1. Noninvasive Extraction of Maternal and Fetal ECG using Periodic Progressive FastICA Peel-off
- Author
-
Li, Yao, Luo, Xuanyu, Zhao, Haowen, Cui, Jiawen, She, Yangfan, Li, Dongfang, Jiang, Lai, and Zhang, Xu
- Subjects
Physics - Medical Physics ,Computer Science - Human-Computer Interaction - Abstract
The abdominal electrocardiogram (AECG) gives a safe and non-invasive way to monitor fetal well-being during pregnancy. However, due to the overlap with maternal ECG (MECG) as well as significant external noise, it is challenging to extract weak fetal ECG (FECG) using surface electrodes. In this study, we introduce a novel periodic progressive FastICA peel-off (PPFP) method for noninvasive extraction of weak surface FECG signals, leveraging the two-step FastICA method and a peel-off strategy from the progressive FastICA peel-off (PFP) approach. Specifically, for ECG signals, the periodic constrained FastICA that integrates ECG signal characteristics enables precise extraction of MECG and FECG spike trains. Additionally, a peel-off strategy incorporating SVD waveform reconstruction ensures comprehensive identification of subtle source signals. The performance of the proposed method was examined on public datasets with reference, synthetic data and clinical data, with an F1-scores for FECG extraction on public dataset of 99.59%, on synthetic data with the highest noise level of 99.50%, which are all superior to other comparative methods. Furthermore, clearly periodic and physiologically consistent FECG signals were extracted from clinically collected data. The results indicates that our proposed method has potential and effectiveness to separate MECG and weak FECG from multichannel AECG with high precision in high noise condition, which is of vital importance for ensuring the safety of both the fetus and the mother, as well as the advancement of artificial intelligent clinical monitoring.
- Published
- 2024