摘要
为了提取静息态的默认网络,降低核磁共振图像中的数据运算量,本文提出了数据降维和非线性变换的方法。首先,对核磁共振图像进行主成分分析,降低运算维度和数据复杂度。然后,对静息核磁数据进行稀疏编码学习,提取默认网络。实验结果表明,稀疏编码学习的效果优于传统的独立成分分析,且前者提取默认网络更加迅速,噪声更低。
In order to extract the default mode network（DMN） and to reduce the data complexity of the functional magnetic resonance imaging（FMRI）,a framework of dimensionality reduction and nonlinear transformation is proposed.First,the principal component analysis（PCA） is applied to reduce the time dimension of the FMRI data for simplifying complexity computation and obtaining most of the information.Secondly,modeling the resting-state FMRI data with a sparse decomposition is done to extract the DMN.Experimental results show that the sparse coding provides a better performance for the resting-state FMRI data analysis compared with the classical ICA.Furthermore,the DMN is accurately extracted and the noise is reduced.
出处
《信息化研究》
2012年第2期68-70,共3页
INFORMATIZATION RESEARCH
关键词
稀疏编码
主成分分析
功能核磁共振成像
静息态
sparse coding
principal component analysis
functional magnetic resonance imaging（FMRI）
resting-state
