Skip to main content

DeepEyeNet (DEN): Fundus Report Generation Dataset

15,709 fundus images with paired medical reports and extracted keywords. Only public fundus report-generation dataset — useful for VLM / captioning evaluation.

At a glance

FieldValue
Short namedeepeyenet
Full nameDeepEyeNet (DEN): Fundus Report Generation Dataset
First publishedUnknown
Publication date precisionUnknown
Publication date evidenceUnknown
Publication date source fieldUnknown
Publication date reviewedUnknown
Primary categoryfundus
Resource rolecurrent_dataset
Dataset familydeepeyenet
Contained modalitiesfundus, text
Tasksclassification, multilabel
Primary reported quantity15,709 images
ClassesNot reported (Not reported)
Splitstrain, val, test
Size5.0 GB
Source-stated termsResearch only (NDA via email request)
Normalized termsresearch-only
Descriptive screening labelResearch or challenge restriction recorded; check source
Terms scopedataset_files
Access frictionauthor_contact
Route backendManual (upstream-gated)
Availabilityavailable (checked 2026-07-21)
Acquisition supportmanual_access_blocked
Legacy sample-loader statusMetadata and access only

Reported quantities

RoleCountUnitScopeBasisEvidence
Primary15,709imagesPrimary quantity reported in the reviewed catalog sourcelegacy_catalog_fieldgithub.com/Jhhuangkay

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

NDA gated — email [email protected] to request. No automated mirror exists.

Access information and download

# This route requires upstream human action; no transfer starts.
eyehub download deepeyenet --data-dir ./data --dry-run --json
# Follow the official instructions shown by preflight.

Upstream page: github.com/Jhhuangkay

Source-term evidence: github.com/Jhhuangkay

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

@misc{deepeyenet,
title = { DeepEyeNet (DEN): Fundus Report Generation Dataset },
note = { Huang et al., 'DeepOpht: Medical Report Generation for Retinal Images via Deep Models and Visual Explanation', WACV 2021 },
year = { 2021 },
url = { https://github.com/Jhhuangkay/DeepOpht-Medical-Report-Generation-for-Retinal-Images-via-Deep-Models-and-Visual-Explanation },
}

Source-stated terms

  • Raw source string: Research only (NDA via email request)
  • Normalized category: research-only
  • Apparent scope: dataset_files
  • Descriptive screening label: Research or challenge restriction recorded; check source

⚠️ 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

  • eyecare_100k: Eyecare-100K: Multimodal Ophthalmology VQA Corpus (102,000 question answer pairs, unknown)
  • angioreport: AngioReport Fundus Angiography Report Dataset (55,361 images, unknown)
  • ffa_ir: FFA-IR Medical Report Dataset (47,247 images, unknown)
  • lmod_plus: LMOD+ Multimodal Ophthalmology Benchmark (32,633 annotated instances, unknown)
  • x_pcr: X-PCR Ophthalmology Progressive Clinical Reasoning Benchmark (18,735 rows, unknown)
  • dme_vqa: Diabetic Macular Edema Visual Question Answering Dataset (13,470 question answer pairs, cc-by)
  • dme_vqa_logical: DME VQA Dataset with Logical Relations (13,470 question answer pairs, cc-by)
  • fairvlmed: FairVLMed: Fair Vision-Language Medical Ophthalmic Dataset (10,000 images, cc-by-nc-nd)