Abstract
Abstract Alzheimer’s disease (AD) is a progressive neurodegenerative brain disorder that primarily affects elderly individuals. Mild cognitive impairment (MCI) represents an intermediate stage between normal cognitive functioning and the onset of AD. During this transition state, various subanatomic structures of the brain, including fornix, undergo pathological changes. In this study, an attempt has been made to analyse the structural variations in the fornix region of MCI and AD using invariant moments. For this purpose, T1- weighted brain structural magnetic resonance (sMR) images are obtained from a public database. The pre-processing of the raw images is conducted in FreeSurfer, and the fornix region is segmented using the reaction-diffusion level set (RDLS) method. Further, seven Hu’s invariant moments are extracted from the segmented fornix region, and statistical analysis is carried out using student t-test and Wilcoxon’s rank sum test to identify the significant features that could differentiate between the MCI and AD conditions. The results demonstrate that the combination of FreeSurfer and RDLS technique effectively pre-processes the brain sMR images and accurately delineates the fornix region. Statistical results revealed that six out of seven invariant moments are significant (p<0.001). It is observed that the mean values of all the moments in MCI are lower than AD, suggesting a higher degree of structural variation in AD compared to MCI. Considering the potential of fornix alterations in predicting the early stages of AD, the proposed approach holds considerable clinical relevance for further investigation.
Published Version
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call