A Comparison of Single Channel Fetal ECG Extraction Methods
- 967 Downloads
The abdominal electrocardiogram (ECG) provides a non-invasive method for monitoring the fetal cardiac activity in pregnant women. However, the temporal and frequency overlap between the fetal ECG (FECG), the maternal ECG (MECG) and noise results in a challenging source separation problem. This work seeks to compare temporal extraction methods for extracting the fetal signal and estimating fetal heart rate. A novel method for MECG cancelation using an echo state neural network (ESN) based filtering approach was compared with the least mean square (LMS), the recursive least square (RLS) adaptive filter and template subtraction (TS) techniques. Analysis was performed using real signals from two databases composing a total of 4 h 22 min of data from nine pregnant women with 37,452 reference fetal beats. The effects of preprocessing the signals was empirically evaluated. The results demonstrate that the ESN based algorithm performs best on the test data with an F1 measure of 90.2% as compared to the LMS (87.9%), RLS (88.2%) and the TS (89.3%) techniques. Results suggest that a higher baseline wander high pass cut-off frequency than traditionally used for FECG analysis significantly increases performance for all evaluated methods. Open source code for the benchmark methods are made available to allow comparison and reproducibility on the public domain data.
KeywordsFetal ECG Reservoir computing Template subtraction Adaptive noise canceller
JB is supported by the UK Engineering and Physical Sciences Research Council, the Balliol French Anderson Scholarship Fund and MindChild Medical Inc. North Andover, MA. JO is supported by Wellcome Trust Centre Grant No. 098461/Z/12/Z (Sleep, Circadian Rhythms & Neuroscience Institute). AJ acknowledges the support of the RCUK Digital Economy Programme grant number EP/G036861/1 (Oxford Centre for Doctoral Training in Healthcare Innovation).
- 1.ANSI/AAMI/ISO EC57 (1998/(R)2008) Testing and reporting performance results of cardiac rhythm and ST-segment measurement algorithms.Google Scholar
- 2.Åström, K. J., and B. Wittenmark. Adaptive Control, 2nd ed. Reading, MA: Addison Wesley, 1994.Google Scholar
- 4.Behar, J., A. Johnson, J. Oster, and G. D. Clifford. An Echo State Neural Network for Foetal Electrocardiogram Extraction Optimised by Random Search. Nevada: NIPS Lake Tahoe, 2013a.Google Scholar
- 5.Behar, J., J. Oster, and G. D. Clifford. Non invasive FECG extraction from a set of abdominal sensors. In: Computing in Cardiology 2013, Zaragoza, Spain, 2013b.Google Scholar
- 6.Bergstra, J., and Y. Bengio. Random search for hyper-parameter optimization. J. Mach. Learn. Res. 13:281–305, 2012.Google Scholar
- 7.Cardoso, J., and A. Souloumiac. Blind beamforming for non Gaussian signals. In: Institute Electrical Engineer Proceedings of Radar Signal Processing, London, vol. 140(6), pp. 362–370, 1993.Google Scholar
- 10.Clifford, G. D., J. Behar, J. Oster, and A. Johnson. IPM Open Source Code. https://firstname.lastname@example.org/works/IPMCode/, 2014. Last updated Feb 2014.
- 12.Cohen, W. R., S. Ommani, S. Hassan, F. G. Mirza, M. Solomon, R. Brown, B. S. Schifrin, J. M. Himsworth, and B. R. Hayes-Gill. Accuracy and reliability of fetal heart rate monitoring using maternal abdominal surface electrodes. Acta Obstet .Gynecol. Scand. 91(11):1306–1313, 2012.PubMedCrossRefGoogle Scholar
- 13.Douglas, S. Numerically-robust O (N(2)) RLS algorithms using least-squares prewhitening. In: Proceedings of IEEE International Conference on Acoustic, Speech, and Signal Processing, vol. 1, pp. 412–415, 2000.Google Scholar
- 14.Goldberger, A. L., L. A. Amaral, L. Glass, J. M. Hausdorff, P. C. Ivanov, R. G. Mark, J. E. Mietus, G. B. Moody, C. K. Peng, and H. E. Stanley. PhysioBank, PhysioToolkit, and PhysioNet: components of a new research resource for complex physiologic signals. Circulation 101(23):215–220, 2000.CrossRefGoogle Scholar
- 15.Guerrero-Martinez, J., M. Martinez-Sober, M. Bataller-Mompean, and J. Magdalena-Benedito. New algorithm for fetal QRS detection in surface abdominal records. In: Computation in Cardiology, pp. 441–444, 2006.Google Scholar
- 17.Jaeger, H. The “echo state” approach to analysing and training recurrent neural networks. Technical Report GMD Report 148. German National Research Center for Information Technology 148, 2001. http://www.faculty.jacobs-university.de/hjaeger/pubs/EchoStatesTechRep.pdf.
- 18.Jaeger, H. A tutorial on training recurrent neural networks, covering BPPT, RTRL, EKF and the “echo state network” approach, 3rd revision. GMD-Forschungszentrum Informationstechnik, 2008. http://www.pdx.edu/sites/www.pdx.edu.sysc/files/Jaeger_TrainingRNNsTutorial.2005.pdf.
- 29.Sameni, R. Extraction of Fetal Cardiac Signals from an Array of Maternal Abdominal Recordings. Ph.D. Thesis, Sharif University of Technology, Institut National Polytechnique de Grenoble, 2008. http://www.sameni.info/Publications/Thesis/PhDThesis.pdf.
- 32.Silva, I., J. Behar, G. D. Clifford, and G. B. Moody. Noninvasive fetal ECG: the PhysioNet/Computing in Cardiology Challenge 2013. In: Computing in Cardiology 2013, Zaragoza, Spain, 2013.Google Scholar
- 37.Zaunseder, S., F. Andreotti, M. Cruz, H. Stepan, C. Schmieder, H. Malberg, and A. Jank. (Como, July 2012) Fetal QRS detection by means of Kalman filtering and using the Event Synchronous Canceller. In: 7th International Workshop on Biosignal Interpretation.Google Scholar