Publication Details

Delaunay-Based Vector Segmentation of Volumetric Medical Images

ŠPANĚL, M.; KRŠEK, P.; ŠVUB, M.; ŠTANCL, V.; ŠILER, O. Delaunay-Based Vector Segmentation of Volumetric Medical Images. In Proceedings of the 12th International Conference on Computer Analysis of Images and Patterns, CAIP 2007. Lecture Notes in Computer Science. LNCS 4673. Berlin Heidelberg: Springer Verlag, 2007. p. 261-269. ISBN: 3-540-74271-9. ISSN: 0302-9743.
Czech title
Vektorová segmentace objemových medicínských dat
Type
conference paper
Language
English
Authors
Španěl Michal, Ing., Ph.D. (DCGM)
Kršek Přemysl, doc. Ing., Ph.D. (UTKO)
Švub Miroslav, Ing.
Štancl Vít, Ing.
Šiler Ondřej, Ing.
URL
Keywords

Medical image processing, CT/MRI data, vector image segmentation, 3D Delaunay triangulation, tetraheral mesh, isotropic meshing, classification.

Abstract

The image segmentation plays an important role in medical image processing. Many segmentation algorithms exist. Most of them produce raster data which is not suitable for 3D geometrical modeling of human tissues. In this paper, a vector segmentation algorithm based on 3D Delaunay triangulation is proposed. Tetrahedral mesh is used to divide volumetric CT/MR data into non-overlapping regions whose characteristics are similar. Novel methods for improving quality of the mesh and its adaptation to the 3D image structure are also presented.

Published
2007
Pages
261–269
Journal
Lecture Notes in Computer Science, vol. 2007, no. 08, ISSN 0302-9743
Proceedings
Proceedings of the 12th International Conference on Computer Analysis of Images and Patterns, CAIP 2007
Series
LNCS 4673
ISBN
3-540-74271-9
Publisher
Springer Verlag
Place
Berlin Heidelberg
BibTeX 
@inproceedings{BUT26059,
  author="Michal {Španěl} and Přemysl {Kršek} and Miroslav {Švub} and Vít {Štancl} and Ondřej {Šiler}",
  title="Delaunay-Based Vector Segmentation of Volumetric Medical Images",
  booktitle="Proceedings of the 12th International Conference on Computer Analysis of Images and Patterns, CAIP 2007",
  year="2007",
  series="LNCS 4673",
  journal="Lecture Notes in Computer Science",
  volume="2007",
  number="08",
  pages="261--269",
  publisher="Springer Verlag",
  address="Berlin Heidelberg",
  isbn="3-540-74271-9",
  issn="0302-9743"
}
Back to top