Novel histogram-weighted cortical thickness networks and a multi-scale analysis of predictive power in Alzheimer's disease

Network analysis based on anatomical covariance (cortical thickness) has been gaining increasing popularity in the last decade. However, there has not been a systematic study of the impact of nodal sizes and edge definitions on predictive performance among various network studies. In order to obtain a clear understanding of relative performance, there is a need for systematic comparison. In this study, we present a histogram-based approach to construct weighted networks that enables a comparison across vastly different methods of network analysis. We design several weighted networks based on cortical thickness and perform a robust evaluation and comparison of their predictive power. We present several interesting insights obtained.