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

Multimodal image registration is a very challenging problem for deep learningapproaches. Most current work focuses on either supervised learning thatrequires labelled training scans and may yield models that bias towardsannotated structures or unsupervised approaches that are based on hand-craftedsimilarity metrics and may therefore not outperform their classical non-trainedcounterparts. We believe that unsupervised domain adaptation can be beneficialin overcoming the current limitations for multimodal registration, where goodmetrics are hard to define. Domain adaptation has so far been mainly limited toclassification problems. We propose the first use of unsupervised domainadaptation for discrete multimodal registration. Based on a source domain forwhich quantised displacement labels are available as supervision, we transferthe output distribution of the network to better resemble the target domain(other modality) using classifier discrepancies. To improve upon the slicedWasserstein metric for 2D histograms, we present a novel approximation thatprojects predictions into 1D and computes the L1 distance of their cumulativesums. Our proof-of-concept demonstrates the applicability of domain transferfrom mono- to multimodal (multi-contrast) 2D registration of canine MRI scansand improves the registration accuracy from 33% (using sliced Wasserstein) to44%.

Unsupervised learning of multimodal image registration using domain adaptation with projected Earth Move's discrepancies