Multiview deep-learning-enabled histopathology for prognostic and therapeutic stratification in stage II colorectal cancer: A retrospective multicenter study
PLOS Medicine · 13.01.2026 · 23 (1) · e1004614
DOI: 10.1371/journal.pmed.1004614 ↗Kurz gefasst
Multizentrische Studie in der Zeitschrift PLOS Medicine, online erschienen am 13.01.2026. Verfasst von Zihan Zhao und 15 weiteren Autor:innen. Beteiligte Einrichtung: Department of Pathology, State Key Laboratory of Oncology in South China, Guangdong Provincial Clinical Research Center for Cancer, Sun Yat-sen Unive…. Hauptthemen laut MEDLINE: Colorectal Neoplasms, Deep Learning. Die Arbeit wurde bisher 14-mal zitiert (Crossref) und nennt 56 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Science and Technology Planning Project of Guangdong Province, the Guangdong Excellent Youth Team Program.
Abstract (Originalsprache)
Background
Approximately 20% of patients with stage II colorectal cancer (CRC) experience tumor relapse despite standard surgical treatment. Histopathological analysis holds promise for postsurgical risk stratification and guiding adjuvant chemotherapy (ACT) decisions. The aim of this study was to use deep learning to extract explainable tissue biomarkers from whole-slide images. Methods and findings In this retrospective cohort study, we developed and validated SurvFinder, an interpretable deep learning framework designed to autonomously identify tissue-based risk biomarkers from hematoxylin and eosin (H&E)-stained slides. The framework aims to support individualized risk stratification and explore associations with treatment outcomes. The present study included 6,950 H&E slides from 1,604 patients with stage II CRC across four independent cohorts in China. Patients were enrolled from 2012 to 2018 and followed for a minimum of 24 months. The primary outcome of the study was relapse-free survival (RFS). Our analyses identified tertiary lymphoid structures (TLSs) as critical prognostic features in stage II CRC. The multi-view integration of TLS characteristics by SurvFinder consistently demonstrated superior predictive and prognostic accuracy across four multicenter datasets (AUROC with 95% confidence interval [CI]: 0.827 [0.789,0.864], 0.805 [0.749,0.860], 0.805 [0.748,0.861], and 0.712 [0.621,0.804]), surpassing traditional clinical prognostic parameters (hazard ratio [HR]: 8.23, 95% CI: 5.43–12.47; p < 0.001). Using explainable AI (XAI) methods, we ensured model transparency and identified key TLS features-such as their location at the tumor periphery and their maturity state-as significant factors influencing prognosis and the efficacy of adjuvant therapy. The retrospective design without prospective validation and real-world clinical deployment is the main limitation of this study.
Conclusions
Together, these results highlight the potential utility of deep learning-based histopathological analysis for automated risk stratification in stage II CRC. In particular, our findings support the relevance of TLSs as a histological biomarker with potential implications for personalizing ACT decisions.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Substanzen
Autor:innen und Institutionen
- Department of Pathology, State Key Laboratory of Oncology in South China, Guangdong Provincial Clinical Research Center for Cancer, Sun Yat-sen University Cancer Center, Guangzhou, Guangdong, China.
- School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, Guangdong, China.
- Department of Pathology, Tianjin Medical University Cancer Institute and Hospital, Tianjin, China.
- Department of General Surgery (Colorectal Surgery), The Sixth Affiliated Hospital, Sun Yat-sen University, Guangzhou, Guangdong, China.
- Electrical Engineering & Computer Science, Johns Hopkins University, Baltimore, Maryland, United States of America.
- Department of Pathology, Fudan University Shanghai Cancer Center, Shanghai, China.
ORCID-Profile: Ruixuan Wang, Mengke Ma, Muyan Cai
Förderung
- National Natural Science Foundation of China
- Science and Technology Planning Project of Guangdong Province
- the Guangdong Excellent Youth Team Program
- Basic and Applied Basic Research Foundation of Guangdong Province
- Chih Kuang Scholarship for Outstanding Young Physician-Scientists of Sun Yat-sen University Cancer Center
Zitieren
APA
Zhao, Z., Chen, D., Wang, R., Zhang, X., Wen, X., Zheng, X., Liu, S., Chen, H., Zhang, Y., Huang, D., Zheng, C., Ma, M., Xie, D., Sun, Y., He, X., & Cai, M. (2026). Multiview deep-learning-enabled histopathology for prognostic and therapeutic stratification in stage II colorectal cancer: A retrospective multicenter study. PLOS Medicine, 23(1), e1004614. https://doi.org/10.1371/journal.pmed.1004614
Vancouver
Zhao Z, Chen D, Wang R, Zhang X, Wen X, Zheng X, et al. Multiview deep-learning-enabled histopathology for prognostic and therapeutic stratification in stage II colorectal cancer: A retrospective multicenter study. PLOS Medicine. 2026;23(1):e1004614. doi:10.1371/journal.pmed.1004614
BibTeX
@article{Zhao2026,
author = {Zhao, Zihan and Chen, Dexia and Wang, Ruixuan and Zhang, Xinke and Wen, Xiaobo and Zheng, Xueyi and Liu, Shasha and Chen, Hao and Zhang, Yuqian and Huang, Dan and Zheng, Chengyou and Ma, Mengke and Xie, Dan and Sun, Yan and He, Xiaosheng and Cai, Muyan},
title = {Multiview deep-learning-enabled histopathology for prognostic and therapeutic stratification in stage II colorectal cancer: A retrospective multicenter study},
journal = {PLOS Medicine},
year = {2026},
volume = {23},
number = {1},
pages = {e1004614},
doi = {10.1371/journal.pmed.1004614}
}
EUVIMED