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

Self-supervised learning (SSL) has been widely applied to learn imagerepresentations through exploiting unlabeled images. However, it has not beenfully explored in the medical image analysis field. In this work, we proposeSaliency-guided Self-Supervised image Transformer (SSiT) for diabeticretinopathy (DR) grading from fundus images. We novelly introduce saliency mapsinto SSL, with a goal of guiding self-supervised pre-training withdomain-specific prior knowledge. Specifically, two saliency-guided learningtasks are employed in SSiT: (1) We conduct saliency-guided contrastive learningbased on the momentum contrast, wherein we utilize fundus images' saliency mapsto remove trivial patches from the input sequences of the momentum-updated keyencoder. And thus, the key encoder is constrained to provide targetrepresentations focusing on salient regions, guiding the query encoder tocapture salient features. (2) We train the query encoder to predict thesaliency segmentation, encouraging preservation of fine-grained information inthe learned representations. Extensive experiments are conducted on fourpublicly-accessible fundus image datasets. The proposed SSiT significantlyoutperforms other representative state-of-the-art SSL methods on all datasetsand under various evaluation settings, establishing the effectiveness of thelearned representations from SSiT. The source code is available athttps://github.com/YijinHuang/SSiT.

SSiT: Saliency-guided Self-supervised Image Transformer for Diabetic Retinopathy Grading