Metraipolis › archive › dc_e603f8c19777

Meta-CLIP: Metadata-Conditioned Contrastive Learning for Zero-Shot Disease Inference — arXiv:2610.33674

Source: arXiv (en)
Original: https://arxiv.org/abs/2610.33674
License (as archived): CC0-1.0
Archived: 2026-10-27T07:57:11.739Z
SHA-256 of the archived text: 3789de9c1b88862a6ded90040910c107c7130a39eee3de1397fd6c1635944af4
Stable URL of this page: https://metraipolis.com/documento/dc_e603f8c19777

How to cite

Meta-CLIP: Metadata-Conditioned Contrastive Learning for Zero-Shot Disease Inference — arXiv:2610.33674 — arXiv (en), https://arxiv.org/abs/2610.33674 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_e603f8c19777 (Metraipolis archive dc_e603f8c19777, sha256 3789de9c1b88862a6ded90040910c107c7130a39eee3de1397fd6c1635944af4)

BibTeX

@misc{dce603f8c19777,
  title = {Meta-CLIP: Metadata-Conditioned Contrastive Learning for Zero-Shot Disease Inference — arXiv:2610.33674},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.33674},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_e603f8c19777; sha256 3789de9c1b88862a6ded90040910c107c7130a39eee3de1397fd6c1635944af4},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.33674. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Medical vision--language pretraining learns transferable representations from paired images and radiology reports, yet differences in scanners and acquisition protocols can impair transfer. Existing approaches primarily enrich clinical semantics, leaving structured acquisition information in DICOM headers underused. We introduce Meta-CLIP, a metadata-conditioned contrastive framework that uses acquisition similarity to reweight cross-modal negatives during pretraining. A kernel over numerical and categorical DICOM fields defines a bounded pairwise margin. This margin increases the contribution of acquisition-similar negatives, emphasizing distinctions among studies that share imaging conditions. The kernel remains fixed during image--text optimization, and inference follows the standard dual-encoder architecture without requiring metadata. We evaluate Meta-CLIP on chest radiography and volumetric chest CT through zero-shot classification, appearance perturbations, grounding, and representation analyses. On CT-RATE, Meta-CLIP improves macro-AUROC over CT-CLIP by 1.41 points, with a 95\% paired bootstrap confidence interval of 0.96--1.85 points. It also achieves the highest macro-AUROC on four of five CXR benchmarks. An exploratory BrgSA evaluation extends the analysis to another CT backbone. These findings support acquisition metadata as a practical training-time prior for medical vision--language learning. Code will be made publicly available upon publication.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2610.33674 — 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 2026-10-27T07:55:30.659Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).