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

Morphological atlases are an important tool in organismal studies, and modernhigh-throughput Computed Tomography (CT) facilities can produce hundreds offull-body high-resolution volumetric images of organisms. However, creating anatlas from these volumes requires accurate organ segmentation. In the lastdecade, machine learning approaches have achieved incredible results in imagesegmentation tasks, but they require large amounts of annotated data fortraining. In this paper, we propose a self-training framework for multi-organsegmentation in tomographic images of Medaka fish. We utilize thepseudo-labeled data from a pretrained Teacher model and adopt a QualityClassifier to refine the pseudo-labeled data. Then, we introduce a pixel-wiseknowledge distillation method to prevent overfitting to the pseudo-labeled dataand improve the segmentation performance. The experimental results demonstratethat our method improves mean Intersection over Union (IoU) by 5.9% on the fulldataset and enables keeping the quality while using three times less markup.

A Knowledge Distillation framework for Multi-Organ Segmentation of Medaka Fish in Tomographic Image