All datasets
AvailableCT

RibFrac

RibFrac is a chest-abdomen CT benchmark for rib fracture detection, instance segmentation and fracture-type classification. It provides voxel-level fracture masks and clinical fracture categories.

Licence and access

The public dataset is available after free registration through the RibFrac Grand Challenge platform. The project states that the work is licensed under the Creative Commons Attribution-NonCommercial 4.0 International license.

registration requiredcommercial use restrictedredistribution allowed
Visit official sourcelast verified 2026-09-14
Coverage
othermixed labelsin vivo
subjects
660
images
660
formats
NIfTI, CSV
origin
China · 2020
Citation
Yang J, Shi R, Jin L, et al. Deep Rib Fracture Instance Segmentation and Classification From CT on the RibFrac Challenge. IEEE Transactions on Medical Imaging. 2025;44(8):3410-3427. DOI: 10.1109/TMI.2025.3565514.
Notes

The public challenge dataset contains 660 CT scans from 660 unique patients and approximately 5,000 rib fractures. It includes 420 training scans, 80 validation scans and 160 evaluation scans. Training and validation annotations are available, while the evaluation labels are hidden. Ribs are not available in the current anatomy enum, so anatomy is recorded as other. The challenge's dataset subpage is not reachable without signing in, so the link points to the challenge home page; the data itself is behind registration.

This record is a pointer. Licence and access terms are recorded as they stood on the verification date above; what binds you is the dataset's own licence text. Confirm at the source before use.

Orthopedic AI Research Updates

Monthly research digest, product updates, and clinical AI insights.

Unsubscribe anytime.

RibFrac, dataset record