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

Peripancreatic vessel segmentation and anatomical labeling play extremelyimportant roles to assist the early diagnosis, surgery planning and prognosisfor patients with pancreatic tumors. However, most current techniques cannotachieve satisfactory segmentation performance for peripancreatic veins andusually make predictions with poor integrity and connectivity. Besides,unsupervised labeling algorithms cannot deal with complex anatomical variationwhile fully supervised methods require a large number of voxel-wise annotationsfor training, which is very labor-intensive and time-consuming. To addressthese problems, we propose our Automated Peripancreatic vEssel Segmentation andlAbeling (APESA) framework, to not only highly improve the segmentationperformance for peripancreatic veins, but also efficiently identify theperipancreatic artery branches. There are two core modules in our proposedAPESA framework: iterative trunk growth module (ITGM) for vein segmentation andweakly supervised labeling mechanism (WSLM) for artery branch identification.Our proposed ITGM is composed of a series of trunk growth modules, each ofwhich chooses the most reliable trunk of a basic vessel prediction by thelargest connected constraint, and seeks for the possible growth branches bybranch proposal network. Our designed iterative process guides the raw trunk tobe more complete and fully connected. Our proposed WSLM consists of anunsupervised rule-based preprocessing for generating pseudo branch annotations,and an anatomical labeling network to learn the branch distribution voxel byvoxel. We achieve Dice of 94.01% for vein segmentation on our collecteddataset, which boosts the accuracy by nearly 10% compared with thestate-of-the-art methods. Additionally, we also achieve Dice of 97.01% onsegmentation and competitive performance on anatomical labeling forperipancreatic arteries.

Automated Peripancreatic Vessel Segmentation and Labeling Based on Iterative Trunk Growth and Weakly Supervised Mechanism