SOURCE-LINKED INTELLIGENCE

KneePreM: Towards 3D Knee MRI Foundation Models via Large-Scale Unlabeled Pretraining and Label-Efficient Fine-Tuning

arXiv · AI, language, vision and robotics · article · Sep 25, 2026 · UTC

Background: Large volumes of unlabeled knee MRI scans are available across repositories but remain insufficiently leveraged. We developed KneePreM, a knee-specific 3D self-supervised model, and evaluated transfer and label efficiency for classification and segmentation. Methods: A 3D U-Net masked autoencoder was pretrained on 19,011 unlabeled Osteoarthritis Initiative (OAI) MRI series from 4,791 participants. Downstream fine-tuning used full and reduced training sets for fastMRI+ two-label classification (1,172 examinations), Arthroscopic Partial Meniscectomy (APM) eight-target classification

Read original source ↗ Open in workspace

recordType

paper

region

Global