FFA-IR Medical Report Dataset

Fundus fluorescein angiography images paired with Chinese and translated English reports for report-generation research.

At a glance

Field	Value
Short name	ffa_ir
Full name	FFA-IR Medical Report Dataset
Primary category	multimodal
Contained modalities	fundus, fundus_angiography, text
Tasks	report_generation, text_generation
Samples	47,247
Classes	Not reported (Not reported)
Splits	all
Size	Not reported
Source-stated terms	PhysioNet credentialed access terms
Normalized terms	unknown
Descriptive screening label	Unknown or unclear; do not assume permission
Terms scope	unknown
Access friction	controlled_or_manual
Route backend	PhysioNet
Availability	available (checked 2026-07-21)
Acquisition support	manual_access_blocked
Legacy sample-loader status	Metadata and access only

Access preflight and acquisition

CLI

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

Python

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

ds = REGISTRY.get_dataset('ffa_ir')
print(preflight_dataset(ds, './data'))  # returns manual_access_blocked

Upstream page: https://doi.org/10.13026/k5rp-9h43

Source-term evidence: https://doi.org/10.13026/k5rp-9h43

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{ffa_ir,
  title  = { FFA-IR Medical Report Dataset },
  note   = { FFA-IR: Towards an Explainable and Reliable Medical Report Generation Benchmark. PhysioNet, 2021 },
  year   = { 2021 },
  url    = { https://doi.org/10.13026/k5rp-9h43 },
}

Plain text

FFA-IR: Towards an Explainable and Reliable Medical Report Generation Benchmark. PhysioNet, 2021.

Source-stated terms

• Raw source string: PhysioNet credentialed access terms
• 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.

Related datasets with shared modalities

• eyecare_100k: Eyecare-100K: Multimodal Ophthalmology VQA Corpus (102,000 records, unknown)
• angioreport: AngioReport Fundus Angiography Report Dataset (55,361 records, unknown)
• x_pcr: X-PCR Ophthalmology Progressive Clinical Reasoning Benchmark (18,700 records, unknown)
• mm_retinal_reason: MM-Retinal-Reason: Ophthalmology Multimodal Reasoning Dataset (count not reported records, unknown)
• ophthalvqa: OphthalVQA Dataset (count not reported records, cc-by)
• lmod_plus: LMOD+ Multimodal Ophthalmology Benchmark (32,633 records, unknown)
• deepeyenet: DeepEyeNet (DEN): Fundus Report Generation Dataset (15,709 records, research-only)
• fundus_report_dataset: Fundus Report Dataset (422 records, cc-by)