Detail publikace

Delaunay-Based Vector Segmentation of Volumetric Medical Images

ŠPANĚL, M. KRŠEK, P. ŠVUB, M. ŠTANCL, V. ŠILER, O.

Originální název

Delaunay-Based Vector Segmentation of Volumetric Medical Images

Typ

článek ve sborníku ve WoS nebo Scopus

Jazyk

angličtina

Originální abstrakt

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.

Klíčová slova

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

Autoři

ŠPANĚL, M.; KRŠEK, P.; ŠVUB, M.; ŠTANCL, V.; ŠILER, O.

Rok RIV

2007

Vydáno

27. 8. 2007

Nakladatel

Springer Verlag

Místo

Berlin Heidelberg

ISBN

3-540-74271-9

Kniha

Proceedings of the 12th International Conference on Computer Analysis of Images and Patterns, CAIP 2007

Edice

LNCS 4673

ISSN

0302-9743

Periodikum

Lecture Notes in Computer Science

Ročník

2007

Číslo

08

Stát

Spolková republika Německo

Strany od

261

Strany do

269

Strany počet

8

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"
}