Publication detail

Support Vector Machines in MR Images Segmentation

MIKULKA, J. DVOŘÁK, P. BARTUŠEK, K.

Original Title

Support Vector Machines in MR Images Segmentation

English Title

Support Vector Machines in MR Images Segmentation

Type

conference paper

Language

en

Original Abstract

The problem most frequently encountered in the practical processing of medical images consists in the lack of instruments enabling machine evaluation of the images. A typical example of this situation is perfusion analysis of brain tumor types. The first and very significant step lies in the segmentation of individual parts of the brain tumor; after segmentation, the rate of penetration by the applied contrast agent is observed in the parts. The common method, in which a high error rate has to be considered, is to mark these tumor portions manually. The quality of brain tissue segmentation exerts significant influence on the quality of evaluation of perfusion parameters; consequently, the tumor type recognition is also influenced. The authors describe classification methods enabling the segmentation of images acquired via magnetic resonance tomography. During the edema segmentation, we obtained the following data: sensitivity 0.78+-0.09, specificity 1.00+-0.00, error rate 0.45+-0.24 %, surface overlap 69.36+-12.04 %, accuracy 99.55+-0.24 %, and surface difference -7.80+-9.13 %.

English abstract

The problem most frequently encountered in the practical processing of medical images consists in the lack of instruments enabling machine evaluation of the images. A typical example of this situation is perfusion analysis of brain tumor types. The first and very significant step lies in the segmentation of individual parts of the brain tumor; after segmentation, the rate of penetration by the applied contrast agent is observed in the parts. The common method, in which a high error rate has to be considered, is to mark these tumor portions manually. The quality of brain tissue segmentation exerts significant influence on the quality of evaluation of perfusion parameters; consequently, the tumor type recognition is also influenced. The authors describe classification methods enabling the segmentation of images acquired via magnetic resonance tomography. During the edema segmentation, we obtained the following data: sensitivity 0.78+-0.09, specificity 1.00+-0.00, error rate 0.45+-0.24 %, surface overlap 69.36+-12.04 %, accuracy 99.55+-0.24 %, and surface difference -7.80+-9.13 %.

Keywords

Perfusion analysis, brain tumor segmentation, data classification, support vector machines, multi-parametric segmentation

RIV year

2013

Released

27.05.2013

ISBN

9788096967254

Book

Measurement 2013

Pages from

157

Pages to

160

Pages count

4

Documents

BibTex


@inproceedings{BUT101099,
  author="Jan {Mikulka} and Pavel {Dvořák} and Karel {Bartušek}",
  title="Support Vector Machines in MR Images Segmentation",
  annote="The problem most frequently encountered in the practical processing of medical images consists in the lack of instruments enabling machine evaluation of the images. A typical example of this situation is perfusion analysis of brain tumor types. The first and very significant step lies in the segmentation of individual parts of the brain tumor; after segmentation, the rate of penetration by the applied contrast agent is observed in the parts. The common method, in which a high error rate has to be considered, is to mark these tumor portions manually. The quality of brain tissue segmentation exerts significant influence on the quality of evaluation of perfusion parameters; consequently, the tumor type recognition is also influenced. The authors describe classification methods enabling the segmentation of images acquired via magnetic resonance tomography. During the edema segmentation, we obtained the following data: sensitivity 0.78+-0.09, specificity 1.00+-0.00, error rate 0.45+-0.24 %, surface overlap 69.36+-12.04 %, accuracy 99.55+-0.24 %, and surface difference -7.80+-9.13 %.",
  booktitle="Measurement 2013",
  chapter="101099",
  howpublished="print",
  year="2013",
  month="may",
  pages="157--160",
  type="conference paper"
}