All datasets
No longer availableMRI

K2S: Knee to Structure Challenge

K2S was a knee MRI challenge based on 3D FSE CUBE acquisitions from GE 3T scanners, with segmentation targets for femur, tibia, patella and three cartilage structures.

Licence and access

The challenge data page listed the dataset under CC BY-NC-ND terms, while the related article has a separate publication license. Redistribution and derivative use should therefore be treated conservatively.

access endedcommercial use restrictedredistribution allowed
Visit official sourcelast verified 2026-09-11This link no longer leads to the data, only to the page where the dataset was described.
Access status: Closed after the challenge concluded. The Grand Challenge page states that no data is shared after the conclusion of the challenge.
Coverage
kneesegmentationin vivo
subjects
350
images
350
formats
DICOM, NIfTI
origin
not verified
Citation
Tolpadi AA, et al. K2S Challenge: From Undersampled Knee MRIs to Segmentations. Bioengineering. 2023;10(2):267. DOI: 10.3390/bioengineering10020267. Challenge design DOI: 10.5281/zenodo.6362605.
Notes

The challenge documentation describes 300 training patients and 50 test patients. The public sharing period ended after the challenge concluded on 2022-07-21.

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.

The record is kept to document that the dataset existed and where it was described.

Orthopedic AI Research Updates

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

Unsubscribe anytime.

K2S: Knee to Structure Challenge, dataset record