Introduction

Alzheimer’s disease (AD) is a slow fatal neurodegenerative disease affecting people over the age of 65 years [1], while early-onset AD is also diagnosed before 65. The deposition of two abnormal protein fragments known as plagues and tangles in the brain causes the death of neuron cells. The hippocampus, where the memories are first formed, is the initially affected region by AD, and thus early symptoms of AD include memory problems resulting difficulties in word finding and thinking processes [2]. AD patients suffer from a lack of initiative, changes in personality or behavior in day-to-day functions at home, or at work, and in taking care of oneself, eventually, leading to death. The brain volume reduces dramatically through time and affects most of its functions with the progression of AD. With the increase in the population of elderly people in developed countries, AD is going to be a major problem in socioeconomic implications. According to the recent report [3], it is expected that the number of affected people will be doubled in the next 20 years and one in two aged above 85 years will suffer from AD by 2050. Thus, accurate diagnosis of AD is very important, especially, at its early stage. Conventionally, the diagnosis of AD is performed by a neuropsychological examination in support of structural imaging. It is reported in [4] that (1) in the early stage of AD, degeneration of neurons takes place in the medial temporal lobe, (2) gradually affecting the entorhinal cortex, the hippocampus, and the limbic system, and (3) neocortical areas are affected at the final stage. Therefore, the study of medial temporal lobe atrophy (MTA), particularly in the hippocampus, the entorhinal cortex, and the amygdala provides the evidence of the progression of AD. Generally, MTA is measured in terms of voxel-based [5], vertex-based [6], and ROI-based [7] approaches. However, as the disease progresses, other regions in the brain are also affected. In such cases, whole-brain methods are preferred rather than a specific region-based method; then, the characterization of brain atrophy for differentiating AD and MCI patients can be performed more efficiently.