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

We identify and address three research gaps in the field of vesselsegmentation for funduscopy. The first focuses on the task of inference onhigh-resolution fundus images for which only a limited set of ground-truth datais publicly available. Notably, we highlight that simple rescaling and paddingor cropping of lower resolution datasets is surprisingly effective.Additionally we explore the effectiveness of semi-supervised learning forbetter domain adaptation. Our results show competitive performance on a set ofcommon public retinal vessel datasets using a small and light-weight neuralnetwork. For HRF, the only very high-resolution dataset currently available, wereach new state-of-the-art performance by solely relying on training imagesfrom lower-resolution datasets. The second topic concerns evaluation metrics.We investigate the variability of the F1-score on the existing datasets andreport results for recent SOTA architectures. Our evaluation show that mostSOTA results are actually comparable to each other in performance. Last, weaddress the issue of reproducibility by open-sourcing our complete pipeline.

On the Evaluation and Real-World Usage Scenarios of Deep Vessel Segmentation for Retinography