| Summary: | Thesis (S.M.)--Massachusetts Institute of Technology, Dept. of Electrical Engineering and Computer Science, 2012. === Cataloged from PDF version of thesis. === Includes bibliographical references (p. 41-44). === Automatic segmentation of spinal nerve bundles originating within the dural sac and exiting the spinal canal is important for diagnosis and surgical planning. The variability in intensity, contrast, shape and direction of nerves seen in high resolution myelographic MR images makes segmentation a challenging task. In this thesis, we present an automatic tracking method for segmentation of nerve bundles based on particle filters. We develop a novel approach to flexible particle representation of tubular structures based on Bezier splines. We construct an appropriate dynamics to reflect the continuity and smoothness properties of real nerve bundles. Moreover, we introduce a robust image likelihood model that enables delineation of nerve bundles and ganglia from the surrounding anatomical structures. We evaluate the results by comparing them to expert manual segmentation, and we demonstrate accurate and fast nerve tracking. === by Adrian Vasile Dalca. === S.M.
|
|---|
