Age-Agnostic, Unsupervised Segmentation of Infant Brains using Magnetic Resonance Fingerprinting

Brain segmentation is challenging in infants, as rapid changes to tissue properties and shapes during developmental growth make atlas-based modeling difficult. We use MRF-derived image features and density-based clustering to segment 2D brain slices from subjects without assumptions about subject age, brain shape, or image intensity. Segmentations from the proposed method closely match SPM without needing different atlases for subjects of varying ages. With flexible assumptions about the number of tissues present in an image, the proposed method identifies additional tissues such as CSF partial volume voxels and neonatal myelination that are not segmented by atlas-based approaches.