospective multi-cohort study. Physiol. Meas. 36:L1 10.1088/0967-3334/36/5/L1
    1. Lin C.-Y., Li S., Wu H.-t. (2016). Wave-shape function analysis–when cepstrum meets time-frequency analysis. arXiv:1605.01805 J. Four. Anal. Appl. 10.1007/s00041-017-9523-0
    1. Liu H. L., Garzoni L., Herry C., Durosier L. D., Cao M., Burns P., et al. . (2016). Can monitoring fetal intestinal inflammation using heart rate variability analysis signal incipient necrotizing enterocolitis of the neonate? Pediatr. Crit. Care Med. 17, 165–176. 10.1097/PCC.0000000000000643
    1. Niknazar M., Rivet B., Jutten C. (2013). Fetal ECG extraction by extended state Kalman filtering based on single-channel recordings. IEEE Trans. Biomed. Eng. 60, 1345–1352. 10.1109/TBME.2012.2234456
    1. Olofsson P. S., Rosas-Ballina M., Levine Y. A., Tracey K. J. (2012). Rethinking inflammation: neural circuits in the regulation of immunity. Immunol. Rev. 248, 188–204. 10.1111/j.1600-065X.2012.01138.x
    1. Papyan V., Talmon R. (2016). Multimodal latent variable analysis. ArXiv:1611.08472.
    1. Poian G. D., Bernardini R., Rinaldo R. (2015). Sparse representation for fetal QRS detection in abdominal ECG recordings, in The 5th IEEE International Conference on E-Health and Bioengineering - EHB 2015 (Iasi: ), 1–4. 10.1109/ehb.2015.7391501
    1. Richter M., Schreiber T., Kaplan D. (1998). Fetal ECG extraction with nonlinear state-space projections. IEEE Trans. Biomed. Eng. 45, 133–137. 10.1109/10.650369
    1. Rodrigues R. (2014). Fetal beat detection in abdominal ECG recordings: global and time adaptive approaches. Physiol. Meas. 35, 1699–1711. 10.1088/0967-3334/35/8/1699
    1. Sameni R. (2008). Extraction of Fetal Cardiac Signals From An Array of Maternal Abdominal Recordings. Ph.D. thesis, Sharif University of Technology – Institut National Polytechnique de Grenoble.
    1. Sameni R., Jutten C., Shamsollahi M. (2008). Multichannel electrocardiogram decomposition using periodic component analysis. IEEE Trans. Biomed. Eng. 55, 1935–1940. 10.1109/TBME.2008.919714
    1. Singer A., Wu H.-T. (2017). Spectral convergence of the connection laplacian from random samples. Inform. Inference J. IMA. 6, 58–123 10.1093/imaiai/iaw016
    1. Stark J., Broomhead D., Davies M., Huke J. (1997). Takens embedding theorems for forced and stochastic systems. Nonlin. Anal. Theory Methods Appl. 30, 5303–5314. 10.1016/S0362-546X(96)00149-6
    1. Stark J., Broomhead D., Davies M., Huke J. (2003). Delay embeddings for forced systems. II. Stochastic forcing. J. Nonlin. Sci. 13, 519–577. 10.1007/s00332-003-0534-4
    1. Su L., Wu H.-T. (2017). Extract fetal ECG from single-lead abdominal ECG by de-shape short time Fourier transform and nonlocal median. Front. Appl. Math. Stat. 3:2 10.3389/fams.2017.00002
    1. Takens F. (1981). Detecting strange attractors in turbulence, in Dynamical Systems and Turbulence, Vol. 898 of Lecture Notes in Mathematics, eds Rand D., Young L.-S. (Berlin; Heidelberg: Springer; ), 366–381.
    1. Talmon R., Wu H.-T. (2016). Latent common manifold learning with alternating diffusion: analysis and applications. arXiv preprint arXiv:1602.00078.
    1. Varanini M., Tartarisco G., Billeci L., Macerata A., Pioggia G., Balocchi R. (2014). An efficient unsupervised fetal QRS complex detection from abdominal maternal ECG. Physiol. Meas. 35, 1607–1619. 10.1088/0967-3334/35/8/1607
    1. Widrow B., Williams C. S., Glover J. R., McCool J. M., Hearn R. H., Zeidler J. R., et al. (1975). Adaptive noise cancelling: principles and applications. Proc. IEEE 63, 1692–1716. 10.1109/PROC.1975.10036

Source: PubMed

Sponsorer og samarbeidspartnere

Medisinsk tilstand

Legemiddelintervensjoner

3
Abonnere