Deep D-Bar: Real-Time Electrical Impedance Tomography Imaging With Deep Neural Networks
Sarah Hamilton,Andreas Hauptmann +1 more
Reads0
Chats0
TLDR
In this article, D-bar methods are used to provide robust direct reconstructions by using a low-pass filtering of the associated nonlinear Fourier data for electrical impedance tomography (EIT) images.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 paper, 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.read more
Citations
More filters
Journal ArticleDOI
DNNs as Applied to Electromagnetics, Antennas, and Propagation—A Review
TL;DR: A review of the most recent advances in deep learning as applied to electromagnetics, antennas, and propagation is provided, aimed at giving the interested readers and practitioners in EM and related applicative fields some useful insights on the effectiveness and potentialities of DNNs as computational tools with unprecedented computational efficiency.
Journal ArticleDOI
Dominant-Current Deep Learning Scheme for Electrical Impedance Tomography
Zhun Wei,Dong Liu,Xudong Chen +2 more
TL;DR: A dominant-current deep learning scheme for EIT imaging, in which dominant parts of ICC are utilized to generate multi-channel inputs of CNN and significant performance improvements of the proposed methods are shown in reconstructing targets with sharp corners or edges.
Journal ArticleDOI
Two-Step Enhanced Deep Learning Approach for Electromagnetic Inverse Scattering Problems
TL;DR: A new two-step machine learning based approach is proposed to solve the electromagnetic inverse scattering (EMIS) problems, which serves a new path for realizing real-time quantitative microwave imaging for high-contrast objects.
Posted Content
Deep Bayesian Inversion
Jonas Adler,Ozan Öktem +1 more
TL;DR: Characterizing statistical properties of solutions of inverse problems is essential for decision making and Bayesian inversion offers a tractable framework for this purpose, but current approaches are not tractable.
Journal ArticleDOI
Fundamentals, Recent Advances, and Future Challenges in Bioimpedance Devices for Healthcare Applications
TL;DR: The basis and fundamentals of bioimpedance measurements are described covering issues ranging from the hardware diagrams to the configurations and designs of the electrodes and from the mathematical models that describe the frequency behavior of the bioimpingance to the sources of noise and artifacts.
References
More filters
Book ChapterDOI
U-Net: Convolutional Networks for Biomedical Image Segmentation
TL;DR: Neber et al. as discussed by the authors proposed a network and training strategy that relies on the strong use of data augmentation to use the available annotated samples more efficiently, which can be trained end-to-end from very few images and outperforms the prior best method (a sliding-window convolutional network) on the ISBI challenge for segmentation of neuronal structures in electron microscopic stacks.
Journal ArticleDOI
Deep Convolutional Neural Network for Inverse Problems in Imaging
TL;DR: In this paper, the authors proposed a deep convolutional neural network (CNN)-based algorithm for solving ill-posed inverse problems, which combines multiresolution decomposition and residual learning in order to learn to remove these artifacts while preserving image structure.
Journal ArticleDOI
Global uniqueness for a two-dimensional inverse boundary value problem
TL;DR: In this article, it was shown that the coefficient -y(x) of the elliptic equation Vie (QyVu) = 0 in a two-dimensional domain is uniquely determined by the corresponding Dirichlet-to-Neumann map on the boundary.
Journal ArticleDOI
Existence and uniqueness for electrode models for electric current computed tomography
TL;DR: Cheng et al. as mentioned in this paper proposed a model that is capable of predicting the experimentally measured voltages to within 0.1 percent of the observed voltages, and proved the existence and uniqueness of the associated electrical potential.
Journal ArticleDOI
A deep convolutional neural network using directional wavelets for low-dose X-ray CT reconstruction.
TL;DR: This work proposes an algorithm which uses a deep convolutional neural network which is applied to the wavelet transform coefficients of low‐dose CT images and effectively removes complex noise patterns from CT images derived from a reduced X‐ray dose.