The fetal electrocardiogram (FECG) signals are essential to monitor the health condition of the baby. Fetal heart rate(FHR) is commonly used for diagnosing certain abnormalities in the formation of the heart. Usually, non-invasive abdominal electrocardiogram (AbECG) signals are obtained by placing surface electrodes in the abdomen region of the pregnant woman. AbECG signals are often not suitable for the direct analysis of fetal heart activity. Moreover, the strength and magnitude of the FECG signals are low compared to the maternal electrocardiogram (MECG) signals. The MECG signals are often superimposed with the FECG signals that make the monitoring of FECG signals a difficult task.
OBJECTIVE:
Primary goal of the paper is to separate the fetal electrocardiogram (FECG) signals from the unwanted maternal electrocardiogram (MECG) signals.
METHOD:
A multivariate signal processing procedure is proposed here that combines the Multivariate Empirical Mode Decomposition (MEMD) and Independent Component Analysis (ICA).
RESULTS:
The proposed method is evaluated with clinical abdominal signals taken from three pregnant women (N= 3) recorded during the 38-41 weeks of the gestation period. The number of fetal R-wave detected (NEFQRS), the number of unwanted maternal peaks (NMQRS), the number of undetected fetal R-wave (NUFQRS) and the FHR detection accuracy quantifies the performance of our method. Clinical investigation with three test subjects shows an overall detection accuracy of 92.8%.
CONCLUSION:
Comparative analysis with benchmark signal processing method such as ICA suggests the noteworthy performance of our method.
HasanMA, ReazMBI, IbrahimyMI, HussainMS, UddinJ. Detection and processing techniques of FECG signal for fetal monitoring. Biological Procedures Online2009; 11: 263-95. doi: 10.1007/s12575-009-9006-z.
2.
SameniR, CliffordGD. A Review of Fetal ECG Signal Processing; Issues and Promising Directions. The Open Pacing, Electrophysiology & Therapy Journal2010; 3: 4-20. doi: 10.2174/1876536X01003010004.
3.
Van MieghemT, DeKoninckP, SteenhautP, DeprestJ. Methods for prenatal assessment of fetal cardiac function. Prenatal Diagnosis2009; 29: 1193-203. doi: 10.1002/pd.2379.
4.
NeilsonJP. Fetal electrocardiogram (ECG) for fetal monitoring during labour. Cochrane Database of Systematic Reviews (Online)2006; 3: CD000116. doi: 10.1002/14651858.CD000116.pub2.
5.
KarvounisEC, PapaloukasC, FotiadisDI, MichalisLK. Fetal heart rate extraction from composite maternal ECG using complex continuous wavelet transform. Computers in Cardiology2004: 737-40. doi: 10.1109/CIC.2004.1443044.
6.
KarvounisEC, TsipourasMG, FotiadisDI, NakaKK. An Automated Methodology for Fetal Heart Rate Extraction From the Abdominal Electrocardiogram. IEEE Transactions on Information Technology in Biomedicine2007; 11: 628-38. doi: 10.1109/TITB.2006.888698.
7.
CliffordG, SameniR, WardJ, RobinsonJ, WolfbergAJ. Clinically accurate fetal ECG parameters acquired from maternal abdominal sensors. Am J Obstet Gynecol2011; 205: 47. doi: 10.1016/j.ajog.2011.02.066.
8.
SameniR, JuttenC, ShamsollahiMB. Multichannel electrocardiogram decomposition using periodic component analysis. IEEE Transactions on Bio-Medical Engineering2008; 55: 1935-40. doi: 10.1109/TBME.2008.919714.
SatoM, KimuraY, ChidaS, ItoT, KatayamaN, OkamuraK, et al. A novel extraction method of fetal electrocardiogram from the composite abdominal signal. IEEE Transactions on Bio-Medical Engineering2007; 54: 49-58. doi: 10.1109/TBME.2006.883791.
11.
AssalehK, Al-NashashH. A novel technique for the extraction of fetal ECG using polynomial networks. IEEE Transactions on Biomedical Engineering2005; 52: 1148-52. doi: 10.1109/TBME.2005.844046.
12.
KarvounisEC, TsipourasMG, FotiadisDI. Detection of fetal heart rate through 3-D phase space analysis from multivariate abdominal recordings. IEEE Transactions on Bio-Medical Engineering2009; 56: 1394-406. doi: 10.1109/TBME.2009.2014691.
13.
LiuG, LuanY. An adaptive integrated algorithm for noninvasive fetal ECG separation and noise reduction based on ICA-EEMD-WS. Medical & Biological Engineering & Computing2015. doi: 10.1007/s11517-015-1389-1.
14.
NiknazarM, RivetB, JuttenC. Fetal ECG extraction by extended state Kalman filtering based on single-channel recordings. IEEE Transactions on Bio-Medical Engineering2013; 60: 1345-52. doi: 10.1109/TBME.2012.2234456.
15.
Martín-ClementeR, Camargo-OlivaresJL, Hornillo-MelladoS, ElenaM, RomanI. Fast technique for noninvasive fetal ECG extraction. IEEE Transactions on Bio-Medical Engineering2011; 58: 227-30. doi: 10.1109/TBME.2010.2059703.
16.
Camargo-OlivaresJL, Martín-ClementeR, Hornillo-MelladoS, ElenaMM, RománI, Martiín-ClementeR, et al. The maternal abdominal ECG as input to MICA in the fetal ECG extraction problem. IEEE Signal Processing Letters2011; 18: 161-4. doi: 10.1109/LSP.2011.2104415.
17.
AlmeidaR, GonçalvesH, BernardesJ, RochaAP. Fetal QRS detection and heart rate estimation: A wavelet-based approach. Physiological Measurement2014; 35: 1723-35. doi: 10.1088/0967-3334/35/8/1723.
18.
WuS, ShenY, ZhouZ, LinL, ZengY, GaoX. Research of fetal ECG extraction using wavelet analysis and adaptive filtering. Computers in Biology and Medicine2013; 43: 1622-7. doi: 10.1016/j.compbiomed.2013.07.028.
19.
Arias-OrtegaR. Single channel abdominal ECG algorithm for real-time maternal and fetal heart rate monitoring. Revista Mexicana de Ingeniería Biomédica2010; 31(2): 111-118.
20.
KotasM, JezewskiJ, HorobaK, MatoniaA. Application of spatio-temporal filtering to fetal electrocardiogram enhancement. Computer Methods and Programs in Biomedicine2011; 104: 1-9. doi: 10.1016/j.cmpb.2010.07.004.
21.
MandicDP, Ur RehmanN, WuZ, HuangNE. Empirical mode decomposition-based time-frequency analysis of multivariate signals: The power of adaptive data analysis. IEEE Signal Processing Magazine2013; 30: 74-86. doi: 10.1109/MSP.2013.2267931.
22.
BeharJ, JohnsonA, CliffordGD, OsterJ. A comparison of single channel fetal ECG extraction methods. Annals of Biomedical Engineering2014; 42: 1340-53. doi: 10.1007/s10439-014-0993-9.
23.
GoldbergerAL, AmaralLA, GlassL, HausdorffJM, IvanovPC, MarkRG, et al. PhysioBank, PhysioToolkit, and PhysioNet: Components of a new research resource for complex physiologic signals. Circulation2000; 101: E215-20. doi: 10.1161/01.CIR.101.23.e215.
24.
KotasM, JezewskiJ, MatoniaA, KupkaT. Towards noise immune detection of fetal QRS complexes. Computer Methods and Programs in Biomedicine2010; 97: 241-56. doi: 10.1016/j.cmpb.2009.09.005.
25.
HuangNE. Review of empirical mode decomposition. Proceedings of SPIE, vol. 4391, 2001, p. 71-80. doi: 10.1117/12.421232.
Ur RehmanN, MandicDP. Empirical mode decomposition for trivariate signals. IEEE Transactions on Signal Processing2010; 58: 1059-68. doi: 10.1109/TSP.2009.2033730.
29.
RehmanN, MandicDP. Multivariate empirical mode decomposition. Proceedings of the Royal Society A: Mathematical, Physical and Engineering Sciences2009; 466: 1291-302. doi: 10.1098/rspa.2009.0502.
30.
HuangNE, ShenZ, LongSR, WuMC, ShihHH, ZhengQ, et al. The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis. Proceedings of the Royal Society A: Mathematical, Physical and Engineering Sciences1998; 454: 903-95. doi: 10.1098/rspa.1998.0193.
31.
LangloisD, ChartierS, GosselinD. An Introduction to Independent Component Analysis: InfoMax and FastICA Algorithms. Tutorials in Quantitative Methods for Psychology2010; 6: 31-8.
32.
RutledgeDN, Jouan-Rimbaud BouveresseD. Independent Components Analysis with the JADE algorithm. TrAC - Trends in Analytical Chemistry2013; 50: 22-32. doi: 10.1016/j.trac.2013.03.013.
33.
PanJ, TompkinsWJ. A real-time QRS detection algorithm. IEEE Transactions on Bio-Medical Engineering1985; 32: 230-6. doi: 10.1109/TBME.1985.325532.
34.
ArzenoNM, DengZ-D, PoonC-S. Analysis of first-derivative based QRS detection algorithms. IEEE Transactions on Bio-Medical Engineering2008; 55: 478-84. doi: 10.1109/TBME.2007.912658.
35.
HasanM, IbrahimyM, ReazM. An efficient method for fetal electrocardiogram extraction from the abdominal electrocardiogram signal. Journal of Computer Science2009; 5(9): 619-623. doi: 10.3844/jcssp.2009.619.623.
