In the context of fetal monitoring, non-invasive fetal electrocardiography is an alternative approach to the traditional Doppler ultrasound technique. However, separating the fetal electrocardiography (FECG) component from the abdominal electrocardiography (AECG) remains a challenging task. This is mainly due to the interference from maternal electrocardiography, which has larger amplitude and overlaps with the FECG in both temporal and frequency domains. The main objective is to present a novel approach to FECG extraction by using a deep learning strategy from single-channel AECG recording. A residual convolutional encoder-decoder network (RCED-Net) is developed for this task of FECG extraction. The single-channel AECG recording is the input to the RCED-Net. And the RCED-Net extracts the feature of AECG and directly outputs the estimate of FECG component in the AECG recording. The AECG recordings from two different databases are collected to illustrate the efficiency of the proposed method. And the achieved results show that the proposed technique exhibits the best performance when compared to the existing methods in the literature. This work is a proof of concept that the proposed method could effectively extract the FECG component from AECG recordings. The focus on single-channel FECG extraction technique contributes to the commercial applications for long-term fetal monitoring.
Keywords: Convolutional encoder–decoder networks; FECG extraction; Fetal monitoring; Non-invasive fetal electrocardiography.