Image Reconstruction Algorithm in Electrical Impedance Tomography Based on Improved CNN-RBF Model

Electrical Impedance Tomography (EIT) is a noninvasive and real-time medical imaging technique, which means more potential applications for clinical diagnosis and treatments. However, EIT reconstruction problem is a highly nonlinear and ill-posed problem which will lead to poor reconstruction quality. Since neural networks have been proven to fit any nonlinearmapping theoretically, there are significant advantages of neural networks for EIT reconstruction. Convolutional neural networks (CNN), as one of the most famous neural networks, have powerful spatial feature extraction capabilities. Radial basis function (RBF) neural networks represent local approximators to nonlinear mapping, which has the significant advantage of short training time. In this paper, we proposed a two-part solver for the EIT reconstruction problem based on deep learning. RBF neural networks are used to solve the EIT reconstruction problem while CNN are used for feature extraction.