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

Robot-assisted Fenestrated Endovascular Aortic Repair (FEVAR) is currentlynavigated by 2D fluoroscopy which is insufficiently informative. Previously, asemi-automatic 3D shape instantiation method was developed to instantiate the3D shape of a main, deployed, and fenestrated stent graft from a singlefluoroscopy projection in real-time, which could help 3D FEVAR navigation androbotic path planning. This proposed semi-automatic method was based on theRobust Perspective-5-Point (RP5P) method, graft gap interpolation andsemi-automatic multiple-class marker center determination. In this paper, anautomatic 3D shape instantiation could be achieved by automatic multiple-classmarker segmentation and hence automatic multiple-class marker centerdetermination. Firstly, the markers were designed into five different shapes.Then, Equally-weighted Focal U-Net was proposed to segment the fluoroscopyprojections of customized markers into five classes and hence to determine themarker centers. The proposed Equally-weighted Focal U-Net utilized U-Net as thenetwork architecture, equally-weighted loss function for initial markersegmentation, and then equally-weighted focal loss function for improving theinitial marker segmentation. This proposed network outperformed traditionalWeighted U-Net on the class-imbalance segmentation in this paper with reducingone hyper-parameter - the weight. An overall mean Intersection over Union(mIoU) of 0.6943 was achieved on 78 testing images, where 81.01% markers weresegmented with a center position error <1.6mm. Comparable accuracy of 3D shapeinstantiation was also achieved and stated. The data, trained models andTensorFlow codes are available on-line.

Towards Automatic 3D Shape Instantiation for Deployed Stent Grafts: 2D  Multiple-class and Class-imbalance Marker Segmentation with Equally-weighted  Focal U-Net