独立变量分析及其在脑功能可视化中应用

在数据分析和信号处理领域中经常遇到的一个问题就是如何从多元数据中提取有用部分。为使计算简便,通常对原始数据作线性变换。常用的变换方法有:主分量分析,因子分析以及投影追踪法等。一种近期发展起来的线性变换方法称独立分量分析(ICA)。该方法能够从混合信号中分离出最独立的信号。本文介绍了ICA的原理、方法及其在fMRI图像中的应用。该方法有效地抑制了fMRI图像中的随机噪声及生理信号(例如,心电、呼吸等),增强了功能信号。

Independent Component Analysis and Its Application in fMRI

A common problem encountered in such disciplines as statistics, data analysis, signal processing, and neural network research, is finding a useful part from multivariate data. For computational and conceptual simplicity, such a representation is often sought as a linear transformation of the original data. Well-known linear transformation methods include, for example, principal component analysis, factor analysis, and projection pursuit. A recently developed linear transformation method is Independent Component Analysis (ICA), in which the desired representation is the one that maximized the dependence of the component. This paper describes the basic concepts, method of ICA and its application in fMRI images. With ICA,random noise and physiological interferences such as heart beats,respiration,are suppressed effectively, and functional signals of the image are enhanced.