AeroPath: airway and lung segmentation benchmark on 27 contrast-enhanced chest CT scans with challenging pathology
- Provider
- Erlend Hofstad, David Bouget et al.; mirrored by MedOtter
- License
- CC-BY-4.0 (source)
- Size
- 84 files
- Format
- NIfTI, Parquet (in sampled files)
- Stored at
- Hugging Face (https://huggingface.co/datasets/MedOtter/AeroPath)
- Access
- Free and public. No account with the data provider is needed.
- DOI
- 10.5281/zenodo.10069289
- Category
- Health & Biomedical
- Source
- https://doi.org/10.1371/journal.pone.0311416
About this dataset
AeroPath is an airway segmentation benchmark built from 27 contrast-enhanced chest CT (CTA) scans acquired at St. Olavs Hospital, Trondheim, Norway, chosen to include challenging pathology rather than healthy airways. Each subject folder under AeroPath/ holds the CT volume ({N}_CT_HR.nii.gz) with an airway tree mask ({N}_CT_HR_label_airways.nii.gz) and a lung mask ({N}_CT_HR_label_lungs.nii.gz). About 5 GB (measured 2026-11-17). Use to evaluate bronchial tree segmentation and lung masking on diseased lungs. 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 10069289 is CC BY 4.0; cite Hofstad, Bouget et al., AeroPath: An airway segmentation benchmark dataset with challenging pathology, PLOS ONE (doi 10.1371/journal.pone.0311416).
How to load this dataset in Python
from datasets import load_dataset
ds = load_dataset("MedOtter/AeroPath")
print(ds)Data structure
File types in sampled files: NIfTI, Parquet
Files
Example file: data/train-00000-of-00001.parquet
Analyze this dataset without downloading it
On Scigantic, AeroPath: airway and lung segmentation benchmark on 27 contrast-enhanced chest CT scans with challenging pathology 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
- ARCADE: X-ray coronary angiography images for SYNTAX segment labeling and stenosis detection
- VitaminP ORION-CRC: paired H&E and Hoechst immunofluorescence patches of colorectal cancer with nucleus and whole-cell masks
- IDC NLM-Visible-Human-Project: Normal (non-cancer) MRI, CT, XC (2 patients)
- PBC: 17,092 microscopy images of normal peripheral blood cells in eight classes (CellaVision, Hospital Clinic of Barcelona)
- EPA Dynamically Downscaled Ensemble (EDDE) Version 1
- STOIC2021 Training
- IDC CMB-BRCA: Breast Invasive Carcinoma CT, MRI, whole-slide microscopy, mammography (86 patients)
- IDC RIDER Pilot: Lung Cancer CT, radiographs (8 patients)