A pointwise correspondence based DT-MRI fiber similarity measure

Diffusion Tensor Magnetic Resonance Imaging (DTI) fiber tractography is a way to reconstruct fiber tracts underlying data according to local anisotropic diffusion characteristics. Reliability of fiber tracts as a result of tractography decreases due to noise in the data, error accumulation during integration and stochastic nature of the underlying data. We proposed a new similarity measure based on point-wise correspondence between tracts. Laplacian Eigenmaps are used to embed the fiber tracts into ℜ(3) based on the new similarity measure. We compared our method with a previously proposed method, on real and phantom data, that uses a 9D feature space to measure fiber similarity and showed that the new similarity measure results in a low dimensional manifold representing the fiber bundles. We presented preliminary results demonstrating that the fibers that fall far from this manifold correspond to outliers.