Deep D-bar: Real time Electrical Impedance Tomography Imaging with Deep Neural Networks

Abstract

The mathematical problem for Electrical Impedance Tomography (EIT) is a highly nonlinear ill-posed inverse problem requiring carefully designed reconstruction procedures to ensure reliable image generation. D-bar methods are based on a rigorous mathematical analysis and provide robust direct reconstructions by using a low-pass filtering of the associated nonlinear Fourier data. Similarly to low-pass filtering of linear Fourier data, only using low frequencies in the image recovery process results in blurred images lacking sharp features such as clear organ boundaries. Convolutional Neural Networks provide a powerful framework for post-processing such convolved direct reconstructions. In this study, we demonstrate that these CNN techniques lead to sharp and reliable reconstructions even for the highly nonlinear inverse problem of EIT. The network is trained on data sets of simulated examples and then applied to experimental data without the need to perform an additional transfer training. Results for absolute EIT images are presented using experimental EIT data from the ACT4 and KIT4 EIT systems.

11 pages, 13 figures

Cited by in corpus (24)

• Non-invasive Inference of Thrombus Material Properties with Physics-informed Neural Networks
• Solving inverse problems using conditional invertible neural networks
• Deep Bayesian Inversion
• Numerical Solution of Inverse Problems by Weak Adversarial Networks
• Structural engineering from an inverse problems perspective
• Deep Learning Methods for Partial Differential Equations and Related Parameter Identification Problems
• Estimation of groundwater storage from seismic data using deep learning
• Impedance-optical Dual-modal Cell Culture Imaging with Learning-based Information Fusion
• An efficient Quasi-Newton method for nonlinear inverse problems via learned singular values
• Neural networks for classification of strokes in electrical impedance tomography on a 3D head model
• A Two-Stage Imaging Framework Combining CNN and Physics-Informed Neural Networks for Full-Inverse Tomography: A Case Study in Electrical Impedance Tomography (EIT)
• Log-Gaussian Gamma Processes for Training Bayesian Neural Networks in Raman and CARS Spectroscopies
• Is Machine Learning Able to Detect and Classify Failure in Piezoresistive Bone Cement Based on Electrical Signals?
• Enhancing Electrical Impedance Tomography reconstruction using Learned Half-Quadratic Splitting Networks with Anderson Acceleration
• A boundary integral equation method for the complete electrode model in electrical impedance tomography with tests on experimental data
• CorDEL: A Contrastive Deep Learning Approach for Entity Linkage
• Machine learning for structural design models of continuous beam systems via influence zones
• Construct Deep Neural Networks Based on Direct Sampling Methods for Solving Electrical Impedance Tomography
• On Reconstruction of Binary Images by Efficient Sample-based Parameterization in Applications for Electrical Impedance Tomography
• Fusing electrical and elasticity imaging
• On the randomised stability constant for inverse problems
• Learned enclosure method for experimental EIT data
• Solver-in-the-Loop joint operator learning: fractional Laplace-Beltrami features for interface reconstruction
• Optimizing electrode positions in 2D Electrical Impedance Tomography using deep learning