This is an early access version, the complete PDF, HTML, and XML versions will be available soon.
Use of a Pathomics Signature to Predict the Prognosis of Hepatocellular Carcinoma with Cirrhosis: A Multicentre Retrospective Study
by
, ,
Ting Wang
1,†, 
Jixiang Zheng
2,†,
Lingling Guo
3,
Jiawen Fan
4,
Yubin Lu
5,
Zhen Peng
1,
Yanfeng Zhong
6,
Zhengjun Zhou
7,* and
Erbao Chen
1,* 1
1. Department of Hepatobiliary and Pancreatic Surgery, Peking University Shenzhen Hospital, Shenzhen 518036, China
2
Department of General Surgery, Guangzhou Digestive Disease Center, Guangzhou First People’s Hospital, Guangzhou Medical University, Guangzhou 510180, China
3
Department of Radiation Oncology, Peking University Shenzhen Hospital, Shenzhen 518036, China
4
Department of Gastrointestinal Surgery, Shenzhen Hospital of Southern Medical University, Shenzhen 518100, China
5
Minimally Invasive Interventional Department, Peking University Shenzhen Hospital, Shenzhen 518036, China
6
Central Laboratory, Peking University Shenzhen Hospital, Shenzhen 518036, China
7
Liver Cancer Institute, Zhongshan Hospital, Fudan University, Shanghai 200032, China
*
Authors to whom correspondence should be addressed.
†
These authors contributed equally to this article.
Cancers 2025, 17(19), 3192; https://doi.org/10.3390/cancers17193192
Submission received: 13 August 2025
/
Revised: 19 September 2025
/
Accepted: 23 September 2025
/
Published: 30 September 2025
(This article belongs to the Section Cancer Biomarkers)
Simple Summary
Prognostic models are lacking for cirrhotic hepatocellular carcinoma (HCC). We constructed a pathomics signature based on pathomics features extracted from digital H-E images and LASSO Cox regression, which was easy to reproduce and may be conveniently applied in clinical practice. The pathomics signature is the independent predictor of OS and DFS, and the nomograms incorporating the pathomics signature and clinicopathological factors outperformed the traditional model consisting of clinicopathological factors alone. These findings may contribute to the use of the pathomics signature in clinical practice and facilitate personalized treatment strategies for HCC with cirrhosis.
Abstract
Background: Hepatocellular carcinoma (HCC) is a highly aggressive and heterogeneous malignancy which predominantly arises in the setting of cirrhosis, and there is lack of models to predict prognosis in cirrhotic HCC. This study aims to develop and validate a prediction model based on the pathomics signature and clinicopathological characteristics to predict the prognosis of HCC with cirrhosis. Methods: In this multicenter, retrospective study, 389 patients were enrolled (training cohort: 268; independent validation cohort: 121). A total of 351 pathomics features were extracted from digital H-E–stained images, and a pathomics signature (PSHCC) was constructed using a least absolute shrinkage and selection operator Cox regression model. Then two nomograms were established by combining the PSHCC and clinicopathological characteristics. Further validation was performed in the validation cohort. Results: This study included 389 patients. A 24 feature-based PSHCC was constructed. A higher PSHCC was significantly associated with worse OS and DFS in both the training (OS: hazard ratio [HR], 4.341 [95% CI, 3.109–6.062]; DFS: HR, 3.058 [95% CI, 2.223–4.207]) and validation (OS: HR, 4.145 [95% CI, 2.357–7.291]; DFS: HR, 3.395 [95% CI, 2.104–5.479]) cohorts (p < 0.001 for all comparisons). Multivariable analysis revealed that the PSHCC was an independent factor associated with OS and DFS. Integrating the PSHCC into pathomics nomograms resulted in better performance for prognosis prediction than the traditional model in both cohorts. Conclusions: The PSHCC may serve as a reliable surrogate for prognosis, and the nomograms offer promising tools to predict individual outcomes, facilitating personalized management of HCC with cirrhosis.
Keywords:
hepatocellular carcinoma; cirrhosis; pathomics; prognosis prediction
