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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Image registration is an essential step in many medical image analysis tasks.Traditional methods for image registration are primarily optimization-driven,finding the optimal deformations that maximize the similarity between twoimages. Recent learning-based methods, trained to directly predicttransformations between two images, run much faster, but suffer fromperformance deficiencies due to model generalization and the inefficiency inhandling individual image specific deformations. Here we present a new neuralnet based image registration framework, called NIR (Neural Image Registration),which is based on optimization but utilizes deep neural nets to modeldeformations between image pairs. NIR represents the transformation between twoimages with a continuous function implemented via neural fields, receiving a 3Dcoordinate as input and outputting the corresponding deformation vector. NIRprovides two ways of generating deformation field: directly output adisplacement vector field for general deformable registration, or output avelocity vector field and integrate the velocity field to derive thedeformation field for diffeomorphic image registration. The optimalregistration is discovered by updating the parameters of the neural field viastochastic gradient descent. We describe several design choices that facilitatemodel optimization, including coordinate encoding, sinusoidal activation,coordinate sampling, and intensity sampling. Experiments on two 3D MR brainscan datasets demonstrate that NIR yields state-of-the-art performance in termsof both registration accuracy and regularity, while running significantlyfaster than traditional optimization-based methods.

Medical Image Registration via Neural Fields