AOD: Augmented Ocular Diseases Dataset

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

At a glance

Field	Value
Short name	aod
Full name	AOD: Augmented Ocular Diseases Dataset
Publication date	2021-08-20
Date basis	Initial dataset release
Publication date precision	day
Publication date evidence	kaggle.com/api
Publication date source field	versions[0].creationDate (version 1, Initial release)
Publication date reviewed	2026-09-11
Date notes	The catalog resource is the augmented ODIR-derived Kaggle dataset itself; its public v1 release is dated directly by Kaggle API metadata.
Primary category	fundus
Resource role	derivative_dataset
Dataset family	aod
Contained modalities	fundus
Tasks	classification
Primary reported quantity	14,813 images
Classes	8 (Normal, Diabetes, Glaucoma, Cataract, AMD, Hypertension, Myopia, Other)
Splits	train, test
Size	2.0 GB
Source-stated terms	See Kaggle dataset page
Normalized terms	unknown
Descriptive screening label	Unknown or unclear; do not assume permission
Terms scope	unknown
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	14,813	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.

Notes

OVERLAP: AOD is an augmented variant of ODIR-2019 (already in EyeDataHub as odir2019). Preprocessing (CLAHE) and augmentation explain the 14,813 vs 16,000 image count delta. Kept because the augmented split appears in downstream benchmarks separately.

Documented relationships

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

• This record is derived from odir2019: The AOD deposit describes an augmented and preprocessed ODIR-5K resource. (evidence)

Access information and download

CLI

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

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

Python

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

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

Citation

BibTeX

@misc{aod,
  title  = { AOD: Augmented Ocular Diseases Dataset },
  note   = { AOD Dataset. Kaggle. https://www.kaggle.com/datasets/nurmukhammed7/augemnted-ocular-diseases },
  url    = { https://www.kaggle.com/datasets/nurmukhammed7/augemnted-ocular-diseases },
}

Plain text

AOD Dataset. Kaggle. https://www.kaggle.com/datasets/nurmukhammed7/augemnted-ocular-diseases

Source-stated terms

• Raw source string: See Kaggle dataset page
• Normalized category: unknown
• Apparent scope: unknown
• Descriptive screening label: Unknown or unclear; do not assume permission

⚠️ 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)