Metraipolis › archive › dc_0f8d42544bc4

KneePreM: Towards 3D Knee MRI Foundation Models via Large-Scale Unlabeled Pretraining and Label-Efficient Fine-Tuning — arXiv:2609.31461

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.31461
License (as archived)
CC0-1.0
Archived
2026-10-08T03:12:48.952Z
SHA-256 of the archived text
ea4b58f4f9764f5dfef8949a7d75e9cf3ca9158eec3d3c239458ef24154c7d46
Stable URL of this page
https://metraipolis.com/documento/dc_0f8d42544bc4

How to cite

KneePreM: Towards 3D Knee MRI Foundation Models via Large-Scale Unlabeled Pretraining and Label-Efficient Fine-Tuning — arXiv:2609.31461 — arXiv (en), https://arxiv.org/abs/2609.31461 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_0f8d42544bc4 (Metraipolis archive dc_0f8d42544bc4, sha256 ea4b58f4f9764f5dfef8949a7d75e9cf3ca9158eec3d3c239458ef24154c7d46)
BibTeX
@misc{dc0f8d42544bc4,
  title = {KneePreM: Towards 3D Knee MRI Foundation Models via Large-Scale Unlabeled Pretraining and Label-Efficient Fine-Tuning — arXiv:2609.31461},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.31461},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_0f8d42544bc4; sha256 ea4b58f4f9764f5dfef8949a7d75e9cf3ca9158eec3d3c239458ef24154c7d46},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.31461. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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 (1,716 examinations), SKM-TEA segmentation (155 examinations), and APM segmentation (25 examinations). Baselines were random initialization and SuPreM. Deployment workflow was implemented with a Model Context Protocol interface. Evaluation metrics included balanced accuracy, F1 score, ROC AUC, PR AUC, and Dice score. Statistical analysis used bootstrap confidence intervals and paired bootstrap tests for classification and Wilcoxon signed-rank tests for segmentation. Results: KneePreM achieved higher full-data macro ROC AUC than both baselines for fastMRI+ and APM (all p < .001). For fastMRI+ classification, KneePreM achieved a ROC AUC of 0.722 using 50% of the training data, exceeding both full-data baselines. In APM classification, KneePreM reached a ROC AUC of 0.740 with 70% of the data, matching the full-data random baseline and outperforming SuPreM. For SKM-TEA segmentation, its 70%-data Dice of 0.838 exceeded the full-data random baseline (0.835) and both same-budget comparators. In APM segmentation, its 75%-data Dice of 0.746 exceeded the full-data random baseline (0.731) and both same-budget comparators. Conclusion: KneePreM improves transfer performance and label efficiency across knee MRI classification and segmentation tasks, particularly when labeled training data are limited.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-28 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2609.31461 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-08T02:50:19.110Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-28?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).