Data and Image Prior Integration for Image Reconstruction Using Consensus Equilibrium

  title={Data and Image Prior Integration for Image Reconstruction Using Consensus Equilibrium},
  author={Muhammad Usman Ghani and W. Clem Karl},
  journal={IEEE Transactions on Computational Imaging},
  • M. Ghani, W. Karl
  • Published 31 August 2020
  • Computer Science, Mathematics
  • IEEE Transactions on Computational Imaging
Image domain prior models have been shown to improve the quality of reconstructed images, especially when data are limited. Pre-processing of raw data, through the implicit or explicit inclusion of data domain priors have separately also shown utility in improving reconstructions. In this work, a principled approach is presented allowing the unified integration of both data and image domain priors for improved image reconstruction. The consensus equilibrium framework is extended to integrate… 

Figures and Tables from this paper

CoIL: Coordinate-based Internal Learning for Imaging Inverse Problems
We propose Coordinate-based Internal Learning (CoIL) as a new deep-learning (DL) methodology for continuous representation of measurements. Unlike traditional DL methods that learn a mapping from the
Multi-Resolution Data Fusion for Super Resolution Imaging
Applications in materials and biological imaging are limited by the ability to collect high-resolution data over large areas in practical amounts of time. One solution to this problem is to collect


A Plug-and-Play Priors Approach for Solving Nonlinear Imaging Inverse Problems
This letter develops the fast iterative shrinkage/thresholding algorithm variant of PPP for model-based nonlinear inverse scattering and shows that the PPP approach is applicable beyond linear inverse problems.
Deep Residual Learning for Model-Based Iterative CT Reconstruction Using Plug-and-Play Framework
Plug-and-Play (PnP) framework is used and the state-of-the-art deep residual learning for the image denoising operator is adopted which represents the prior model in MBIR, reducing the noise and artifacts compared to analytical reconstruction and standard MBIr with MRF prior.
Data Consistent Artifact Reduction for Limited Angle Tomography with Deep Learning Prior
A data consistent artifact reduction (DCAR) method is introduced that achieves significant image quality improvement: for 120-degree cone-beam limited angle tomography more than 10% RMSE reduction in noise-free case and more than 24% RM SE reduction in noisy case compared with a state-of-the-art U-Net based method.
Plug-and-Play priors for model based reconstruction
This paper demonstrates with some simple examples how Plug-and-Play priors can be used to mix and match a wide variety of existing denoising models with a tomographic forward model, thus greatly expanding the range of possible problem solutions.
Deep-Neural-Network-Based Sinogram Synthesis for Sparse-View CT Image Reconstruction
A deep-neural-network-enabled sinogram synthesis method for sparse-view CT is introduced and its outperformance to the existing interpolation methods and also to the iterative image reconstruction approach is shown.
Deep Learning-Based Sinogram Completion for Low-Dose CT
This work examines the potential of a deep-learning-based method to construct a mapping from the observed, sparsely sampled, CT projection data to a set of densely sampled projection estimates directly in the original projection domain and casts the problem as one of sinogram in-painting and focuses on completing the projection data prior to reconstructing the images.
Integrating Data and Image Domain Deep Learning for Limited Angle Tomography using Consensus Equilibrium
Conditional generative adversarial networks (cGANs) are used in both the data and the image domain for enhanced performance and efficient computation and combine them through a consensus process in a two-step process based on the consensus equilibrium (CE) framework.
CNN-Based Projected Gradient Descent for Consistent CT Image Reconstruction
A relaxed version of PGD wherein gradient descent enforces measurement consistency, while a CNN recursively projects the solution closer to the space of desired reconstruction images and shows an improvement over total variation-based regularization, dictionary learning, and a state-of-the-art deep learning-based direct reconstruction technique.
Deep Learning Computed Tomography: Learning Projection-Domain Weights From Image Domain in Limited Angle Problems
A new type of cone-beam back-projection layer is proposed, efficiently calculating the forward pass of this layer, and it is shown that the learned algorithm can be interpreted using known concepts from cone beam reconstruction: the network is able to automatically learn strategies such as compensation weights and apodization windows.
Deep Residual Learning for Accelerated MRI Using Magnitude and Phase Networks
Comparisons using single and multiple coil acquisition show that the proposed deep residual learning network provides good reconstruction results with orders of magnitude faster computational time than existing CS methods.