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 the last decade, convolutional neural networks (ConvNets) have dominatedand achieved state-of-the-art performances in a variety of medical imagingapplications. However, the performances of ConvNets are still limited bylacking the understanding of long-range spatial relations in an image. Therecently proposed Vision Transformer (ViT) for image classification uses apurely self-attention-based model that learns long-range spatial relations tofocus on the relevant parts of an image. Nevertheless, ViT emphasizes thelow-resolution features because of the consecutive downsamplings, result in alack of detailed localization information, making it unsuitable for imageregistration. Recently, several ViT-based image segmentation methods have beencombined with ConvNets to improve the recovery of detailed localizationinformation. Inspired by them, we present ViT-V-Net, which bridges ViT andConvNet to provide volumetric medical image registration. The experimentalresults presented here demonstrate that the proposed architecture achievessuperior performance to several top-performing registration methods.

ViT-V-Net: Vision Transformer for Unsupervised Volumetric Medical Image Registration