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

Diabetic retinopathy is the most important complication of diabetes. Earlydiagnosis of retinal lesions helps to avoid visual loss or blindness. Due tohigh-resolution and small-size lesion regions, applying existing methods, suchas U-Nets, to perform segmentation on fundus photography is very challenging.Although downsampling the input images could simplify the problem, it losesdetailed information. Conducting patch-level analysis helps reaching fine-scalesegmentation yet usually leads to misunderstanding as the lack of contextinformation. In this paper, we propose an efficient network that combines themtogether, not only being aware of local details but also taking fully use ofthe context perceptions. This is implemented by integrating the decoder partsof a global-level U-net and a patch-level one. The two streams are jointlyoptimized, ensuring that they are enhanced mutually. Experimental resultsdemonstrate our new framework significantly outperforms existing patch-basedand global-based methods, especially when the lesion regions are scattered andsmall-scaled.

Learning Mutually Local-global U-nets For High-resolution Retinal Lesion Segmentation in Fundus Images