Metraipolis › archive › dc_7030ca0506d5
Segmentation Pre-training for Label-Efficient Lumbar Spine Degeneration Grading — arXiv:2608.04810
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.04810
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-31T11:48:09.905Z
- SHA-256 of the archived text
debae3a365085add5b662938e88b11d674c9f589f79931731a8013aecb021c8e- Stable URL of this page
https://metraipolis.com/documento/dc_7030ca0506d5
How to cite
Segmentation Pre-training for Label-Efficient Lumbar Spine Degeneration Grading — arXiv:2608.04810 — arXiv (en), https://arxiv.org/abs/2608.04810 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7030ca0506d5 (Metraipolis archive dc_7030ca0506d5, sha256 debae3a365085add5b662938e88b11d674c9f589f79931731a8013aecb021c8e)
BibTeX
@misc{dc7030ca0506d5,
title = {Segmentation Pre-training for Label-Efficient Lumbar Spine Degeneration Grading — arXiv:2608.04810},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.04810},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7030ca0506d5; sha256 debae3a365085add5b662938e88b11d674c9f589f79931731a8013aecb021c8e},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.04810. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Automated assessment of degenerative pathology in the lumbar spine on magnetic resonance imaging (MRI) requires access to large-scale datasets of expert-annotated radiological gradings. In contrast, segmentation pseudo-labels can be generated by automated tools at negligible radiologist cost. We examine whether pre-training on segmentation can effectively replace a fraction of the manual grading annotations required for downstream supervision. We pre-train a 3D ResNet encoder to segment the vertebrae, intervertebral discs (IVDs), and the spinal canal, then fine-tune lightweight task-specific grading heads using different proportions of the available training data, ranging from $10\%$ to $100\%$. On a multicentre dataset of ${\sim}2{,}000$ subjects across 11 pathologies, segmentation pre-training, achieving a Dice score of $0.94$ against pseudo-labels, improved the task-averaged (macro) one-vs-rest ROC-AUC at all proportions. With only 20\% of grading labels after pre-training, the method achieved near full-supervision performance, with the largest gains observed for either low-prevalence or spatially grounded pathologies.
Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-06 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2608.04810 — 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 2026-10-31T11:37:40.717Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-08-06?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).