Calderon's Method-Guided Deep Neural Network for Electrical Impedance Tomography

Electrical impedance tomography (EIT) is a noninvasive, cost-effective, and structurally simple technology that enables applications in many fields by measuring changes in electrical parameters. However, the nonlinearity and ill-posedness of the EIT image reconstruction process hinder the complete recovery of the electrical parameters of the field from the measured data, making it still challenging. A Calderon's method-guided deep neural network (CGDNN) which consists of Calderon's method as a preliminary imaging module and deep neural network as an image segmentation module is proposed in this article. The preliminary imaging module of CGDNN avoids the computation of the sensitivity matrix and provides a fast and stable nonlinear mapping from measurement data to reconstruction images to facilitate image-to-image mapping by deep neural networks. The preliminary imaging module and the image segmentation module are connected by multichannel to avoid the manual selection of optimal preimage. In order to obtain more accurate reconstruction results, a network structure of multilevel U-Net with dense skip connections is applied. Simulation data and experimental data are used to evaluate the feasibility and effectiveness of CGDNN. The results show that CGDNN can obtain high-quality electrical properties distribution images quickly and accurately compared with traditional methods and deep learning image reconstruction methods.