Liu Chun, Shan Shengchang, Ding Xinshun, Wang Huan, Jiao Zhuqing
School of Safety Science and Engineering, Changzhou University, 213164, China; CI Xbot School, Changzhou University, 213164, China.
Wangzheng School of Microelectronics, Changzhou University, 213164, China.
Comput Med Imaging Graph. 2025 Sep;124:102612. doi: 10.1016/j.compmedimag.2025.102612. Epub 2025 Aug 9.
The vast amount of healthcare data is characterized by its diversity, dynamic nature, and large scale. It is a challenge that directly training a Graph Convolutional Neural Network (GCN) in a multi-site dataset poses to protecting the privacy of Major Depressive Disorder (MDD) patients. Federated learning enables the training of a global model without the need to share data. However, some previous methods overlook the potential value of non-image information, such as gender, age, education years, and site information. Multi-site datasets often exhibit the problem of Non-Independent and Identically Distributed (Non-IID) data, which leads to the loss of edge information across local models, ultimately weakening the generalization ability of the federated learning models. Accordingly, we propose a Federated Graph Convolutional Network framework with Dual Graph Attention Network (FGDN) for multi-site MDD diagnosis. Specifically, both linear and nonlinear information are extracted from the functional connectivity matrix via different correlation measures. A Dual Graph Attention Network (DGAT) module is designed to capture complementary information between these two types. Then a Federated Graph Convolutional Network (FedGCN) module is introduced to address the issue of missing edge information across local models. It allows each local model to receive aggregated feature information from neighboring nodes of other local models. Additionally, the privacy of patients is protected with fully homomorphic encryption. The experimental results demonstrate that FGDN achieves a classification accuracy of 61.8% on 841 subjects from three different sites, and outperforms some recent centralized learning frameworks and federated learning frameworks. This proves it fully mines the feature information in brain functional connectivity, alleviates the information loss caused by Non-IID data, and secures the healthcare data.
大量的医疗保健数据具有多样性、动态性和大规模的特点。在多站点数据集中直接训练图卷积神经网络（GCN）对保护重度抑郁症（MDD）患者的隐私构成了挑战。联邦学习能够在无需共享数据的情况下训练全局模型。然而，一些先前的方法忽略了非图像信息（如性别、年龄、受教育年限和站点信息）的潜在价值。多站点数据集常常存在非独立同分布（Non-IID）数据的问题，这会导致局部模型之间的边缘信息丢失，最终削弱联邦学习模型的泛化能力。因此，我们提出了一种用于多站点MDD诊断的带有双图注意力网络的联邦图卷积网络框架（FGDN）。具体而言，通过不同的相关性度量从功能连接矩阵中提取线性和非线性信息。设计了一个双图注意力网络（DGAT）模块来捕捉这两种类型信息之间的互补信息。然后引入一个联邦图卷积网络（FedGCN）模块来解决局部模型之间边缘信息缺失的问题。它允许每个局部模型接收来自其他局部模型相邻节点的聚合特征信息。此外，使用全同态加密来保护患者的隐私。实验结果表明，FGDN在来自三个不同站点的841名受试者上实现了61.8%的分类准确率，并且优于一些近期的集中学习框架和联邦学习框架。这证明它充分挖掘了脑功能连接中的特征信息，减轻了由非IID数据导致的信息损失，并保障了医疗保健数据的安全。
