Wang Lei, Zeng Weiming, Zhao Le, Shi Yuhu
Lab of Digital Image and Intelligent Computation, Shanghai Maritime University, Shanghai, China.
Appl Neuropsychol Adult. 2024 Mar 21:1-12. doi: 10.1080/23279095.2024.2330100.
Investigating the functional interactions between different brain regions and revealing the transmission of information by computing brain connectivity have great potential and significance in the diagnosis of early Mild Cognitive Impairment (EMCI).
The Granger causality with Gate Recurrent Unit (GRU_GC) model is a suitable method that allows the detection of a nonlinear causal relationship and solves the limitation of fixed time lag, which cannot be detected by the classical Granger method. The model can transmit time series signals with any transmission delay length, and the time series can be screened and learned through the gate model.
The classification experiment of 89 EMCI and 73 neurologically healthy controls (HC) shows that the accuracy reached 87.88%. Compared with multivariate variables GC (MVGC) and Long Short-Term Memory-based GC (LSTM_GC), the GRU_GC significantly improved the estimation of brain connectivity communication. Constructing a difference network to explore the brain effective connectivity between EMCI and HC.
The GRU_GC can discover the abnormal brain regions, including the parahippocampal gyrus, the posterior cingulate gyrus. The method can be used in clinical applications as an effective brain connectivity analysis tool and provides auxiliary means for the medical diagnosis of EMCI.
研究不同脑区之间的功能相互作用并通过计算脑连接性来揭示信息传递，在早期轻度认知障碍（EMCI）的诊断中具有巨大潜力和重要意义。
带有门控循环单元的格兰杰因果关系（GRU_GC）模型是一种合适的方法，它能够检测非线性因果关系并解决固定时间滞后的局限性，而经典格兰杰方法无法检测到这种局限性。该模型可以传输具有任何传输延迟长度的时间序列信号，并且时间序列可以通过门控模型进行筛选和学习。
对89名EMCI患者和73名神经健康对照（HC）进行的分类实验表明，准确率达到了87.88%。与多变量格兰杰因果关系（MVGC）和基于长短期记忆的格兰杰因果关系（LSTM_GC）相比，GRU_GC显著提高了脑连接性通信的估计。构建差异网络以探索EMCI和HC之间的脑有效连接性。
GRU_GC可以发现异常脑区，包括海马旁回、后扣带回。该方法可作为一种有效的脑连接性分析工具应用于临床，为EMCI的医学诊断提供辅助手段。
