Detail publikace

Automated Multi-Contrast Brain Pathological Area Extraction from MR Images

Originální název

Automated Multi-Contrast Brain Pathological Area Extraction from MR Images

Anglický název

Automated Multi-Contrast Brain Pathological Area Extraction from MR Images

Jazyk

en

Originální abstrakt

The aim of this work is to propose the fully automated pathological area extraction from multi-parametric 2D MR images of brain. The proposed method is based on multi-resolution symmetry analysis and automatic thresholding. The proposed algorithm first detects the presence of pathology and then starts its extraction. T2 images are used for the presence detection and the multi-contrast MRI, concretely T2 and FLAIR images, is used for the extraction. The extraction is based on thresholding, where the Otsu's algorithm is used for the automatic determination of the threshold. Since the method is based on symmetry, it works for both axial and coronal planes. In both these planes of healthy brain, the approximate left-right symmetry exists and it is used as the prior knowledge for searching the approximate pathology location. It is assumed that this area is not located symmetrically in both hemispheres, which is met in most cases. The detection algorithm was tested on 203 T2-weighted images and reached the true positive rate 87.52% and true negative rate 93.14%. The extraction algorithm was tested on 357 axial and 443 coronal real images from publicly available BRATS databases containing 3D volumes brain tumor patients. The results were evaluated by Dice Coefficient (axial: 0.85, coronal 0.82) and by Accuracy (axial: 0.96, coronal 0.94).

Anglický abstrakt

The aim of this work is to propose the fully automated pathological area extraction from multi-parametric 2D MR images of brain. The proposed method is based on multi-resolution symmetry analysis and automatic thresholding. The proposed algorithm first detects the presence of pathology and then starts its extraction. T2 images are used for the presence detection and the multi-contrast MRI, concretely T2 and FLAIR images, is used for the extraction. The extraction is based on thresholding, where the Otsu's algorithm is used for the automatic determination of the threshold. Since the method is based on symmetry, it works for both axial and coronal planes. In both these planes of healthy brain, the approximate left-right symmetry exists and it is used as the prior knowledge for searching the approximate pathology location. It is assumed that this area is not located symmetrically in both hemispheres, which is met in most cases. The detection algorithm was tested on 203 T2-weighted images and reached the true positive rate 87.52% and true negative rate 93.14%. The extraction algorithm was tested on 357 axial and 443 coronal real images from publicly available BRATS databases containing 3D volumes brain tumor patients. The results were evaluated by Dice Coefficient (axial: 0.85, coronal 0.82) and by Accuracy (axial: 0.96, coronal 0.94).

BibTex


@article{BUT109915,
  author="Pavel {Dvořák} and Karel {Bartušek} and Walter G. {Kropatsch} and Zdeněk {Smékal}",
  title="Automated Multi-Contrast Brain Pathological Area Extraction from MR Images",
  annote="The aim of this work is to propose the fully automated pathological area extraction from multi-parametric 2D MR images of brain. The proposed method is based on multi-resolution symmetry analysis and automatic thresholding. The proposed algorithm first detects the presence of pathology and then starts its extraction. T2 images are used for the presence detection and the multi-contrast MRI, concretely T2 and FLAIR images, is used for the extraction. The extraction is based on thresholding, where the Otsu's algorithm is used for the automatic determination of the threshold. Since the method is based on symmetry, it works for both axial and coronal planes. In both these planes of healthy brain, the approximate left-right symmetry exists and it is used as the prior knowledge for searching the approximate pathology location. It is assumed that this area is not located symmetrically in both hemispheres, which is met in most cases. The detection algorithm was tested on 203 T2-weighted images and reached the true positive rate 87.52% and true negative rate 93.14%. The extraction algorithm was tested on 357 axial and 443 coronal real images from publicly available BRATS databases containing 3D volumes brain tumor patients. The results were evaluated by Dice Coefficient (axial: 0.85, coronal 0.82) and by Accuracy (axial: 0.96, coronal 0.94).",
  chapter="109915",
  howpublished="online",
  number="1",
  volume="13",
  year="2015",
  month="february",
  pages="58--69",
  type="journal article - other"
}