Cancellation of the maternal and extraction of the fetal ECG in noninvasive recordings

No signal processing technique has been able to reliably deliver an undistorted fetal electrocardiographic (fECG) signal from electrodes placed on the maternal abdomen because of the low signal-to-noise ratio of the fECG recorded from the maternal body surface, resulting in increased rates of Caesarean deliveries of healthy infants. In an attempt to solve the problem a Physionet/Computing in Cardiology announced the 2013 Challenge: Noninvasive fetal ECG. We are suggesting a method for cancellation of the maternal ECG consisting of maternal QRS detection, heart rate dependant P-QRS-T interval selection, location of the fiducial points inside this interval for best matching by cross correlation, superimposition of the intervals, calculation of the mean signal of the P-QRS-T interval, and sequential subtraction of the mean signal from the whole jECG recording. A combined lead of all the 4 channels was synthesized and fetal QRS detection was performed on it. All 100 recordings of test set B were processed, the times of occurrence of the fetal QRSs were recorded and sent as results to the Organizers of the Challenge. The calculated average scores are: 285.132 for Events 1 and 4: Fetal heart rate measurement; 19. 962 for Events 2 and 5: Fetal RR interval measurement.