Zhang Zuozhen, Zhang Ziqi, Ji Junzhong, Liu Jinduo
The Beijing Municipal Key Laboratory of Multimedia and Intelligent Software Technology, Beijing Institute of Artificial Intelligence, Faculty of Information Technology, Beijing University of Technology, Beijing 100124, China.
Brain Sci. 2023 Jun 25;13(7):995. doi: 10.3390/brainsci13070995.
Using machine learning methods to estimate brain effective connectivity networks from functional magnetic resonance imaging (fMRI) data has garnered significant attention in the fields of neuroinformatics and bioinformatics. However, existing methods usually require retraining the model for each subject, which ignores the knowledge shared across subjects. In this paper, we propose a novel framework for estimating effective connectivity based on an amortization transformer, named AT-EC. In detail, AT-EC first employs an amortization transformer to model the dynamics of fMRI time series and infer brain effective connectivity across different subjects, which can train an amortized model that leverages the shared knowledge from different subjects. Then, an assisted learning mechanism based on functional connectivity is designed to assist the estimation of the brain effective connectivity network. Experimental results on both simulated and real-world data demonstrate the efficacy of our method.
使用机器学习方法从功能磁共振成像（fMRI）数据中估计大脑有效连接网络在神经信息学和生物信息学领域引起了广泛关注。然而，现有方法通常需要为每个受试者重新训练模型，这忽略了不同受试者之间共享的知识。在本文中，我们提出了一种基于摊销变压器估计有效连接的新框架，称为AT-EC。具体来说，AT-EC首先使用摊销变压器对fMRI时间序列的动态进行建模，并推断不同受试者之间的大脑有效连接，这可以训练一个利用不同受试者共享知识的摊销模型。然后，设计了一种基于功能连接的辅助学习机制，以协助大脑有效连接网络的估计。在模拟和真实数据上的实验结果证明了我们方法的有效性。
