MEPNet: A Model-Driven Equivariant Proximal Network for Joint Sparse-View Reconstruction and Metal Artifact Reduction in CT Images (2023-06-25T00:00:00.000000Z)

TL;DR

A dual-domain reconstruction model is constructed and a model-driven equivariant proximal network is proposed, called MEPNet, which finely represents the inherent rotational prior underlying the CT scanning that the same organ can be imaged at different angles.

Abstract

Sparse-view computed tomography (CT) has been adopted as an important technique for speeding up data acquisition and decreasing radiation dose. However, due to the lack of sufficient projection data, the reconstructed CT images often present severe artifacts, which will be further amplified when patients carry metallic implants. For this joint sparse-view reconstruction and metal artifact reduction task, most of the existing methods are generally confronted with two main limitations: 1) They are almost built based on common network modules without fully embedding the physical imaging geometry constraint of this specific task into the dual-domain learning; 2) Some important prior knowledge is not deeply explored and sufficiently utilized. Against these issues, we specifically construct a dual-domain reconstruction model and propose a model-driven equivariant proximal network, called MEPNet. The main characteristics of MEPNet are: 1) It is optimization-inspired and has a clear working mechanism; 2) The involved proximal operator is modeled via a rotation equivariant convolutional neural network, which finely represents the inherent rotational prior underlying the CT scanning that the same organ can be imaged at different angles. Extensive experiments conducted on several datasets comprehensively substantiate that compared with the conventional convolution-based proximal network, such a rotation equivariance mechanism enables our proposed method to achieve better reconstruction performance with fewer network parameters. We will release the code at \url{https://github.com/hongwang01/MEPNet}.

Authors

References33 items

Scale-Equivariant Unrolled Neural Networks for Data-Efficient Accelerated MRI Reconstruction

DuDoTrans: Dual-Domain Transformer Provides More Attention for Sinogram Restoration in Sparse-View CT Reconstruction

DICDNet: Deep Interpretable Convolutional Dictionary Network for Metal Artifact Reduction in CT Images

DuDoDR-Net: Dual-domain data consistent recurrent network for simultaneous sparse view and metal artifact reduction in computed tomography

InDuDoNet: An Interpretable Dual Domain Network for CT Metal Artifact Reduction

NeRP: Implicit Neural Representation Learning With Prior Embedding for Sparsely Sampled Image Reconstruction

Fourier Series Expansion Based Filter Parametrization for Equivariant Convolutions

Equivariant Imaging: Learning Beyond the Range Space

Limited View Tomographic Reconstruction Using a Cascaded Residual Dense Spatial-Channel Attention Network With Projection Data Fidelity Layer

TransCT: Dual-Path Transformer for Low Dose Computed Tomography

Equivariant neural networks for inverse problems

Deep learning to segment pelvic bones: large-scale CT datasets and baseline models

Deep Sinogram Completion With Image Prior for Metal Artifact Reduction in CT Images

PDO-eConvs: Partial Differential Operator Based Equivariant Convolutions

MetaInv-Net: Meta Inversion Network for Sparse View CT Image Reconstruction

Scale-Equivariant Steerable Networks

ADN: Artifact Disentanglement Network for Unsupervised Metal Artifact Reduction

DuDoNet: Dual Domain Network for CT Metal Artifact Reduction

Fast Enhanced CT Metal Artifact Reduction Using Data Domain Deep Learning

Metal artifact reduction on cervical CT images by deep residual learning

A Sparse-View CT Reconstruction Method Based on Combination of DenseNet and Deconvolution

Deep-Neural-Network-Based Sinogram Synthesis for Sparse-View CT Image Reconstruction

Deep Lesion Graphs in the Wild: Relationship Learning and Organization of Significant Radiology Image Findings in a Diverse Large-Scale Lesion Database

Learning Steerable Filters for Rotation Equivariant CNNs

Automatic differentiation in PyTorch

Convolutional Neural Network Based Metal Artifact Reduction in X-Ray Computed Tomography

ADMM-Net: A Deep Learning Approach for Compressive Sensing MRI

Deep Convolutional Neural Network for Inverse Problems in Imaging

Group Equivariant Convolutional Networks

DeepOrgan: Multi-level Deep Convolutional Networks for Automated Pancreas Segmentation

Proximal Algorithms

Learnable Multi-scale Fourier Interpolation for Sparse View CT Image Reconstruction

Model-Driven Equivariant