Automated brain tractography segmentation using curvature points

Classification of brain fiber tracts is an important problem in brain tractography analysis. We propose a supervised algorithm which learns features for anatomically meaningful fiber clusters, from labeled DTI white matter data. The classification is performed at two levels: a) Grey vs White matter (macro level) and b) White matter clusters (micro level). Our approach focuses on high curvature points in the fiber tracts, which embodies the unique characteristics of the respective classes. Any test fiber is classified into one of these learned classes by comparing proximity using the learned curvature-point model (for micro level) and with a neural network classifier (at macro level). The proposed algorithm has been validated with brain DTI data for three subjects containing about 2,50,000 fibers per subject, and is shown to yield high classification accuracy (> 93%) at both macro and micro levels.