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

The long-tailed distribution problem in medical image analysis reflects ahigh prevalence of common conditions and a low prevalence of rare ones, whichposes a significant challenge in developing a unified model capable ofidentifying rare or novel tumor categories not encountered during training. Inthis paper, we propose a new zero-shot pan-tumor segmentation framework (ZePT)based on query-disentangling and self-prompting to segment unseen tumorcategories beyond the training set. ZePT disentangles the object queries intotwo subsets and trains them in two stages. Initially, it learns a set offundamental queries for organ segmentation through an object-aware featuregrouping strategy, which gathers organ-level visual features. Subsequently, itrefines the other set of advanced queries that focus on the auto-generatedvisual prompts for unseen tumor segmentation. Moreover, we introducequery-knowledge alignment at the feature level to enhance each query'sdiscriminative representation and generalizability. Extensive experiments onvarious tumor segmentation tasks demonstrate the performance superiority ofZePT, which surpasses the previous counterparts and evidence the promisingability for zero-shot tumor segmentation in real-world settings. Codes will bemade publicly available.

ZePT: Zero-Shot Pan-Tumor Segmentation via Query-Disentangling and Self-Prompting