DSFedMed: Dual-Scale Federated Medical Image Segmentation via Mutual Distillation Between Foundation and Lightweight Models

2026-01-22

AI Summary

This work addresses the challenges of high computational overhead, substantial communication costs, and expensive inference associated with deploying foundation models in federated medical image segmentation. To overcome these limitations, the authors propose a dual-scale federated framework that enables efficient collaborative training through bidirectional knowledge distillation between a centralized foundation model and lightweight client-side models. The approach innovatively leverages synthetically generated high-quality medical images to replace real data and incorporates a learnability-guided sample selection strategy to enhance model generalization. Experimental results across five medical image segmentation datasets demonstrate that the proposed method improves the average Dice score by 2% while reducing both communication costs and inference time by nearly 90%.

Technology Category

• Machine Learning: Distributed Machine Learning & Federated Learning
• Computer Vision: Segmentation
• Multiagent Systems: Other Foundations of Multi Agent Systems

Application Category

• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Federated Web and WoT systems, including distributed, federated and edge-based data processing

Abstract

Foundation Models (FMs) have demonstrated strong generalization across diverse vision tasks. However, their deployment in federated settings is hindered by high computational demands, substantial communication overhead, and significant inference costs. We propose DSFedMed, a dual-scale federated framework that enables mutual knowledge distillation between a centralized foundation model and lightweight client models for medical image segmentation. To support knowledge distillation, a set of high-quality medical images is generated to replace real public datasets, and a learnability-guided sample selection strategy is proposed to enhance efficiency and effectiveness in dual-scale distillation. This mutual distillation enables the foundation model to transfer general knowledge to lightweight clients, while also incorporating client-specific insights to refine the foundation model. Evaluations on five medical imaging segmentation datasets show that DSFedMed achieves an average 2 percent improvement in Dice score while reducing communication costs and inference time by nearly 90 percent compared to existing federated foundation model baselines. These results demonstrate significant efficiency gains and scalability for resource-limited federated deployments.

Problem

• Federated Learning
• Foundation Models
• Medical Image Segmentation
• Communication Overhead
• Computational Efficiency

Innovation

• Federated Learning
• Foundation Models
• Knowledge Distillation
• Medical Image Segmentation
• Lightweight Models