基于空间约束的时间独立成分分析方法分析fMRI数据  

Analysis of Functional MRI Data Using Temporal Independent Component Analysis with Spatial Restriction

作　　者：王世杰[1] 罗立民[1] 

机构地区：[1]东南大学影像科学与技术实验室,南京210096

出　　处：《生物医学工程学杂志》2007年第6期1205-1210,共6页Journal of Biomedical Engineering

基　　金：国家重点基础研究发展计划资助项目(2003CB716102)

摘　　要：首先采用相关分析初步检测可能的功能激活区域,并以初步检测的功能激活区域作为空间约束条件,对fMRI数据进行时间模式的独立成分分析,然后利用功能实验设计时序信息,通过典型相关分析方法对独立成分排序,自动识别与功能实验设计相关的功能信号成分,最后以识别的功能信号成分作为参考函数,重新利用相关分析自适应地分析fMRI数据。通过对实际的fMRI数据分析验证了提出方法的有效性及可靠性。Functional MRI data is analyzed by using temporal independent component analysis confined to the potential activation extent which is firstly detected by using correlation analysis. Based on the prior information about the activation paradigm, the functional signal component is identified automatically by ordering the resultant independent components with canonical correlation analysis. Finally, the functional MRI data is reanalyzed adaptively by using correlation analysis with the recognized functional signal component as the reference function. The experimental results of analyzing actual functional MRI data show the validity and the reliability of the presented method.

关 键 词：功能磁共振成像 独立成分分析 典型相关分析 

分 类 号：R318[医药卫生—生物医学工程]