Title: Harmonizing neuroimaging data acquired under complex study designs
Authors: Russell Shinohara - University of Pennsylvania (United States) [presenting]
Abstract: As multi-center studies in imaging science become increasingly commonplace, there is a need for understanding and mitigating biases associated with the acquisition on multiple scanners. We will review the state-of-the-art in image harmonization, and explore harmonization in new settings such as longitudinal study designs and complex covariance structures in imaging features. We will conclude with a discussion of future directions and areas for improvement in study design and analysis.