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

Automated anatomical labeling plays a vital role in coronary artery diseasediagnosing procedure. The main challenge in this problem is the largeindividual variability inherited in human anatomy. Existing methods usuallyrely on the position information and the prior knowledge of the topology of thecoronary artery tree, which may lead to unsatisfactory performance when themain branches are confusing. Motivated by the wide application of the graphneural network in structured data, in this paper, we propose a conditionalpartial-residual graph convolutional network (CPR-GCN), which takes bothposition and CT image into consideration, since CT image contains abundantinformation such as branch size and spanning direction. Two majority parts, aPartial-Residual GCN and a conditions extractor, are included in CPR-GCN. Theconditions extractor is a hybrid model containing the 3D CNN and the LSTM,which can extract 3D spatial image features along the branches. On thetechnical side, the Partial-Residual GCN takes the position features of thebranches, with the 3D spatial image features as conditions, to predict thelabel for each branches. While on the mathematical side, our approach twiststhe partial differential equation (PDE) into the graph modeling. A dataset with511 subjects is collected from the clinic and annotated by two experts with atwo-phase annotation process. According to the five-fold cross-validation, ourCPR-GCN yields 95.8% meanRecall, 95.4% meanPrecision and 0.955 meanF1, whichoutperforms state-of-the-art approaches.

CPR-GCN: Conditional Partial-Residual Graph Convolutional Network in Automated Anatomical Labeling of Coronary Arteries