A Complex UNet Approach for Non-Invasive Fetal ECG Extraction Using Single-Channel Dry Textile Electrodes

Abstract

Continuous, non-invasive pregnancy monitoring is crucial for minimising potential complications. The fetal electrocardiogram (fECG) represents a promising tool for assessing fetal health beyond clinical environments. Home-based monitoring necessitates the use of a minimal number of comfortable and durable electrodes, such as dry textile electrodes. However, this setup presents many challenges, including increased noise and motion artefacts, which complicate the accurate extraction of fECG signals. To overcome these challenges, we introduce a pioneering method for extracting fECG from single-channel recordings obtained using dry textile electrodes using AI techniques. We created a new dataset by simulating abdominal recordings, including noise closely resembling real-world characteristics of in-vivo recordings through dry textile electrodes, alongside mECG and fECG. To ensure the reliability of the extracted fECG, we propose an innovative pipeline based on a complex-valued denoising network, Complex UNet. Unlike previous approaches that focused solely on signal magnitude, our method processes both real and imaginary components of the spectrogram, addressing phase information and preventing incongruous predictions. We evaluated our novel pipeline against traditional, well-established approaches, on both simulated and real data in terms of fECG extraction and R-peak detection. The results showcase that our suggested method achieves new state-of-the-art results, enabling an accurate extraction of fECG morphology across all evaluated settings. This method is the first to effectively extract fECG signals from single-channel recordings using dry textile electrodes, making a significant advancement towards a fully non-invasive and self-administered fECG extraction solution.