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 study, we present a method for generating automated anatomysegmentation datasets using a sequential process that involves nnU-Net-basedpseudo-labeling and anatomy-guided pseudo-label refinement. By combiningvarious fragmented knowledge bases, we generate a dataset of whole-body CTscans with $142$ voxel-level labels for 533 volumes providing comprehensiveanatomical coverage which experts have approved. Our proposed procedure doesnot rely on manual annotation during the label aggregation stage. We examineits plausibility and usefulness using three complementary checks: Human expertevaluation which approved the dataset, a Deep Learning usefulness benchmark onthe BTCV dataset in which we achieve 85% dice score without using its trainingdataset, and medical validity checks. This evaluation procedure combinesscalable automated checks with labor-intensive high-quality expert checks.Besides the dataset, we release our trained unified anatomical segmentationmodel capable of predicting $142$ anatomical structures on CT data.

Towards Unifying Anatomy Segmentation: Automated Generation of a Full-body CT Dataset via Knowledge Aggregation and Anatomical Guidelines