Skip to main content

CAVRI: Computer Analysis of VitreoRetinal Interface Dataset

50 annotated 3D SD-OCT volumes (7,050 B-scans, 640×385 px) from subjects with vitreomacular adhesion (VMA, 25 eyes) and vitreomacular traction (VMT, 25 eyes). Each volume: 141 B-scans over 2×7×7 mm. Annotated boundaries: PCV, ILM, RPE. Device: Optovue Avanti RTvue.

At a glance

FieldValue
Short namecavri
Full nameCAVRI: Computer Analysis of VitreoRetinal Interface Dataset
Primary categoryoct
Contained modalitiesoct
Taskssegmentation
Samples50
Classes3 (PCV, ILM, RPE)
Splitstrain, val, test
Size3.0 GB
Source-stated termsResearch/educational use only (no commercial redistribution)
Normalized termsresearch-only
Descriptive screening labelResearch or challenge restriction recorded; check source
Terms scopeunknown
Access frictionauthor_contact
Route backendManual (upstream-gated)
Availabilityavailable (checked 2026-07-21)
Acquisition supportmanual_access_blocked
Legacy sample-loader statusStandard loader included

Notes

Access by email request: [email protected] or [email protected]. Dataset page: https://dsp.put.poznan.pl/cavri_database-191/ GitHub (segmentation code): https://github.com/krzyk87/pcv_segmentation

Access preflight and acquisition

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

Upstream page: dsp.put.poznan.pl/cavri_database-191

Source-term evidence: dsp.put.poznan.pl/cavri_database-191

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

Citation

@misc{cavri,
title = { CAVRI: Computer Analysis of VitreoRetinal Interface Dataset },
note = { Stankiewicz A et al., 'Segmentation of Preretinal Space in Optical Coherence Tomography Images Using Deep Neural Networks', Sensors 21(22):7521 (2021). doi:10.3390/s21227521 },
year = { 2021 },
url = { https://dsp.put.poznan.pl/cavri_database-191/ },
}

Source-stated terms

  • Raw source string: Research/educational use only (no commercial redistribution)
  • Normalized category: research-only
  • Apparent scope: unknown
  • 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.

  • syn_oct: SYN-OCT Synthetic Glaucoma OCT Dataset (200,000 records, cc-by)
  • eyecare_100k: Eyecare-100K: Multimodal Ophthalmology VQA Corpus (102,000 records, unknown)
  • kermany_oct: Kermany OCT 2018: Retinal OCT Image Classification (84,484 records, cc-by)
  • multieye: MultiEYE: OCT-Enhanced Fundus Multi-Disease Benchmark (58,036 records, mit)
  • lmod_plus: LMOD+ Multimodal Ophthalmology Benchmark (32,633 records, unknown)
  • harvard_fairvision: Harvard-FairVision (AMD + DR + Glaucoma, paired SLO + OCT) (30,000 records, cc-by-nc-nd)
  • mario: MARIO: AMD-Progression Longitudinal OCT (MICCAI 2024) (30,000 records, cc-by)
  • mmrdr: MMRDR: Multi-Modal Retinal Diabetic Retinopathy Dataset (24,460 records, cc-by)