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/

Zendy Plus

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

Zendy Tools

Zendy Open

Manually annotating medical images is extremely expensive, especially forlarge-scale datasets. Self-supervised contrastive learning has been explored tolearn feature representations from unlabeled images. However, unlike naturalimages, the application of contrastive learning to medical images is relativelylimited. In this work, we propose a self-supervised framework, namelylesion-based contrastive learning for automated diabetic retinopathy (DR)grading. Instead of taking entire images as the input in the common contrastivelearning scheme, lesion patches are employed to encourage the feature extractorto learn representations that are highly discriminative for DR grading. We alsoinvestigate different data augmentation operations in defining our contrastiveprediction task. Extensive experiments are conducted on the publicly-accessibledataset EyePACS, demonstrating that our proposed framework performsoutstandingly on DR grading in terms of both linear evaluation and transfercapacity evaluation.

Lesion-based Contrastive Learning for Diabetic Retinopathy Grading from Fundus Images