Adaptive Convolutional Dictionary Network for CT Metal Artifact Reduction

  title={Adaptive Convolutional Dictionary Network for CT Metal Artifact Reduction},
  author={Hong Wang and Yuexiang Li and Deyu Meng and Yefeng Zheng},
  booktitle={International Joint Conference on Artificial Intelligence},
Inspired by the great success of deep neural networks, learning-based methods have gained promising performances for metal artifact reduction (MAR) in computed tomography (CT) images. However, most of the existing approaches put less emphasis on modelling and embedding the intrinsic prior knowledge underlying this specific MAR task into their network designs. Against this issue, we propose an adaptive convolutional dictionary network (ACDNet), which leverages both model-based and learning-based… 

TriDoNet: A Triple Domain Model-driven Network for CT Metal Artifact Reduction

A novel triple domain model-driven CTMAR network, termed as TriDoNet, is proposed, whose network training exploits triple domain knowledge, i.e., the knowledge of the sinogram, CT image, and metal artifact domains, to explore the non-local repetitive streaking patterns of metal artifacts.

RCDNet: An Interpretable Rain Convolutional Dictionary Network for Single Image Deraining

A novel deep architecture is built, called rain convolutional dictionary network (RCDNet), which embeds the intrinsic priors of rain streaks and has clear interpretability, especially on its well generality to diverse testing scenarios and good interpretability for all its modules.



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

A deep interpretable convolutional dictionary network (DICDNet) for metal artifact reduction (MAR) with superior interpretability, compared to current state-of-the-art MAR methods is proposed.

ADN: Artifact Disentanglement Network for Unsupervised Metal Artifact Reduction

A novel artifact disentanglement network that disentangles the metal artifacts from CT images in the latent space is introduced that achieves comparable performance to existing supervised models for MAR and demonstrates better generalization ability over the supervised models.

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

A novel interpretable dual domain network, termed as InDuDoNet, is proposed, which combines the advantages of model-driven and data-driven methodologies, and utilizes the proximal gradient technique to design an iterative algorithm for solving it.

InDuDoNet+: A Model-Driven Interpretable Dual Domain Network for Metal Artifact Reduction in CT Images

Comprehensive experiments on synthesized data and clinical data substantiate the superiority of the proposed methods as well as the superior generalization performance beyond the current state-of-the-art (SOTA) MAR methods.

Fast Enhanced CT Metal Artifact Reduction Using Data Domain Deep Learning

This work treats the projection data corresponding to dense, metal objects as missing data and train an adversarial deep network to complete the missing data directly in the projection domain, resulting in an end-to-end metal artifact reduction algorithm that is computationally efficient textcolorredand therefore practical and fits well into existing CT workflows allowing easy adoption in existing scanners.

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

A convolutional neural network (CNN)-based open MAR framework, which fuses the information from the original and corrected images to suppress artifacts and demonstrate the superior MAR capability of the proposed method to its competitors in terms of artifact suppression and preservation of anatomical structures in the vicinity of metal implants.

Encoding Metal Mask Projection for Metal Artifact Reduction in Computed Tomography

This work proposes to address the problem of metal artifact reduction in computed tomography by retaining the metal-affected regions in sinogram and replacing the binarized metal trace with the metal mask projection such that the geometry information of metal implants is encoded.

Conditional Generative Adversarial Networks for Metal Artifact Reduction in CT Images of the Ear

An approach based on a conditional generative adversarial network (cGAN) for the reduction of metal artifacts in computed tomography (CT) ear images of cochlear implants (CIs) recipients and it is shown that the proposed method leads to an average surface error of 0.18 mm which is about half of what could be achieved with a previously proposed technique.

DuDoNet: Dual Domain Network for CT Metal Artifact Reduction

This work proposes an end-to-end trainable Dual Domain Network (DuDoNet) to simultaneously restore sinogram consistency and enhance CT images, and is the first end- to-end dual-domain network for MAR.

Metal artifact reduction on cervical CT images by deep residual learning

The RL-ARCNN indicates that residual learning of CNN remarkably reduces metal artifacts and improves critical structure visualization and confidence of radiation oncologists in target delineation.