Adaptive Aggregation Weights for Federated Segmentation of Pancreas MRI

2024-10-29

arXiv.org

AI Summary

To address domain shift in cross-center pancreatic MRI segmentation under federated learning—caused by heterogeneous imaging protocols and population differences—this paper proposes a domain-aware adaptive aggregation method. Unlike conventional FedAvg, which performs uniform model averaging, our approach explicitly models client-specific domain shifts and dynamically adjusts each center’s contribution to global aggregation via gradient similarity measurement and domain-aware weight estimation. To the best of our knowledge, this is the first work to introduce explicit domain shift modeling and adaptive weighted aggregation for medical image federated segmentation. Evaluated on a multi-center pancreatic MRI dataset, the method achieves a 3.2% improvement in Dice score over baselines including FedAvg and FedProx, while reducing inter-domain performance variance by 41%. These results demonstrate significantly enhanced cross-domain generalization and segmentation robustness under privacy-preserving constraints.

Technology Category

• Machine Learning: Distributed Machine Learning & Federated Learning
• Computer Vision: Segmentation
• Multiagent Systems: Adversarial Agents

Application Category

• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization
• Search and Retrieval-Augmented AI: Vertical and domain-specific search
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

Federated learning (FL) enables collaborative model training across institutions without sharing sensitive data, making it an attractive solution for medical imaging tasks. However, traditional FL methods, such as Federated Averaging (FedAvg), face difficulties in generalizing across domains due to variations in imaging protocols and patient demographics across institutions. This challenge is particularly evident in pancreas MRI segmentation, where anatomical variability and imaging artifacts significantly impact performance. In this paper, we conduct a comprehensive evaluation of FL algorithms for pancreas MRI segmentation and introduce a novel approach that incorporates adaptive aggregation weights. By dynamically adjusting the contribution of each client during model aggregation, our method accounts for domain-specific differences and improves generalization across heterogeneous datasets. Experimental results demonstrate that our approach enhances segmentation accuracy and reduces the impact of domain shift compared to conventional FL methods while maintaining privacy-preserving capabilities. Significant performance improvements are observed across multiple hospitals (centers).

Problem

• Improving generalization in federated pancreas MRI segmentation
• Addressing domain-specific differences in FL aggregation
• Enhancing accuracy while preserving data privacy

Innovation

• Adaptive aggregation weights for FL
• Dynamic client contribution adjustment
• Enhanced segmentation across domains