Metraipolis › archive › dc_6ce59600dc77

Foundation model embeddings capture pre-diagnostic changes on screening mammograms — arXiv:2609.26605

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.26605
License (as archived)
CC0-1.0
Archived
2026-10-08T15:11:35.128Z
SHA-256 of the archived text
43f369341431192c5a44af5a36b64b9ca29eb0b009265d2346564ebf12b49c24
Stable URL of this page
https://metraipolis.com/documento/dc_6ce59600dc77

How to cite

Foundation model embeddings capture pre-diagnostic changes on screening mammograms — arXiv:2609.26605 — arXiv (en), https://arxiv.org/abs/2609.26605 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_6ce59600dc77 (Metraipolis archive dc_6ce59600dc77, sha256 43f369341431192c5a44af5a36b64b9ca29eb0b009265d2346564ebf12b49c24)
BibTeX
@misc{dc6ce59600dc77,
  title = {Foundation model embeddings capture pre-diagnostic changes on screening mammograms — arXiv:2609.26605},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.26605},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_6ce59600dc77; sha256 43f369341431192c5a44af5a36b64b9ca29eb0b009265d2346564ebf12b49c24},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.26605. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Foundation model embeddings of screening mammograms may encode pre-diagnostic tissue change without task-specific adaptation. We tested whether embeddings move faster along a data-derived "cancer direction" in women later biopsied for cancer than in matched screen-negative controls, and whether this depends on pretraining domain. We studied 1,773 biopsied women (785 malignant, 988 biopsy-negative) and 1,773 matched controls, each with at least two annual screening exams before their index exam. An identical pipeline was applied to four 2D models: Mammo-CLIP (MC, out-of-distribution mammography), HOPPR (in-distribution mammography), MedImageInsight (MII, general medical imaging), and BiomedCLIP (biomedical vision-language pretraining on literature figures). Breast-level embeddings quantified longitudinal movement along the cancer direction. We compared cases and controls using a between-patient design with complementary mixed-effects analysis, and biopsied versus healthy contralateral breasts within patients. Under matched modality in MII embedding space, malignant cases drifted significantly faster than controls in the first two screening intervals preceding the index exam; biopsy-negative cases showed significance only in the first. MC differences were significant in the first interval for both biopsy groups. Within-patient comparisons showed a broadly similar pattern, with MC significance extending to the second interval in both groups and HOPPR showing significance at interval 1. BiomedCLIP showed no significant differences in either design or biopsy group. Overall, directional embedding velocity emerges as a property of clinically grounded rather than general biomedical pretraining, showing that foundation model embeddings can encode pre-diagnostic mammographic change without task-specific adaptation.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-23 in cs.LG).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2609.26605 — 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 2026-10-08T14:37:29.579Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-23?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).