Wang Haishuai, Jing Hezi, Yang Jianjun, Liu Chao, Hu Liwei, Tao Guangyu, Zhao Ziping, Shen Ning
College of Computer Science, Zhejiang University, Hangzhou, China.
College of Computer Science, Tianjin Normal University, Tianjin, China.
Npj Ment Health Res. 2024 May 2;3(1):15. doi: 10.1038/s44184-023-00050-x.
The application of deep learning models to precision medical diagnosis often requires the aggregation of large amounts of medical data to effectively train high-quality models. However, data privacy protection mechanisms make it difficult to perform medical data collection from different medical institutions. In autism spectrum disorder (ASD) diagnosis, automatic diagnosis using multimodal information from heterogeneous data has not yet achieved satisfactory performance. To address the privacy preservation issue as well as to improve ASD diagnosis, we propose a deep learning framework using multimodal feature fusion and hypergraph neural networks for disease prediction in federated learning (FedHNN). By introducing the federated learning strategy, each local model is trained and computed independently in a distributed manner without data sharing, allowing rapid scaling of medical datasets to achieve robust and scalable deep learning predictive models. To further improve the performance with privacy preservation, we improve the hypergraph model for multimodal fusion to make it suitable for autism spectrum disorder (ASD) diagnosis tasks by capturing the complementarity and correlation between modalities through a hypergraph fusion strategy. The results demonstrate that our proposed federated learning-based prediction model is superior to all local models and outperforms other deep learning models. Overall, our proposed FedHNN has good results in the work of using multi-site data to improve the performance of ASD identification.
深度学习模型在精准医学诊断中的应用通常需要聚合大量医学数据，以有效训练高质量模型。然而，数据隐私保护机制使得从不同医疗机构收集医学数据变得困难。在自闭症谱系障碍（ASD）诊断中，利用来自异构数据的多模态信息进行自动诊断尚未取得令人满意的性能。为了解决隐私保护问题并改善ASD诊断，我们提出了一种深度学习框架，该框架在联邦学习（FedHNN）中使用多模态特征融合和超图神经网络进行疾病预测。通过引入联邦学习策略，每个本地模型在不共享数据的情况下以分布式方式独立训练和计算，从而能够快速扩展医学数据集，以实现强大且可扩展的深度学习预测模型。为了在保护隐私的同时进一步提高性能，我们改进了用于多模态融合的超图模型，通过超图融合策略捕捉模态之间的互补性和相关性，使其适用于自闭症谱系障碍（ASD）诊断任务。结果表明，我们提出的基于联邦学习的预测模型优于所有本地模型，并且性能优于其他深度学习模型。总体而言，我们提出的FedHNN在利用多站点数据提高ASD识别性能的工作中取得了良好的结果。
