Publication detail

Segmentace medicínských obrazů s využitím grafové reprezentace

KOZLOVÁ, D. JAKUBÍČEK, R.

Original Title

Segmentace medicínských obrazů s využitím grafové reprezentace

English Title

MEDICAL IMAGE SEGMENTATION BASED ON GRAPH CUT WITH SHAPE PRIOR

Type

conference paper

Language

Czech

Original Abstract

This paper deals with a graph-based image segmentation and its improvement by using the information about the shape of the object for creating specific graph architecture (template). Improved method allows the cut to prefer more complicated structures, especially when the image contains a lot of noise and the object is hardly indistinguishable from the background. Algorithm was tested on simulated data and real CT and MRI images of vertebra and brain in 2D. Method was also extended to 3D further purposes.

English abstract

This paper deals with a graph-based image segmentation and its improvement by using the information about the shape of the object for creating specific graph architecture (template). Improved method allows the cut that prefer more complicated structures, especially when the image contains a lot of noise and the object is hardly indistinguishable from the background. Algorithm was tested on simulated data and real CT and MRI images of vertebra and brain in 2D. The method was also extended it 3D further purposes.

Keywords

Medical image segmentation, Graph theory, Graph cut, Template

Key words in English

Medical image segmentation, Graph theory, Graph cut, Template

Authors

KOZLOVÁ, D.; JAKUBÍČEK, R.

Released

28. 4. 2016

Publisher

Vysoké učení technické v Brně, Fakulta elektrotechniky a komunikačních

Location

Brno

ISBN

978-80-214-5350-0

Book

Proceedings of the 21st Conference STUDENT EEICT 2015

Edition

1

Edition number

1

Pages from

50

Pages to

52

Pages count

3

URL

http://www.feec.vutbr.cz/EEICT/2016/sbornik/EEICT-2016-sborn%C3%ADk-komplet.pdf

BibTex

@inproceedings{BUT125420,
  author="Dominika {Kozlová} and Roman {Jakubíček}",
  title="Segmentace medicínských obrazů s využitím grafové reprezentace",
  booktitle="Proceedings of the 21st Conference STUDENT EEICT 2015",
  year="2016",
  series="1",
  number="1",
  pages="50--52",
  publisher="Vysoké učení technické v Brně, Fakulta elektrotechniky a komunikačních",
  address="Brno",
  isbn="978-80-214-5350-0",
  url="http://www.feec.vutbr.cz/EEICT/2016/sbornik/EEICT-2016-sborn%C3%ADk-komplet.pdf"
}