RSNA Intracranial Aneurysm Detection

Intracranial saccular aneurysms on CTA, MRA, and brain MRI, including series without an aneurysm

Non-commercialVerifiedAccount required
AREANeuroMODCT, MRFORMATDICOM, NIfTINORMALSYesLICKaggle competition rules (non-commercial)CHECKED2026-11-11

Open the source page ↗ See it in the directory

At a glance

What it is
Intracranial saccular aneurysms on CTA, MRA, and brain MRI, including series without an aneurysm
Area
Neuro
Modality
CT, MR
Format
DICOM, NIfTI
Size
7,202 CTA, MRA, and MRI series from 4,278 patients in the 2026 dataset paper. MIRA publishes 5,041 of them: 4,346 series kept from the challenge training set, plus 695 post-challenge series. The original Kaggle training release was 4,348 series
Normals included
Yes
License
Kaggle competition rules (non-commercial)
Commercial use
Not allowed under the free terms
Access
Free account and data-use terms required
Status
Verified: source page reviewed by Hounsfield Lab
Added
2026-10-18
Last checked
2026-11-11
Source
www.kaggle.com/competitions/rsna-intracranial-aneurysm-detection

How to access

Create a free Kaggle account, open this competition, accept the rules, then download from the Data tab. Do not pass the files to anyone who has not accepted the rules. An AWS Open Data copy is documented at https://registry.opendata.aws/rsna-intracranial-aneurysm-detection-dataset/ and is also non-commercial. The collection is also published on RSNA's MIRA platform at https://mira.rsna.org/dataset/7 . The Kaggle page stays the primary link. An unauthenticated request to the MIRA dataset API redirected to a login page, so this row does not quote MIRA's own license or account terms.

Limitations

Kaggle rules: non-commercial, no redistribution to people who have not agreed. The AWS registry text (checked 2026-10-18) allows non-commercial academic and educational use, forbids re-identification, and requires a citation; one version of that text also restricts redistribution. Read the copy you actually download. The AWS description calls these CT brain scans and says about 200 studies have AI segmentations. The dataset paper describes CTA, MRA (time-of-flight and post-contrast), and T1-post and T2 MRI, stored as DICOM, with NIfTI segmentations of the challenge-defined arterial segments for 178 series. Those segmentations were produced with a model and then reviewed by neuroradiologists. MIRA holds 4,346 series from the original challenge training set, after two series were removed for severe artifacts, plus a 695-series post-challenge set from three sites that were not in the challenge. The paper states that the data are freely available for noncommercial research use. Described in Correia de Verdier et al., The RSNA Intracranial Aneurysm (RSNA-ICA) Dataset, https://arxiv.org/abs/2610.01135 .

Citation required?

Yes. Cite the Radiological Society of North America Intracranial Aneurysm Detection (RSNA-ICA) Dataset, July 2025. https://doi.org/10.1148/dataset.ica.2025 . Also cite Correia de Verdier et al., The RSNA Intracranial Aneurysm (RSNA-ICA) Dataset, https://arxiv.org/abs/2610.01135 .

Related open-source tools

More neuro datasets

Hounsfield Lab links to the source and does not host images. The license and access summary reflects the source page on the last-checked date; terms can change, so read the source before you download. Not legal advice.

← All DICOM datasets