White Matter Mapping in DT-MRI Using Geometric Flows
We present a 3D geometric flow designed to evolve in Diffusion Tensor Magnetic Resonance Images(DT-MRI) along fiber tracts by measuring the diffusive similarity between voxels. Therefore we define a front propagation speed that is proportional to the similarity between the tensors lying on the surface and its neighbor in the propagation direction. The method is based on the assumption that successive voxels in a tract have similar diffusion properties. The front propagation is implemented using level set methods by Osher and Sethian  to simplify the handling of topology changes and provides an elegant tool for smoothing the segmented tracts. While many methods demand a regularized tensor field, our geometrical flow performs a regularization as it evolves along the fibers. This is done by a curvature dependent smoothing term adapted for thin tubular structures. The purpose of our approach is to get a quantitative measure of the diffusion in segmented fiber tracts. This kind of information can also be used for white matter registration and for surgical planning.