Statistical Methods for Segmentation
Multiple sclerosis (MS) is an inflammatory disease of the brain and spinal cord characterized by demyelinating lesions that are visible in the white matter of the brain MRI. Quantitative analyses of MRI, such as the number and volume of lesions, and the evolution of these lesions over time, are essential for evaluating disease-modifying therapies and monitoring disease progression. Consequently, much work has centered on automatic cross-sectional segmentation of MRIs of patients with MS. Our group works on statistical approaches for cross-sectional and longitudinal segmentation. We are also interested more broadly in statistical methods for segmentation and other biomedical image segmentation problems.