Support Vector Machines in MR Images Segmentation

Support Vector Machines in MR Images Segmentation

Paper in proceedings (conference paper)

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 %.

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 %.

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

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

MIKULKA, J.; DVOŘÁK, P.; BARTUŠEK, K.

2014

27.05.2013

9788096967254

Measurement 2013

157

160

4