End-to-End Deep Learning Architecture for Separating Maternal and Fetal ECGs Using W-Net

Fetal cardiac monitoring and assessment during pregnancy play a critical role in the early detection of potential risk fetal problems, thus allowing for timely preventive measures healthy births. It is necessary to continuously monitor heart this purpose. Methods by extracting maternal electrocardiograms (ECGs) from abdominal ECGs have been extensively investigated. However, extraction clear ECG major challenge because signals are typically dominated noise. Most existing methods involve several steps, such as removing then ECG. To address complexity process, we propose novel method effectively decomposing single-channel into without using multiple steps employing an end-to-end deep learning network architecture W-net. Model training performed simulation dataset. Then, extracted real The performance proposed compared with that other state-of-the-art models on basis QRS complexes. model shows higher precision recall values F1 scores. This demonstrates can extract expected contribute commercial applications long-term monitoring.