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

Estimating clinically-relevant vascular features following vesselsegmentation is a standard pipeline for retinal vessel analysis, which providespotential ocular biomarkers for both ophthalmic disease and systemic disease.In this work, we integrate these clinical features into a novel vascularfeature optimised loss function (VAFO-Loss), in order to regularise networks toproduce segmentation maps, with which more accurate vascular features can bederived. Two common vascular features, vessel density and fractal dimension,are identified to be sensitive to intra-segment misclassification, which is awell-recognised problem in multi-class artery/vein segmentation particularlyhindering the estimation of these vascular features. Thus we encode these twofeatures into VAFO-Loss. We first show that incorporating our end-to-endVAFO-Loss in standard segmentation networks indeed improves vascular featureestimation, yielding quantitative improvement in stroke incidence prediction, aclinical downstream task. We also report a technically interesting finding thatthe trained segmentation network, albeit biased by the feature optimised lossVAFO-Loss, shows statistically significant improvement in segmentation metrics,compared to those trained with other state-of-the-art segmentation losses.

VAFO-Loss: VAscular Feature Optimised Loss Function for Retinal Artery/Vein Segmentation