Skip to main content

CATARACTS 2017: Surgical Tool Detection Challenge

50 cataract surgery videos (>9 hours total) with frame-level annotations of 21 surgical tools. Earlier and larger sibling to Cataract-1K.

At a glance

FieldValue
Short namecataracts2017
Full nameCATARACTS 2017: Surgical Tool Detection Challenge
First published2017
Publication date precisionyear
Publication date evidencearxiv.org/abs
Publication date source fieldAssociated CATARACTS challenge paper: explicit dataset release statement
Publication date reviewed2026-09-11
Primary categorysurgical_video
Resource rolecurrent_dataset
Dataset familycataracts2017
Contained modalitiessurgical_video
Tasksclassification, multilabel
Primary reported quantity50 videos
Classes21 (Not reported)
Splitstrain, test
Size50.0 GB
Source-stated termsCC BY 4.0 (IEEE DataPort)
Normalized termscc-by
Descriptive screening labelStandard label without an explicit NC clause; not a permission finding
Terms scopedataset_files
Access frictionself_service_authenticated
Route backendManual (upstream-gated)
Availabilityavailable (checked 2026-07-21)
Acquisition supportguided_instructions_only
Legacy sample-loader statusMetadata and access only

Reported quantities

RoleCountUnitScopeBasisEvidence
Primary50videosPrimary quantity reported in the reviewed catalog sourcelegacy_catalog_fieldieee-dataport.org/open-access

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

IEEE DataPort free account login required.

Documented relationships

These links record source-supported lineage or overlap, not merely similar modality tags.

  • cadis is derived from this record: CaDIS adds semantic segmentation labels to frames selected from CATARACTS videos. (evidence)

Access information and download

# Read-only preflight
eyehub download cataracts2017 --data-dir ./data --dry-run --json

# Download, only when preflight reports supported behavior
eyehub download cataracts2017 --data-dir ./data

Upstream page: ieee-dataport.org/open-access

Source-term evidence: ieee-dataport.org/open-access

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{cataracts2017,
title = { CATARACTS 2017: Surgical Tool Detection Challenge },
note = { Al Hajj et al., 'CATARACTS: Challenge on Automatic Tool Annotation for cataRACT Surgery', Medical Image Analysis 2019 },
year = { 2019 },
url = { https://ieee-dataport.org/open-access/cataracts },
}

Source-stated terms

  • Raw source string: CC BY 4.0 (IEEE DataPort)
  • 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

  • ophora: Ophora-160K: Ophthalmic Surgical Video Instruction Dataset (162,185 video clip instruction pairs, unknown)
  • lmod_plus: LMOD+ Multimodal Ophthalmology Benchmark (32,633 annotated instances, unknown)
  • insegcat: InSegCat: Instance Segmentation for Cataract Surgery (5,581 annotated images, research-only)
  • cadis: CaDIS: Cataract Dataset for Image Segmentation (4,670 images, research-only)
  • cataract_lmm: Cataract-LMM: Large-Scale Multi-Source Multi-Task Cataract Surgery Benchmark (3,000 videos, cc-by-nc-nd)
  • ophnet2024: OphNet2024: Ophthalmic Surgical Video Dataset (2,278 videos, cc-by-nc-sa)
  • lmod_cataract_1k: LMOD-Cataract-1K (2,256 images, cc-by)
  • lmod_cataract_1k_cot: Cataract-1K Surgical Analysis Chain-of-Thought Dataset (2,256 images, mit)