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

Chiara M. L. Loeffler, Hideaki Bando, Srividhya Sainath, Hannah Sophie Muti, Xiaofeng Jiang, Marko 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 () and Jakob Nikolas Kather ()
Additional contact information
Chiara M. L. Loeffler: Technical University Dresden
Hideaki Bando: National Cancer Center Hospital East
Srividhya Sainath: Technical University Dresden
Hannah Sophie Muti: Technical University Dresden
Xiaofeng Jiang: Technical University Dresden
Marko Treeck: Technical University Dresden
Nic Gabriel Reitsam: Technical University Dresden
Zunamys I. Carrero: Technical University Dresden
Asier Rabasco Meneghetti: Technical University Dresden
Tomomi Nishikawa: National Cancer Center Hospital East
Toshihiro Misumi: National Cancer Center Hospital East
Saori Mishima: National Cancer Center Hospital East
Daisuke Kotani: National Cancer Center Hospital East
Hiroya Taniguchi: Aichi Cancer Center Hospital
Ichiro Takemasa: Sapporo Medical University
Takeshi Kato: NHO Osaka National Hospital
Eiji Oki: Kyushu University
Yuan Tanwei: German Cancer Research Center (DKFZ)
Wankhede Durgesh: German Cancer Research Center (DKFZ)
Sebastian Foersch: University Medical Center Mainz
Hermann Brenner: German Cancer Research Center (DKFZ)
Michael Hoffmeister: German Cancer Research Center (DKFZ)
Yoshiaki Nakamura: National Cancer Center Hospital East
Takayuki Yoshino: National Cancer Center Hospital East
Jakob Nikolas Kather: Technical University Dresden

Nature Communications, 2025, vol. 16, issue 1, 1-11

Abstract: Abstract 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

Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
https://www.nature.com/articles/s41467-025-62910-8 Abstract (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:nat:natcom:v:16:y:2025:i:1:d:10.1038_s41467-025-62910-8

Ordering information: This journal article can be ordered from
https://www.nature.com/ncomms/

DOI: 10.1038/s41467-025-62910-8

Access Statistics for this article

Nature Communications is currently edited by Nathalie Le Bot, Enda Bergin and Fiona Gillespie

More articles in Nature Communications from Nature
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().