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

Deformable image registration (DIR), aiming to find spatial correspondencebetween images, is one of the most critical problems in the domain of medicalimage analysis. In this paper, we present a novel, generic, and accuratediffeomorphic image registration framework that utilizes neural ordinarydifferential equations (NODEs). We model each voxel as a moving particle andconsider the set of all voxels in a 3D image as a high-dimensional dynamicalsystem whose trajectory determines the targeted deformation field. Our methodleverages deep neural networks for their expressive power in modeling dynamicalsystems, and simultaneously optimizes for a dynamical system between the imagepairs and the corresponding transformation. Our formulation allows variousconstraints to be imposed along the transformation to maintain desiredregularities. Our experiment results show that our method outperforms thebenchmarks under various metrics. Additionally, we demonstrate the feasibilityto expand our framework to register multiple image sets using a unified form oftransformation,which could possibly serve a wider range of applications.

NODEO: A Neural Ordinary Differential Equation Based Optimization Framework for Deformable Image Registration