All datasets
Application requiredMRI

SKM-TEA

SKM-TEA is a quantitative knee MRI dataset pairing raw k-space measurements and scanner-generated images with tissue segmentations and three-dimensional bounding-box annotations for clinically relevant pathologies.

Licence and access

The standard Stanford AIMI shared-data license is restricted to non-commercial purposes. Commercial use requires a separate application, Stanford approval, a signed commercial license, and payment of the applicable annual fee.

application requiredcommercial use restrictedredistribution restricted
Visit official sourcelast verified 2026-09-03
Access status: Access requires an application, data-use agreement, registration workflow or institutional approval.
Coverage
kneemixed labelsin vivo
subjects
155
images
not verified
formats
DICOM, HDF5, NIfTI, JSON, CSV
origin
not verified
Citation
Desai AD, Schmidt AM, Rubin EB, et al. SKM-TEA: A Dataset for Accelerated MRI Reconstruction with Dense Image Labels for Quantitative Clinical Evaluation. NeurIPS Datasets and Benchmarks. 2021. arXiv:2203.06823. Dataset DOI: 10.71718/2ghb-nv62.
Notes

The dataset contains 155 scans from 155 patients, divided into 86 training, 33 validation and 36 test scans. The publication reports approximately 25,000 slices, but an exact image count is not provided, so num_images is null. Segmentations cover six classes derived from patellar, femoral and tibial cartilage and the medial and lateral meniscus.

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.

SKM-TEA, dataset record