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

Renal compartment segmentation on CT images targets on extracting the 3Dstructure of renal compartments from abdominal CTA images and is of greatsignificance to the diagnosis and treatment for kidney diseases. However, dueto the unclear compartment boundary, thin compartment structure and largeanatomy variation of 3D kidney CT images, deep-learning based renal compartmentsegmentation is a challenging task. We propose a novel weakly supervisedlearning framework, Cycle Prototype Network, for 3D renal compartmentsegmentation. It has three innovations: 1) A Cycle Prototype Learning (CPL) isproposed to learn consistency for generalization. It learns from pseudo labelsthrough the forward process and learns consistency regularization through thereverse process. The two processes make the model robust to noise andlabel-efficient. 2) We propose a Bayes Weakly Supervised Module (BWSM) based oncross-period prior knowledge. It learns prior knowledge from cross-periodunlabeled data and perform error correction automatically, thus generatesaccurate pseudo labels. 3) We present a Fine Decoding Feature Extractor (FDFE)for fine-grained feature extraction. It combines global morphology informationand local detail information to obtain feature maps with sharp detail, so themodel will achieve fine segmentation on thin structures. Our model achievesDice of 79.1% and 78.7% with only four labeled images, achieving a significantimprovement by about 20% than typical prototype model PANet.

CPNet: Cycle Prototype Network for Weakly-supervised 3D Renal Compartments Segmentation on CT Images