Rajesh Ranjan Nandy1, Brad Mcevoy2
1Psychology and Biostatistics, University of California, Los Angeles, CA, USA; 2University of California, USA
In recent times, Bayesian approaches have been increasingly popular in fMRI data analysis due to its easy interpretability and its ability to incorporate anatomical information or other expert knowledge into the model. In a classical framework this can be achieved only with segmentation or a region of interest (ROI) based approach, which is too restrictive. One popular Bayesian approach that does not suffer from the problems of the classical approach is the spatial Bayesian variable selection (SBVS) framework introduced by Smith which can only be applied to single subject analysis. Here we modify and extend SBVS to fMRI group analysis. Furthermore, this model can account for anatomical heterogeneity across subjects.