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

Medical image segmentation typically necessitates a large and preciselyannotated dataset. However, obtaining pixel-wise annotation is alabor-intensive task that requires significant effort from domain experts,making it challenging to obtain in practical clinical scenarios. In suchsituations, reducing the amount of annotation required is a more practicalapproach. One feasible direction is sparse annotation, which involvesannotating only a few slices, and has several advantages over traditional weakannotation methods such as bounding boxes and scribbles, as it preserves exactboundaries. However, learning from sparse annotation is challenging due to thescarcity of supervision signals. To address this issue, we propose a frameworkthat can robustly learn from sparse annotation using the cross-teaching of both3D and 2D networks. Considering the characteristic of these networks, wedevelop two pseudo label selection strategies, which are hard-soft confidencethreshold and consistent label fusion. Our experimental results on the MMWHSdataset demonstrate that our method outperforms the state-of-the-art (SOTA)semi-supervised segmentation methods. Moreover, our approach achieves resultsthat are comparable to the fully-supervised upper bound result.

3D Medical Image Segmentation with Sparse Annotation via Cross-Teaching between 3D and 2D Networks