U²-Net for 3D Electrical Impedance Tomography With Combined Electrodes

A flexible Electrical Impedance Tomography (EIT) sensor with combined electrodes is proposed to reconstruct 3D image. The 3D EIT sensor consists of 24 combined electrodes, each consisting of a center electrode and an around electrode. The accuracy of measurement data has been improved by using the combined electrodes. In this study, an innovative U2-Net neural network structure is implemented to solve the inverse problem of 3D EIT. Significant amounts of priori information obtained from simulation are stored in the U2-Net, which facilitates the improvement of image reconstruction quality. The proposed 3D EIT sensor is verified by simulation and experiment. In the simulations, U2-Net shows better performance than U-Net. Combined electrodes show better robustness than conventional structure which shows higher accuracy when the signal to noise ratio (SNR) is 20 dB or 30 dB. In the experiments, structural similarity index measure (SSIM) is proposed to evaluate the image reconstruction quality. Experimental results show that the proposed 3D EIT sensor using U2-Net improves accuracy of image reconstruction. In addition, the proposed 3D EIT sensor improves the robustness of measurement results, which is satisfactory for the requirements of 3D image reconstruction.

I. Introduction

Electrical Impedance Tomography (EIT) is a technique which reconstructs images of the conductivity distribution in the measurement domain [1], [2]. The voltage signal is measured by applying a certain excitation current signal at the boundary of the field, which is used to calculate the conductivity in the domain by a reconstruction algorithm [3], [4]. EIT has the advantages of non-invasive and fast imaging speed. Over the past 30 years, EIT technology has been widely used for lung ventilation monitoring [5]–[8], breast cancer examination [9], [10], brain detection [11] and other fields.