HIBRID: histology-based risk-stratification with deep learning and ctDNA in colorectal cancer
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.
Authors
- Tanwei Yuan (ORCID: https://orcid.org/0000-0001-7387-6327)
- Yoshiaki Nakamura (ORCID: https://orcid.org/0000-0002-5241-6855)
- Xiaofeng Jiang (ORCID: https://orcid.org/0000-0002-3716-8232)
- Ichiro Takemasa (ORCID: https://orcid.org/0000-0003-1595-2453)
- Takeshi Kato (ORCID: https://orcid.org/0000-0001-8978-6019)
- Toshihiro Misumi (ORCID: https://orcid.org/0000-0001-8339-2895)
- Daisuke Kotani (ORCID: https://orcid.org/0000-0002-4196-555X)
- Marko van Treeck
- Srividhya Sainath (ORCID: https://orcid.org/0009-0006-6227-747X)
- Michael Hoffmeister (ORCID: https://orcid.org/0000-0002-8307-3197)
- Nic G. Reitsam (ORCID: https://orcid.org/0000-0002-0070-3158)
- Hideaki Bando (ORCID: https://orcid.org/0000-0001-5041-2765)
- Asier Rabasco Meneghetti (ORCID: https://orcid.org/0000-0002-1508-9410)
- T. Nishikawa (ORCID: https://orcid.org/0000-0001-6586-6604)
- Takayuki Yoshino (ORCID: https://orcid.org/0000-0002-0489-4756)
- Eiji Oki (ORCID: https://orcid.org/0000-0002-9763-9366)
- Hannah Sophie Muti
- Hiroya Taniguchi (ORCID: https://orcid.org/0000-0003-1407-6682)
- Zunamys I. Carrero (ORCID: https://orcid.org/0000-0001-8501-1566)
- Sebastian Foersch (ORCID: https://orcid.org/0000-0002-4740-6900)
- Jakob Nikolas Kather (ORCID: https://orcid.org/0000-0002-3730-5348)
- Hermann Brenner (ORCID: https://orcid.org/0000-0002-6129-1572)
- Chiara Maria Lavinia Loeffler (ORCID: https://orcid.org/0009-0002-9659-5194)
- Saori Mishima
- Wankhede Durgesh
Institutions
- Kyushu University (JP)
- Sapporo Medical University (JP)
- University of Augsburg (DE)
- German Cancer Research Center (DE)
- Johannes Gutenberg University Mainz (DE)
- Heidelberg University (DE)
- University Hospital Heidelberg (DE)
- Osaka National Hospital (JP)
- University Medical Center of the Johannes Gutenberg University Mainz (DE)
- Fresenius (Germany) (DE)
- National Center for Tumor Diseases (DE)
- Aichi Cancer Center (JP)
- National Cancer Center Hospital East (JP)
- University Hospital Carl Gustav Carus (DE)
- Technische Universität Dresden (DE)
Publication Details
- Journal
- Nature Communications
- Published
- 2025-08-14
- DOI
- https://doi.org/10.1038/s41467-025-62910-8
- Citations
- 8
- Primary Topic
- Cancer Genomics and Diagnostics
- Type
- article
- Field-Weighted Citation Impact
- 7.49
Funders
- National Institute for Health and Care Research
- Department of Health and Social Care
- European Commission
- Deutscher Akademischer Austauschdienst
- Deutsche Forschungsgemeinschaft
- Bundesministerium für Bildung und Forschung
- Deutsche Krebshilfe
- Gemeinsame Bundesausschuss
- HORIZON EUROPE Framework Programme