FETAL_PLANES_DB: maternal-fetal screening ultrasound images labeled by fetal anatomical plane (Burgos-Artizzu et al., Barcelona)

Provider
Xavier P. Burgos-Artizzu, Elisenda Eixarch, Eduard Gratacos et al.; repackaged by Chehab Lab
License
CC-BY-4.0 (source)
Size
7 files
Format
Parquet (in sampled files)
Stored at
Hugging Face (https://huggingface.co/datasets/chehablab/FETAL_PLANES_DB)
Access
Free and public. No account with the data provider is needed.
DOI
10.5281/zenodo.3904280
Category
Health & Biomedical
Source
https://doi.org/10.1038/s41598-020-67076-5

About this dataset

FETAL_PLANES_DB is a large set of routine maternal-fetal screening ultrasound images collected at two hospitals by several operators on different ultrasound machines, and labeled by an expert maternal-fetal clinician into the standard planes a sonographer must capture: fetal abdomen, fetal brain, fetal femur, fetal thorax, maternal cervix, and other. Fetal brain images also carry one of the three most common brain sub-plane labels. The repackaging keeps the original images unchanged and adds the original train/test split column, patient number, operator, ultrasound machine, plane and an integer label, so models can be tested across operators and devices. Five Parquet files under data/, about 2.1 GB (measured 2026-11-21); read with Hugging Face datasets. Use for automatic fetal ultrasound plane classification and prenatal screening quality control. Original data on Zenodo (DOI 10.5281/zenodo.3904280), released under CC BY 4.0. Cite Burgos-Artizzu et al., Scientific Reports 10:10200 (2020), doi 10.1038/s41598-020-67076-5.

How to load this dataset in Python

from datasets import load_dataset
ds = load_dataset("chehablab/FETAL_PLANES_DB")
print(ds)

Data structure

File types in sampled files: Parquet

Files

Example file: data/train-00000-of-00005.parquet

Analyze this dataset without downloading it

On Scigantic, FETAL_PLANES_DB: maternal-fetal screening ultrasound images labeled by fetal anatomical plane (Burgos-Artizzu et al., Barcelona) 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 Health & Biomedical datasets