The Fred Hutch Biostatistics Program hosts regular seminars featuring presentation by Fred Hutch and outside scientists to share their latest developments and recent research. Each seminar includes an hour-long presentation and discussion during which speakers showcase their work and findings.
Brains differ in size, shape, and function. However, population analyses of brain images have been usually performed following a spatial normalization step. This is the process of deforming the individuals' brain scans to a common template image. Therefore, size and shape are usually treated as nuisance variables. In this talk, I will introduce a comprehensive framework for the analysis of images whose domain is subject to variability from sample to sample. The proposed framework enables a joint representation of the geometric and functional aspects of the data. We apply the proposed model to the analysis of imaging data of cortical thickness, acquired from the brains of different subjects, and thus lying on domains with different geometries.