Can Machine Learning Predict Metastatic Sites in Pancreatic Ductal Adenocarcinoma? A Radiomic Analysis.

Journal: Journal of imaging informatics in medicine
Published Date: Aug 4, 2025

Abstract

Pancreatic ductal adenocarcinoma (PDAC) exhibits high metastatic potential, with distinct prognoses based on metastatic sites. Radiomics enables quantitative imaging analysis for predictive modeling. To evaluate the feasibility of radiomic models in predicting PDAC metastatic patterns, specifically distinguishing between hepatic and pulmonary metastases. This retrospective study included 115 PDAC patients with either liver (n = 94) or lung (n = 21) metastases. Radiomic features were extracted from pancreatic arterial and venous phase CT scans of primary tumors using PyRadiomics. Two radiologists independently segmented tumors for inter-reader reliability assessment. Features with ICC > 0.9 underwent LASSO regularization for feature selection. Class imbalance was addressed using SMOTE and class weighting. Model performance was evaluated using fivefold cross-validation and bootstrap resampling. The multivariate logistic regression model achieved an AUC-ROC of 0.831 (95% CI: 0.752-0.910). At the optimal threshold, sensitivity was 0.762 (95% CI: 0.659-0.865) and specificity was 0.787 (95% CI: 0.695-0.879). The negative predictive value for lung metastases was 0.810 (95% CI: 0.734-0.886). LargeDependenceEmphasis showed a trend toward significance (p = 0.0566) as a discriminative feature. Precision was 0.842, recall 0.762, and F1 score 0.800. Radiomic analysis of primary pancreatic tumors demonstrates potential for predicting hepatic versus pulmonary metastatic patterns. The high negative predictive value for lung metastases may support clinical decision-making. External validation is essential before clinical implementation. These findings from a single-center study require confirmation in larger, multicenter cohorts.

Authors

  • F Spoto
    Department of Diagnostics and Public Health Radiology Institute, University of Verona, Policlinico 'G. B. Rossi', Integrated University Hospital, Verona, Italy. flaviospoto@hotmail.it.
  • R De Robertis
    Department of Diagnostics and Public Health Radiology Institute, University of Verona, Policlinico 'G. B. Rossi', Integrated University Hospital, Verona, Italy.
  • N Cardobi
    Department of Diagnostics and Public Health Radiology Institute, University of Verona, Policlinico 'G. B. Rossi', Integrated University Hospital, Verona, Italy.
  • A Garofano
    Department of Diagnostics and Public Health Radiology Institute, University of Verona, Policlinico 'G. B. Rossi', Integrated University Hospital, Verona, Italy.
  • L Messineo
    Section of Innovation Biomedicine-Oncology Area, Department of Engineering for Innovation Medicine (DIMI), University of Verona and University and Hospital Trust (AOUI) of Verona, P.le L.A. Scuro 10, Verona, 37134, Italy.
  • E Lucin
    Section of Innovation Biomedicine-Oncology Area, Department of Engineering for Innovation Medicine (DIMI), University of Verona and University and Hospital Trust (AOUI) of Verona, P.le L.A. Scuro 10, Verona, 37134, Italy.
  • M Milella
    Section of Innovation Biomedicine-Oncology Area, Department of Engineering for Innovation Medicine (DIMI), University of Verona and University and Hospital Trust (AOUI) of Verona, P.le L.A. Scuro 10, Verona, 37134, Italy.
  • M D'Onofrio
    Department of Diagnostics and Public Health Radiology Institute, University of Verona, Policlinico 'G. B. Rossi', Integrated University Hospital, Verona, Italy.

Keywords

No keywords available for this article.

External Resources

Popular Topics
Recent Journals