Papers › SKID: Self-Supervised Learning for Knee Injury Diagnosis from MRI Data
SKID: Self-Supervised Learning for Knee Injury Diagnosis from MRI Data
Siladittya Manna, Saumik Bhattacharya, Umapada Pal
In medical image analysis, the cost of acquiring high-quality data and their annotation by experts is a barrier in many medical applications. Most of the techniques used are based on supervised learning framework and need a large amount of annotated data to achieve satisfactory performance. As an alternative, in this paper, we propose a self-supervised learning (SSL) approach to learn the spatial anatomical representations from the frames of magnetic resonance (MR) video clips for the diagnosis of knee medical conditions. The pretext model learns meaningful spatial context-invariant representations. The downstream task in our paper is a class imbalanced multi-label classification. Different experiments show that the features learnt by the pretext model provide competitive performance in the downstream task. Moreover, the efficiency and reliability of the proposed pretext model in learning representations of minority classes without applying any strategy towards imbalance in the dataset can be seen from the results. To the best of our knowledge, this work is the first work of its kind in showing the effectiveness and reliability of self-supervised learning algorithms in class imbalanced multi-label classification tasks on MR videos. The code for evaluation of the proposed work is available at https://github.com/sadimanna/skid.
Code
Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Multi-Label Classification | MRNet | SKIDv3 | AUC on ACL Tear (ACL) | 0.893 | #2 of 2 | Archive leaderboard | report |
| Multi-Label Classification | MRNet | SKIDv3 | AUC on Abnormality (ABN) | 0.904 | #2 of 2 | Archive leaderboard | report |
| Multi-Label Classification | MRNet | SKIDv3 | AUC on Meniscus Tear (MEN) | 0.810 | #2 of 2 | Archive leaderboard | report |
| Multi-Label Classification | MRNet | SKIDv3 | Accuracy on ACL Tear (ACL) | 0.800 | #2 of 2 | Archive leaderboard | report |
| Multi-Label Classification | MRNet | SKIDv3 | Accuracy on Abnormality (ABN) | 0.874 | #2 of 2 | Archive leaderboard | report |
| Multi-Label Classification | MRNet | SKIDv3 | Accuracy on Meniscus Tear (MEN) | 0.725 | #2 of 2 | Archive leaderboard | report |
| Multi-Label Classification | MRNet | SKIDv3 | Average AUC | 0.869 | #2 of 2 | Archive leaderboard | report |
| Multi-Label Classification | MRNet | SKIDv3 | Average Accuracy | 0.799 | #2 of 2 | Archive leaderboard | report |
Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections