Metraipolis › archive › dc_0ece4ff20d14

LAPIS: Clinically Constrained Patient-Identity Residual Learning for Chest X-Ray Anonymization — arXiv:2610.40722

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.40722
License (as archived)
CC0-1.0
Archived
2026-11-03T08:33:12.203Z
SHA-256 of the archived text
fe94e14fb6e1bc12aea2debb521ed23b6f3ff8e4cae0bbbcb857b9f167450608
Stable URL of this page
https://metraipolis.com/documento/dc_0ece4ff20d14

How to cite

LAPIS: Clinically Constrained Patient-Identity Residual Learning for Chest X-Ray Anonymization — arXiv:2610.40722 — arXiv (en), https://arxiv.org/abs/2610.40722 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_0ece4ff20d14 (Metraipolis archive dc_0ece4ff20d14, sha256 fe94e14fb6e1bc12aea2debb521ed23b6f3ff8e4cae0bbbcb857b9f167450608)
BibTeX
@misc{dc0ece4ff20d14,
  title = {LAPIS: Clinically Constrained Patient-Identity Residual Learning for Chest X-Ray Anonymization — arXiv:2610.40722},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.40722},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_0ece4ff20d14; sha256 fe94e14fb6e1bc12aea2debb521ed23b6f3ff8e4cae0bbbcb857b9f167450608},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.40722. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Biometric information in chest radiographs limits their release for research, as patients can be re-identified. We propose LAPIS, which jointly adapts a spatial chest-radiograph latent space so that patient-discriminative information concentrates in a compact, replaceable channel residual while most clinically relevant content stays in the complement. The residual is defined by an exactly semi-orthogonal basis, a spatial adversary suppresses identity leakage from the complement, and replacement-aware training teaches the decoder cross-patient residual swaps under output identity, clinical and realism constraints, so that replacing the residual yields a valid image. At release, the residual is replaced by a mixture of donor residuals. On patient-disjoint model, release and test sets from ChestX-ray14, we evaluate attackers adapted to the anonymized setting, a structural source-retrieval attack, and pathology classifiers trained on released images and tested on real ones. LAPIS reduces worst-case cross-study linkability from 0.961 to 0.791 AUC at a macro AUROC cost of 0.012 relative to reconstruction; a deformation-based baseline, however, remains better at structural source retrieval.

Tema degli esploratori: statistica e scienza dei dati (elenco arXiv eess.IV, nuovi lavori del giorno).
Categorie arXiv: Image and Video Processing (eess.IV).
Pagina del lavoro: https://arxiv.org/abs/2610.40722 — 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 2026-11-03T08:16:09.246Z dalla pagina https://arxiv.org/list/eess.IV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).