# CTPelvic1K CLINIC and CLINIC-metal: pelvic CT with sacrum, hip and lumbar vertebra segmentations (117 cases)

## Facts

- Provider: Pengbo Liu, Hu Han et al.; mirrored by MedOtter
- License: CC-BY-4.0 (https://zenodo.org/records/4588403)
- Size: 237 files
- Format: NIfTI, JSON Lines (in sampled files)
- Stored at: Hugging Face, https://huggingface.co/datasets/MedOtter/CTPelvic1K
- Access: public, readable without an account
- DOI: https://doi.org/10.5281/zenodo.4588403
- Category: Health & Biomedical
- Source: https://huggingface.co/datasets/MedOtter/CTPelvic1K
- Page: https://scigantic.com/archive/bd97b765-30b1-5e00-9931-6278e4331c35
- Keywords: Health & Biomedical, CT, image segmentation, NIfTI, JSON Lines, Hugging Face

## About

Pelvic bone CT with dense segmentations of the sacrum, left hip, right hip and lumbar vertebrae, from the CTPelvic1K dataset. This mirror carries only the two subsets whose images the authors released under their own license: dataset6 CLINIC (103 clinical CT scans) and dataset7 CLINIC-metal (14 scans with metal implants and their artifacts), each with masks, as NIfTI in CTPelvic1K_dataset6_data/, CTPelvic1K_dataset6_Anonymized_mask/, CTPelvic1K_dataset7_data/ and CTPelvic1K_dataset7_mask/, indexed by train.jsonl. Images for datasets 1 to 5 (drawn from KiTS19, BTCV, COLONOG and MSD under their own terms) are intentionally not included. About 10 GB (measured 2026-11-17). Use for pelvic bone segmentation and for testing robustness to metal artifacts. Load with nibabel or SimpleITK. Mirrored on Hugging Face by MedOtter from the authors' release, with a card documenting provenance and any normalization. The authors' Zenodo record 4588403 (annotations and the CLINIC and CLINIC-metal data) is CC BY 4.0; cite Liu, Han et al., CTPelvic1K.

## Load the data

```python
from datasets import load_dataset
ds = load_dataset("MedOtter/CTPelvic1K")
print(ds)
```

## Data structure

File types in sampled files: NIfTI, JSON Lines

Example file: `train.jsonl`

## Open it

- In a hosted notebook with the data mounted: https://scigantic.com/archive/bd97b765-30b1-5e00-9931-6278e4331c35
- Full record as JSON (schema card included): https://api.scigantic.com/api/archives/bd97b765-30b1-5e00-9931-6278e4331c35
- Over MCP: `get_schema_card` with id `bd97b765-30b1-5e00-9931-6278e4331c35` at https://api.scigantic.com/mcp

## Related topics

- [Image segmentation datasets](https://scigantic.com/topics/image-segmentation)
- [Health & Biomedical datasets](https://scigantic.com/topics/health-and-biomedical)
- [CT datasets](https://scigantic.com/topics/ct)
- [JSON Lines datasets](https://scigantic.com/topics/json-lines)
- [NIfTI datasets](https://scigantic.com/topics/nifti)
