RFMiD: Retinal Fundus Multi-disease Image Dataset

3200 fundus images annotated for 45 retinal conditions. Used for multi-label disease classification.

At a glance

Field	Value
Short name	rfmid
Full name	RFMiD: Retinal Fundus Multi-disease Image Dataset
First published	2020-11-22
Publication date precision	day
Publication date evidence	riadd.grand-challenge.org
Publication date source field	Official RIADD Important Dates: Training Data Release (Images + Ground truth)
Publication date reviewed	2026-09-11
Primary category	fundus
Resource role	current_dataset
Dataset family	rfmid
Contained modalities	fundus
Tasks	multilabel, classification
Primary reported quantity	3,200 images
Classes	29 (Disease_Risk, DR, ARMD, MH, DN, MYA, BRVO, TSLN, ERM, LS, MS, CSR, ODC, CRVO, TV, AH, ODP, ODE, ST, AION, PT, RT, RS, CRS, EDN, RPEC, MHL, RP, other)
Splits	train, val, test
Size	1.5 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	Kaggle
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	3,200	images	Primary quantity reported in the reviewed catalog source	legacy_catalog_field	kaggle.com/datasets

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.

Documented relationships

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

• amdnet23 is derived from this record: AMDNet23 compiles preprocessed images from ODIR, RFMiD, HRF, ARIA, DR_200, and Fundus Dataset. (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)
• multieye is derived from this record: The MultiEYE paper names this record as one of the public fundus or OCT sources assembled for the benchmark. (evidence)
• mured is derived from this record: The MuReD description identifies STARE, RFMiD, and ARIA as image sources and applies post-processing. (evidence)
• rao_fundus is derived from this record: The RAO source reports use of public web images plus RFMiD and JSIEC images. (evidence)
• rfmid2 is extension of this record: RFMiD 2.0 is described as an auxiliary dataset to the earlier RFMiD release, not as the same image cohort. (evidence)

Access information and download

CLI

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

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

Python

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

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

Upstream page: kaggle.com/datasets

Source-term evidence: kaggle.com/datasets

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

Citation

BibTeX

@misc{rfmid,
  title  = { RFMiD: Retinal Fundus Multi-disease Image Dataset },
  note   = { Pachade et al., 'Retinal Fundus Multi-disease Image Dataset (RFMiD): A Dataset for Multi-Disease Detection Research', Data 2021 },
  year   = { 2021 },
  url    = { https://www.kaggle.com/datasets/andrewmvd/retinal-disease-classification },
}

Plain text

Pachade et al., 'Retinal Fundus Multi-disease Image Dataset (RFMiD): A Dataset for Multi-Disease Detection Research', Data 2021.

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

• 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)
• ffa_ir: FFA-IR Medical Report Dataset (47,247 images, unknown)
• mfiddr: MFIDDR: Multi-Field Imaging Dataset for Diabetic Retinopathy (34,452 images, mit)