RSNA Intracranial Aneurysm Detection
Intracranial saccular aneurysms on CTA, MRA, and brain MRI, including series without an aneurysm
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
- HD-BET: Deep-learning brain extraction (skull stripping) for MRI
- FastSurfer: Deep-learning whole-brain segmentation and cortical surface reconstruction, a fast alternative to FreeSurfer recon-all
- FreeSurfer: Neuroimaging analysis and visualization suite
- BrainChop: In-browser 3D MRI rendering and segmentation
- Neuro-VL: Neuroimaging vision-language model (Neuro-VL-8B-Thinking, Qwen3-8B language model with an HLIP visual encoder) that reads complete MRI and CT exams, converses about findings, drafts reports with reasoning traces and compares serial exams; trained on nearly 1 million clinical neuroimaging studies from 450,000 patients; released with the NeuroBench benchmark
- dcm2niix: Converts DICOM to NIfTI with JSON sidecars; the standard converter in many brain MRI and BIDS pipelines
- pydicom: Read, modify and write DICOM files in Python
More neuro datasets
- BrainMetShare: MR · Stanford AIMI research use agreement (non-commercial; commercial license sold separately)
- Burdenko-GBM-Progression: MR, CT · NIH Controlled Data Access Policy (images); CC BY 4.0 (clinical and genomic CSV)
- CFB-GBM: MR, CT · CC BY 4.0
- CPAISD: CT · CC BY 4.0
- CQ500: CT · CC BY-NC-SA 4.0
- CT-ICH: CT · PhysioNet Restricted Health Data License 1.5.0
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.