Meeting Banner
Abstract #5325

Spatial Adaptive Kernel Canonical Correlation Analysis

Zhengshi Yang1, Xiaowei Zhuang1, Tim Curran2, Richard Byrd2, Virendra Mishra1, Karthik Sreenivasan1, and Dietmar Cordes1,2

1Cleveland Clinic Lou Ruvo Center for Brain Health, LAS VEGAS, NV, United States, 2University of Colorado Boulder, CO, United States

Spatially adaptive multivariate methods were applied in fMRI activation analysis to alleviate low sensitivity in commonly used Gaussian smoothing single voxel analysis. Usually these methods require constraint to avoid the curse of high degrees of freedom. We have developed a novel spatially adaptive kernel canonical correlation analysis method, which does not require constraint and has superior performance compared to other methods.

This abstract and the presentation materials are available to members only; a login is required.

Join Here