Scholarlink

<p>Although surgical resection is the standard therapy for stage II/III colorectal cancer, recurrence rates exceed 30%. Circulating tumor DNA (ctNDA) detects molecular residual disease (MRD), but lacks spatial and tumor microenvironment information. Here, we develop a deep learning (DL) model to predict disease-free survival from hematoxylin &amp; eosin stained whole slide images in stage II-IV colorectal cancer. The model is trained on the DACHS cohort (<i>n</i> = 1766) and validated on the GALAXY cohort (<i>n</i> = 1404). In GALAXY, the DL model categorizes 304 patients as DL high-risk and 1100 as low-risk (HR 2.31; <i>p</i> &lt; 0.005). Combining DL scores with MRD status improves prognostic stratification in both MRD-positive (HR 1.58; <i>p</i> &lt; 0.005) and MRD-negative groups (HR 2.1; <i>p</i> &lt; 0.005). Notably, MRD-negative patients predicted as DL high-risk benefit from adjuvant chemotherapy (HR 0.49; <i>p</i> = 0.01) vs. DL low-risk (HR = 0.92; <i>p</i> = 0.64). Combining ctDNA with DL-based histology analysis significantly improves risk stratification, with the potential to improve follow-up and personalized adjuvant therapy decisions.</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

HIBRID: histology-based risk-stratification with deep learning and ctDNA in colorectal cancer

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年8月14日

查看全文
  • Chiara M. L. Loeffler,
  • Hideaki Bando,
  • Srividhya Sainath,
  • Hannah Sophie Muti,
  • Xiaofeng Jiang,
  • Marko van Treeck,
  • Nic Gabriel Reitsam,
  • Zunamys I. Carrero,
  • Asier Rabasco Meneghetti,
  • Tomomi Nishikawa,
  • Toshihiro Misumi,
  • Saori Mishima,
  • Daisuke Kotani,
  • Hiroya Taniguchi,
  • Ichiro Takemasa,
  • Takeshi Kato,
  • Eiji Oki,
  • Yuan Tanwei,
  • Wankhede Durgesh,
  • Sebastian Foersch,
  • Hermann Brenner,
  • Michael Hoffmeister,
  • Yoshiaki Nakamura,
  • Takayuki Yoshino,
  • Jakob Nikolas Kather

摘要

Although surgical resection is the standard therapy for stage II/III colorectal cancer, recurrence rates exceed 30%. Circulating tumor DNA (ctNDA) detects molecular residual disease (MRD), but lacks spatial and tumor microenvironment information. Here, we develop a deep learning (DL) model to predict disease-free survival from hematoxylin & eosin stained whole slide images in stage II-IV colorectal cancer. The model is trained on the DACHS cohort (n = 1766) and validated on the GALAXY cohort (n = 1404). In GALAXY, the DL model categorizes 304 patients as DL high-risk and 1100 as low-risk (HR 2.31; p < 0.005). Combining DL scores with MRD status improves prognostic stratification in both MRD-positive (HR 1.58; p < 0.005) and MRD-negative groups (HR 2.1; p < 0.005). Notably, MRD-negative patients predicted as DL high-risk benefit from adjuvant chemotherapy (HR 0.49; p = 0.01) vs. DL low-risk (HR = 0.92; p = 0.64). Combining ctDNA with DL-based histology analysis significantly improves risk stratification, with the potential to improve follow-up and personalized adjuvant therapy decisions.