Enhancing diffusion MRI measures by integrating grey and white matter morphometry with hyperbolic wasserstein distance

In order to improve the preclinical diagnose of Alzheimer's disease (AD), there is a great deal of interest in analyzing the AD related brain structural changes with magnetic resonance image (MRI) analyses. As the major features, variation of the structural connectivity and the cortical surface morphometry provide different views of structural changes to determine whether AD is present on presymptomatic patients. However, the large scale tensor-valued information and relatively low imaging resolution in diffusion MRI (dMRI) have created huge challenges for analysis. In this paper, we propose a novel framework that improves dMRI analysis power by fusing cortical surface morphometry features from structural MRI (sMRI). We first compute the hyperbolic harmonic maps between cortical surfaces with the landmark constraints thus to precisely evaluate surface tensor-based morphometry. Meanwhile, the graph-based analysis of structural connectivity derived from dMRI is conducted. Next, we fuse these two features via the optimal mass transportation (OMT) and eventually the Wasserstein distance (WD) based single image index is computed as a potential clinical multimodality imaging score. We apply our framework to brain images of 20 AD patients and 20 matched healthy controls, randomly chosen from the Alzheimer's Disease Neuroimaging Initiative (ADNI2) dataset. Our preliminary experimental results of group classification outperformed those of some other single dMRI-based features, such as regional hippocampal volume, mean scores of fractional anisotropy (FA) and mean axial (MD). The novel image fusion pipeline and simple imaging score of structural changes may benefit the preclinical AD and AD prevention research.

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.