EyeQ Retinal Image Quality Assessment Dataset

Quality labels for 28,792 EyePACS fundus images, graded as good, usable, or reject and divided into the original EyePACS train and test partitions.

At a glance

Field	Value
Short name	eyeq
Full name	EyeQ Retinal Image Quality Assessment Dataset
First published	Unknown
Publication date precision	Unknown
Publication date evidence	Unknown
Publication date source field	Unknown
Publication date reviewed	Unknown
Primary category	fundus
Resource role	annotation_layer
Dataset family	eyeq
Contained modalities	fundus
Tasks	quality, grading
Primary reported quantity	28,792 images
Classes	3 (good, usable, reject)
Splits	train, test
Size	Not reported
Source-stated terms	Unknown for released quality labels; code is CC BY-NC-SA 4.0
Normalized terms	unknown
Descriptive screening label	Unknown or unclear; do not assume permission
Terms scope	dataset_files
Access friction	anonymous_direct
Route backend	GitHub
Availability	available (checked 2026-07-21)
Acquisition support	end_to_end_tested
Legacy sample-loader status	Metadata and access only

Reported quantities

Role	Count	Unit	Scope	Basis	Evidence
Primary	28,792	images	Primary quantity reported in the reviewed catalog source	legacy_catalog_field	github.com/HzFu

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

EyeQ is a distinct annotation layer over EyePACS. The repository license covers the code but does not clearly license the quality labels. It does not provide the source images. Users must obtain EyePACS separately and comply with its terms.

Documented relationships

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

• This record is derived from eyepacs: EyeQ provides quality labels for 28,792 images from the EyePACS train and test partitions. (evidence)

Access information and download

CLI

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

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

Python

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

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

Upstream page: github.com/HzFu

Source-term evidence: github.com/HzFu

Loader status

This catalog record provides metadata and access instructions, but it does not yet include a standard DatasetSample loader. Inspect the source file structure or contribute a loader before using it in a training pipeline.

Citation

BibTeX

@misc{eyeq,
  title  = { EyeQ Retinal Image Quality Assessment Dataset },
  note   = { Fu H, Wang B, Shen J, et al. Evaluation of retinal image quality assessment networks in different color-spaces. MICCAI. 2019. doi:10.1007/978-3-030-32239-7_6 },
  year   = { 2019 },
  url    = { https://github.com/HzFu/EyeQ },
}

Plain text

Fu H, Wang B, Shen J, et al. Evaluation of retinal image quality assessment networks in different color-spaces. MICCAI. 2019. doi:10.1007/978-3-030-32239-7_6

Source-stated terms

• Raw source string: Unknown for released quality labels; code is CC BY-NC-SA 4.0
• Normalized category: unknown
• Apparent scope: dataset_files
• 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)