Neuroimaging by MRI is one of the most active areas of research, producing a large body of descriptive results. In the conventional research model, the morphological heterogeneity of a given group is often reduced to the mean, diluting some of the individual variability. We will discuss how quantitative structure-based analysis can reduce images to a standardized and quantitative vector (or matrix) that captures features appropriately without erasing the individual variability. We will illustrate dimension reduction and integration of T1-WI, DTI, resting state fMRI, and other contrasts through multi-atlas segmentation in research and personalized medicine
This abstract and the presentation materials are available to members only; a login is required.