Enhancing Brain Volume Analysis Accuracy in Alzheimer's Disease: A Novel Image Registration Method Using Tsallis Entropy

The aim of this paper is to enhance the accuracy of image registration in the SPM toolbox, utilizing magnetic resonance imaging (MRI) of patients with Alzheimer’s disease (AD) and healthy individuals. Alzheimer’s disease is a progressive brain disorder that gradually impairs memory, learning abilities, reasoning, judgment, communication, and the ability to perform daily activities. It is the most common cause of dementia and a significant contributor to global mortality rates. This disease was first described in ۱۹۰۶ by Alois Alzheimer, a German psychiatrist and neuropathologist, in the brain of a patient who exhibited speech and behavioral disturbances. In recent years, extensive efforts have been made by researchers to enable early diagnosis of Alzheimer’s disease through MRI processing and the measurement of brain region volumes. One widely used tool for brain volume measurement is the SPM software. SPM estimates brain region volumes through a five-step process, one of which is image registration. The registration process in SPM is based on Shannon mutual information. However, due to inaccuracies and errors, the measured volumes may lack precision. This study aims to address the limitations of SPM by improving its registration method using Tsallis mutual information. The volumes of different brain regions were analyzed and compared in MRI scans of seven adult males with Alzheimer’s disease and seven healthy adult males. The findings demonstrate that the data derived from the proposed processing method can be effectively utilized for the diagnosis and evaluation of Alzheimer’s disease. The results indicate a significant improvement in registration accuracy with the proposed method compared to the standard SPM protocol.

کلیدواژه ها:

Alzheimer’s disease ، Rigid registration ، SPM toolbox ، Shannon entropy ، Tsallis entropy