A Sobolev norm based distance measure for HARDI clustering: a feasibility study on phantom and real data

Ellen Brunenberg; Remco Duits; Bart ter Haar Romeny; Bram Platel

doi:10.1007/978-3-642-15705-9_22

A Sobolev norm based distance measure for HARDI clustering: a feasibility study on phantom and real data

Med Image Comput Comput Assist Interv. 2010;13(Pt 1):175-82. doi: 10.1007/978-3-642-15705-9_22.

Authors

Ellen Brunenberg¹, Remco Duits, Bart ter Haar Romeny, Bram Platel

Affiliation

¹ Biomedical Engineering, Eindhoven University of Technology. [email protected]

PMID: 20879229
DOI: 10.1007/978-3-642-15705-9_22

Abstract

Dissimilarity measures for DTI clustering are abundant. However, for HARDI, the L2 norm has up to now been one of only few practically feasible measures. In this paper we propose a new measure, that not only compares the amplitude of diffusion profiles, but also rewards coincidence of the extrema. We tested this on phantom and real brain data. In both cases, our measure significantly outperformed the L2 norm.

Publication types

Research Support, Non-U.S. Gov't

MeSH terms

Algorithms*
Brain / cytology*
Diffusion Magnetic Resonance Imaging / instrumentation
Diffusion Magnetic Resonance Imaging / methods*
Feasibility Studies
Humans
Image Enhancement / methods
Image Interpretation, Computer-Assisted / methods*
Neurons / cytology*
Pattern Recognition, Automated / methods*
Phantoms, Imaging
Reproducibility of Results
Sensitivity and Specificity