Application requiredMRI

MRNet

Name: MRNet
License: 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.

MRNet is a knee MRI dataset containing examination-level labels for overall abnormality, anterior cruciate ligament tears and meniscal tears. The labels were manually extracted from clinical reports.

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 source ↗last verified 2026-09-07

Access status: Access requires an application, data-use agreement, registration workflow or institutional approval.

Coverage

kneeclassificationin vivo

subjects

1,312

images

not verified

formats

NPY, CSV

origin

USA · 2018

Citation

Bien N, Rajpurkar P, Ball RL, et al. Deep-learning-assisted diagnosis for knee magnetic resonance imaging: Development and retrospective validation of MRNet. PLOS Medicine. 2018;15(11):e1002699. DOI: 10.1371/journal.pmed.1002699. Dataset DOI: 10.71718/rcbp-8c35.

Notes

The dataset contains 1,370 examinations from 1,312 patients. It is divided into 1,130 training examinations from 1,088 patients, 120 validation examinations from 111 patients and 120 hidden test examinations from 113 patients. A total MRI slice count is not reported, so num_images is null.

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.