# HC18: fetal head circumference measurement in 2D ultrasound

## Facts

- Provider: Thomas van den Heuvel et al., Radboud University Medical Center (converted by MedOtter)
- License: CC-BY-4.0 (https://zenodo.org/records/1327317)
- Size: 4 files
- Format: Parquet (in sampled files)
- Stored at: Hugging Face, https://huggingface.co/datasets/MedOtter/HC18
- Access: public, readable without an account
- DOI: https://doi.org/10.5281/zenodo.1327317
- Category: Medicine
- Source: https://doi.org/10.1371/journal.pone.0200412
- Page: https://scigantic.com/archive/b6924b16-bf75-55d6-8e5c-cf40f6d14fd3
- Keywords: Medicine, image segmentation, Parquet, Hugging Face

## About

HC18 is the 2D ultrasound dataset of the HC18 Grand Challenge for automated fetal head circumference measurement, from van den Heuvel et al., PLoS ONE 2018. It contains 1,334 standard-plane images of the fetal head acquired from 551 pregnant women at Radboud University Medical Center (Nijmegen) between May 2014 and May 2015. The training set of 999 images carries sonographer ellipse annotations of the skull outline, per-image pixel size and the ground-truth head circumference in millimetres; the 335 test images ship with pixel size only, as the challenge holds the ground truth. The MedOtter conversion adds a flood-filled binary mask beside the original outline image, with filename, subject ID and frame index columns. As measured 2026-11-14 the data are two Parquet files (train and test) totalling about 0.18 GB; load with datasets (load_dataset('MedOtter/HC18')) or pyarrow. Used for obstetric ultrasound segmentation, ellipse fitting and fetal biometry and gestational age estimation. Released by the authors on Zenodo under CC BY 4.0; cite van den Heuvel et al. 2018.

## Load the data

```python
from datasets import load_dataset
ds = load_dataset("MedOtter/HC18")
print(ds)
```

## Data structure

File types in sampled files: Parquet

Example file: `data/test-00000-of-00001.parquet`

## Open it

- In a hosted notebook with the data mounted: https://scigantic.com/archive/b6924b16-bf75-55d6-8e5c-cf40f6d14fd3
- Full record as JSON (schema card included): https://api.scigantic.com/api/archives/b6924b16-bf75-55d6-8e5c-cf40f6d14fd3
- Over MCP: `get_schema_card` with id `b6924b16-bf75-55d6-8e5c-cf40f6d14fd3` at https://api.scigantic.com/mcp

## Related topics

- [Parquet datasets](https://scigantic.com/topics/parquet)
- [Image segmentation datasets](https://scigantic.com/topics/image-segmentation)
- [Medicine datasets](https://scigantic.com/topics/medicine)
