1. Introduction
Many neurodegenerative diseases have been found to come with the brain anatomical changes, for instance, Alzheimer's disease (AD) [1]. By observing the disease related structural alterations, it might help physicians to precisely diagnose patients even at the preclinical stage. Diffusion MRI (dMRI) is a powerful technique to study white matter structures such as the fiber connection that reflect axonal organization. However, its large scale tensor-valued information and relatively low imaging resolution (2–3 mm) have created huge challenges for analysis. Because of the noise and partial volume effects, there are frequent false-negative and false-positive results [2]. In recent years, there is a growing interest to take a multi-model analysis approach to improve dMRI image analysis power [3], [4]. On the other hand, in clinical settings, one would favor a single imaging score [5], which capitalizes on as much of the data in the image as possible. Naturally, a stable method to compute a single imaging index by integrating features from both sMRI and dMRI would be highly advantageous to this research field.