Metraipolis › archive › dc_424a457ebbcd

Can Protein-Derived Knowledge Improve Pathology Foundation Models? — arXiv:2609.33178

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.33178
License (as archived): CC0-1.0
Archived: 2026-10-07T23:51:25.703Z
SHA-256 of the archived text: d1ee7a62b9d71b4ae37f92234215c8f8f8f401e5cf5dbccdc5ced791e3b2f003
Stable URL of this page: https://metraipolis.com/documento/dc_424a457ebbcd

How to cite

Can Protein-Derived Knowledge Improve Pathology Foundation Models? — arXiv:2609.33178 — arXiv (en), https://arxiv.org/abs/2609.33178 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_424a457ebbcd (Metraipolis archive dc_424a457ebbcd, sha256 d1ee7a62b9d71b4ae37f92234215c8f8f8f401e5cf5dbccdc5ced791e3b2f003)

BibTeX

@misc{dc424a457ebbcd,
  title = {Can Protein-Derived Knowledge Improve Pathology Foundation Models? — arXiv:2609.33178},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.33178},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_424a457ebbcd; sha256 d1ee7a62b9d71b4ae37f92234215c8f8f8f401e5cf5dbccdc5ced791e3b2f003},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.33178. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Molecularly guided pathology foundation models (PFMs) exploit transcriptomic or proteomic information to enrich whole-slide image (WSI) representations, yet effectively leveraging large standalone molecular corpora remains challenging. First, existing molecular foundation models encode protein sequences or single-cell states, not the patient-level bulk expression profiles paired with WSIs. Second, because cross-modal supervision is restricted to paired WSI-omics samples, knowledge from standalone molecular corpora reaches the pathology encoder only indirectly, creating a paired-support bottleneck. To address these challenges, we propose a three-stage framework that decouples proteomic knowledge acquisition from cross-modal transfer, yielding ProSlide, a slide-level hierarchical pathology foundation model. First, to close the modality gap, we pretrain a Proteomic Foundation Encoder (PFE) on 12,695 sample-level bulk protein profiles using virtual profile generation and expression-space multi-view pretraining. Second, we pretrain ProSlide, a patch-region-slide encoder, to predict protein expression from paired WSI-protein samples. Third, to relax the paired-support bottleneck, we introduce Prot2Path, a cross-modal relational distillation objective. For each paired sample, it aligns the similarity distributions of the WSI and its protein profile over a shared, frozen bank of PFE-encoded paired and standalone profiles. We evaluate ProSlide on 12 downstream tasks across breast, lung, and renal cancers. Despite being pretrained with only 2,229 WSIs and 12,695 sample-level protein profiles, ProSlide achieves the highest mean accuracy and AUC within each cancer group.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-29 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2609.33178 — 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 2026-10-07T23:29:27.158Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).