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

While Model Based Iterative Reconstruction (MBIR) of CT scans has been shownto have better image quality than Filtered Back Projection (FBP), its use hasbeen limited by its high computational cost. More recently, deep convolutionalneural networks (CNN) have shown great promise in both denoising andreconstruction applications. In this research, we propose a fast reconstructionalgorithm, which we call Deep Learning MBIR (DL-MBIR), for approximating MBIRusing a deep residual neural network. The DL-MBIR method is trained to producereconstructions that approximate true MBIR images using a 16 layer residualconvolutional neural network implemented on multiple GPUs using GoogleTensorflow. In addition, we propose 2D, 2.5D and 3D variations on the DL-MBIRmethod and show that the 2.5D method achieves similar quality to the fully 3Dmethod, but with reduced computational cost.

2.5D Deep Learning for CT Image Reconstruction using a Multi-GPU implementation