Metraipolis › archive › dc_e52b79b8dc49

How Far from Clinical Deployment? Evaluating the Complete Unsupervised Domain Adaptation Pipeline in Medical Imaging — arXiv:2608.12035

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.12035
License (as archived)
CC0-1.0
Archived
2026-10-19T05:16:23.509Z
SHA-256 of the archived text
b75143fdfb85fab805e61c974be0dbe56e11804c3e050c5eebf086223e36ab26
Stable URL of this page
https://metraipolis.com/documento/dc_e52b79b8dc49

How to cite

How Far from Clinical Deployment? Evaluating the Complete Unsupervised Domain Adaptation Pipeline in Medical Imaging — arXiv:2608.12035 — arXiv (en), https://arxiv.org/abs/2608.12035 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_e52b79b8dc49 (Metraipolis archive dc_e52b79b8dc49, sha256 b75143fdfb85fab805e61c974be0dbe56e11804c3e050c5eebf086223e36ab26)
BibTeX
@misc{dce52b79b8dc49,
  title = {How Far from Clinical Deployment? Evaluating the Complete Unsupervised Domain Adaptation Pipeline in Medical Imaging — arXiv:2608.12035},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.12035},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_e52b79b8dc49; sha256 b75143fdfb85fab805e61c974be0dbe56e11804c3e050c5eebf086223e36ab26},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.12035. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Deploying unsupervised domain adaptation (UDA) in clinical practice requires choosing which algorithm to use and which of its trained models to ship. However, the deployment (target) domain is unlabeled, so models cannot be evaluated directly on it, leaving it unclear which to select. We address this by evaluating the complete UDA pipeline, considering both adaptation and label-free selection together. Our study covers eleven clinically relevant cross-domain scenarios from nine medical imaging datasets, with ten UDA algorithms and 13 label-free selection methods (validators), evaluating over 80,000 trained models in total. By this, we find that a capable adapted model usually exists, but identifying it without target labels is difficult: the validator-selected models leave a large and structural target performance gap to the best available one, with no evaluated validator consistently reliable. Towards closing it, we explore two strategies, ensembling and a small target-labeling budget; both narrow this gap but do not close it entirely. Overall, deployable UDA depends on the complete pipeline; addressing the less explored selection step could bring much of current UDA closer to clinical use.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-13 in cs.AI).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2608.12035 — 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 2026-10-19T05:08:46.756Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-13?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).