MRNet

Dataset Information
Introduced
2018
License
Unknown
Homepage
Official Website
Contents

Overview

The MRNet dataset consists of 1,370 knee MRI exams performed at Stanford University Medical Center. The dataset contains 1,104 (80.6%) abnormal exams, with 319 (23.3%) ACL tears and 508 (37.1%) meniscal tears; labels were obtained through manual extraction from clinical reports.

Source: MRNet

Variants: MRNet

Associated Benchmarks

This dataset is used in 1 benchmark:

  • Multi-Label Classification - Metrics: Average AUC, AUC on Abnormality (ABN), AUC on ACL Tear (ACL), AUC on Meniscus Tear (MEN), Average Accuracy, Accuracy on Abnormality (ABN), Accuracy on ACL Tear (ACL), Accuracy on Meniscus Tear (MEN)

Recent Benchmark Submissions

Task Model Paper Date
Multi-Label Classification SKIDv3 SKID: Self-Supervised Learning for Knee … 2021-04-21

Research Papers

Recent papers with results on this dataset:

External Links: