2 Hits in 2.2 sec

Functional Segmentation of fMRI Data Using Adaptive Non-negative Sparse PCA (ANSPCA) [chapter]

Bernard Ng, Rafeef Abugharbieh, Martin J. McKeown
2009 Lecture Notes in Computer Science  
In addition, our method adaptively combines PCA and replicator dynamics, which we show to be equivalent to non-negative sparse PCA, based on the sparsity of the activation pattern.  ...  We propose a novel method for functional segmentation of fMRI data that incorporates multiple functional attributes such as activation effects and functional connectivity, under a single framework.  ...  We thus refer to this method as adaptive non-negative sparse PCA (ANSPCA).  ... 
doi:10.1007/978-3-642-04271-3_60 fatcat:fhz4dsphrndzrhz777fmnrrvba

Prior-informed multivariate models for functional magnetic resonance imaging

Bernard Ng
In particular, functional magnetic resonance imaging (fMRI) has become one of the dominant means for studying brain activity in healthy and diseased subjects.  ...  On both synthetic and real data, we showed that exploitation of prior information enables more sensitive activation detection, more refined ROI characterization, more robust functional connectivity analysis  ...  Our other related contributions that are not discussed in this chapter include a new sparse multivariate method that we refer to as "adaptive non-negative sparse PCA" (ANSPCA) [P2] for incorporating functional  ... 
doi:10.14288/1.0072231 fatcat:bhujl6xw5rh7pat2qehqhug6ty