OLIVES: Ophthalmic Labels for Investigating Visual Eye Semantics
Longitudinal OCT + fundus dataset from AMD/DME patients across multiple clinical visits. 9,408 OCT B-scans have biomarker labels for 8 categories (fluid, drusen, scarring, PED variants, etc.); 78,000+ images include clinical measurements (BCVA, CST). Also includes 1,268 paired fundus photographs.
At a glance
| Field | Value |
|---|---|
| Short name | olives |
| Full name | OLIVES: Ophthalmic Labels for Investigating Visual Eye Semantics |
| First published | 2022-06-09 |
| Publication date precision | day |
| Publication date evidence | zenodo.org/api |
| Publication date source field | metadata.publication_date (earliest repository version) |
| Publication date reviewed | 2026-09-11 |
| Primary category | oct |
| Resource role | current_dataset |
| Dataset family | olives |
| Contained modalities | oct, fundus, tabular |
| Tasks | multilabel, classification |
| Primary reported quantity | 9,408 b scans |
| Classes | 8 (Fluid, Hard Exudate, Soft Exudate, Drusen, Scar, Laser Scar, Fibrovascular PED, Serous PED) |
| Splits | train, val, test |
| Size | 20.0 GB |
| Source-stated terms | CC BY 4.0 |
| Normalized terms | cc-by |
| 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 | Zenodo |
| 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 | 9,408 | b_scans | Biomarker-labeled OCT B-scans | official_source_description | zenodo.org/records |
| Additional | 1,268 | images | Paired fundus photographs | official_source_description | zenodo.org/records |
| Additional | 96 | eyes | Longitudinal eye-level cohort | official_source_description | zenodo.org/records |
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
9,408 biomarker-labelled B-scans from 96 patients (6 clinical visits × 49 B-scans/visit). Full OCT volume set ~62,000 B-scans. Also available on HuggingFace: gOLIVES/OLIVES_Dataset. Contains paired fundus photos and clinical metadata.
Access information and download
- CLI
- Python
# Read-only preflight
eyehub download olives --data-dir ./data --dry-run --json
# Download, only when preflight reports supported behavior
eyehub download olives --data-dir ./data
from eyedatahub.acquisition import preflight_dataset
from eyedatahub.datasets.registry import REGISTRY
ds = REGISTRY.get_dataset('olives')
print(preflight_dataset(ds, './data')) # no download
Upstream page: zenodo.org/records
Source-term evidence: zenodo.org/records
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('olives')
samples = ds.load(data_dir, split='test')
for s in samples[:5]:
print(s.sample_id, s.label, s.image_path)
Citation
- BibTeX
- Plain text
@misc{olives,
title = { OLIVES: Ophthalmic Labels for Investigating Visual Eye Semantics },
note = { Prabhushankar M et al., 'OLIVES Dataset: Ophthalmic Labels for Investigating Visual Eye Semantics', NeurIPS Datasets & Benchmarks 2022. https://zenodo.org/records/7105232 },
year = { 2022 },
url = { https://zenodo.org/records/7105232 },
}
Prabhushankar M et al., 'OLIVES Dataset: Ophthalmic Labels for Investigating Visual Eye Semantics', NeurIPS Datasets & Benchmarks 2022. https://zenodo.org/records/7105232
Source-stated terms
- Raw source string: CC BY 4.0
- Normalized category:
cc-by - 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
- lmod_plus: LMOD+ Multimodal Ophthalmology Benchmark (32,633 annotated instances,
unknown) - grape: GRAPE: Glaucoma Real-world Appraisal Progression Ensemble (1,115 examinations,
cc0) - 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) - harvard_fairvision: Harvard-FairVision (AMD + DR + Glaucoma, paired SLO + OCT) (30,000 participants,
cc-by-nc-nd) - mmrdr: MMRDR: Multi-Modal Retinal Diabetic Retinopathy Dataset (24,460 images,
cc-by) - x_pcr: X-PCR Ophthalmology Progressive Clinical Reasoning Benchmark (18,735 rows,
unknown) - fairvlmed: FairVLMed: Fair Vision-Language Medical Ophthalmic Dataset (10,000 images,
cc-by-nc-nd)