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

Non-contrast computed tomography (NCCT) is commonly acquired for lung cancerscreening, assessment of general abdominal pain or suspected renal stones,trauma evaluation, and many other indications. However, the absence of contrastlimits distinguishing organ in-between boundaries. In this paper, we propose anovel unsupervised approach that leverages pairwise contrast-enhanced CT (CECT)context to compute non-contrast segmentation without ground-truth label. Unlikegenerative adversarial approaches, we compute the pairwise morphologicalcontext with CECT to provide teacher guidance instead of generating fakeanatomical context. Additionally, we further augment the intensity correlationsin 'organ-specific' settings and increase the sensitivity to organ-awareboundary. We validate our approach on multi-organ segmentation with pairednon-contrast & contrast-enhanced CT scans using five-fold cross-validation.Full external validations are performed on an independent non-contrast cohortfor aorta segmentation. Compared with current abdominal organs segmentationstate-of-the-art in fully supervised setting, our proposed pipeline achieves asignificantly higher Dice by 3.98% (internal multi-organ annotated), and 8.00%(external aorta annotated) for abdominal organs segmentation. The code andpretrained models are publicly available athttps://github.com/MASILab/ContrastMix.

Pseudo-Label Guided Multi-Contrast Generalization for Non-Contrast Organ-Aware Segmentation