Scholarlink

<p>Recently, histopathology foundation models (hFM) have rapidly advanced in size and complexity, achieving excellent performance in cancer diagnosis and biomarker discovery. Here, we specialise pre-trained hFMs to invasive tumour tissue and present three key contributions. First, we systematically evaluate the biological concepts encoded in hFM representations across multiple biological scales. Second, we demonstrate that informed extended pre-training transforms generalist models into tumour-specialised ones encoding richer semantic information, enabling discovery of recurrent tumour archetypes with consistent morphological and molecular identities across patients. Third, we identify dominant tumour archetypes with aberrant gene-expression programs coexisting within tumours and recurring across heterogeneous epithelial cancers, including HER2-positive and triple-negative breast cancer. Crucially, these archetypes exhibit prognostic value, with RNA splicing-associated archetypes consistently predicting poorer outcomes. Our work shows that tumour-specialised hFMs unlock rich molecular and morphological information from routine H&amp;E slides, providing computationally efficient and biologically informed solutions for biological discovery and patient stratification.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Prognostic RNA-splicing archetypes in breast cancer identified by extended pre-training of histopathology foundation models

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年7月7日

查看全文
  • Lisa Fournier,
  • Garance Haefliger,
  • Albin Vernhes,
  • Vincent Jung,
  • Lena Loye,
  • Valentine Du Bois,
  • Intidhar Labidi-Galy,
  • Pascal Frossard,
  • Igor Letovanec,
  • Cédric Vincent-Cuaz,
  • Raphaëlle Luisier

摘要

Recently, histopathology foundation models (hFM) have rapidly advanced in size and complexity, achieving excellent performance in cancer diagnosis and biomarker discovery. Here, we specialise pre-trained hFMs to invasive tumour tissue and present three key contributions. First, we systematically evaluate the biological concepts encoded in hFM representations across multiple biological scales. Second, we demonstrate that informed extended pre-training transforms generalist models into tumour-specialised ones encoding richer semantic information, enabling discovery of recurrent tumour archetypes with consistent morphological and molecular identities across patients. Third, we identify dominant tumour archetypes with aberrant gene-expression programs coexisting within tumours and recurring across heterogeneous epithelial cancers, including HER2-positive and triple-negative breast cancer. Crucially, these archetypes exhibit prognostic value, with RNA splicing-associated archetypes consistently predicting poorer outcomes. Our work shows that tumour-specialised hFMs unlock rich molecular and morphological information from routine H&E slides, providing computationally efficient and biologically informed solutions for biological discovery and patient stratification.