Sunnybrook Cardiac Data
Cine cardiac MRI: healthy, hypertrophy, heart failure with infarction, and heart failure without infarction
Open the source page ↗ See it in the directory
At a glance
- What it is
- Cine cardiac MRI: healthy, hypertrophy, heart failure with infarction, and heart failure without infarction
- Area
- Cardiac
- Modality
- MR
- Format
- DICOM
- Size
- 45 cases in 3 DICOM parts plus contours; SourceForge lists about 608 MB for the project files
- Normals included
- Partial (mixed or unlabeled)
- License
- CC0 1.0
- Commercial use
- Allowed by the license, with its attribution terms
- Access
- Open download, no account
- Status
- Verified: source page reviewed by Hounsfield Lab
- Added
- 2026-10-18
- Last checked
- 2026-11-11
- Source
- sourceforge.net/projects/cardiac-mr/files/
How to access
Download the original 2009 challenge release from the SourceForge project page: three DICOM zip parts, three contour zip parts, and the age and gender table. The README states CC0 1.0 Universal (changed from Open Data Commons PDDL on 2 Sept 2010). No account is required. The Cardiac Atlas page that used to host a five-batch copy of this set no longer resolves.
Limitations
Small challenge set. Pathologies are mixed with healthy cases. Contours are the left ventricle from the 2009 short-axis segmentation challenge, in the challenge’s three parts (online contest, validation, and training). This is that SourceForge release, not the later Cardiac Atlas packaging of five DICOM batches and a CAP ID crosswalk CSV, which is no longer online. CC0 does not require attribution. The former project page asked you to cite Radau et al. if you publish; the SourceForge README does not.
Citation required?
Requested, not required by CC0. Radau et al., Evaluation Framework for Algorithms Segmenting Short Axis Cardiac MRI. The MIDAS Journal. http://hdl.handle.net/10380/3070
Related open-source tools
- MONAI: PyTorch-based AI toolkit for healthcare imaging
- nnU-Net: Self-configuring segmentation framework
- 3D Slicer: Open platform for visualization, segmentation and image computing
- pydicom: Read, modify and write DICOM files in Python
- highdicom: High-level Python API on pydicom for reading images and writing AI results as DICOM Segmentation, Structured Report, parametric map and annotation objects
- OHIF Viewer: Zero-footprint web DICOM viewer
- Orthanc: Lightweight DICOM server; this repo builds the Docker images and installers
More cardiac datasets
- COCA: CT · Stanford AIMI research use agreement (non-commercial; commercial license sold separately)
- EchoNet-Dynamic: US · Stanford AIMI research use agreement (non-commercial; commercial license sold separately)
- Medical Segmentation Decathlon: CT, MR · CC BY-SA 4.0
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.