Metraipolis › archive › dc_89d688dfd59d

DINOv2 for PET: A Pre-Training Domain Benchmark Across Classification, Segmentation, and Prognosis — arXiv:2610.40018

Source: arXiv (en)
Original: https://arxiv.org/abs/2610.40018
License (as archived): CC0-1.0
Archived: 2026-11-01T02:42:14.964Z
SHA-256 of the archived text: 1a623b2debdcfdc055078676a4b8796298f087f75072fa88da0a438398e9b337
Stable URL of this page: https://metraipolis.com/documento/dc_89d688dfd59d

How to cite

DINOv2 for PET: A Pre-Training Domain Benchmark Across Classification, Segmentation, and Prognosis — arXiv:2610.40018 — arXiv (en), https://arxiv.org/abs/2610.40018 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_89d688dfd59d (Metraipolis archive dc_89d688dfd59d, sha256 1a623b2debdcfdc055078676a4b8796298f087f75072fa88da0a438398e9b337)

BibTeX

@misc{dc89d688dfd59d,
  title = {DINOv2 for PET: A Pre-Training Domain Benchmark Across Classification, Segmentation, and Prognosis — arXiv:2610.40018},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.40018},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_89d688dfd59d; sha256 1a623b2debdcfdc055078676a4b8796298f087f75072fa88da0a438398e9b337},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.40018. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

DINO (self-DIstillation with NO labels) has become a stan- dard for self-supervised pre-training, producing features that generalise across datasets and downstream tasks. In medical imaging it has been adopted mainly for radiology (X-ray, CT and MRI), where even natural- image DINO features transfer well. In the literature, these features have been reported to transfer worse to functional imaging such as PET. Yet PET-specific DINO models have barely been introduced, and even less validated across multiple tasks and datasets. We present PET-DINOv2-2D, the first DINOv2 model pre-trained on 2D PET, and benchmark it against open-source encoders: the origi- nal DINOv2 (pre-trained on the LVD-142M natural-image dataset) and OmniRad (pre-trained on CT, MRI and ultrasound). Using the same lightweight heads for every backbone, and despite far less pre-training data, PET-DINOv2-2D matches or outperforms both on three down- stream PET tasks: normal/abnormal classification, lesion segmentation and recurrence-free survival prognosis. Its advantage is largest when few labels are available, suggesting that PET pre-training gives more transferable, label-efficient features. Code is made available at this https URL .

Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.CV, nuovi lavori del giorno).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2610.40018 — 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 2026-11-01T02:16:43.963Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).