Alzheimer Classification Using a Minimum Spanning Tree of High-Order Functional Network on fMRI Dataset.
Alzheimer Classification Using a Minimum Spanning Tree of High-Order Functional Network on fMRI Dataset.
复制标题
在 fMRI 数据集上使用高阶功能网络的最小生成树进行阿尔茨海默病分类
DOI：
10.3389/fnins.2017.00639
复制
发表时间：
2017
影响因子：
4.3
通讯作者：
Jie X
中科院分区：
文献类型：
--
作者：
Guo H;Liu L;Chen J;Xu Y;Jie X
功能磁共振成像（fMRI）是生成大脑功能连接网络的最有用的方法之一。然而，传统的网络生成方法忽略了脑区域间功能连通性的动态变化。已有研究提出构建考虑功能连通性时变特征的高阶功能连通性网络，并采用聚类方法降低计算成本。然而，随机选择初始聚类中心和聚类数量会对分类精度产生负面影响，并且网络失去神经学上的可解释性。本文提出了一种将最小生成树方法引入到高阶功能连通网络中的新方法。作为一种无偏方法，最小生成树在保留高阶网络核心框架的同时，简化了网络结构。该方法不丢失时间序列的动态特性，保证了网络的神经学解释。同时，我们提出了一个从最小生成树高阶功能连接网络中提取判别特征的多参数优化框架。与传统方法相比，基于最小生成树高阶功能连接网络的静息状态fMRI分类方法大大提高了对阿尔茨海默病的诊断准确率。
Functional magnetic resonance imaging (fMRI) is one of the most useful methods to generate functional connectivity networks of the brain. However, conventional network generation methods ignore dynamic changes of functional connectivity between brain regions. Previous studies proposed constructing high-order functional connectivity networks that consider the time-varying characteristics of functional connectivity, and a clustering method was performed to decrease computational cost. However, random selection of the initial clustering centers and the number of clusters negatively affected classification accuracy, and the network lost neurological interpretability. Here we propose a novel method that introduces the minimum spanning tree method to high-order functional connectivity networks. As an unbiased method, the minimum spanning tree simplifies high-order network structure while preserving its core framework. The dynamic characteristics of time series are not lost with this approach, and the neurological interpretation of the network is guaranteed. Simultaneously, we propose a multi-parameter optimization framework that involves extracting discriminative features from the minimum spanning tree high-order functional connectivity networks. Compared with the conventional methods, our resting-state fMRI classification method based on minimum spanning tree high-order functional connectivity networks greatly improved the diagnostic accuracy for Alzheimer's disease.
登录
查看更多内容
影响因子：
5.3
作者：
Achard, S;Salvador, R;Bullmore, ET
通讯作者：
Bullmore, ET
影响因子：
4.8
作者：
Chen X;Zhang H;Gao Y;Wee CY;Li G;Shen D;Alzheimer's Disease Neuroimaging Initiative
通讯作者：
Alzheimer's Disease Neuroimaging Initiative
DOI：
10.1093/brain/aww083
发表时间：
2016-07
期刊：
Brain : a journal of neurology
影响因子：
--
作者：
Aggleton JP;Pralus A;Nelson AJ;Hornberger M
通讯作者：
Hornberger M
影响因子：
3.7
作者：
Allen, Elena A.;Damaraju, Eswar;Calhoun, Vince D.
通讯作者：
Calhoun, Vince D.
影响因子：
4.7
作者：
Khazaee, Ali;Ebrahimzadeh, Ata;Babajani-Feremi, Abbas
通讯作者：
Babajani-Feremi, Abbas