17 docs tagged with "resource-role-derivative-dataset"

Two thousand preprocessed fundus images compiled from six public sources for normal, diabetes, cataract, and age-related macular degeneration classification.

Augmented ODIR-5K fundus photographs for 8-class ocular disease classification: Normal, Diabetes, Glaucoma, Cataract, AMD, Hypertension, Myopia, Other. Preprocessing includes CLAHE and standard augmen

Precomputed image embeddings for BRSET and mBRSET to support efficient ophthalmic AI research without raw-image redistribution.

Five-domain optic disc/cup segmentation benchmark composed from REFUGE, Drishti-GS, ORIGA, RIGA, and related sources.

Synthetic glaucoma/normal fundus images with documented human source collections.

OCT images for intraretinal cystoid-fluid segmentation, partly derived from public OCT DME sources with expert-selected masks.

Processed Cataract-1K surgical-frame dataset for segmentation/object-detection workflows.

Composite multimodal ophthalmology benchmark with multi-granular anatomical, diagnostic, staging, demographic, and text annotations.

Multi-modal DR dataset combining color fundus photographs (CFP), OCT B-scans, and ultra-widefield (UWF) fundus images, annotated for DR detection and severity grading. Published in Nature Scientific D

58,036 fundus + 45,923 OCT images assembled for multi-disease classification (8 classes) with cross-modal distillation. Sourced from multiple public ophthalmic datasets.

2,208 color fundus images with 20-class multi-label disease annotations.

Augmented DRIVE, STARE, and CHASE_DB1 vessel-segmentation images for out-of-distribution robustness evaluation.

Fundus-photography dataset for retinal artery occlusion diagnosis, based on web-derived public data and public fundus datasets.

RIGA/MESSIDOR-derived benchmark for optic disc and cup segmentation domain adaptation.

~12,000 fundus images aggregated from 19 public glaucoma datasets with standardized disc/cup/vessel channels and unified labels. CC0 — fully public domain.

Synthetic OCT images for the four Kermany diagnostic classes.

The version-pinned public deposit contains 18,735 ophthalmic image-text benchmark rows across CFP, external-eye, FFA, OCT, and RetCam subsets.