Enhancing electrical resistance tomography reconstruction from conductive fabric: a comparative study of CycleGAN and pix2pixGAN

Abstract

Abstract Monitoring fetal health is crucial in prenatal care, and existing techniques for assessing fetal movements are often expensive and limited to clinical environments. This research investigates the potential of utilizing electrical resistance tomography (ERT) with a conductive fabric to create a cost-effective and non-invasive imaging solution for fetal monitoring. The fusion of ERT with wearable e-textile devices facilitates continuous and portable monitoring. To improve the quality of ERT-generated images, we propose the application of CycleGAN and pix2pixGAN, both machine learning models based on generative adversarial networks. These models learn to map reconstructed images to target images, thereby enhancing reconstruction precision and image quality. The outcomes of this research highlight the effectiveness of the suggested method in managing noisy data and achieving superior image generation. This work presents a promising approach to fetal monitoring using ERT and deep learning techniques, opening possibilities for more affordable and accessible prenatal care.