在联邦学习中优化医学影像模型，提升阿尔茨海默病诊断效率
Federated Fine-tuning of SAM-Med3D for MRI-based Dementia Classification
- 采用联邦微调策略，在多中心脑部MRI数据上训练大模型
- 冻结编码器效果接近全量微调，节省计算资源
- 先进聚合方法优于传统平均法，适合临床部署
尽管基础模型（FMs）在基于AI的痴呆症诊断中具有巨大潜力，但其在联邦学习（FL）系统中的应用仍缺乏研究。本基准研究系统评估了关键设计选择对联邦基础模型微调性能与效率的影响：分类头结构、微调策略和聚合方法。基于大规模多队列数据集，我们发现分类头架构显著影响模型表现，冻结基础模型编码器可达到与全量微调相当的效果，且先进聚合方法优于标准联邦平均。研究结果为在去中心化临床环境中部署基础模型提供了实用指导，并揭示了未来方法开发应权衡的关键取舍。
原文摘要 · Abstract (English)
While foundation models (FMs) offer strong potential for AI-based dementia diagnosis, their integration into federated learning (FL) systems remains underexplored. In this benchmarking study, we systematically evaluate the impact of key design choices: classification head architecture, fine-tuning strategy, and aggregation method, on the performance and efficiency of federated FM tuning using brain MRI data. Using a large multi-cohort dataset, we find that the architecture of the classification head substantially influences performance, freezing the FM encoder achieves comparable results to full fine-tuning, and advanced aggregation methods outperform standard federated averaging. Our results offer practical insights for deploying FMs in decentralized clinical settings and highlight trade-offs that should guide future method development.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。