A comprehensive survey on signal processing and machine learning techniques for non-invasive fetal ECG extraction

Despite the rapid growth in the area of adult ECG signal processing and monitoring systems, the morphological analysis of fetal ECG signals lags farther behind and demands much attention. Non-invasive fetal Electrocardiography is the safest approach for monitoring the fetus health condition by processing the abdominal ECG (AECG) signals acquired by placing electrodes on the mother's abdomen. The primary challenge associated with this method is the very poor SNR of the signal recorded because of dominant maternal ECG and other interferences contained in the AECG signal. This paper aims to provide an extensive review of the existing state of art techniques for extracting the fetal ECG signal from the AECG signals. We present details on methods available in modeling the fetal ECG, challenges associated with electrode placements, morphological analysis of extracted fetal ECG, and evaluation metrics for measuring the performance of extraction techniques. This paper provides the researchers with a detailed understanding of the problem of interest and helps in addressing future directions for processing the abdominal ECG signals.

Automated summary

Despite the rapid growth in the field of adult ECG signal processing and monitoring systems, the analysis of fetal ECG signals lags behind and requires attention. Non-invasive fetal Electrocardiography is the safest method for monitoring fetal health by processing abdominal ECG (AECG) signals acquired by placing electrodes on the mother's abdomen. The primary challenge is the low signal-to-noise ratio of the recorded signal due to the dominant maternal ECG and other interferences present in the AECG signal. This paper provides an extensive review of existing techniques for extracting fetal ECG signals from AECG signals, including modeling methods, challenges with electrode placements, morphological analysis, and evaluation metrics.