MMRDR: Multi-Modal Retinal Diabetic Retinopathy Dataset

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 Data 2026.

At a glance

Field	Value
Short name	mmrdr
Full name	MMRDR: Multi-Modal Retinal Diabetic Retinopathy Dataset
Primary category	multimodal
Contained modalities	fundus, oct, uwf_fundus
Tasks	grading, classification
Samples	24,460
Classes	5 (No DR, Mild DR, Moderate DR, Severe DR, Proliferative DR)
Splits	train, test
Size	18.61 GB
Source-stated terms	CC BY 4.0
Normalized terms	cc-by
Descriptive screening label	Standard label without an explicit NC clause; not a permission finding
Terms scope	dataset_files
Access friction	anonymous_direct
Route backend	Figshare
Availability	available (checked 2026-07-21)
Acquisition support	standard_platform_supported
Legacy sample-loader status	Standard loader included

Notes

Contains 24,460 images across CFP, OCT, and UWF modalities. The source-reported unit is images rather than unique patients. Evaluation code: https://github.com/Vladimirovich2019/MMRDR_Evaluation

Access preflight and acquisition

CLI

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

# Explicit transfer, only when preflight reports supported behavior
eyehub download mmrdr --data-dir ./data

Python

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

ds = REGISTRY.get_dataset('mmrdr')
print(preflight_dataset(ds, './data'))  # no transfer

Upstream page: https://doi.org/10.6084/m9.figshare.29423747

Source-term evidence: https://doi.org/10.6084/m9.figshare.29423747

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

Citation

BibTeX

@misc{mmrdr,
  title  = { MMRDR: Multi-Modal Retinal Diabetic Retinopathy Dataset },
  note   = { MMRDR: Multi-Modal Retinal Diabetic Retinopathy Dataset. Nature Scientific Data 2026. Figshare: https://doi.org/10.6084/m9.figshare.29423747 — GitHub: https://github.com/Vladimirovich2019/MMRDR_Evaluation },
  year   = { 2026 },
  url    = { https://doi.org/10.6084/m9.figshare.29423747 },
}

Plain text

MMRDR: Multi-Modal Retinal Diabetic Retinopathy Dataset. Nature Scientific Data 2026. Figshare: https://doi.org/10.6084/m9.figshare.29423747 — GitHub: https://github.com/Vladimirovich2019/MMRDR_Evaluation

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.

Related datasets with shared modalities

• eyecare_100k: Eyecare-100K: Multimodal Ophthalmology VQA Corpus (102,000 records, unknown)
• multieye: MultiEYE: OCT-Enhanced Fundus Multi-Disease Benchmark (58,036 records, mit)
• lmod_plus: LMOD+ Multimodal Ophthalmology Benchmark (32,633 records, unknown)
• harvard_fairvision: Harvard-FairVision (AMD + DR + Glaucoma, paired SLO + OCT) (30,000 records, cc-by-nc-nd)
• x_pcr: X-PCR Ophthalmology Progressive Clinical Reasoning Benchmark (18,700 records, unknown)
• olives: OLIVES: Ophthalmic Labels for Investigating Visual Eye Semantics (9,408 records, cc-by)
• oct_fundus_dme_dr_mexico: OCT and Eye Fundus Dataset for DME and DR (2,661 records, unknown)
• deepdrid: DeepDRiD: Diabetic Retinopathy Grading and Image Quality Dataset (2,256 records, cc-by-sa)