Solving electrical impedance tomography with deep learning
From MaRDI portal
Abstract: 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.
Recommendations
- Construct Deep Neural Networks based on Direct Sampling Methods for Solving Electrical Impedance Tomography
- Numerical solution of inverse problems by weak adversarial networks
- Learning nonlinear electrical impedance tomography
- Solving optical tomography with deep learning
- High-Order Regularized Regression in Electrical Impedance Tomography
Cites work
- A multiscale neural network based on hierarchical nested bases
- A nonlinear multigrid for imaging electrical conductivity and permittivity at low frequency
- A Nonlinear Primal-Dual Method for Total Variation-Based Image Restoration
- BCR-net: A neural network based on the nonstandard wavelet form
- Deep learning
- Dirichlet-to-Neumann maps on bounded Lipschitz domains
- Electrical impedance tomography
- Electrical impedance tomography and Calderón's problem
- Elliptic partial differential equations of second order
- Examples of instability in inverse boundary-value problems
- Fast wavelet transforms and numerical algorithms I
- Hidden physics models: machine learning of nonlinear partial differential equations
- scientific article; zbMATH DE number 4173559 (Why is no real title available?)
- Inverse problems with structural prior information
- On an inverse boundary value problem
- On optimization techniques for solving nonlinear inverse problems
- Regularizing properties of a truncated newton-cg algorithm for nonlinear inverse problems
- Solving for high-dimensional committor functions using artificial neural networks
- Solving high-dimensional partial differential equations using deep learning
- Solving the quantum many-body problem with artificial neural networks
- Stability and resolution analysis of a linearized problem in electrical impedance tomography
- Stable determination of conductivity by boundary measurements
- The deep Ritz method: a deep learning-based numerical algorithm for solving variational problems
Cited in
(43)- Non-cooperative finite element games
- Learning nonlinear electrical impedance tomography
- Solving optical tomography with deep learning
- Solving inverse problems using conditional invertible neural networks
- Meta-learning pseudo-differential operators with deep neural networks
- Neural networks for classification of strokes in electrical impedance tomography on a 3D head model
- A deep learning-based hybrid approach for the solution of multiphysics problems in electrosurgery
- An overview on deep learning-based approximation methods for partial differential equations
- Linearized inverse Schrödinger potential problem with partial data and its deep neural network inversion
- Solving traveltime tomography with deep learning
- The Random Feature Model for Input-Output Maps between Banach Spaces
- Construct Deep Neural Networks based on Direct Sampling Methods for Solving Electrical Impedance Tomography
- Algorithms for solving high dimensional PDEs: from nonlinear Monte Carlo to machine learning
- On reconstruction of binary images by efficient sample-based parameterization in applications for electrical impedance tomography
- Machine learning enhanced electrical impedance tomography for 2D materials
- Numerical solution of inverse problems by weak adversarial networks
- Classification of stroke using neural networks in electrical impedance tomography
- Application of a class of iterative algorithms and their accelerations to Jacobian-based linearized EIT image reconstruction
- Multilevel Fine-Tuning: Closing Generalization Gaps in Approximation of Solution Maps under a Limited Budget for Training Data
- Strong Solutions for PDE-Based Tomography by Unsupervised Learning
- PDE-aware deep learning for inverse problems in cardiac electrophysiology
- Combining gradient optimization and machine learning methods for inverse problems in layered heterogeneous media
- Electrical impedance tomography with deep Calderón method
- Convergence Rates for Learning Linear Operators from Noisy Data
- A high order discontinuous Galerkin method for the recovery of the conductivity in electrical impedance tomography
- Enhancing electrical impedance tomography reconstruction using learned half-quadratic splitting networks with Anderson acceleration
- Solving inverse problems with deep learning
- On mathematical modeling in image reconstruction and beyond
- Conductivity Imaging from Internal Measurements with Mixed Least-Squares Deep Neural Networks
- A two-step accelerated Landweber-type iteration regularization algorithm for sparse reconstruction of electrical impedance tomography
- Optimal transportation for electrical impedance tomography
- The Calderón's problem via DeepONets
- A comparative study of variational autoencoders, normalizing flows, and score-based diffusion models for electrical impedance tomography
- Operator learning using random features: a tool for scientific computing
- Current density impedance imaging with PINNs
- An analysis of discontinuous Galerkin method for electrical impedance tomography with partial data
- A comparison of techniques to improve pulmonary EIT image resolution using a database of simulated EIT images
- The discrete inverse conductivity problem solved by the weights of an interpretable neural network
- Multi-scale frequency-enhanced deep D-bar method for electrical impedance tomography
- Solving high-dimensional Kolmogorov backward equations with functional hierarchical tensor operators
- ODE-DPS: ODE-based diffusion posterior sampling for linear inverse problems in partial differential equation
- Operator learning for hyperbolic PDEs
- The use of neural network approximation models to speed up the optimisation process in electrical impedance tomography
This page was built for publication: Solving electrical impedance tomography with deep learning
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2223016)
