English

Graph Convolutional Networks for Model-Based Learning in Nonlinear Inverse Problems

Image and Video Processing 2021-07-12 v2 Machine Learning Numerical Analysis Neural and Evolutionary Computing Numerical Analysis Optimization and Control

Abstract

The majority of model-based learned image reconstruction methods in medical imaging have been limited to uniform domains, such as pixelated images. If the underlying model is solved on nonuniform meshes, arising from a finite element method typical for nonlinear inverse problems, interpolation and embeddings are needed. To overcome this, we present a flexible framework to extend model-based learning directly to nonuniform meshes, by interpreting the mesh as a graph and formulating our network architectures using graph convolutional neural networks. This gives rise to the proposed iterative Graph Convolutional Newton-type Method (GCNM), which includes the forward model in the solution of the inverse problem, while all updates are directly computed by the network on the problem specific mesh. We present results for Electrical Impedance Tomography, a severely ill-posed nonlinear inverse problem that is frequently solved via optimization-based methods, where the forward problem is solved by finite element methods. Results for absolute EIT imaging are compared to standard iterative methods as well as a graph residual network. We show that the GCNM has strong generalizability to different domain shapes and meshes, out of distribution data as well as experimental data, from purely simulated training data and without transfer training.

Keywords

Cite

@article{arxiv.2103.15138,
  title  = {Graph Convolutional Networks for Model-Based Learning in Nonlinear Inverse Problems},
  author = {William Herzberg and Daniel B. Rowe and Andreas Hauptmann and Sarah J. Hamilton},
  journal= {arXiv preprint arXiv:2103.15138},
  year   = {2021}
}

Comments

9 figures, 5 tables

R2 v1 2026-06-24T00:37:28.488Z