Imaging Conductivity from Current Density Magnitude using Neural Networks

Abstract

Conductivity imaging represents one of the most important tasks in medical imaging. In this work we develop a neural network based reconstruction technique for imaging the conductivity from the magnitude of the internal current density. It is achieved by formulating the problem as a relaxed weighted least-gradient problem, and then approximating its minimizer by standard fully connected feedforward neural networks. We derive bounds on two components of the generalization error, i.e., approximation error and statistical error, explicitly in terms of properties of the neural networks (e.g., depth, total number of parameters, and the bound of the network parameters). We illustrate the performance and distinct features of the approach on several numerical experiments. Numerically, it is observed that the approach enjoys remarkable robustness with respect to the presence of data noise.

29 pp, 9 figures (several typos are corrected in the new version), to appear at Inverse Problems

References in corpus (7)

• Algorithms for Solving High Dimensional PDEs: From Nonlinear Monte Carlo to Machine Learning
• The Finite Neuron Method and Convergence Analysis
• Solving inverse-PDE problems with physics-aware neural networks
• Numerical Solution of Inverse Problems by Weak Adversarial Networks
• Convergence Rate Analysis for Deep Ritz Method
• Two-Layer Neural Networks for Partial Differential Equations: Optimization and Generalization Theory
• A Priori Analysis of Stable Neural Network Solutions to Numerical PDEs