Predicting Synchronous Liver Metastasis in Pancreatic Cancer Using CT Radiomics and Clinical Features: A Machine Learning Approach
Academic Radiology · 2026-08
DOI: 10.1016/j.acra.2026.08.028 ↗Kurz gefasst
Fachartikel in der Zeitschrift Academic Radiology, 2026-08. Verfasst von Yuzhe Han und 7 weiteren Autor:innen. Beteiligte Einrichtung: Department of Gastrointestinal Surgery, the Affiliated Hospital of Qingdao University, Qingdao, Shandong, China; Department of Basic Medicine, Qingda…. Die Arbeit nennt 27 Literaturangaben. Gefördert von: Key Technology Research and Development Program of Shandong Province, China Postdoctoral Science Foundation, National Natural Science Foundation of China.
Abstract (Originalsprache)
RATIONALE AND OBJECTIVES: To address the challenge of preoperative prediction of synchronous liver metastasis (LM) in pancreatic cancer (PC), we developed and validated machine learning models integrating clinical and computed tomography (CT) radiomics features, and compared the performance and interpretability of linear (linear discriminant analysis [LDA]) versus nonlinear (multilayer perceptron [MLP]) architectures. MATERIALS AND METHODS: This retrospective study enrolled 340 patients with pancreatic ductal adenocarcinoma (190 with LM, 150 without). Five radiomics features were selected using the minimum redundancy maximum relevance and least absolute shrinkage and selection operator methods. Based on independent clinical predictors (age, carcinoembryonic antigen [CEA], and clinical N stage) and the selected radiomics features, 26 machine learning models were constructed. The optimal models (LDA and MLP) were evaluated in an independent validation cohort (n = 102) using receiver operating characteristic curves, calibration, decision curve analysis, and SHAP (SHapley Additive exPlanations) analysis. RESULTS: In the validation cohort, LDA achieved an area under the curve (AUC) of 0.828 (95% confidence interval [CI]: 0.735-0.897), and MLP achieved 0.822 (95% CI: 0.732-0.895). Both models demonstrated good calibration, with Hosmer-Lemeshow test P values of 0.551 (Brier score = 0.168) for LDA and 0.682 (Brier score = 0.172) for MLP, alongside high net clinical benefit. SHAP analysis revealed that clinical N stage dominated the LDA model, whereas CEA and radiomics features played more prominent roles in the MLP model. Friedman's H-statistic identified five significant feature interactions. Subgroup analysis showed that MLP maintained stable performance (AUC 0.66-0.77), whereas LDA performed poorly in the lymph-node-negative (AUC = 0.50) and pancreatic head tumor (AUC = 0.62) subgroups. The clinical nomogram achieved an AUC of 0.788 in the validation cohort. CONCLUSION: The integrated model enables accurate preoperative prediction of synchronous LM in PC. Rather than replacing pathological diagnosis, this tool is designed to assist clinical decision-making in the common dilemma of indeterminate subcentimeter liver lesions on CT: a low-risk score supports surveillance and spares unnecessary biopsy, whereas a high-risk score prompts confirmatory biopsy or a shift toward neoadjuvant systemic therapy. Both architectures exhibit robust discrimination and clinical utility; however, the nonlinear MLP model shows superior stability across clinical subgroups, offering a promising tool for individualized risk assessment and treatment planning.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Gastrointestinal Surgery, the Affiliated Hospital of Qingdao University, Qingdao, Shandong, China; Department of Basic Medicine, Qingdao University, Qingdao, China. Electronic address: 15689701156@163.com.
- Department of Pancreatic and Gastric Surgery, National Cancer Center, National Clinical Research Center for Cancer, Cancer Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing, China.…
- Department of Gastrointestinal Surgery, the Affiliated Hospital of Qingdao University, Qingdao, Shandong, China. Electronic address: qddxjinghanhui@163.com.
- Department of Basic Medicine, Qingdao University, Qingdao, China. Electronic address: chy01030124@126.com.
- Department of Blood Transfusion, the Affiliated Hospital of Qingdao University, Qingdao, Shandong, China. Electronic address: liying@qdu.edu.cn.
- Department of Basic Medicine, Qingdao University, Qingdao, China. Electronic address: 18853963770@163.com.
Förderung
- Key Technology Research and Development Program of Shandong Province
- China Postdoctoral Science Foundation
- National Natural Science Foundation of China
Zitieren
APA
Han, Y., Xiang, S., Jing, H., Cao, H., Li, Y., Sui, J., Tian, G., & Liu, S. (2026). Predicting Synchronous Liver Metastasis in Pancreatic Cancer Using CT Radiomics and Clinical Features: A Machine Learning Approach. Academic Radiology. https://doi.org/10.1016/j.acra.2026.08.028
Vancouver
Han Y, Xiang S, Jing H, Cao H, Li Y, Sui J, et al. Predicting Synchronous Liver Metastasis in Pancreatic Cancer Using CT Radiomics and Clinical Features: A Machine Learning Approach. Academic Radiology. 2026. doi:10.1016/j.acra.2026.08.028
BibTeX
@article{Han2026,
author = {Han, Yuzhe and Xiang, Shuai and Jing, Hanhui and Cao, Hongyu and Li, Ying and Sui, Jiazhen and Tian, Guangye and Liu, Shanglong},
title = {Predicting Synchronous Liver Metastasis in Pancreatic Cancer Using CT Radiomics and Clinical Features: A Machine Learning Approach},
journal = {Academic Radiology},
year = {2026},
doi = {10.1016/j.acra.2026.08.028}
}
EUVIMED