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

Existing methods to reconstruct vascular structures from a computedtomography (CT) angiogram rely on injection of intravenous contrast to enhancethe radio-density within the vessel lumen. However, pathological changes can bepresent in the blood lumen, vessel wall or a combination of both that preventaccurate reconstruction. In the example of aortic aneurysmal disease, a bloodclot or thrombus adherent to the aortic wall within the expanding aneurysmalsac is present in 70-80% of cases. These deformations prevent the automaticextraction of vital clinically relevant information by current methods. In thisstudy, we implemented a modified U-Net architecture with attention-gating toestablish a high-throughput and automated segmentation pipeline of pathologicalblood vessels in CT images acquired with or without the use of a contrastagent. Twenty-six patients with paired non-contrast and contrast-enhanced CTimages within the ongoing Oxford Abdominal Aortic Aneurysm (OxAAA) study wererandomly selected, manually annotated and used for model training andevaluation (13/13). Data augmentation methods were implemented to diversify thetraining data set in a ratio of 10:1. The performance of our Attention-basedU-Net in extracting both the inner lumen and the outer wall of the aorticaneurysm from CT angiograms (CTA) was compared against a generic 3-D U-Net anddisplayed superior results. Subsequent implementation of this networkarchitecture within the aortic segmentation pipeline from bothcontrast-enhanced CTA and non-contrast CT images has allowed for accurate andefficient extraction of the entire aortic volume. This extracted volume can beused to standardize current methods of aneurysmal disease management and setsthe foundation for subsequent complex geometric and morphological analysis.Furthermore, the proposed pipeline can be extended to other vascularpathologies.

A Deep Learning Approach to Automate High-Resolution Blood Vessel  Reconstruction on Computerized Tomography Images With or Without the Use of  Contrast Agent