IPMN Risk Assessment under Federated Learning Paradigm

2024-11-08

arXiv.org

AI Summary

Privacy preservation and model accuracy are often conflicting objectives in multi-center intraductal papillary mucinous neoplasm (IPMN) risk assessment. Method: We propose the first federated learning framework specifically designed for pancreatic MRI, supporting distributed training on both T1- and T2-weighted images across institutions. Leveraging DenseNet-121, we design a local update and global aggregation protocol. The framework is validated on a collaboratively curated,迄今 largest and most diverse IPMN MRI dataset—comprising 1,307 cases from seven leading hospitals. Results: Our method achieves classification accuracy comparable to centralized training while strictly preserving data locality. It significantly enhances cross-institutional robustness and generalizability, with no patient data leaving its source institution. This work establishes a reproducible paradigm and empirical benchmark for federated modeling in medical imaging, advancing privacy-preserving collaborative AI in radiology.

Technology Category

• Machine Learning: Distributed Machine Learning & Federated Learning
• Computer Vision: Multi-modal Vision
• Natural Language Processing: Language Grounding & Multi-modal NLP

Application Category

• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization
• Security and Privacy: Security and privacy of machine learning and AI applications
• Systems and Infrastructure for Web, Mobile and WoT: Federated Web and WoT systems, including distributed, federated and edge-based data processing

Abstract

Accurate classification of Intraductal Papillary Mucinous Neoplasms (IPMN) is essential for identifying high-risk cases that require timely intervention. In this study, we develop a federated learning framework for multi-center IPMN classification utilizing a comprehensive pancreas MRI dataset. This dataset includes 652 T1-weighted and 655 T2-weighted MRI images, accompanied by corresponding IPMN risk scores from 7 leading medical institutions, making it the largest and most diverse dataset for IPMN classification to date. We assess the performance of DenseNet-121 in both centralized and federated settings for training on distributed data. Our results demonstrate that the federated learning approach achieves high classification accuracy comparable to centralized learning while ensuring data privacy across institutions. This work marks a significant advancement in collaborative IPMN classification, facilitating secure and high-accuracy model training across multiple centers.

Problem

• Patient Privacy
• IPMN Risk Assessment
• Federated Learning

Innovation

• Federated Learning
• DenseNet-121
• Privacy Protection