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

Automatic semantic segmentation of magnetic resonance imaging (MRI) imagesusing deep neural networks greatly assists in evaluating and planningtreatments for various clinical applications. However, training these models isconditioned on the availability of abundant annotated data to implement theend-to-end supervised learning procedure. Even if we annotate enough data, MRIimages display considerable variability due to factors such as differences inpatients, MRI scanners, and imaging protocols. This variability necessitatesretraining neural networks for each specific application domain, which, inturn, requires manual annotation by expert radiologists for all new domains. Torelax the need for persistent data annotation, we develop a method forunsupervised federated domain adaptation using multiple annotated sourcedomains. Our approach enables the transfer of knowledge from several annotatedsource domains to adapt a model for effective use in an unannotated targetdomain. Initially, we ensure that the target domain data shares similarrepresentations with each source domain in a latent embedding space, modeled asthe output of a deep encoder, by minimizing the pair-wise distances of thedistributions for the target domain and the source domains. We then employ anensemble approach to leverage the knowledge obtained from all domains. Weprovide theoretical analysis and perform experiments on the MICCAI 2016multi-site dataset to demonstrate our method is effective.

Unsupervised Federated Domain Adaptation for Segmentation of MRI Images