InSegCat: Instance Segmentation for Cataract Surgery
Two COCO-format instance-segmentation datasets derived from cataract surgery videos, covering instruments and anatomical structures.
At a glance
| Field | Value |
|---|---|
| Short name | insegcat |
| Full name | InSegCat: Instance Segmentation for Cataract Surgery |
| Primary category | surgical_video |
| Contained modalities | surgical_video |
| Tasks | segmentation |
| Samples | Not reported |
| Classes | Not reported (Not reported) |
| Splits | train, test |
| Size | 10.0 GB |
| Source-stated terms | Research only (ITEC AAU) |
| Normalized terms | research-only |
| Descriptive screening label | Research or challenge restriction recorded; check source |
| Terms scope | dataset_files |
| 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 | Metadata and access only |
Access preflight and acquisition
- CLI
- Python
# Read-only preflight
eyehub download insegcat --data-dir ./data --dry-run --json
# Explicit transfer, only when preflight reports supported behavior
eyehub download insegcat --data-dir ./data
from eyedatahub.acquisition import preflight_dataset
from eyedatahub.datasets.registry import REGISTRY
ds = REGISTRY.get_dataset('insegcat')
print(preflight_dataset(ds, './data')) # no transfer
Upstream page: ftp.itec.aau.at/datasets
Source-term evidence: ftp.itec.aau.at/datasets
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
- BibTeX
- Plain text
@misc{insegcat,
title = { InSegCat: Instance Segmentation for Cataract Surgery },
note = { InSegCat dataset, ITEC AAU. COCO-format instance segmentation for cataract surgery },
url = { https://ftp.itec.aau.at/datasets/ovid/InSegCat/ },
}
InSegCat dataset, ITEC AAU. COCO-format instance segmentation for cataract surgery.
Source-stated terms
- Raw source string: Research only (ITEC AAU)
- Normalized category:
research-only - Apparent scope:
dataset_files - 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
- ophora: Ophora-160K: Ophthalmic Surgical Video Instruction Dataset (160,185 records,
unknown) - lmod_plus: LMOD+ Multimodal Ophthalmology Benchmark (32,633 records,
unknown) - cadis: CaDIS: Cataract Dataset for Image Segmentation (4,670 records,
research-only) - cataract_lmm: Cataract-LMM: Large-Scale Multi-Source Multi-Task Cataract Surgery Benchmark (3,000 records,
cc-by-nc-nd) - ophnet2024: OphNet2024: Ophthalmic Surgical Video Dataset (2,278 records,
cc-by-nc-sa) - cataract1k: Cataract-1K: Large-Scale Cataract Surgery Video Dataset (1,000 records,
research-only) - migs_video: Multicenter Fine-Annotated MIGS Surgical Video Dataset (186 records,
cc-by) - sics155: SICS-155 Small Incision Cataract Surgery Videos (155 records,
cc-by-nc)