Abstract:
Neuroimaging and full genome sequencing in large samples promise to reveal subtle genetic and disease effects in the brain. Computational problems in imaging genetics arise from persistent themes in brain image analysis: high dimensionality and heterogeneity of the data, complex spatial processes, and great variety of imaging modalities. A variety of mathematical and statistical learning tools have been used in imaging over the years to solve these problems. In this talk, I will present some of the proposed solutions, including applications from continuum mechanics, differential geometry and shape spaces, and network analysis.
