• Corpus ID: 118929554

Machine-learning-based nonlinear decomposition of CT images for metal artifact reduction

@article{Park2017MachinelearningbasedND,
  title={Machine-learning-based nonlinear decomposition of CT images for metal artifact reduction},
  author={Hyung Suk Park and Sung Min Lee and Hwa Pyung Kim and Jin Keun Seo},
  journal={arXiv: Medical Physics},
  year={2017}
}
Computed tomography (CT) images containing metallic objects commonly show severe streaking and shadow artifacts. Metal artifacts are caused by nonlinear beam-hardening effects combined with other factors such as scatter and Poisson noise. In this paper, we propose an implant-specific method that extracts beam-hardening artifacts from CT images without affecting the background image. We found that in cases where metal is inserted in the water (or tissue), the generated beam-hardening artifacts… 

Figures and Tables from this paper

Metal artifact reduction in 2D CT images with self-supervised cross-domain learning

TLDR
This work proposes a self-supervised cross-domain learning framework to alleviate the need for anatomically identical CT image pairs and incorporates the metal trace replacement into this framework and replaces the metal-affected projections of the original sinogram with the prior sinogram generated by the forward projection of the CNN output.

Metal artifact reduction based on fully convolutional networks in CT image domain

TLDR
Experimental results demonstrate that the proposed method can well reduce metal artifacts of CT images, and take a shorter time to process the images than traditional method.

Metal Artifact Reduction for X-Ray Computed Tomography Using U-Net in Image Domain

TLDR
The experimental results show that the proposed U-net-based metal artifact reduction method can well reduce metal artifacts of CT images, and this method has higher computational efficiency and greatly shortens the processing time, making it ideal for existing CT workflows.

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

TLDR
A generalizable framework for metal artifact reduction (MAR) is proposed by simultaneously leveraging the advantages of image domain and sinogram domain-based MAR techniques and produces superior artifact-reduced results while preserving the anatomical structures and outperforms other MAR methods.

Fully convolutional networks based sinogram correction for metal artifact reduction

TLDR
This work proposes a novel method based on full convolutional network (FCN) for metal artifact reduction in the sinogram domain and presents initial results on a simulated dataset to demonstrate the potential effectiveness of this new approach to suppressing artifacts.

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

TLDR
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.

Machine learning-based noise reduction for craniofacial bone segmentation in CT images

TLDR
Dedicated to the delineation of craniofacial bones, the presented study showed high prediction accuracy and the use of mean squared errors presented superiority to Dice or Jaccard loss.

Generative Mask Pyramid Network for CT/CBCT Metal Artifact Reduction with Joint Projection-Sinogram Correction

TLDR
This work proposes to replace metal artifact affected regions with anatomically consistent content through joint projection-sinogram correction as well as adversarial learning and proposes a novel mask pyramid network that enforces the mask information across the network's encoding layers and a mask fusion loss that reduces early saturation of adversarial training.

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

TLDR
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.

Medical Image Computing and Computer Assisted Intervention – MICCAI 2018

TLDR
An approach based on a conditional generative adversarial network (cGAN) for the reduction of metal artifacts (RMA) 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.

References

SHOWING 1-10 OF 30 REFERENCES

Normalized metal artifact reduction (NMAR) in computed tomography.

PURPOSE While modern clinical CT scanners under normal circumstances produce high quality images, severe artifacts degrade the image quality and the diagnostic value if metal prostheses or other

Spurious structures created by interpolation-based CT metal artifact reduction

TLDR
It is concluded that a restoration scheme without additionally information is not sufficient for a successful metal artifacts reduction method, and the application of a more sophisticated artifact reduction method based on a segmentation of a preliminary reconstructed image decreases the number of newly introduced artifacts to a large degree.

Metal artifact reduction in CT by identifying missing data hidden in metals.

TLDR
A new MAR method that uses the Laplacian operator to reveal background projection data hidden in regions containing data from metal, which improves image quality and increases the standard of 3D reconstruction images of the teeth and mandible.

Metal Artifact Reduction for Polychromatic X-ray CT Based on a Beam-Hardening Corrector

TLDR
A new method to correct beam hardening artifacts caused by the presence of metal in polychromatic X-ray computed tomography without degrading the intact anatomical images is proposed.

X-ray CT Metal Artifact Reduction Using Wavelet Domain $L_{0}$ Sparse Regularization

TLDR
The qualitative and quantitative evaluations showed that the proposed L0-DRS MAR algorithm substantially suppresses streaking artifacts and can outperform both linear interpolation and NMAR algorithms.

Suppression of Metal Artifacts in CT Using a Reconstruction Procedure That Combines MAP and Projection Completion

TLDR
A new reconstruction procedure is proposed that reduces the streak artifacts and that might improve the diagnostic value of the CT images, and was validated on simulations, phantom and patient data, and compared with other metal artifact reduction algorithms.

Multi-Scale Wavelet Domain Residual Learning for Limited-Angle CT Reconstruction

TLDR
A novel multi-scale wavelet domain residual learning architecture is proposed, which compensates for the artifacts in CT images from limited angles, thereby preserving edge and global structures of the image.

Correction of CT artifacts and its influence on Monte Carlo dose calculations.

TLDR
Whereas beam hardening has a minor effect on metal artifacts, scatter is an important cause of these artifacts and a simple Monte Carlo model for a CT scanner is developed and developed.

Iterative deblurring for CT metal artifact reduction

TLDR
In experiments with synthetic noise-free and additive noisy projection data of dental phantoms, it is found that both simultaneous iterative algorithms produce superior image quality as compared to filtered backprojection after linearly fitting projection gaps.