Title :
A modified maximum correlation modeling method for fMRI brain mapping; application for detecting dyslexia
Author :
Ji, Soo-Yeon ; Najarian, Kayvan
Author_Institution :
Dept. of Comput. Sci., Virginia Commonwealth Univ., Richmond, CA
Abstract :
Functional magnetic resonance imaging (fMRI) is one of technologies that have proved to be helpful in studying the brain functions. In this paper, we have designed a hierarchical method that applies an optimization algorithm based on modified maximum correlation model (MCM) that can detect small variations across the two study groups. Based on the proposed method, we also hypothesize that dyslexia might represent fMRI brain signal activities in specific regions of the brain that are distinguishable from healthy brain fMRIpsilas. We have successfully tested our hypothesis using the proposed method on a dataset containing the fMRI of both healthy and dyslexic subjects.
Keywords :
biomedical MRI; brain; correlation methods; medical image processing; neurophysiology; optimisation; signal detection; time series; dyslexia detection; fMRI brain mapping; functional magnetic resonance imaging; maximum correlation modeling method; optimization algorithm; time series; Brain mapping; Brain modeling; Distortion; Filtering; Hemodynamics; Image analysis; Pattern analysis; Scanning probe microscopy; Signal processing; Testing; Dyslexia; Maximum Correlation Model (MCM); Statistical Parametric Mapping (SPM); fMRI time series;
Conference_Titel :
Bioinformatics and Biomeidcine Workshops, 2008. BIBMW 2008. IEEE International Conference on
Conference_Location :
Philadelphia, PA
Print_ISBN :
978-1-4244-2890-8
DOI :
10.1109/BIBMW.2008.4686210