Papers › U-Net with Hierarchical Bottleneck Attention for Landmark Detection in Fundus Images...
U-Net with Hierarchical Bottleneck Attention for Landmark Detection in Fundus Images of the Degenerated Retina
Shuyun Tang, Ziming Qi, Jacob Granley, Michael Beyeler
Fundus photography has routinely been used to document the presence and severity of retinal degenerative diseases such as age-related macular degeneration (AMD), glaucoma, and diabetic retinopathy (DR) in clinical practice, for which the fovea and optic disc (OD) are important retinal landmarks. However, the occurrence of lesions, drusen, and other retinal abnormalities during retinal degeneration severely complicates automatic landmark detection and segmentation. Here we propose HBA-U-Net: a U-Net backbone enriched with hierarchical bottleneck attention. The network consists of a novel bottleneck attention block that combines and refines self-attention, channel attention, and relative-position attention to highlight retinal abnormalities that may be important for fovea and OD segmentation in the degenerated retina. HBA-U-Net achieved state-of-the-art results on fovea detection across datasets and eye conditions (ADAM: Euclidean Distance (ED) of 25.4 pixels, REFUGE: 32.5 pixels, IDRiD: 32.1 pixels), on OD segmentation for AMD (ADAM: Dice Coefficient (DC) of 0.947), and on OD detection for DR (IDRiD: ED of 20.5 pixels). Our results suggest that HBA-U-Net may be well suited for landmark detection in the presence of a variety of retinal degenerative diseases.
Code
Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Fovea Detection | ADAM | HBA-U-Net | Euclidean Distance (ED) | 25.4 | #1 of 1 | Archive leaderboard | report |
| Fovea Detection | IDRiD | HBA-U-Net | Euclidean Distance (ED) | 32.1 | #1 of 1 | Archive leaderboard | report |
| Fovea Detection | REFUGE | HBA-U-Net | Euclidean Distance (ED) | 32.5 | #1 of 1 | Archive leaderboard | report |
| Optic Disc Detection | IDRiD | HBA-U-Net | Euclidean Distance (ED) | 20.5 | #1 of 1 | Archive leaderboard | report |
Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.
Methods
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections