Analyzing global features of magnetic resonance images in widespread neurodegenerative diseases: new hope to understand brain mechanism and robust neurodegenerative disease diagnosis.

Neurodegenerative diseases are caused by progressive degeneration of the central nervous system (CNS)'s neuronal structure. Well-known diseases in this category include Alzheimer's disease (AD), Parkinson's disease (PD), and multiple sclerosis (MS), which are also addressed in this study. The CNS appears to be a complex dynamic system, whose parameters change during the disease due to neuronal damage, resulting in various symptoms. Since the change in dynamic behavior is due to the neurons' death and change in neurons' connectivity, brain images of the affected areas appear to provide a good understanding of this change. This work attempts to focus on brain magnetic resonance images (MRI) and examine the effect of neuronal loss on the images. To this end, the complex features of these images, including 2D and Higuchi's fractal dimensions (HFD), correlation dimension (CD), largest Lyapunov exponent (LLE), and approximate entropy (ApEn) were calculated. Despite small differences in numerical values (0.01-0.35), these values differ significantly. This shows that the brain dynamic system behaves and functions differently in the disease state, which is clear in the behavior of global features. These three diseases have the same functional pattern, and this study seems to have captured the roots of these seemingly variant diseases.