Publication detail

Automatic system for MR perfusion images processing

ČÁP, M. BARTUŠEK, K. MARCOŇ, P.

Original Title

Automatic system for MR perfusion images processing

English Title

Automatic system for MR perfusion images processing

Type

conference paper

Language

en

Original Abstract

This article describes automated detection and segmentation of the tumor and tumor edema. Automated detection of the tumor tissue area is based on the human brain symmetry. Healthy brain has a strong sagittal symmetry. Assuming the tumor is not placed symmetrically in both hemispheres, is possible use this method for its detection. Tumor area is evaluated from image which is obtained by summing partial results from all T2 weighted images. Segmentation and precise etection of the tumor in the by previous step marked area is based on Chan Vese algorithm. Segmentation is provided in T1 and T2 weighted images in order to achieve highest precision on the tumor border. Resulting masks are transformed into perfusion image coordinates and applied to the various perfusion maps.

English abstract

This article describes automated detection and segmentation of the tumor and tumor edema. Automated detection of the tumor tissue area is based on the human brain symmetry. Healthy brain has a strong sagittal symmetry. Assuming the tumor is not placed symmetrically in both hemispheres, is possible use this method for its detection. Tumor area is evaluated from image which is obtained by summing partial results from all T2 weighted images. Segmentation and precise etection of the tumor in the by previous step marked area is based on Chan Vese algorithm. Segmentation is provided in T1 and T2 weighted images in order to achieve highest precision on the tumor border. Resulting masks are transformed into perfusion image coordinates and applied to the various perfusion maps.

Keywords

perfusion MRI, segmentation, Chan Vese

RIV year

2013

Released

08.09.2013

Location

Brno, Czech Republic

ISBN

978-80-214-4759-2

Book

International Interdisciplinary PhD Workshop 2013, Proceedings

Pages from

297

Pages to

301

Pages count

5

BibTex


@inproceedings{BUT102216,
  author="Martin {Čáp} and Karel {Bartušek} and Petr {Marcoň}",
  title="Automatic system for MR perfusion images processing",
  annote="This article describes automated detection and segmentation of the tumor and tumor edema. Automated detection of the tumor tissue area is based on the human brain symmetry. Healthy brain has a strong sagittal symmetry. Assuming the tumor is not placed symmetrically in both hemispheres, is possible use this method for its detection. Tumor area is evaluated from image which is obtained by summing partial results from all T2 weighted images. Segmentation and precise  etection of the tumor in the by previous step marked area is based on Chan Vese algorithm. Segmentation is provided in T1 and T2 weighted images in order to achieve highest precision on the tumor border. Resulting masks are transformed  into perfusion image coordinates and applied to the various perfusion maps.",
  booktitle="International Interdisciplinary PhD Workshop 2013, Proceedings",
  chapter="102216",
  howpublished="electronic, physical medium",
  year="2013",
  month="september",
  pages="297--301",
  type="conference paper"
}