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

Medical image registration aims at identifying the spatial deformationbetween images of the same anatomical region and is fundamental to image-baseddiagnostics and therapy. To date, the majority of the deep learning-basedregistration methods employ regularizers that enforce global spatialsmoothness, e.g., the diffusion regularizer. However, such regularizers are nottailored to the data and might not be capable of reflecting the complexunderlying deformation. In contrast, physics-inspired regularizers promotephysically plausible deformations. One such regularizer is the linear elasticregularizer which models the deformation of elastic material. Theseregularizers are driven by parameters that define the material's physicalproperties. For biological tissue, a wide range of estimations of suchparameters can be found in the literature and it remains an open challenge toidentify suitable parameter values for successful registration. To overcomethis problem and to incorporate physical properties into learning-basedregistration, we propose to use a hypernetwork that learns the effect of thephysical parameters of a physics-inspired regularizer on the resulting spatialdeformation field. In particular, we adapt the HyperMorph framework to learnthe effect of the two elasticity parameters of the linear elastic regularizer.Our approach enables the efficient discovery of suitable, data-specificphysical parameters at test time.

Learning Physics-Inspired Regularization for Medical Image Registration with Hypernetworks