Skip to main content

MGD-1k Meibomian Gland Dataset

One thousand infrared meibography images with meibomian-gland masks, eyelid masks, and six rounds of expert meiboscore grading.

At a glance

FieldValue
Short namemgd1k
Full nameMGD-1k Meibomian Gland Dataset
Primary categoryexternal_eye
Contained modalitiesexternal_eye
Taskssegmentation, grading
Samples1,000
ClassesNot reported (Not reported)
Splitsall
SizeNot reported
Source-stated termsUnknown; project page states All Rights Reserved
Normalized termsunknown
Descriptive screening labelUnknown or unclear; do not assume permission
Terms scopeunknown
Access frictionanonymous_direct
Route backendGitHub
Availabilityavailable (checked 2026-07-21)
Acquisition supportloader_implemented_not_live_tested
Legacy sample-loader statusMetadata and access only

Notes

Official project page reports 1,000 infrared meibomian-gland images from 320 patients, 1,000 gland masks, 1,000 eyelid masks, and six meiboscore rounds. License is not explicit; verify source terms before reuse.

Access preflight and acquisition

# Read-only preflight
eyehub download mgd1k --data-dir ./data --dry-run --json

# Explicit transfer, only when preflight reports supported behavior
eyehub download mgd1k --data-dir ./data

Upstream page: mgd1k.github.io/index.html

Source-term evidence: mgd1k.github.io/index.html

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{mgd1k,
title = { MGD-1k Meibomian Gland Dataset },
note = { Saha RK, Chowdhury AM, Na KS, Hwang GD, Eom Y, Kim J, Jeon HG, Hwang HS, Chung E. Automated quantification of meibomian gland dropout in infrared meibography using deep learning. The Ocular Surface. 2022;26:283-294 },
year = { 2022 },
url = { https://mgd1k.github.io/index.html },
}

Source-stated terms

  • Raw source string: Unknown; project page states All Rights Reserved
  • 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.

  • eyecare_100k: Eyecare-100K: Multimodal Ophthalmology VQA Corpus (102,000 records, unknown)
  • lmod_plus: LMOD+ Multimodal Ophthalmology Benchmark (32,633 records, unknown)
  • x_pcr: X-PCR Ophthalmology Progressive Clinical Reasoning Benchmark (18,700 records, unknown)
  • popeye_nir: PopEYE Infrared Ocular Image Dataset (14,976 records, cc-by)
  • mcoa: MCOA: Multimodal Corneal Opacity Assessment Dataset (6,664 records, cc-by)
  • tear_meniscus: Multicentre Tear Meniscus Segmentation Dataset (3,432 records, cc-by)
  • uveitis_smote: Image Dataset on Eye Diseases Classification with Symptoms and SMOTE Validation (3,245 records, cc-by)
  • eed_astig: EED-Astig Pediatric External-Eye Dataset (3,088 records, research-only)