A New Approach for Separation of Functional MRI Images´ Components Using Modified FastICA Algorithm

Author

Larijani, Houtan Haddad ; Rad, Gholamali Rezai

Author_Institution

Electr. Eng. Dept., Iran Univ. of Sci. & Technol., Tehran

fYear

2008

fDate

9-11 July 2008

Firstpage

83

Lastpage

87

Abstract

This paper proposes a new approach for separation of components in functional MRI sequences using FastICA. In this paper we will demonstrate that if we subtract background (which is separated from sources by PCA) from other principal components, the algorithm converges very fast. The proposed method is more robust and much more computationally efficient than methods, which previously has been applied for separation of components in functional MRI sequences.

Keywords

biomedical MRI; independent component analysis; medical image processing; principal component analysis; PCA; algorithm convergence; background sutraction; functional MRI image component separation; modified FastICA algorithm; principal component; Biomedical imaging; Biomedical informatics; Convergence; Image converters; Independent component analysis; Magnetic resonance imaging; Principal component analysis; Robustness; Signal processing algorithms; Visualization; Biomedical Image Processing; Independent Component Analysis; Principal Component Analysis; functional MRI;

fLanguage

English

Publisher

ieee

Conference_Titel

BioMedical Visualization, 2008. MEDIVIS '08. Fifth International Conference

Conference_Location

London

Print_ISBN

978-0-7695-3284-4

Type

conf

DOI

10.1109/MediVis.2008.8

Filename

4618618