Brain Segmentation

Neuroanatomical segmentation is a problem of extraction of a description of particular neuroanatomical structures of interest that reflects the morphometry (shape measurements) of the subject's neuroanatomy from any image rendering the neuroanatomical structures of the subject. Brain segmentation work at the NeuroInformatics center has focused on the development of a set of software tools (called BrainK) for extracting and integrating head tissue geometries from CT and / or MR images.

Fundamental algorithms in our approach include a novel relative thresholding approach, topology correction for white matter, and cortical surface reconstruction with marching a cube isosurface algorithm modified to preserve topology. The advantages of our tools are mainly attributed to extensive exploration of various structural, geometrical, morphological, and radiological a priori knowledge, which persists despite of image artifacts and inter-subject anatomical variations.