Reconstruction of EIT images via patch based sparse representation over learned dictionaries

Image reconstruction for electrical impedance tomography (EIT) is a nonlinear problem. A generalized inverse operator is usually ill-posed and ill-conditioned. Therefore, the solutions for EIT are not unique and highly sensitive to the measurement noise. To improve the image quality, a new image reconstruction algorithm for EIT based on patch-based sparse representation is proposed. For each iterative step, the sparsifying dictionary optimization and image reconstruction are performed alternately. The proposed algorithm has been evaluated by simulation with noise for different conductivity distributions. It can tolerate a relatively high level of noise in the measured voltages of EIT.