NON-UNIFORM SMOOTHING IN HIPPOCAMPUS-SPECIFIC GROUP FMRI ANALYSIS

A framework for generating group-level statistical maps of functional activation in the hippocampus is presented. It aims to maximize the sensitivity and specificity of hippocampal maps by using a deformable model to normalize the hippocampus across subjects and by using a non-uniform smoothing strategy to reduce the confounding effects of extrahippocampal activation. Results of applying this framework with different smoothing parameters are presented in the context of a visual scene encoding study. The significance reported by the method in the hippocampus at low levels of smoothing is greater than when whole-brain analysis is used, while at higher levels of smoothing, whole-brain analysis detects clusters of equally high significance around the hippocampus, but not directly in the hippocampus.