Scholarlink

<p>Ductal Carcinoma In Situ (DCIS) is a non-obligate precursor of invasive breast cancer. Due to a lack of reliable prognostic markers, nearly all women with DCIS undergo intensive treatment—often unnecessarily. The LORD trial addresses this by offering active surveillance to women with screen-detected, ER-positive, HER2-negative, grade 1 or 2 DCIS, aiming to reduce overtreatment. To support this, we developed a deep learning pipeline based on foundation models to predict grade, ER, and HER2 status directly from H&amp;E-stained digitized pathology slides. Models were trained and tested on a Dutch multicenter dataset (n = 887) and externally validated on a UK dataset (n = 259). On the Dutch data, the models achieved mean AUROCs of 0.90 (ER), 0.84 (HER2), and 0.86 (grade); external validation yielded 0.80, 0.74, and 0.75, respectively. Using these outputs, we stratified patients according to active surveillance criteria, reaching balanced accuracies of 0.81 (Dutch) and 0.64 (UK), with corresponding NPVs of 0.86 and 0.76. Our models generalize across cohorts and reliably predict key biomarkers, supporting the identification of DCIS patients eligible for less aggressive management.</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

Enabling DCIS subtyping: leveraging foundation models for robust grading and molecular biomarker scoring

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年5月6日

查看全文
  • S. Doyle,
  • M. A. Oerlemans,
  • J. Brunekreef,
  • E. Marcus,
  • L. Mulder,
  • Y. Liu,
  • I. Bouybayoune,
  • E. J. Sawyer,
  • A. M. Thompson,
  • S. E. Pinder,
  • Jelle Wesseling,
  • Alastair Thompson,
  • Serena Nik-Zainal,
  • Elinor J. Sawyer,
  • Helen Davies,
  • Andrew Futreal,
  • Nicholas Navin,
  • E. Shelley Hwang,
  • Jos Jonkers,
  • Jacco van Rheenen,
  • Fariba Behbod,
  • Esther H. Lips,
  • Marjanka Schmidt,
  • Lodewyk F. A. Wessels,
  • Daniel Rea,
  • Proteeti Bhattacharjee,
  • Hilary Stobart,
  • Deborah Collyar,
  • Donna Pinto,
  • Ellen Verschuur,
  • Marja van Oirsouw,
  • Jelle Wesseling,
  • Alastair Thompson,
  • Serena Nik-Zainal,
  • Elinor J. Sawyer,
  • Helen Davies,
  • Andrew Futreal,
  • Nicholas Navin,
  • E. Shelley Hwang,
  • Jos Jonkers,
  • Jacco van Rheenen,
  • Fariba Behbod,
  • Esther H. Lips,
  • Marjanka Schmidt,
  • Lodewyk F. A. Wessels,
  • Daniel Rea,
  • Proteeti Bhattacharjee,
  • Hilary Stobart,
  • Deborah Collyar,
  • Donna Pinto,
  • Ellen Verschuur,
  • Marja van Oirsouw,
  • C. I. Sánchez,
  • J. Teuwen,
  • J. Wesseling,
  • E. H. Lips

摘要

Ductal Carcinoma In Situ (DCIS) is a non-obligate precursor of invasive breast cancer. Due to a lack of reliable prognostic markers, nearly all women with DCIS undergo intensive treatment—often unnecessarily. The LORD trial addresses this by offering active surveillance to women with screen-detected, ER-positive, HER2-negative, grade 1 or 2 DCIS, aiming to reduce overtreatment. To support this, we developed a deep learning pipeline based on foundation models to predict grade, ER, and HER2 status directly from H&E-stained digitized pathology slides. Models were trained and tested on a Dutch multicenter dataset (n = 887) and externally validated on a UK dataset (n = 259). On the Dutch data, the models achieved mean AUROCs of 0.90 (ER), 0.84 (HER2), and 0.86 (grade); external validation yielded 0.80, 0.74, and 0.75, respectively. Using these outputs, we stratified patients according to active surveillance criteria, reaching balanced accuracies of 0.81 (Dutch) and 0.64 (UK), with corresponding NPVs of 0.86 and 0.76. Our models generalize across cohorts and reliably predict key biomarkers, supporting the identification of DCIS patients eligible for less aggressive management.