Metraipolis › archive › dc_a4c135fda74a

MagViT: Interpretable Multi-Magnification Transformers with Patient-Level Model Selection for Breast Histopathology — arXiv:2608.16959

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.16959
License (as archived)
CC0-1.0
Archived
2026-10-18T14:48:53.999Z
SHA-256 of the archived text
c2f96995984fbf1c862cfe331891789fee6b3dee45d93628b50f6630b4d85aac
Stable URL of this page
https://metraipolis.com/documento/dc_a4c135fda74a

How to cite

MagViT: Interpretable Multi-Magnification Transformers with Patient-Level Model Selection for Breast Histopathology — arXiv:2608.16959 — arXiv (en), https://arxiv.org/abs/2608.16959 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_a4c135fda74a (Metraipolis archive dc_a4c135fda74a, sha256 c2f96995984fbf1c862cfe331891789fee6b3dee45d93628b50f6630b4d85aac)
BibTeX
@misc{dca4c135fda74a,
  title = {MagViT: Interpretable Multi-Magnification Transformers with Patient-Level Model Selection for Breast Histopathology — arXiv:2608.16959},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.16959},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_a4c135fda74a; sha256 c2f96995984fbf1c862cfe331891789fee6b3dee45d93628b50f6630b4d85aac},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.16959. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Breast cancer is one of the most common types of cancer among women around the world. Rapid detection and early treatment can hinder its progress to more complex stages and can impede its spread to other parts of the body. Histopathological image classification is the most common task in cancer detection due to its robustness in analyzing cellular data. Breast histopathology classification requires handling both multi-scale tissue morphology and clinically relevant generalization beyond the source domain. This paper presents MagViT, an interpretable multi-magnification transformer framework with scale-gated fusion and patient-level model selection. The model uses four BreakHis magnifications (40X, 100X, 200X, 400X) and extracts per-scale representations with a ViT backbone, and combines them via a learnable gate that masks missing scales. Patient-level five-fold cross-validation with a fixed seed has been run and compared with three architectural branches. The most accurate branch is then selected as the final model due to the strongest patient-level accuracy while retaining the simplest fusion pathway. On BreakHis, our architecture achieves a mean image accuracy of 0.9191, a mean patient accuracy of 0.9643, and a mean macro-F1 of 0.9042. External transfer experiments provide preliminary evidence of cross-dataset generalization under controlled adaptation settings on BUSI (image accuracy 0.8306, macro-F1 0.7480, patient accuracy 0.8291) and IDC (image accuracy 0.8577, macro-F1 0.8191, patient accuracy 0.8372). Grad-CAM visualization indicates that the model focuses on diagnostically significant and meaningful regions across magnifications. Relative to prior ViT-centered BreakHis work, this study emphasizes patient-level selection and cross-dataset robustness under a reproducible protocol.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-19 in cs.LG).
Categorie arXiv: Image and Video Processing (eess.IV) ; Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2608.16959 — 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 2026-10-18T14:47:59.438Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-08-19?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).