Coloring of DT-MRI FIber Traces using Laplacian Eigenmaps

A. Brun, H. J. Park, H. Knutsson, C.-F. Westin
Computer Aided Systems Theory (EUROCAST'03), Lecture Notes in Computer Science 2809
Pages 564-572
February 24-28, 2003

Download full paper

Abstract

We propose a novel post processing method for visualization of fiber traces from DT-MRI data. Using a recently proposed non-linear dimensionality reduction technique, Laplacian eigenmaps, we create a mapping from a set of fiber traces to a lowdimensional Euclidean space. Laplacian eigenmaps constructs this mapping so that similar traces are mapped to similar points, given a custom made pairwise similarity measure for fiber traces.We demonstrate that when the low-dimensional space is the RGB color space, this can be used to visualize fiber traces in a way which enhances the perception of fiber bundles and connectivity in the human brain.

Fiber traces from a human brain, colored such that traces with similar endpoints have been assigned similar colors. Simple PDD fiber tracking have been initiated from and constrained to voxels with high anisotropy index. Left: Axial view. The head facing up. Middle: Sagittal view. The head facing left. Right: Coronal view. The head facing inwards.

Reference

Brun A, Park HJ, Knutsson H, Westin CF. Coloring of DT-MRI fiber traces using laplacian eigenmaps. In RM Diaz, AQ Arencibia, eds., Computer Aided Systems Theory (EUROCAST'03), Lecture Notes in Computer Science 2809. Las Palmas de Gran Canaria, Spain: Springer Verlag, 2003;564-572.

Bibtex entry

@INPROCEEDINGS{brunEUROCAST03,
  author         = {Anders Brun and Hae-Jeong Park and Hans Knutsson and       
                   Carl-Fredrik Westin},                                       
  title          = {Coloring of {DT-MRI} FIber Traces using Laplacian          
                   Eigenmaps},                                                 
  editor         = {Roberto Moreno Diaz and Alexis Quesada Arencibia},         
  booktitle      = {Computer Aided Systems Theory (EUROCAST'03), Lecture Notes 
                   in Computer Science 2809},                                  
  pages          = {564--572},                                                 
  month          = {February 24--28},                                          
  year           = {2003},                                                     
  address        = {Las Palmas de Gran Canaria, Spain},                        
  publisher      = {Springer Verlag},                                          
  note           = {}
}

Grants

NIH P41-RR13218 (NAC), CIMIT, NIH R01-MH50747

Research areas

DTMRI, Tensor