Deep D-bar: Real time Electrical Impedance Tomography Imaging with Deep Neural Networks

TL;DR

This paper introduces Deep D-bar, a neural network approach that enhances real-time Electrical Impedance Tomography images by sharpening blurred reconstructions, combining rigorous mathematical methods with deep learning for improved image quality.

Contribution

The study integrates CNN post-processing with D-bar EIT methods, enabling sharp, reliable images without transfer training on experimental data.

Findings

CNN improves image sharpness and reliability

Method works on experimental EIT data

Real-time imaging capability demonstrated

Abstract

The mathematical problem for Electrical Impedance Tomography (EIT) is a highly nonlinear ill-posed inverse problem requiring carefully designed reconstruction procedures to ensure reliable image generation. D-bar methods are based on a rigorous mathematical analysis and provide robust direct reconstructions by using a low-pass filtering of the associated nonlinear Fourier data. Similarly to low-pass filtering of linear Fourier data, only using low frequencies in the image recovery process results in blurred images lacking sharp features such as clear organ boundaries. Convolutional Neural Networks provide a powerful framework for post-processing such convolved direct reconstructions. In this study, we demonstrate that these CNN techniques lead to sharp and reliable reconstructions even for the highly nonlinear inverse problem of EIT. The network is trained on data sets of simulated examples and then applied to experimental data without the need to perform an additional transfer training. Results for absolute EIT images are presented using experimental EIT data from the ACT4 and KIT4 EIT systems.