A data-driven spatially adaptive sparse generalized linear model for functional MRI analysis

A novel data-driven sparse generalized linear model (GLM) and statistical analysis method for fMRI is developed. Although independent component analysis (ICA) has been broadly applied to fMRI to separate spatially or temporally independent components, recent studies show that ICA does not guarantee...

Full description

Saved in:
Bibliographic Details
Published in2011 IEEE International Symposium on Biomedical Imaging: From Nano to Macro pp. 1027 - 1030
Main Authors Kangjoo Lee, Sungho Tak, Jong Chul Ye
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.03.2011
Subjects
Algorithm design and analysis
Brain modeling
compressed sensing
Correlation
data-driven fMRI analysis
Dictionaries
Encoding
Independent component analysis
K-SVD
sparse dictionary learning
Sparse GLM
Sparse matrices
Online AccessGet full text

Cover

More Information
Summary:A novel data-driven sparse generalized linear model (GLM) and statistical analysis method for fMRI is developed. Although independent component analysis (ICA) has been broadly applied to fMRI to separate spatially or temporally independent components, recent studies show that ICA does not guarantee independence of simultaneously occurred distinct activity patterns in the brain and sparsity of the signal has been shown to be more important. Motivated from the ICA and biological findings such as sparse coding in the primary visual cortex simple cells, we propose a compressed sensing based data-driven sparse GLM solely based upon the sparsity of the signal. It enables estimation of spatially adaptive design matrix from sparse signal components that represent synchronous neural hemodynamics. Furthermore, an MDL based model order selection rule can determine unknown sparsity for sparse dictionary learning.
ISBN:1424441277
9781424441273
ISSN:1945-7928
1945-8452
DOI:10.1109/ISBI.2011.5872576