STAGE 2023 Task 1 — Mean Deviation Prediction from OCT

400 macular OCT volumes; predict glaucoma Mean Deviation (MD, dB) from 24-2 Humphrey visual field test. Scalar regression task.

At a glance

Field	Value
Short name	stage_task1
Full name	STAGE 2023 Task 1 — Mean Deviation Prediction from OCT
Primary category	oct
Contained modalities	oct, visual_field
Tasks	regression
Samples	400
Classes	Not reported (Not reported)
Splits	train, test
Size	5.0 GB
Source-stated terms	Non-commercial research (Baidu AI Studio)
Normalized terms	research-only
Descriptive screening label	Research or challenge restriction recorded; check source
Terms scope	unknown
Access friction	self_service_clickthrough
Route backend	Manual (upstream-gated)
Availability	available (checked 2026-07-21)
Acquisition support	guided_instructions_only
Legacy sample-loader status	Standard loader included

Notes

Registration on Baidu AI Studio required. All 3 tasks share the same OCT volume set (~5 GB).

Access preflight and acquisition

CLI

# Read-only preflight
eyehub download stage_task1 --data-dir ./data --dry-run --json

# Explicit transfer, only when preflight reports supported behavior
eyehub download stage_task1 --data-dir ./data

Python

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

ds = REGISTRY.get_dataset('stage_task1')
print(preflight_dataset(ds, './data'))  # no transfer

Upstream page: aistudio.baidu.com/aistudio

Source-term evidence: aistudio.baidu.com/aistudio

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('stage_task1')
samples = ds.load(data_dir, split='test')
for s in samples[:5]:
    print(s.sample_id, s.label, s.image_path)

Citation

BibTeX

@misc{stage_task1,
  title  = { STAGE 2023 Task 1 — Mean Deviation Prediction from OCT },
  note   = { MICCAI 2023 STAGE Challenge. https://aistudio.baidu.com/aistudio/competition/detail/968 },
  year   = { 2023 },
  url    = { https://aistudio.baidu.com/aistudio/competition/detail/968/0/datasets },
}

Plain text

MICCAI 2023 STAGE Challenge. https://aistudio.baidu.com/aistudio/competition/detail/968

Source-stated terms

• Raw source string: Non-commercial research (Baidu AI Studio)
• 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.

Related datasets with shared modalities

• grape: GRAPE: Glaucoma Real-world Appraisal Progression Ensemble (1,115 records, cc0)
• harvard_gdp: Harvard GDP: Glaucoma Detection and Progression Dataset (1,000 records, cc-by-nc-nd)
• stage_task2: STAGE 2023 Task 2 — Visual Field Sensitivity Map Prediction (400 records, research-only)
• stage_task3: STAGE 2023 Task 3 — Pattern Deviation Probability Map (400 records, research-only)
• 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)