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

In this work, we study various hybrid models of entropy-based andrepresentativeness sampling techniques in the context of active learning inmedical segmentation, in particular examining the role of UMAP (UniformManifold Approximation and Projection) as a technique for capturingrepresentativeness. Although UMAP has been shown viable as a general purposedimension reduction method in diverse areas, its role in deep learning-basedmedical segmentation has yet been extensively explored. Using the cardiac andprostate datasets in the Medical Segmentation Decathlon for validation, wefound that a novel hybrid combination of Entropy-UMAP sampling techniqueachieved a statistically significant Dice score advantage over the randombaseline ($3.2 \%$ for cardiac, $4.5 \%$ for prostate), and attained thehighest Dice coefficient among the spectrum of 10 distinct active learningmethodologies we examined. This provides preliminary evidence that there is aninteresting synergy between entropy-based and UMAP methods when the formerprecedes the latter in a hybrid model of active learning.

Exploring UMAP in hybrid models of entropy-based and representativeness sampling for active learning in biomedical segmentation