AI 中文总结
本研究提出一种实用联邦学习框架，通过Tailscale保障通信安全，采用Flower框架实现聚合，评估轻量型MobileNet系列架构，得出基于MNv4-Conv-S的全局模型在口腔癌筛查中AUC达0.929、准确率87%的最优结果。
AI 中文摘要
数据是构建稳健AI模型的基石。然而在医疗领域，可靠数据的获取受到监管要求和患者隐私的限制，临床口腔图像尤其难以获得。联邦学习（FL）通过在不集中或共享患者数据的情况下，支持跨分散式数据集的协作式模型开发，缓解了这些限制。本研究提出了一种实用的联邦学习框架，支持AI医疗研究人员之间的地理分布式协作，并助力开发用于口腔癌筛查的稳健模型。客户端设备通过Tailscale互连，以提供安全的网络和实时通信。我们使用Flower框架实现联邦学习工作流用于服务器端聚合，而客户端部署与编排则手动配置，未使用企业级联邦学习平台。为支持基于智能手机的筛查应用，我们评估了适用于移动设备的轻量型架构，包括MobileNetV2、MobileNetV3Large和MobileNetV4-Conv-Small（MNv4-Conv-S）。在使用FedAvg聚合的全局轻量型模型中，基于MNv4-Conv-S的全局模型（GM-V4）表现最佳，AUC达到0.929，准确率为87%。
英文摘要
Data are the cornerstone of robust AI models. However, in the medical domain, access to reliable data is constrained by regulatory requirements and patient privacy, and clinical oral images are particularly difficult to obtain. Federated learning (FL) mitigates these constraints by enabling collaborative model development across decentralized datasets without centralizing or sharing patient data. This work presents a practical FL framework that supports geographically distributed collaboration among AI healthcare researchers and facilitates the development of robust models for oral cancer screening. Client devices were interconnected via Tailscale to provide secure networking and real-time communication. We implemented the FL workflow using the Flower framework for server-side aggregation, while client deployment and orchestration were configured manually; no enterprise FL platforms were used. To support a smartphone-based screening application, we evaluated lightweight, mobile-friendly architectures including MobileNetV2, MobileNetV3Large, and MobileNetV4-Conv-Small (MNv4-Conv-S). Across the global lightweight models aggregated using FedAvg, the MNv4-Conv-S based global model (GM-V4) achieved the best performance, reaching an AUC of 0.929 and an accuracy of 87%
