HC18: fetal head circumference measurement in 2D ultrasound

Provider
Thomas van den Heuvel et al., Radboud University Medical Center (converted by MedOtter)
License
CC-BY-4.0 (source)
Size
4 files
Format
Parquet (in sampled files)
Stored at
Hugging Face (https://huggingface.co/datasets/MedOtter/HC18)
Access
Free and public. No account with the data provider is needed.
DOI
10.5281/zenodo.1327317
Category
Medicine
Source
https://doi.org/10.1371/journal.pone.0200412

About HC18: fetal head circumference measurement in 2D ultrasound

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.

How to load HC18: fetal head circumference measurement in 2D ultrasound in Python

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

Data structure

File types in sampled files: Parquet

Files

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

Analyze this dataset without downloading it

On Scigantic, HC18: fetal head circumference measurement in 2D ultrasound opens in a hosted JupyterLab notebook with the data already mounted, so you can read files where they are stored instead of copying them first. Each notebook includes an AI assistant that can see the mounted files and write and run analysis code. Open the dataset page to launch a notebook, or browse the full catalog.

This page is also available as Markdown and as JSON.

Related Medicine datasets