Automatic Tractography Segmentation Using a High-Dimensional White Matter Atlas

Lauren J. O'Donnell, C.-F. Westin
IEEE Transactions on Medical Imaging
Volume 26, Number 11, Pages 1562-1575
November, 2007

Download full paper

Abstract

We propose a new white matter atlas creation method that learns a model of the common white matter structures present in a group of subjects. We demonstrate that our atlas creation method, which is based on group spectral clustering of tractography, discovers structures corresponding to expected white matter anatomy such as the corpus callosum, uncinate fasciculus, cingulum bundles, arcuate fasciculus, and corona radiata. The white matter clusters are augmented with expert anatomical labels and stored in a new type of atlas that we call a high-dimensional white matter atlas. We then show how to perform automatic segmentation of tractography from novel subjects by extending the spectral clustering solution, stored in the atlas, using the Nystrom method.We present results regarding the stability of our method and parameter choices. Finally we give results from an atlas creation and automatic segmentation experiment. We demonstrate that our automatic tractography segmentation identifies corresponding white matter regions across hemispheres and across subjects, enabling group comparison of white matter anatomy.

Comparison of standard and bilateral clustering (using midsagittal reflection). Note the increased right-left symmetry in the bilateral clustering result. However note that the conversion of the atlas to voxels (for visualization) is imperfect because the atlas is not voxel-based. The atlas may represent any number of structures inside the volume of a voxel, thus when one structure is selected for visualization information is lost.

Reference

O'Donnell LJ, Westin CF. Automatic tractography segmentation using a high-dimensional white matter atlas. IEEE Transactions on Medical Imaging 2007;26(11):1562-1575.

Bibtex entry

@ARTICLE{odonnellTMI07,
  author         = {Lauren J. O'Donnell and Carl-Fredrik Westin},              
  title          = {Automatic Tractography Segmentation Using a                
                   High-Dimensional  White Matter Atlas},                      
  journal        = {IEEE Transactions on Medical Imaging},                     
  year           = {2007},                                                     
  volume         = {26},                                                       
  pages          = {1562--1575},                                               
  number         = {11},                                                       
  month          = {November}
}

Grants

NIH U54-EB005149 (NAMIC), NIH P41-RR13218 (NAC), NIH R01-MH074794