Multi-Channel Fetal ECG Denoising With Deep Convolutional Neural Networks

Abstract

Non-invasive fetal electrocardiography represents a valuable alternative continuous fetal monitoring method that has recently received considerable attention in assessing fetal health. However, the non-invasive fetal electrocardiogram (ECG) is typically severely contaminated by a considerable amount of various noise sources, rendering fetal ECG denoising a very challenging task. This work employs a deep learning approach for removing the residual noise from multi-channel fetal ECG after the maternal ECG has been suppressed. We propose a deep convolutional encoder-decoder network with symmetric skip-layer connections, learning end-to-end mappings from noise-corrupted fetal ECG signals to clean ones. Experiments on simulated data show an average signal-to-noise ratio (SNR) improvement of 9.5 dB for fetal ECG signals with input SNR ranging between −20 and 20 dB. The method is additionally evaluated on a large set of real signals, demonstrating that it can provide significant quality improvement of the noisy fetal ECG signals. We further show that employment of multi-channel signal information by the network provides superior and more reliable performance as opposed to its single-channel network counterpart. The presented method is able to preserve beat-to-beat morphological variations and does not require any prior information on the power spectra of the noise or the pulse location.

Pharmacological cardioversion of supraventricular tachycardia in pregnancy during continuous electrophysiological foetal monitoring: a case report

“…In this case report, we used an end-to-end trained deep convolutional neural network for denoising the foetal ECG signals. 10 The noninvasive foetal ECG displays variations in amplitude. Foetal movements or maternal breathing may cause such variations.…”

Non-Invasive Fetal Electrocardiogram Extraction Based on Novel Hybrid Method for Intrapartum ST Segment Analysis

“…• Artificial neural networks are used for parallel data processing based on mimicking the behavior of biological structures. The use of convolutional neural networks (CNN) to remove noise from the fECG signal has been tested in [65] with very good results. High-quality fECG filtration was also achieved in [66], where dynamic neural networks (DNN) with FIR synapses were tested and analyzed.…”

Pembersihan Artefak EOG dari Sinyal EEG menggunakan Denoising Autoencoder

“…AE merupakan salah satu model generatif, disebut generatif karena model dapat menghasilkan data berupa sinyal (Fotiadou & Vullings, 2020) ataupun gambar (Lee, dkk, 2018). Generatif model digunakan untuk beberapa tujuan salah satunya untuk meningkatkan atau menurunkan resolusi sinyal (Hartmann, dkk, 2018) (Luo, dkk, 2020), augmentasi data (Hwang, dkk, 2019) (Jiao, dkk, 2020), dan tujuan lainnya (Hu, dkk, 2015) (Nejedly, dkk, 2019).…”

“…Generatif model digunakan untuk beberapa tujuan salah satunya untuk meningkatkan atau menurunkan resolusi sinyal (Hartmann, dkk, 2018) (Luo, dkk, 2020), augmentasi data (Hwang, dkk, 2019) (Jiao, dkk, 2020), dan tujuan lainnya (Hu, dkk, 2015) (Nejedly, dkk, 2019). Turunan AE dengan peruntukan membersihkan derau disebut Denoising AE (DAE), DAE telah terbukti berhasil membersihkan derau dari data EKG (Fotiadou & Vullings, 2020) dan membersihkan foto dari hujan (Lee, dkk, 2018). Pada penelitian ini kami menggunakan DAE untuk merekonstruksi sinyal EEG yang terkontaminasi artefak EOG.…”