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

X-ray computed tomography (CT) reconstructs cross-sectional images fromprojection data. However, ionizing X-ray radiation associated with CT scanningmight induce cancer and genetic damage. Therefore, the reduction of radiationdose has attracted major attention. Few-view CT image reconstruction is animportant topic to reduce the radiation dose. Recently, data-driven algorithmshave shown great potential to solve the few-view CT problem. In this paper, wedevelop a dual network architecture (DNA) for reconstructing images directlyfrom sinograms. In the proposed DNA method, a point-based fully-connected layerlearns the backprojection process requesting significantly less memory than theprior arts do. Proposed method uses O(C*N*N_c) parameters where N and N_cdenote the dimension of reconstructed images and number of projectionsrespectively. C is an adjustable parameter that can be set as low as 1. Ourexperimental results demonstrate that DNA produces a competitive performanceover the other state-of-the-art methods. Interestingly, natural images can beused to pre-train DNA to avoid overfitting when the amount of real patientimages is limited.

Dual Network Architecture for Few-view CT -- Trained on ImageNet Data and Transferred for Medical Imaging