A study on the predictive strength of fractal dimension of white and grey matter on MRI images in Alzheimer’s disease

Abstract Many recent studies have shown that Fractal Dimension (FD), a ratio for figuring out the complexity of system given its measurements, can be used as an useful index to provide information about certain brain disease. Our research focuses on Alzheimer’s disease changes in white and grey matters detected through FD indexes their contours. Data this study were obtained from Disease (AD) Neuroimaging Initiative database (Normal Condition, N = 57, Disease, 60). After standard preprocessing pipeline, matter 3D are computed two groups. A statistical analysis shows only able differentiate healthy AD subjects. Although do not, it is remarkable presence enhance separation capability previous ones. In order valuate classification these subjects, we define several Neural Networks models. The performances models vary according reach best when each input changed into sequence 2D (a subset of) horizontal slices volumes.