Stability of Electrical Impedance Tomography with Anisotropies and its Application to the Deep Caldeón Method

2026/08/04 by Tianhao Hu, Bangti Jin, Yiran Wang
Mathematics · #math.AP

paper · pdf

arxiv created 2026/08/04 · arxiv updated 2026/08/05

Abstract

In this work, we establish new conditional Lipschitz stability results for electrical impedance tomography (EIT) with anisotropies, of recovering the conductivity in a conformal class of a known anisotropic conductivity in both two- and multi-dimensional cases. Then we employ the stability theory to understand the property of the deep Calderón method, one deep learning-based technique for image reconstruction in EIT that has shown promising empirical results, but still lacks theoretical underpinnings. Specifically, we relate the stability theory to the robustness of the method with the proper choice of the training data, and present numerical results in two-dimension to complement the theoretical analysis.

Citations

• Extension and neural operator approximation of the electrical impedance tomography inverse map
• Numerical Analysis of Unsupervised Learning Approaches for Parameter Identification in PDEs
• Neural Correction Operator: A Reliable and Fast Approach for Electrical Impedance Tomography
• Learning-Enhanced Variational Regularization for Electrical Impedance Tomography via \Calderon's Method
• On the non-convexity issue in the radial Calderón problem
• Infinite-dimensional Lipschitz stability in the Calderón problem and general Zernike bases
• Robustness of data-driven approaches in limited angle tomography
• Electrical Impedance Tomography with Deep Calderón Method
• Rethinking Lipschitz Neural Networks and Certified Robustness: A Boolean Function Perspective
• The anisotropic Calderón problem at large fixed frequency on manifolds with invertible ray transform
• Theoretical Perspectives on Deep Learning Methods in Inverse Problems
• Lipschitz stable determination of polyhedral conductivity inclusions from local boundary measurements
• Training Certifiably Robust Neural Networks with Efficient Local Lipschitz Bounds
• MMV-Net: A Multiple Measurement Vector Network for Multi-frequency Electrical Impedance Tomography
• The anisotropic Calderón problem for high fixed frequency
• Construct Deep Neural Networks Based on Direct Sampling Methods for Solving Electrical Impedance Tomography
• A direct reconstruction algorithm for the anisotropic inverse conductivity problem based on Calderón's method in the plane
• The troublesome kernel -- On hallucinations, no free lunches and the accuracy-stability trade-off in inverse problems
• Universality of Deep Convolutional Neural Networks
• Universality of deep convolutional neural networks
• Deep Residual Learning for Image Recognition
• Lipschitz stability for the electrostatic inverse boundary value problem with piecewise linear conductivities
• U-Net: Convolutional Networks for Biomedical Image Segmentation
• Adam: A Method for Stochastic Optimization
• Lipschitz stability for the inverse conductivity problem for a conformal class of anisotropic conductivities
• Intriguing properties of neural networks
• Spectroscopic imaging of a dilute cell suspension
• Lipschitz stability of an inverse boundary value problem for a Schrödinger type equation
• On an inverse problem for anisotropic conductivity in the plane
• Limiting Carleman weights and anisotropic inverse problems
• Electrical Impedance Tomography
• Determining anisotropic real‐analytic conductivities by boundary measurements
• A Global Uniqueness Theorem for an Inverse Boundary Value Problem