Detection of Local Cortical Asymmetry via Discriminant Power Analysis

Introduction: We present a discriminant power analysis framework that can be used in localizing the abnormal cortical thickness asymmetry pattern in a clinical group compared with a control group. In our example, we show that a group of high functioning autistic subjects has a cortical thickness asymmetry pattern that differs reliably from controls. Unlike previous literature, our approach does not require any preselected feature vectors and performs the classification at each mesh vertex.