Federated CT foundation models for multi-center detection of lymph node metastasis in pancreatic cancer.
Authors
Affiliations (9)
Affiliations (9)
- Clinic for Diagnostic and Interventional Radiology, University Hospital Bonn, University of Bonn, Bonn, Germany.
- Department of Clinical and Intervention Radiology, University Medical Center Göttingen, Göttingen, Germany.
- Department of General, Visceral and Pediatric Surgery, University Medical Center Göttingen, Göttingen, Germany.
- Department of Radiology, Charité-Universitätsmedizin Berlin, Berlin, Germany.
- Department of Surgery, CCM | CVK, Charité-Universitätsmedizin Berlin, Berlin, Germany.
- Clinic and Polyclinic for General, Visceral, Thoracic, and Vascular Surgery, University of Bonn, Bonn, Germany.
- Department of General and Visceral Surgery, CBF, Charité-Universitätsmedizin Berlin, Berlin, Germany.
- Clinic for Diagnostic and Interventional Radiology, University Hospital Bonn, University of Bonn, Bonn, Germany. [email protected].
- TUM School of Computation, Information and Technology, Technical University of Munich, Munich, Germany. [email protected].
Abstract
Pancreatic ductal adenocarcinoma (PDAC) remains one of the most lethal malignancies, with prognosis strongly influenced by the presence of lymph node metastasis (LNM). However, preoperative LNM assessment from computed tomography (CT) is limited by low sensitivity, high inter-observer variability, and substantial heterogeneity across imaging protocols. This retrospective multi-center study (546 patients from three institutions) introduces a privacy-preserving deep learning framework that integrates large-scale CT foundation model pre-training with heterogeneity-aware federated optimization to improve LNM detection in PDAC. A CT Vision Foundation Model, pre-trained on 148,000 volumetric CT scans using contrastive self-supervised learning, is fine-tuned to generate transferable 3D representations for patient-level LNM classification. To enable decentralized model training while mitigating inter-institutional variability, we extend federated aggregation to jointly account for label-distribution discrepancies and representation-level divergence across clients. The centralized model achieved a balanced accuracy of 0.601 and a diagnostic odds ratio (DOR) of 3.45, outperforming classical machine learning baselines and prior PDAC LNM approaches. Under federated settings, the proposed heterogeneity-aware strategy consistently outperformed standard FedAvg, recovering a substantial proportion of the centralized model's performance while preserving strict data privacy. In particular, it improved balanced accuracy by 12.6% over FedAvg and demonstrated superior discriminative ability across all participating cohorts. These findings indicate that combining foundation model pre-training with discrepancy-aware federated learning enhances generalization, robustness, and clinical relevance for multi-center PDAC LNM detection. The proposed framework offers a scalable and privacy-preserving pathway for deploying deep learning models across distributed healthcare systems.