English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

The presence of metallic implants often introduces severe metal artifacts inthe X-ray CT images, which could adversely influence clinical diagnosis or dosecalculation in radiation therapy. In this work, we present a noveldeep-learning-based approach for metal artifact reduction (MAR). In order toalleviate the need for anatomically identical CT image pairs (i.e., metalartifact-corrupted CT image and metal artifact-free CT image) for networklearning, we propose a self-supervised cross-domain learning framework.Specifically, we train a neural network to restore the metal trace regionvalues in the given metal-free sinogram, where the metal trace is identified bythe forward projection of metal masks. We then design a novel FBPreconstruction loss to encourage the network to generate more perfectcompletion results and a residual-learning-based image refinement module toreduce the secondary artifacts in the reconstructed CT images. To preserve thefine structure details and fidelity of the final MAR image, instead of directlyadopting CNN-refined images as output, we incorporate the metal tracereplacement into our framework and replace the metal-affected projections ofthe original sinogram with the prior sinogram generated by the forwardprojection of the CNN output. We then use the filtered backward projection(FBP) algorithms for final MAR image reconstruction. We conduct an extensiveevaluation on simulated and real artifact data to show the effectiveness of ourdesign. Our method produces superior MAR results and outperforms othercompelling methods. We also demonstrate the potential of our framework forother organ sites.

Metal Artifact Reduction in 2D CT Images with Self-supervised Cross-domain Learning