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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Diabetic retinopathy (DR) is one of the major blindness-causing diseasescurrently known. Automatic grading of DR using deep learning methods not onlyspeeds up the diagnosis of the disease but also reduces the rate ofmisdiagnosis. However,problems such as insufficient samples and imbalancedclass distribution in small DR datasets have constrained the improvement ofgrading performance. In this paper, we apply the idea of multi-stage transferlearning into the grading task of DR. The new transfer learning techniqueutilizes multiple datasets with different scales to enable the model to learnmore feature representation information. Meanwhile, to cope with the imbalancedproblem of small DR datasets, we present a class-balanced loss function in ourwork and adopt a simple and easy-to-implement training method for it. Theexperimental results on IDRiD dataset show that our method can effectivelyimprove the grading performance on small data, obtaining scores of 0.7961 and0.8763 in terms of accuracy and quadratic weighted kappa, respectively. Ourmethod also outperforms several state-of-the-art methods.

A Multi-stage Transfer Learning Framework for Diabetic Retinopathy Grading on Small Data