Metraipolis › archive › dc_96043eb04ea2

L2GSSL: Label-Efficient Local-to-Global Self-Supervised Learning for Volumetric Healthcare Data — arXiv:2610.21356

Source: arXiv (en)
Original: https://arxiv.org/abs/2610.21356
License (as archived): CC0-1.0
Archived: 2026-10-16T10:25:12.060Z
SHA-256 of the archived text: b02fab6eb5add212b45a793f51c79ac2af593c768921a5e52e36d519febdf303
Stable URL of this page: https://metraipolis.com/documento/dc_96043eb04ea2

How to cite

L2GSSL: Label-Efficient Local-to-Global Self-Supervised Learning for Volumetric Healthcare Data — arXiv:2610.21356 — arXiv (en), https://arxiv.org/abs/2610.21356 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_96043eb04ea2 (Metraipolis archive dc_96043eb04ea2, sha256 b02fab6eb5add212b45a793f51c79ac2af593c768921a5e52e36d519febdf303)

BibTeX

@misc{dc96043eb04ea2,
  title = {L2GSSL: Label-Efficient Local-to-Global Self-Supervised Learning for Volumetric Healthcare Data — arXiv:2610.21356},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.21356},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_96043eb04ea2; sha256 b02fab6eb5add212b45a793f51c79ac2af593c768921a5e52e36d519febdf303},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.21356. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Healthcare institutions routinely accumulate high-dimensional computed tomography (CT) volumes, but only a fraction can be annotated by experts. We present L2GSSL, a local-to-global self-supervised learning framework that leverages unlabeled volumes by decomposing pretraining into intra-slice and inter-slice representation spaces. A slice encoder learns view-invariant local features, and a global encoder aggregates the resulting tokens to model volumetric context. The stop-gradient isolates the local space from the global objective, while slice-wise execution and a three-phase schedule support training under constrained GPU memory. On LIDC-IDRI lung nodule malignancy classification, L2GSSL reaches $0.9229$ AUROC with only $10\%$ of the labels and $0.9377$ with $25\%$, exceeding the volume-level VICReg by $0.0229$ and $0.0294$, respectively. With all labels, the strongest supervised baseline exceeds L2GSSL by only $0.0044$ AUROC, consistent with self-supervised pretraining providing its greatest value when annotations are limited. Without adaptation to the external LNDb cohort, a model fine-tuned on $25\%$ of LIDC-IDRI obtains $0.8138$ AUROC and $0.7589$ AUPRC, improving over the strongest evaluated self-supervised baseline by $0.1130$ and $0.0954$. Experiments across data sources, thoracic and abdominal anatomy, downstream tasks, and two backbones examine healthcare-data variety, while lesion-slice masking shows that the predictions depend on lesion-bearing content.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2610.21356 — 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 2026-10-16T08:48:02.897Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).