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

We present Recurrence with Correlation Network (RWCNet), a medical imageregistration network with multi-scale features and a cost volume layer. Wedemonstrate that these architectural features improve medical imageregistration accuracy in two image registration datasets prepared for theMICCAI 2022 Learn2Reg Workshop Challenge. On the large-displacement NationalLung Screening Test (NLST) dataset, RWCNet is able to achieve a totalregistration error (TRE) of 2.11mm between corresponding keypoints withoutinstance fine-tuning. On the OASIS brain MRI dataset, RWCNet is able to achievean average dice overlap of 81.7% for 35 different anatomical labels. Itoutperforms another multi-scale network, the Laplacian Image RegistrationNetwork (LapIRN), on both datasets. Ablation experiments are performed tohighlight the contribution of the various architectural features. Whilemulti-scale features improved validation accuracy for both datasets, the costvolume layer and number of recurrent steps only improved performance on thelarge-displacement NLST dataset. This result suggests that cost volume layerand iterative refinement using RNN provide good support for optimization andgeneralization in large-displacement medical image registration. The code forRWCNet is available athttps://github.com/vigsivan/optimization-based-registration.

Recurrence With Correlation Network for Medical Image Registration