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

Domain adaptation (DA) has been widely applied in the diabetic retinopathy(DR) grading of unannotated ultra-wide-field (UWF) fundus images, which cantransfer annotated knowledge from labeled color fundus images. However,suffering from huge domain gaps and complex real-world scenarios, the DRgrading performance of most mainstream DA is far from that of clinicaldiagnosis. To tackle this, we propose a novel source-free active domainadaptation (SFADA) in this paper. Specifically, we focus on DR grading problemitself and propose to generate features of color fundus images withcontinuously evolving relationships of DRs, actively select a few valuable UWFfundus images for labeling with local representation matching, and adapt modelon UWF fundus images with DR lesion prototypes. Notably, the SFADA also takesdata privacy and computational efficiency into consideration. Extensiveexperimental results demonstrate that our proposed SFADA achievesstate-of-the-art DR grading performance, increasing accuracy by 20.9% andquadratic weighted kappa by 18.63% compared with baseline and reaching 85.36%and 92.38% respectively. These investigations show that the potential of ourapproach for real clinical practice is promising.

Source-free Active Domain Adaptation for Diabetic Retinopathy Grading Based on Ultra-wide-field Fundus Image