A family-constrained local canonical correlation model to improve activation detection in fMRI
Xiaowei Zhuang1, Zhengshi Yang1, Tim Curran2, and Dietmar Cordes1,2
1Cleveland Clinic Lou Ruvo Center for Brain Health, Las Vegas, NV, United States, 2Department of Psychology and Neuroscience, University of Colorado Boulder, Boulder, CO, United States
A family constrained CCA (cCCA) method was
introduced to improve the accuracy of activation detection in noisy fMRI data.
The cCCA was converted into a constrained multivariate multiple regression problem and solved
efficiently with a numerical optimization algorithm. Results from both
simulated data and real episodic memory data indicated that a higher detection
sensitivity for a fixed specificity can be achieved with the proposed cCCA
method as compared to the widely used mass-univariate or other conventional
multivariate (CCA) approaches.
This abstract and the presentation materials are available to members only;
a login is required.
