Gao Libin, Hu Zhongyi, Li Rui, Lu Xingjin, Li Zuoyong, Zhang Xiabin, Xu Shiwei
College of Computer Science and Aritificial Intelligence, Wenzhou University, Wenzhou 325035, China.
Key Laboratory of Intelligent Image Processing and Analysis, Wenzhou 325035, China.
Brain Sci. 2022 Oct 5;12(10):1348. doi: 10.3390/brainsci12101348.
Resting-state functional magnetic resonance imaging (rs-fMRI) has been used to construct functional connectivity (FC) in the brain for the diagnosis and analysis of brain disease. Current studies typically use the Pearson correlation coefficient to construct dynamic FC (dFC) networks, and then use this as a network metric to obtain the necessary features for brain disease diagnosis and analysis. This simple observational approach makes it difficult to extract potential high-level FC features from the representations, and also ignores the rich information on spatial and temporal variability in FC. In this paper, we construct the Latent Space Representation Network (LSRNet) and use two stages to train the network. In the first stage, an autoencoder is used to extract potential high-level features and inner connections in the dFC representations. In the second stage, high-level features are extracted using two perspective feature parses. Long Short-Term Memory (LSTM) networks are used to extract spatial and temporal features from the local perspective. Convolutional neural networks extract global high-level features from the global perspective. Finally, the fusion of spatial and temporal features with global high-level features is used to diagnose brain disease. In this paper, the proposed method is applied to the ANDI rs-fMRI dataset, and the classification accuracy reaches 84.6% for NC/eMCI, 95.1% for NC/AD, 80.6% for eMCI/lMCI, 84.2% for lMCI/AD and 57.3% for NC/eMCI/lMCI/AD. The experimental results show that the method has a good classification performance and provides a new approach to the diagnosis of other brain diseases.
静息态功能磁共振成像（rs-fMRI）已被用于构建大脑中的功能连接（FC），以用于脑部疾病的诊断和分析。当前的研究通常使用皮尔逊相关系数来构建动态功能连接（dFC）网络，然后将其作为网络指标来获取脑部疾病诊断和分析所需的特征。这种简单的观察方法使得难以从表征中提取潜在的高级功能连接特征，并且还忽略了功能连接中关于空间和时间变异性的丰富信息。在本文中，我们构建了潜在空间表征网络（LSRNet），并分两个阶段训练该网络。在第一阶段，使用自动编码器提取dFC表征中的潜在高级特征和内部连接。在第二阶段，使用两种视角特征解析来提取高级特征。长短期记忆（LSTM）网络用于从局部视角提取空间和时间特征。卷积神经网络从全局视角提取全局高级特征。最后，将空间和时间特征与全局高级特征融合用于脑部疾病诊断。在本文中，所提出的方法应用于ANDI rs-fMRI数据集，对于NC/eMCI的分类准确率达到84.6%，对于NC/AD为95.1%，对于eMCI/lMCI为80.6%，对于lMCI/AD为84.2%，对于NC/eMCI/lMCI/AD为57.3%。实验结果表明该方法具有良好的分类性能，并为其他脑部疾病的诊断提供了一种新方法。
