Classification of Alzheimer’s Disease Based on White Matter Architecture

Alzheimers disease is the most common form of dementia in adults aged 65 or older. Although many studies have measured the effect of tissue degeneration for subcortical structures such as the hippocampi, amygdala, and the ventricles, little is known about the changes that occur in the architecture of the white matter during the course of this disease. The shape and properties of white-matter structures can be measured using Diffusion Tensor Imaging (DTI), a relatively new neuroimaging technique. Differences in these structures have been shown to be related to behavior, cognition, and neurological diseases [3]. In this project, we use machine learning tools to classify Alzheimer’s patients and normal controls based on the architectural attributes of white matter tracts. The results are promising and demonstrate that the shape of white matter structures is useful in the quest to better understand the biomarkers and neural correlates of this disease.