DTI Connectivity by Segmentation


This paper proposes a new method to compute connectivity information from diffusion weighted images. It is inspired by graph-based approaches to connectivity definition, but formulates the estimation problem in the continuum. In particular, it defines the connectivity through the minimum cut in tensor-weighted space. It is therefore closely related to prior work on segmentation using continuous versions of graph cuts. A numerical solution based on a staggered grid is proposed which allows for the computation of flux directly through diffusion tensors. The resulting global connectivity measure is the maximum diffusive flow supported between two regions of interest.

Medical Imaging and Augmented Reality - 5th International Workshop, MIAR 2010, Beijing, China, September 19-20, 2010. Proceedings
Marc Niethammer
Marc Niethammer
Professor of Computer Science

My research interests include image registration, image segmentation, shape analysis, machine learning, and biomedical applications.