Correlation of Diffusion Tensor Imaging Indices with MMSE Score in Alzheimer Patients: A Sub-anatomic Region Based Study on ADNI Database

Abstract

In this study, an attempt has been made to find the correlation between Diffusion Tensor Imaging (DTI) indices of White Matter (WM) regions and Mini Mental State Examination (MMSE) score of Alzheimer patients. Diffusion weighted images are obtained from the ADNI database. These are preprocessed for eddy current correction and removal of non brain tissue. Fractional Anisotropy (FA), Mean Diffusivity (MD), Radial Diffusivity (RD) and Axial Diffusivity (DA) indices are computed over significant regions (Fornix left, Splenium of corpus callosum left, Splenium of corpus callosum right, Bilateral genu of the corpus callosum) affected by AD pathology. The correlation is computed between diffusion indices of the significant regions and MMSE score using linear fit technique so as to find the relation between clinical parameters and the image features. Binary classification has been employed using SVM, Decision Stumps and Simple Logistic classifiers on the extracted DTI indices along with MMSE score to classify Alzheimer patients from healthy controls. It is observed that distinct values of DTI indices exist for the range of MMSE score. However, there is no strong correlation (r varies from 0.0383 to -0.1924) between the MMSE score and the diffusion indices over the significant regions. Further, the performance evaluation of classifiers shows 94% accuracy using SVM in differentiating AD and Control. In isolation clinical and images features can be used for pre screening and diagnosis of AD but no sub anatomic region correlation exist between these features set. The discussion on the correlation of diffusion indices of WM with MMSE score is presented in this study.