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

Objective and Impact Statement: Accurate organ segmentation is critical formany clinical applications at different clinical sites, which may have theirspecific application requirements that concern different organs. Introduction:However, learning high-quality, site-specific organ segmentation models ischallenging as it often needs on-site curation of a large number of annotatedimages. Security concerns further complicate the matter. Methods: The paperaims to tackle these challenges via a two-phase aggregation-then-adaptationapproach. The first phase of federated aggregation learns a single multi-organsegmentation model by leveraging the strength of 'bigger data', which areformed by (i) aggregating together datasets from multiple sites that withdifferent organ labels to provide partial supervision, and (ii) conductingpartially supervised learning without data breach. The second phase of siteadaptation is to transfer the federated multi-organ segmentation model tosite-specific organ segmentation models, one model per site, in order tofurther improve the performance of each site's organ segmentation task.Furthermore, improved marginal loss and exclusion loss functions are used toavoid 'knowledge conflict' problem in a partially supervision mechanism.Results and Conclusion: Extensive experiments on five organ segmentationdatasets demonstrate the effectiveness of our multi-site approach,significantly outperforming the site-per-se learned models and achieving theperformance comparable to the centrally learned models.

Multi-site Organ Segmentation with Federated Partial Supervision and Site Adaptation