Graph based MRI analysis for evaluating the prognostic relevance of longitudinal brain atrophy estimation in post-traumatic diffuse axonal injury

The brain volume is a biomarker for neurodegenerative diseases therefore quantitative measurement of change in brain size and shape (e. g., to estimate atrophy) is an important current area of research. New methods of change detection are proposed in an attempt to improve accuracy, robustness, and level of automation. In this work a new strategy for estimating the prognostic relevance of longitudinal brain atrophy in post-traumatic diffuse axonal injury is presented. A key point in the strategy is the correlation of the changes in the brain volume and the patient response to neuropsychological assessment; an accurate and robust brain segmentation method is required. In this work a graph-based segmentation framework is adopted within the overall procedure to extract the volume changes of White Matter (WM), Gray Matter (GM) and CSF Cerebral Spinal Fluid (CSF).