Classification of Patients with Alzheimer's Disease and Healthy Subjects from MRI Brain Images Using the Existence Probability of Tissue Types.

In the current study, we examined the effectiveness of classification of patients with Alzheimer's disease (AD) and healthy subjects (HS) based on brain magnetic resonance imaging (MRI) using the existence probability of various tissue types. This method quantitatively evaluates brain structural changes between two time points using existence probabilities obtained by image segmentation of brain images into four region types: gray matter (GM), white matter (WM), cerebrospinal fluid (CSF) and background. Assuming a linear relationship between the probabilities at two points, we obtained a 4×4 matrix including16 coefficients reflecting probability changes (CPCs). We performed classification of 10 AD patients and 10 HS using CPCs as features. We tested three kinds of features, excluding the CPCs that corresponded to background: all nine CPCs, diagonal CPCs reflecting structural preservation, and six non-diagonal CPCs showing structural changes, such as atrophy. Although nine CPCs showed the best performance in terms of average accuracy (77%), the maximum accuracy was 95% when non-diagonal CPCs were used as features and images at the first and last time points were compared.