Solving Electrical Impedance Tomography with Deep Learning
This addresses EIT, a domain-specific imaging problem, with an incremental approach using deep learning.
The paper tackled the problem of solving electrical impedance tomography (EIT) by inverting the electrical conductivity from the Dirichlet-to-Neumann map, proposing compact neural network architectures for both forward and inverse maps in 2D and 3D, with numerical results demonstrating efficiency.
This paper introduces a new approach for solving electrical impedance tomography (EIT) problems using deep neural networks. The mathematical problem of EIT is to invert the electrical conductivity from the Dirichlet-to-Neumann (DtN) map. Both the forward map from the electrical conductivity to the DtN map and the inverse map are high-dimensional and nonlinear. Motivated by the linear perturbative analysis of the forward map and based on a numerically low-rank property, we propose compact neural network architectures for the forward and inverse maps for both 2D and 3D problems. Numerical results demonstrate the efficiency of the proposed neural networks.