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

Medical image segmentation modeling is a high-stakes task where understandingof uncertainty is crucial for addressing visual ambiguity. Prior work hasdeveloped segmentation models utilizing probabilistic or generative mechanismsto infer uncertainty from labels where annotators draw a singular boundary.However, as these annotations cannot represent an individual annotator'suncertainty, models trained on them produce uncertainty maps that are difficultto interpret. We propose a novel segmentation representation, ConfidenceContours, which uses high- and low-confidence ``contours'' to captureuncertainty directly, and develop a novel annotation system for collectingcontours. We conduct an evaluation on the Lung Image Dataset Consortium (LIDC)and a synthetic dataset. From an annotation study with 30 participants, resultsshow that Confidence Contours provide high representative capacity withoutconsiderably higher annotator effort. We also find that general-purposesegmentation models can learn Confidence Contours at the same performance levelas standard singular annotations. Finally, from interviews with 5 medicalexperts, we find that Confidence Contour maps are more interpretable thanBayesian maps due to representation of structural uncertainty.

Confidence Contours: Uncertainty-Aware Annotation for Medical Semantic Segmentation