Brain Tractography Classification using Curvature Points

Classification of fiber tracts is an important problem in brain tractography.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 each class. A 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 is validated over brain DTI data for three subjects containing about 2,50,000 fibers per subject, and has been shown to yield high classification accuracy at both macro and micro levels.