DeepDRiD: Diabetic Retinopathy Grading and Image Quality Dataset

2,000 regular fundus images (500 patients × 2 fields × 2 eyes) plus 256 ultra-widefield fundus images labeled for DR severity (ICDR grades 0-4) and image quality assessment (gradable/ungradable). From the DeepDRiD challenge (MICCAI 2020 / ISBI 2020).

At a glance

Field	Value
Short name	deepdrid
Full name	DeepDRiD: Diabetic Retinopathy Grading and Image Quality Dataset
First published	2020-01-22
Publication date precision	day
Publication date evidence	biomedicalimaging.org/2020
Publication date source field	official ISBI 2020 challenge timeline: Training Data Release (Images + Groundtruth)
Publication date reviewed	2026-09-11
Primary category	fundus
Resource role	current_dataset
Dataset family	deepdrid
Contained modalities	fundus, uwf_fundus
Tasks	grading, classification, quality
Primary reported quantity	2,256 images
Classes	5 (No DR, Mild NPDR, Moderate NPDR, Severe NPDR, Proliferative DR)
Splits	train, val, test
Size	3.0 GB
Source-stated terms	CC BY-SA 4.0
Normalized terms	cc-by-sa
Descriptive screening label	Standard label without an explicit NC clause; not a permission finding
Terms scope	dataset_files
Access friction	self_service_authenticated
Route backend	Zenodo
Availability	available (checked 2026-07-21)
Acquisition support	standard_platform_supported
Legacy sample-loader status	Standard loader included

Reported quantities

Role	Count	Unit	Scope	Basis	Evidence
Primary	2,256	images	Primary quantity reported in the reviewed catalog source	legacy_catalog_field	zenodo.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

Contains both regular fundus (2000 images in dual-field pairs) and ultra-widefield fundus (256 images). Labels CSV includes DR grade (0-4) and quality score.

Documented relationships

These links record source-supported lineage or overlap, not merely similar modality tags.

• fundus_report_dataset is derived from this record: The dataset card reports 203 source images from DeepDRiD and 219 from OUWFD. (evidence)
• mm_retinal_reason is derived from this record: The version-pinned official dataset card lists this record among the CFP or OCT sources used to construct MM-Retinal-Reason. (evidence)
• x_pcr is derived from this record: Source labels in the version-pinned public X-PCR deposit identify this catalog record as upstream material. (evidence)

Access information and download

CLI

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

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

Python

from eyedatahub.acquisition import preflight_dataset
from eyedatahub.datasets.registry import REGISTRY

ds = REGISTRY.get_dataset('deepdrid')
print(preflight_dataset(ds, './data'))  # no download

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('deepdrid')
samples = ds.load(data_dir, split='test')
for s in samples[:5]:
    print(s.sample_id, s.label, s.image_path)

Citation

BibTeX

@misc{deepdrid,
  title  = { DeepDRiD: Diabetic Retinopathy Grading and Image Quality Dataset },
  note   = { Liu R et al., 'DeepDRiD: Diabetic Retinopathy—Grading and Image Quality Estimation Challenge', Patterns 2022. Zenodo: https://zenodo.org/records/8248825 },
  year   = { 2022 },
  url    = { https://zenodo.org/records/8248825 },
}

Plain text

Liu R et al., 'DeepDRiD: Diabetic Retinopathy—Grading and Image Quality Estimation Challenge', Patterns 2022. Zenodo: https://zenodo.org/records/8248825

Source-stated terms

• Raw source string: CC BY-SA 4.0
• Normalized category: cc-by-sa
• 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

• mmrdr: MMRDR: Multi-Modal Retinal Diabetic Retinopathy Dataset (24,460 images, cc-by)
• fundus_report_dataset: Fundus Report Dataset (422 image report pairs, cc-by)
• airogs: AIROGS: AI for Robust Glaucoma Screening (113,893 images, cc-by-nc-nd)
• multieye: MultiEYE: OCT-Enhanced Fundus Multi-Disease Benchmark (103,959 images, mit)
• eyecare_100k: Eyecare-100K: Multimodal Ophthalmology VQA Corpus (102,000 question answer pairs, unknown)
• justraigs: JustRAIGS: Just Referral AI Glaucoma Screening Dataset (101,442 images, cc-by-nc-nd)
• eyepacs: EyePACS — Diabetic Retinopathy Detection (Kaggle 2015) (88,702 images, research-only)
• angioreport: AngioReport Fundus Angiography Report Dataset (55,361 images, unknown)