Classifying Early and Late Mild Cognitive Impairment Stages of Alzheimer’s Disease by Analyzing Different Brain Areas

Abstract

Early detection of the stage of mild cognitive impairment (MCI) is very important for early diagnosis of dementia and slowing down the progression of Alzheimer’s disease. Atrophy values obtained by magnetic resonance imaging (MRI), one of the neuroimaging techniques, are considered to be a fairly powerful diagnostic biomarker used in the detection of Alzheimer. Since the transition from early mild cognitive impairment (EMCI) to late mild cognitive impairment (LMCI) is irreversible and implies a significant change in a patient’s condition, we focus on to the classification of these two stages in this work. In this study, atrophy values of 13 brain areas of 90 early mild cognitive impairment, 38 late mild cognitive impairment, 14 mild cognitive impairment participants were used in the diagnosis of the disease. Diagnosis groups have been classified with an accuracy of 68.8% as a result of data estimations obtained using classification algorithms. When the classification has been made only by taking effective values, an accuracy rate of 75% has been achieved and this means a significative improvement. The deep analysis of the disease and the focusing on the brain regions where it has more impact in order to distinguish the stages early, show the potential of utilizing MRI features to improve cognitive assessment.