Skip to main content

HPMI: High & Pathological Myopia Identification

4,011 color fundus images labeled for high-myopia vs pathological-myopia classification — largest public dataset for HM/PM separation.

At a glance

FieldValue
Short namehpmi
Full nameHPMI: High & Pathological Myopia Identification
First published2023-12-13
Publication date precisionday
Publication date evidenceapi.figshare.com/v2
Publication date source fieldpublished_date (Figshare version 1)
Publication date reviewed2026-09-11
Primary categoryfundus
Resource rolecurrent_dataset
Dataset familyhpmi
Contained modalitiesfundus
Tasksclassification
Primary reported quantity4,011 images
Classes2 (high_myopia, pathological_myopia)
Splitsall
Size2.0 GB
Source-stated termsCC BY 4.0
Normalized termscc-by
Descriptive screening labelStandard label without an explicit NC clause; not a permission finding
Terms scopedataset_files
Access frictionself_service_authenticated
Route backendFigshare
Availabilityavailable (checked 2026-07-21)
Acquisition supportend_to_end_tested
Legacy sample-loader statusMetadata and access only

Reported quantities

RoleCountUnitScopeBasisEvidence
Primary4,011imagesPrimary quantity reported in the reviewed catalog sourcelegacy_catalog_fieldhttps://doi.org/10.6084/m9.figshare.24800232

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

Complements EyeDataHub's PALM (pathological-myopia challenge).

Access information and download

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

# Download, only when preflight reports supported behavior
eyehub download hpmi --data-dir ./data

Upstream page: https://doi.org/10.6084/m9.figshare.24800232

Source-term evidence: https://doi.org/10.6084/m9.figshare.24800232

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{hpmi,
title = { HPMI: High & Pathological Myopia Identification },
note = { Huang et al., 'HPMI: A retinal fundus image dataset for identification of high and pathological myopia based on deep learning', Figshare 2024. doi:10.6084/m9.figshare.24800232 },
year = { 2024 },
url = { https://doi.org/10.6084/m9.figshare.24800232 },
}

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

  • airogs: AIROGS: AI for Robust Glaucoma Screening (113,893 images, cc-by-nc-nd)
  • 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)
  • justraigs: JustRAIGS: Just Referral AI Glaucoma Screening Dataset (101,442 images, cc-by-nc-nd)
  • eyepacs: EyePACS — Diabetic Retinopathy Detection (Kaggle 2015) (88,702 images, research-only)
  • angioreport: AngioReport Fundus Angiography Report Dataset (55,361 images, unknown)
  • ffa_ir: FFA-IR Medical Report Dataset (47,247 images, unknown)
  • mfiddr: MFIDDR: Multi-Field Imaging Dataset for Diabetic Retinopathy (34,452 images, mit)