fMRI动态功能网络构建及其在脑部疾病识别中的应用  

Building of fMRI Dynamic Functional Connectivity Network and its Applications in Brain Diseases Identification

作　　者：马士林[1] 梅雪[1] 李微微[1] 周宇[1] MA Shi-lin MEI Xue LI Wei-wei ZHOU Yu(College of Electrical Engineering and Control Science, Naniing Tech University, Naniing 211816, China)

机构地区：[1]南京工业大学电气工程与控制科学学院,南京211816

出　　处：《计算机科学》2016年第10期317-321,共5页Computer Science

基　　金：江苏省普通高校研究生创新计划项目(KYLX_0754);2015年江苏省六大人才高峰项目(XXRJ-012)资助

摘　　要：如何从复杂的fMRI数据中提取丰富的大脑信息是提高脑部疾病识别精度的关键。传统的静息态功能磁共振成像分析中,功能连接网络被认为是稳定不变的。提出一种基于成组独立成分分析的构建动态功能连接网络的方法,并通过该网络来获取功能网络本身的动态特性。首先,利用成组独立成分分析法提取fMRI数据的空间独立成分作为网络节点,并通过滑动时间窗的方法获取窗口时间序列,构建动态功能连接网络。以动态功能网络作为特征,对精神分裂症患者和正常被试数据进行分类识别。实验结果表明,该方法能够获取fMRI数据的时间维度信息,提高识别效果,在一定程度上能为临床诊断提供客观参照。The way to extract abundant information from complex fMRI data is the key to improve the accuracy net- work in identification of brain diseases. For the conventional resting-state fMRI analysis, functional connectivity is as- sumed to be temporally stationary. A method of building dynamic functional connectivity network based on group ICA was put forward to obtain the dynamic characteristics of functional connectivity network. First, the spatial independent component of fMRI data obtained from group ICA algorithm is used as the network node. And then, the dynamic func- tional connectivity is built based on sliding time windows. The dynamic functional connectivity network is used as a fea- ture to identify the healthy controls and patients with schizophrenia. Experimental results confirm that the proposed method is applicable and effective. It can obtain information of temporal dimension, improve the recognition rate at the same time, and provide an obiective referenee for clinical diagnosis.

关 键 词：功能磁共振成像 动态功能网络 成组独立成分分析 分类识别 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]