Share Email Print

Proceedings Paper

Grid-based spectral fiber clustering
Author(s): Jan Klein; Philip Bittihn; Peter Ledochowitsch; Horst K. Hahn; Olaf Konrad; Jan Rexilius; Heinz-Otto Peitgen
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

We introduce novel data structures and algorithms for clustering white matter fiber tracts to improve accuracy and robustness of existing techniques. Our novel fiber grid combined with a new randomized soft-division algorithm allows for defining the fiber similarity more precisely and efficiently than a feature space. A fine-tuning of several parameters to a particular fiber set - as it is often required if using a feature space - becomes obsolete. The idea is to utilize a 3D grid where each fiber point is assigned to cells with a certain weight. From this grid, an affinity matrix representing the fiber similarity can be calculated very efficiently in time O(n) in the average case, where n denotes the number of fibers. This is superior to feature space methods which need O(n2) time. Our novel eigenvalue regression is capable of determining a reasonable number of clusters as it accounts for inter-cluster connectivity. It performs a linear regression of the eigenvalues of the affinity matrix to find the point of maximum curvature in a list of descending order. This allows for identifying inner clusters within coarse structures, which automatically and drastically reduces the a-priori knowledge required for achieving plausible clustering results. Our extended multiple eigenvector clustering exhibits a drastically improved robustness compared to the well-known elongated clustering, which also includes an automatic detection of the number of clusters. We present several examples of artificial and real fiber sets clustered by our approach to support the clinical suitability and robustness of the proposed techniques.

Paper Details

Date Published: 21 March 2007
PDF: 10 pages
Proc. SPIE 6509, Medical Imaging 2007: Visualization and Image-Guided Procedures, 65091E (21 March 2007); doi: 10.1117/12.706242
Show Author Affiliations
Jan Klein, Ctr. for Medical Image Computing, MeVis Research (Germany)
Philip Bittihn, Goettingen Univ. (Germany)
Peter Ledochowitsch, Goettingen Univ. (Germany)
Horst K. Hahn, Ctr. for Medical Image Computing, MeVis Research (Germany)
Olaf Konrad, Ctr. for Medical Image Computing, MeVis Research (Germany)
Jan Rexilius, Ctr. for Medical Image Computing, MeVis Research (Germany)
Heinz-Otto Peitgen, Ctr. for Medical Image Computing, MeVis Research (Germany)

Published in SPIE Proceedings Vol. 6509:
Medical Imaging 2007: Visualization and Image-Guided Procedures
Kevin R. Cleary; Michael I. Miga, Editor(s)

© SPIE. Terms of Use
Back to Top