3260 papers • 126 benchmarks • 313 datasets
Optic cup segmentation, concentric with optic disc, useful for glaucoma management (ophthalmology)
(Image credit: Papersgraph)
These leaderboards are used to track progress in optic-cup-segmentation-3
Use these libraries to find optic-cup-segmentation-3 models and implementations
No subtasks available.
This database consists of 1020 high resolution colour fundus images and provides ground truth annotations for glaucoma diagnosis, optic disc and optic cup segmentation, vertical cup-to-disc ratio, size of neuroretinal rim in inferior, superior, nasal and temporal quadrants, and bounding box location for optic disc.
The experimental results show that MedSegDiff outperforms state-of-the-art (SOTA) methods with considerable performance gap, indicating the generalization and effectiveness of the proposed model.
Segtran is an alternative segmentation framework based on transformers, which has unlimited effective receptive fields even at high feature resolutions, and a new positional encoding scheme for transformers is proposed, imposing a continuity inductive bias for images.
Adding a benchmark result helps the community track progress.