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

With the injection of contrast material into blood vessels, multi-phasecontrasted CT images can enhance the visibility of vessel networks in the humanbody. Reconstructing the 3D geometric morphology of liver vessels from thecontrasted CT images can enable multiple liver preoperative surgical planningapplications. Automatic reconstruction of liver vessel morphology remains achallenging problem due to the morphological complexity of liver vessels andthe inconsistent vessel intensities among different multi-phase contrasted CTimages. On the other side, high integrity is required for the 3D reconstructionto avoid decision making biases. In this paper, we propose a framework forliver vessel morphology reconstruction using both a fully convolutional neuralnetwork and a graph attention network. A fully convolutional neural network isfirst trained to produce the liver vessel centerline heatmap. Anover-reconstructed liver vessel graph model is then traced based on the heatmapusing an image processing based algorithm. We use a graph attention network toprune the false-positive branches by predicting the presence probability ofeach segmented branch in the initial reconstruction using the aggregated CNNfeatures. We evaluated the proposed framework on an in-house dataset consistingof 418 multi-phase abdomen CT images with contrast. The proposed graph networkpruning improves the overall reconstruction F1 score by 6.4% over the baseline.It also outperformed the other state-of-the-art curvilinear structurereconstruction algorithms.

Graph Attention Network based Pruning for Reconstructing 3D Liver Vessel Morphology from Contrasted CT Images