Diffusion weighted imaging-based maximum density path analysis and classification of Alzheimer's disease

Abstract

Characterizing brain changes in Alzheimer’s disease (AD) is important for patient prognosis, and for assessing brain deterioration in clinical trials. In this diffusion tensor imaging study, we used a new fiber-tract modeling method to investigate white matter integrity in 50 elderly controls (CTL), 113 people with mild cognitive impairment (MCI), and 37 AD patients. After clustering tractography using an ROI atlas, we used a shortest path graph search through each bundle’s fiber density map to derive maximum density paths (MDPs), which we registered across subjects. We calculated the fractional anisotropy (FA) and mean diffusivity (MD) along all MDPs and found significant MD and FA differences between AD patients and CTL subjects as well as MD differences between CTL and late MCI subjects. MD and FA were also associated with widely used clinical scores (MMSE). As an MDP is a compact, low-dimensional representation of white matter organization, we tested the utility of DTI measures along these MDPs as features for support vector machine (SVM) based classification of AD.

Feature selection improves the accuracy of classifying Alzheimer disease using diffusion tensor images

“…Images were processed as in [12]. Briefly, DWI volumes were corrected for eddy current distortions and echo-planar imaging (EPI) induced susceptibility artifacts by mapping to the high-resolution T1-weighted image.…”

“…A support vector machine (SVM) is a binary classification algorithm used widely in neuroimaging, as well as for many other classification tasks [2, 9, 11, 12]. SVM is a supervised classifier that takes into account labeled training samples to learn class differences [17, 18].…”

“…Nir et al . [12] performed a SVM based classification of AD using DTI measures interpolated along the maximum density paths based on whole-brain tractography. They obtained 74.5% accuracy for AD vs NC using FA and 80.6% using MD; of course, these results depend on the age and scan quality of the cohort assessed, and whether patients have other co-morbid conditions.…”

Magnetic resonance imaging in Alzheimer's Disease Neuroimaging Initiative 2

“…Further work used fiber tracking (tractography) to assess the integrity of the brain’s major fiber bundles. Nir et al [164] found significant differences in mean diffusivity (MD) and fractional anisotropy between AD patients and controls, as well as MD differences between people with late mild cognitive impairment [165] and matched elderly controls. MD and FA measures from selected tracts were also associated with widely used clinical scores.…”

Magnetic resonance imaging and positron emission tomography in the diagnosis of neurodegenerative dementias

“…It is generally accepted that FA reflects the structural integrity of white matter fibers with poor specificity to the type of change; axial diffusivity decreases in axonal injury and RD increases with de-or dysmyelination. In patients with AD, myelinated fiber changes, detected by an altered MD/FA ratio, have been reported repeatedly, showing predominantly posterior involvement (Nir et al, 2015). Several DTI studies have reported a reduction in FA with increased MD in the corpus callosum, posterior cingulate, superior longitudinal fasciculus and fornix.…”