Identification of brain white matter regions for diagnosis of Alzheimer using Diffusion Tensor Imaging

Abstract

Diffusion Tensor Imaging (DTI) technique is widely used to probe the white matter (WM) tracts, which is affected most by neurological disorders. The fractional anisotropy (FA) metric has been used predominantly to study changes in the WM tracts. Here an attempt is made to delineate specific regions of interest in the WM that may be probable indicators for the diagnosis of Alzheimer disease (AD). Genetic algorithm has been used as feature reduction method along with Adaptive Boosting (AdaBoost) machine learning technique to determine the most prominent regions in the WM that are indicators of AD. It is found in this study that Fornix region of WM is most affected by Alzheimer. Further, classification was done to differentiate between Alzheimer and Normal controls with accuracy of 84.5%. The results obtained were validated by comparing with the existing literature on Alzheimer.