Deep Convolutional Neural Network for Inverse Problems in Imaging
From MaRDI portal
Abstract: In this paper, we propose a novel deep convolutional neural network (CNN)-based algorithm for solving ill-posed inverse problems. Regularized iterative algorithms have emerged as the standard approach to ill-posed inverse problems in the past few decades. These methods produce excellent results, but can be challenging to deploy in practice due to factors including the high computational cost of the forward and adjoint operators and the difficulty of hyper parameter selection. The starting point of our work is the observation that unrolled iterative methods have the form of a CNN (filtering followed by point-wise non-linearity) when the normal operator (H*H, the adjoint of H times H) of the forward model is a convolution. Based on this observation, we propose using direct inversion followed by a CNN to solve normal-convolutional inverse problems. The direct inversion encapsulates the physical model of the system, but leads to artifacts when the problem is ill-posed; the CNN combines multiresolution decomposition and residual learning in order to learn to remove these artifacts while preserving image structure. We demonstrate the performance of the proposed network in sparse-view reconstruction (down to 50 views) on parallel beam X-ray computed tomography in synthetic phantoms as well as in real experimental sinograms. The proposed network outperforms total variation-regularized iterative reconstruction for the more realistic phantoms and requires less than a second to reconstruct a 512 x 512 image on GPU.
Cited in
(only showing first 100 items - show all)- Mini-workshop: Deep learning and inverse problems. Abstracts from the mini-workshop held March 4--10, 2018
- Regularization by architecture: a deep prior approach for inverse problems
- Networks for nonlinear diffusion problems in imaging
- Non-invasive inference of thrombus material properties with physics-informed neural networks
- A data and knowledge driven approach for SPECT using convolutional neural networks and iterative algorithms
- Deep learning on image denoising: an overview
- Learning to scan: a deep reinforcement learning approach for personalized scanning in CT imaging
- Estimating adsorption isotherm parameters in chromatography via a virtual injection promoting double feed-forward neural network
- Constrained and unconstrained deep image prior optimization models with automatic regularization
- Deep learning architectures for nonlinear operator functions and nonlinear inverse problems
- Solving inverse problems using conditional invertible neural networks
- On finite-horizon \(H_\infty\) state estimation for discrete-time delayed memristive neural networks under stochastic communication protocol
- On the randomised stability constant for inverse problems
- Analytic continuation of noisy data using Adams Bashforth residual neural network
- Solving inverse-PDE problems with physics-aware neural networks
- A Helmholtz equation solver using unsupervised learning: application to transcranial ultrasound
- Feasibility-based fixed point networks
- A tailor-made 3-dimensional directional Haar semi-tight framelet for pMRI reconstruction
- Learnable Douglas-Rachford iteration and its applications in DOT imaging
- A nonlocal image denoising algorithm using the structural similarity metric
- A review on deep learning in medical image reconstruction
- A new overhead crane emergency braking method with theoretical analysis and experimental verification
- On asymptotic behavior for a class of diffusion equations involving the fractional \(\wp (\cdot)\)-Laplacian as \(\wp (\cdot)\) goes to \(\infty\)
- A novel physics-informed framework for reconstruction of structural defects
- Linearized inverse Schrödinger potential problem with partial data and its deep neural network inversion
- Data-consistent neural networks for solving nonlinear inverse problems
- Training Very Deep CNNs for General Non-Blind Deconvolution
- Deep convolutional framelets: a general deep learning framework for inverse problems
- A mathematical framework for deep learning in elastic source imaging
- Deep learning for photoacoustic tomography from sparse data
- Recent trends and advances in solving the inverse problem for EEG source localization
- Bilevel optimization, deep learning and fractional Laplacian regularization with applications in tomography
- Equivariant neural networks for inverse problems
- WARPd: a linearly convergent first-order primal-dual algorithm for inverse problems with approximate sharpness conditions
- scientific article; zbMATH DE number 7625169 (Why is no real title available?)
- Deep Learning--Based Dictionary Learning and Tomographic Image Reconstruction
- Inverse problems on low-dimensional manifolds
- What Kinds of Functions Do Deep Neural Networks Learn? Insights from Variational Spline Theory
- Wasserstein-based projections with applications to inverse problems
- Reversible Autoencoder: A CNN-Based Nonlinear Lifting Scheme for Image Reconstruction
- NETT: solving inverse problems with deep neural networks
- Representation and reconstruction of covariance operators in linear inverse problems
- Computed tomography reconstruction using deep image prior and learned reconstruction methods
- Numerical solution of inverse problems by weak adversarial networks
- Data driven regularization by projection
- Variational inference for computational imaging inverse problems
- Convolutional Neural Networks in Phase Space and Inverse Problems
- Deep synthesis network for regularizing inverse problems
- Determination of singular value truncation threshold for regularization in ill-posed problems
- Shallow neural networks for fluid flow reconstruction with limited sensors
- Deep unfolding of a proximal interior point method for image restoration
- Solving inverse problems using data-driven models
- First arrival traveltime tomography using supervised descent learning technique
- Efficient Training of Convolutional Deep Belief Networks in the Frequency Domain for Application to High-Resolution 2D and 3D Images
- Learning the invisible: a hybrid deep learning-shearlet framework for limited angle computed tomography
- On learned operator correction in inverse problems
- Strong Solutions for PDE-Based Tomography by Unsupervised Learning
- Deep neural networks for inverse problems with pseudodifferential operators: an application to limited-angle tomography
- A dataset-free deep learning method for low-dose CT image reconstruction
- Unsupervised knowledge-transfer for learned image reconstruction
- Bilevel Methods for Image Reconstruction
- Sampling type method combined with deep learning for inverse scattering with one incident wave
- Electrical impedance tomography with deep Calderón method
- Deep learning based source reconstruction method using asymmetric encoder-decoder structure and physics-induced loss
- Neural network approximation of continuous functions in high dimensions with applications to inverse problems
- An introduction to the mathematics of deep learning
- Attenuating and enhancing properties of the approximate deconvolution method based on higher-order explicit and compact filters
- Learn an index operator by CNN for solving diffusive optical tomography: a deep direct sampling method
- Scaling Up Bayesian Uncertainty Quantification for Inverse Problems Using Deep Neural Networks
- Limitations of neural network training due to numerical instability of backpropagation
- Inverse parameter estimation using compressed sensing and POD-RBF reduced order models
- A Note on the Regularity of Images Generated by Convolutional Neural Networks
- DRIP: deep regularizers for inverse problems
- Invertible residual networks in the context of regularization theory for linear inverse problems
- MiPhDUO: microwave imaging via physics-informed deep unrolled optimization
- Measuring Complexity of Learning Schemes Using Hessian-Schatten Total Variation
- On Learning the Invisible in Photoacoustic Tomography with Flat Directionally Sensitive Detector
- Application of machine learning regression models to inverse eigenvalue problems
- Numerical methods for identifying the diffusion coefficient in a nonlinear elliptic equation
- The mathematics of artificial intelligence
- A point-to-point convolutional neural network for reconstructing electromagnetic parameters of multiple cavities scattering with inhomogeneous anisotropic media
- Learning sparsity-promoting regularizers using bilevel optimization
- NF-ULA: normalizing flow-based unadjusted Langevin algorithm for imaging inverse problems
- Exploring structural sparsity of coil images from 3-dimensional directional tight framelets for SENSE reconstruction
- Convergent data-driven regularizations for CT reconstruction
- Training adaptive reconstruction networks for blind inverse problems
- Learning the sparse prior: modern approaches
- Learned iterative reconstruction
- Regularization of inverse problems by neural networks
- Shearlets: from theory to deep learning
- Learned regularizers for inverse problems
- Provably convergent learned inexact descent algorithm for low-dose CT reconstruction
- Degradation simulator for infinite horizon controlled linear time-invariant systems
- Normalizing flow regularization for photoacoustic tomography
- A blind Poisson-Gaussian noise separation using learning copula densities
- Inverse problems are solvable on real number signal processing hardware
- Neural-network-based regularization methods for inverse problems in imaging
- Maximum discrepancy generative regularization and non-negative matrix factorization for single channel source separation
- Instability in deep learning -- when algorithms cannot compute uncertainty quantifications for neural networks
- A weaker adversarial neural networks method for linear second order elliptic PDEs
This page was built for publication: Deep Convolutional Neural Network for Inverse Problems in Imaging
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4619040)
