Title :
A Robust Algorithm for Fiber-Bundle Atlas Construction
Author :
Ziyan, U. ; Sabuncu, Mert R. ; Eric, W. ; Grimson, L. ; Westin, Carl-fredrik
Author_Institution :
MIT Comput. Sci. & Artificial Intelligence Lab, Cambridge
Abstract :
In this paper, we demonstrate an integrated registration and clustering algorithm to compute an atlas of fiber- bundles from a set of multi-subject diffusion weighted MR images. We formulate a maximum likelihood problem which the proposed method solves using a generalized Expectation Maximization (EM) framework. Additionally, the algorithm employs an outlier rejection and denoising strategy to produce sharp probabilistic maps of certain bundles of interest. This map is potentially useful for making diffusion measurements in a common coordinate system to identify pathology related changes or developmental trends.
Keywords :
expectation-maximisation algorithm; image denoising; image registration; maximum likelihood estimation; clustering algorithm; denoising strategy; fiber-bundle atlas construction; generalized expectation maximization framework; maximum likelihood problem; multi-subject diffusion weighted MR images; outlier rejection; registration algorithm; sharp probabilistic maps; Anatomical structure; Clustering algorithms; Computer science; Diffusion tensor imaging; Iterative algorithms; Nerve fibers; Noise reduction; Pathology; Robustness; Tensile stress;
Conference_Titel :
Computer Vision, 2007. ICCV 2007. IEEE 11th International Conference on
Conference_Location :
Rio de Janeiro
Print_ISBN :
978-1-4244-1630-1
Electronic_ISBN :
1550-5499
DOI :
10.1109/ICCV.2007.4409143