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 Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

In this paper, we introduced a novel deep learning-based reconstructiontechnique for low-dose CT imaging using 3 dimensional convolutions to includethe sagittal information unlike the existing 2 dimensional networks whichexploits correlation only in transverse plane. In the proposed reconstructiontechnique, sparse and noisy sinograms are back-projected to the image domainwith FBP operation, then the denoising process is applied with a U-Net like3-dimensional network called 3D U-NetR. The proposed network is trained withsynthetic and real chest CT images, and 2D U-Net is also trained with the samedataset to show the importance of the third dimension in terms of recoveringthe fine details. The proposed network shows better quantitative performance onSSIM and PSNR, especially in the real chest CT data. More importantly, 3DU-NetR captures medically critical visual details that cannot be visualized bya 2D network on the reconstruction of real CT images with 1/10 of the normaldose.

3D U-NetR: Low Dose Computed Tomography Reconstruction via Deep Learning and 3 Dimensional Convolutions