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

Multi-organ segmentation, which identifies and separates different organs inmedical images, is a fundamental task in medical image analysis. Recently, theimmense success of deep learning motivated its wide adoption in multi-organsegmentation tasks. However, due to expensive labor costs and expertise, theavailability of multi-organ annotations is usually limited and hence poses achallenge in obtaining sufficient training data for deep learning-basedmethods. In this paper, we aim to address this issue by combining off-the-shelfsingle-organ segmentation models to develop a multi-organ segmentation model onthe target dataset, which helps get rid of the dependence on annotated data formulti-organ segmentation. To this end, we propose a novel dual-stage methodthat consists of a Model Adaptation stage and a Model Ensemble stage. The firststage enhances the generalization of each off-the-shelf segmentation model onthe target domain, while the second stage distills and integrates knowledgefrom multiple adapted single-organ segmentation models. Extensive experimentson four abdomen datasets demonstrate that our proposed method can effectivelyleverage off-the-shelf single-organ segmentation models to obtain a tailoredmodel for multi-organ segmentation with high accuracy.

Tailored Multi-Organ Segmentation with Model Adaptation and Ensemble