Publication Details
Vector-based Medical Image Segmentation using Adaptive Delaunay Triangulation
ŠPANĚL Michal and KRŠEK Přemysl. Vector-based Medical Image Segmentation using Adaptive Delaunay Triangulation. In: Proceedings of the Sixth IASTED International Conference on Visualization, Imaging, and Image Procesing. 541. Palma de Mallorca: ACTA Press, 2006, p. 6. ISBN 0-88986-600-7.
Czech title
Vektorová segmentace medicínských obrazových dat pomocí adaptivní Delaunay triangulace
Type
conference paper
Language
english
Authors
URL
Keywords
CT/MR data, image segmentation, 3D geometrical model, vector-based segmentation, Delaunay triangulation
Abstract
The image segmentation plays an important role in medical image processing. Many segmentation algorithms exists. Most of them produce raster data which is not suitable for further 3D geometrical modeling of tissues. In this paper, a vector segmentation algorithm based on an adaptive Delaunay triangulation is proposed. Triangular meshes are used to divide an image into several non-overlapping regions whose characteristics are similar. Novel methods for improving quality of the mesh and its adaptation to the image structure are also presented.
Published
2006
Pages
6
Proceedings
Proceedings of the Sixth IASTED International Conference on Visualization, Imaging, and Image Procesing
Series
541
Conference
The Sixth IASTED International Conference on Visualization, Imaging, and Image Processing, Palma de Mallorca, ES
ISBN
0-88986-600-7
Publisher
ACTA Press
Place
Palma de Mallorca, ES
BibTeX
@INPROCEEDINGS{FITPUB8150, author = "Michal \v{S}pan\v{e}l and P\v{r}emysl Kr\v{s}ek", title = "Vector-based Medical Image Segmentation using Adaptive Delaunay Triangulation", pages = 6, booktitle = "Proceedings of the Sixth IASTED International Conference on Visualization, Imaging, and Image Procesing", series = "541", year = 2006, location = "Palma de Mallorca, ES", publisher = "ACTA Press", ISBN = "0-88986-600-7", language = "english", url = "https://www.fit.vut.cz/research/publication/8150" }
Files