Structural complexity of brain regions in mild cognitive impairment and Alzheimer's disease

Abstract

Early detection of Alzheimer's disease (AD) is a major focus of current research efforts to guide early interventions. Subtle neural changes might be observed even before symptoms surface. We interrogated brain images obtained with Magnetic Resonance Imaging (MRI) from two large-scale dementia datasets (ADNI and BioFIND) to establish the utility of fractal dimensionality (FD)—an understudied measure that estimates the complexity of 3D structures (in this case, brain regions)—for AD detection. We show that FD measures are consistent across the two datasets, and can be used to detect group differences between patients and controls, as well as for individual-based classification. We further show that the contribution of specific brain regions to individual-based classification adheres to previous literature on the properties of the brain's memory network and how it relates to cognition. Taken together, the study offers novel and interpretable evidence for the utility of FD for the detection of AD.