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

Limited view tomographic reconstruction aims to reconstruct a tomographicimage from a limited number of sinogram or projection views arising from sparseview or limited angle acquisitions that reduce radiation dose or shortenscanning time. However, such a reconstruction suffers from high noise andsevere artifacts due to the incompleteness of sinogram. To derive qualityreconstruction, previous state-of-the-art methods use UNet-like neuralarchitectures to directly predict the full view reconstruction from limitedview data; but these methods leave the deep network architecture issue largelyintact and cannot guarantee the consistency between the sinogram of thereconstructed image and the acquired sinogram, leading to a non-idealreconstruction. In this work, we propose a novel recurrent reconstructionframework that stacks the same block multiple times. The recurrent blockconsists of a custom-designed residual dense spatial-channel attention network.Further, we develop a sinogram consistency layer interleaved in our recurrentframework in order to ensure that the sampled sinogram is consistent with thesinogram of the intermediate outputs of the recurrent blocks. We evaluate ourmethods on two datasets. Our experimental results on AAPM Low Dose CT GrandChallenge datasets demonstrate that our algorithm achieves a consistent andsignificant improvement over the existing state-of-the-art neural methods onboth limited angle reconstruction (over 5dB better in terms of PSNR) and sparseview reconstruction (about 4dB better in term of PSNR). In addition, ourexperimental results on Deep Lesion datasets demonstrate that our method isable to generate high-quality reconstruction for 8 major lesion types.

Limited View Tomographic Reconstruction Using a Deep Recurrent Framework  with Residual Dense Spatial-Channel Attention Network and Sinogram  Consistency