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

The early diagnosis and screening of glaucoma are important for patients toreceive treatment in time and maintain eyesight. Nowadays, deep learning (DL)based models have been successfully used for computer-aided diagnosis (CAD) ofglaucoma from retina fundus images. However, a DL model pre-trained using adataset from one hospital center may have poor performance on a dataset fromanother new hospital center and therefore its applications in the real sceneare limited. In this paper, we propose a self-adaptive transfer learning (SATL)strategy to fill the domain gap between multicenter datasets. Specifically, theencoder of a DL model that is pre-trained on the source domain is used toinitialize the encoder of a reconstruction model. Then, the reconstructionmodel is trained using only unlabeled image data from the target domain, whichmakes the encoder in the model adapt itself to extract useful high-levelfeatures both for target domain images encoding and glaucoma classification,simultaneously. Experimental results demonstrate that the proposed SATLstrategy is effective in the domain adaptation task between one private and twopublic glaucoma diagnosis datasets, i.e. pri-RFG, REFUGE, and LAG. Moreover,the proposed strategy is completely independent of the source domain data,which meets the real scene application and the privacy protection policy.

Self-Adaptive Transfer Learning for Multicenter Glaucoma Classification in Fundus Retina Images