Skip to main content

DRAC 2022: Diabetic Retinopathy Analysis Challenge

174 OCTA images for DR lesion segmentation (IRMA, NPA, NV), image quality assessment, and DR grading (3-class).

At a glance

FieldValue
Short namedrac22
Full nameDRAC 2022: Diabetic Retinopathy Analysis Challenge
First published2022-07-08
Publication date precisionday
Publication date evidencedrac22.grand-challenge.org/Timeline
Publication date source fieldofficial DRAC22 challenge timeline: training sets for Tasks 2 and 3 released
Publication date reviewed2026-09-11
Primary categoryocta
Resource rolecurrent_dataset
Dataset familydrac22
Contained modalitiesocta
Taskssegmentation, classification, grading
Primary reported quantity174 images
Classes3 (No DR, Non-proliferative DR, Proliferative DR)
Splitstrain, test
Size0.3 GB
Source-stated termsCC BY 4.0
Normalized termscc-by
Descriptive screening labelStandard label without an explicit NC clause; not a permission finding
Terms scopedataset_files
Access frictionself_service_authenticated
Route backendZenodo
Availabilityavailable (checked 2026-07-21)
Acquisition supportstandard_platform_supported
Legacy sample-loader statusStandard loader included

Reported quantities

RoleCountUnitScopeBasisEvidence
Primary174imagesPrimary quantity reported in the reviewed catalog sourcelegacy_catalog_fieldzenodo.org/records

Counts retain their source-reported units. Additional rows can describe components, paired items, or derivative copies and are not automatically added to the primary quantity.

Notes

Available from Grand Challenge after free registration.

Access information and download

# Read-only preflight
eyehub download drac22 --data-dir ./data --dry-run --json

# Download, only when preflight reports supported behavior
eyehub download drac22 --data-dir ./data

Upstream page: zenodo.org/records

Source-term evidence: zenodo.org/records

Loader example

This entry includes a standard DatasetSample loader.

from pathlib import Path
from eyedatahub.datasets.registry import REGISTRY

data_dir = Path('~/.eyedatahub/data').expanduser()
ds = REGISTRY.get_dataset('drac22')
samples = ds.load(data_dir, split='test')
for s in samples[:5]:
print(s.sample_id, s.label, s.image_path)

Citation

@misc{drac22,
title = { DRAC 2022: Diabetic Retinopathy Analysis Challenge },
note = { Qin et al., 'DRAC: Diabetic Retinopathy Analysis Challenge with Ultra-Wide Optical Coherence Tomography Angiography Images', Medical Image Analysis 2024 },
year = { 2024 },
url = { https://zenodo.org/records/10280359 },
}

Source-stated terms

  • Raw source string: CC BY 4.0
  • Normalized category: cc-by
  • Apparent scope: dataset_files
  • Descriptive screening label: Standard label without an explicit NC clause; not a permission finding

⚠️ Source-stated terms, scope, and normalized labels are curation metadata, not legal advice or a permission finding. Review the current official source before transfer or reuse.

Similar resources by shared modality

  • octa_macula_coronal: OCTA Macula Coronal Views (82,560 images, cc-by)
  • octa_500: OCTA-500: Large-scale OCTA Multi-task Benchmark (500 participants, research-only)
  • aroma_octa: AROMA Retinal OCTA Artifact Dataset (281 images, cc-by)
  • rose: ROSE: Retinal OCT-Angiography Vessel Segmentation (229 images, cc-by)
  • soul_octa: SOUL: OCTA Human-Machine Collaborative Annotation Dataset (178 longitudinal samples, cc-by)
  • ut_fsocta: UTHealth Fundus and Synthetic OCTA Dataset (112 participants, unknown)
  • dryad_preeclampsia_ocular_octa: Plane wave ultrasound and OCT angiography of the eye in preeclampsia (Not reported, cc0)
  • retinal_oct_octa_two_subjects_processed: Processed Retinal OCT and OCTA Two-Subject Dataset (Not reported, cc-by)