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

Helical CT has been widely used in clinical diagnosis. Sparsely spacedmultidetector in z direction can increase the coverage of the detector providedlimited detector rows. It can speed up volumetric CT scan, lower the radiationdose and reduce motion artifacts. However, it leads to insufficient data forreconstruction. That means reconstructions from general analytical methods willhave severe artifacts. Iterative reconstruction methods might be able to dealwith this situation but with the cost of huge computational load. In this work,we propose a cascaded dual-domain deep learning method that completes both datatransformation in projection domain and error reduction in image domain. First,a convolutional neural network (CNN) in projection domain is constructed toestimate missing helical projection data and converting helical projection datato 2D fan-beam projection data. This step is to suppress helical artifacts andreduce the following computational cost. Then, an analytical linear operator isfollowed to transfer the data from projection domain to image domain. Finally,an image domain CNN is added to improve image quality further. These threesteps work as an entirety and can be trained end to end. The overall network istrained using a simulated lung CT dataset with Poisson noise from 25 patients.We evaluate the trained network on another three patients and obtain veryencouraging results with both visual examination and quantitative comparison.The resulting RRMSE is 6.56% and the SSIM is 99.60%. In addition, we test thetrained network on the lung CT dataset with different noise level and a newdental CT dataset to demonstrate the generalization and robustness of ourmethod.

A cascaded dual-domain deep learning reconstruction method for sparsely spaced multidetector helical CT