Using Local 3D Structure for Segmentation of Bone from Computer Tomography Images

C.-F. Westin, A. Bhalerao, H. Knutsson, R. Kikinis
CVPR, Puerto Rico
IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR '97)
Pages 794-800
June 17-19, 1997

Download full paper

Abstract

In this paper we focus on using local 3D structure for segmentation. A tensor descriptor is estimated for each neighbourhood, i.e. for each voxel in the data set. The tensors are created from a combination of the outputs form a set of 3D quadrature filters. The shape of the tensors describe locally the structure of the neighbourhood in terms of how much it is like a plane, a line, and a sphere. We apply this to segmentation of bone from Computer Tomography data (CT). Traditional methods are based purely on gray-level value discrimination and have difficulties in recovering thin bone structures due to so called partial voluming, a problem which is present in all such sampled data. We illuminate the partial voluming problem by showing that thresholding creates complicated artifacts even if the signal is densely enough sampled and can be perfectly reconstructed. The unwanted effects of thresholding can be reduced by a change of the signal basis. We show that by using additional local structure information can significantly reduce the degree of sampling artifacts. Evaluation of the method on a clinical case is presented, the segmentation of a human skull from a CT volume. The method shows that many of the thin bone structures which disappear in a pure thresholding can be recovered.

Segmentation by thresholding CT values. Right Segmentation using additional local shape information. The top images show a overview of the surface rendered segmentation. Middle images show a close up of the left orbital region. Bottom images show a close up of the nasal cavity.

Reference

Westin CF, Bhalerao A, Knutsson H, Kikinis R. Using local 3D structure for segmentation of bone from computer tomography images. In IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR '97). Puerto Rico, 1997;794-800.

Bibtex entry

@InProceedings{westinCVPR97,
  author         = {C.-F. Westin and A. Bhalerao and H. Knutsson and R.        
                   Kikinis},                                                   
  title          = {{U}sing Local 3{D} Structure for Segmentation of Bone from 
                   Computer Tomography Images},                                
  booktitle      = {IEEE Computer Society Conference on Computer Vision and    
                   Pattern Recognition ({} '97)},                              
  year           = {1997},                                                     
  address        = {Puerto Rico},                                              
  month          = {June 17-19},                                               
  pages          = {794--800}
}

Research areas

Tensor, CT, Filtering, Local Structure