17 docs tagged with "resource-role-annotation-layer"

Segmentation masks for the vascular arcade and optic nerve head derived from APTOS 2019 fundus images.

Semantic segmentation labels for 4,670 frames from 25 cataract surgery videos (CATARACTS challenge). 25 anatomy and instrument classes.

Extended phase/time labels for the Cataract-101 surgical-video dataset.

Synthetic surgical-analysis instruction/chain-of-thought dataset derived from Cataract-1K frames.

Observation-level source data, annotations, or signals. from Uses human retinal-image benchmarks; it contributes clinician disc tracings.

Fundus-image VQA dataset for diabetic macular edema derived from IDRiD and e-ophtha.

Extension of the DME VQA dataset with logical-relation consistency annotations.

Quality labels for 28,792 EyePACS fundus images, graded as good, usable, or reject and divided into the original EyePACS train and test partitions.

Fundus/UWF image-report dataset derived from DeepDRiD and OUWFD-style resources for report-generation research.

Revised glaucoma reasoning reports paired with the documented source fundus cases.

Extended HRF annotations for optic disc, cup, retinal vessels, and alpha/beta peripapillary zones.

Two COCO-format instance-segmentation datasets derived from cataract surgery videos, covering instruments and anatomical structures.

Human cataract-surgery video frames with iris and pupil pixel masks.

Ophthalmology-specific multimodal reasoning dataset built from 45 public datasets. Chain-of-thought reasoning traces for retinal VQA.

1200 fundus images from REFUGE1 with optic disc/cup segmentation masks annotated by multiple expert raters.

Retinal vessel analysis benchmark with vessel masks, artery/vein masks and skeletons, bifurcation points, vascular trees, and abnormality annotations.

40 fundus images (derived from DRIVE) with artery/vein annotations and vessel-tree structural labels.