Joint Segmentation and Registration for Infant Brain Images

The first year of life is the most dynamic and perhaps the most critical phase of postnatal brain development. The ability to accurately characterize structure changes is very critical in early brain development studies, which highly relies on the performance of image segmentation and registration techniques. However, either infant image segmentation or registration, if deployed independently, encounters much more challenges than the adult brains due to dynamic appearance change with rapid brain development. Fortunately, image segmentation and registration of infant images can assist each other to overcome the above difficulties by harnessing the growth trajectories (temporal correspondences) learned from a large set of training subjects with complete longitudinal data. To this end, we propose a joint segmentation and registration algorithm for infant brain images. Promising segmentation and registration results have been achieved for infant brain MR images aged from 2-week-old to 1-year-old, indicating the applicability of our joint segmentation and registration method in early brain development studies.