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

Accurate fovea localization is essential for analyzing retinal diseases toprevent irreversible vision loss. While current deep learning-based methodsoutperform traditional ones, they still face challenges such as the lack oflocal anatomical landmarks around the fovea, the inability to robustly handlediseased retinal images, and the variations in image conditions. In this paper,we propose a novel transformer-based architecture called DualStreamFoveaNet(DSFN) for multi-cue fusion. This architecture explicitly incorporateslong-range connections and global features using retina and vesseldistributions for robust fovea localization. We introduce a spatial attentionmechanism in the dual-stream encoder to extract and fuse self-learnedanatomical information, focusing more on features distributed along bloodvessels and significantly reducing computational costs by decreasing tokennumbers. Our extensive experiments show that the proposed architecture achievesstate-of-the-art performance on two public datasets and one large-scale privatedataset. Furthermore, we demonstrate that the DSFN is more robust on bothnormal and diseased retina images and has better generalization capacity incross-dataset experiments.

DualStreamFoveaNet: A Dual Stream Fusion Architecture with Anatomical Awareness for Robust Fovea Localization