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

Automatic delineation of organ-at-risk (OAR) and gross-tumor-volume (GTV) isof great significance for radiotherapy planning. However, it is a challengingtask to learn powerful representations for accurate delineation under limitedpixel (voxel)-wise annotations. Contrastive learning at pixel-level canalleviate the dependency on annotations by learning dense representations fromunlabeled data. Recent studies in this direction design various contrastivelosses on the feature maps, to yield discriminative features for each pixel inthe map. However, pixels in the same map inevitably share semantics to becloser than they actually are, which may affect the discrimination of pixels inthe same map and lead to the unfair comparison to pixels in other maps. Toaddress these issues, we propose a separated region-level contrastive learningscheme, namely SepaReg, the core of which is to separate each image intoregions and encode each region separately. Specifically, SepaReg comprises twocomponents: a structure-aware image separation (SIS) module and an intra- andinter-organ distillation (IID) module. The SIS is proposed to operate on theimage set to rebuild a region set under the guidance of structural information.The inter-organ representation will be learned from this set via typicalcontrastive losses cross regions. On the other hand, the IID is proposed totackle the quantity imbalance in the region set as tiny organs may producefewer regions, by exploiting intra-organ representations. We conductedextensive experiments to evaluate the proposed model on a public dataset andtwo private datasets. The experimental results demonstrate the effectiveness ofthe proposed model, consistently achieving better performance thanstate-of-the-art approaches. Code is available athttps://github.com/jcwang123/Separate_CL.

Separated Contrastive Learning for Organ-at-Risk and Gross-Tumor-Volume Segmentation with Limited Annotation