Automatic detection and Segmentation of the Tumor Tissue

0395167 - ÚPT 2014 RIV GB eng C - Conference Paper (international conference)
Čáp, M. - Gescheidtová, E. - Marcon, P. - Bartušek, Karel
Automatic detection and Segmentation of the Tumor Tissue.
PIERS 2013 Taipei Proceedings. Cambridge: The Electromagnetics Academy, 2013, s. 53-56. ISBN 978-1-934142-24-0. ISSN 1559-9450.
[The 33rd PIERS in Taipei. Progress in Electromagnetics Research Symposium. Taipei (TW), 25.03.2013-28.03.2013]
R&D Projects: GA ČR GAP102/11/0318; GA ČR GAP102/12/1104
Institutional support: RVO:68081731
Keywords : segmentation * MRI * tumor tissue * high-grade glioms
Subject RIV: JA - Electronics ; Optoelectronics, Electrical Engineering

MRI is a constantly developing region of medicine, which is suitable for the study of soft tissues. The current methodologies for obtaining images weighted by relaxation times give only an idea of the distribution of soft tissues. Differential diagnosis of a high-grade glioms and solitary metastases is in some cases inconclusive. Investigators in several studies have demon-strated that in perfusion MRI (magnetic resonance imaging) of high-grade glioms and solitary metastases are differences. Analysis of the peritumoral region could be more useful than the analysis of the tumor itself. Precise evaluation of mentioned differences in peritumoral region gives a hopeful chance for tumor diagnosis. 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 detection 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 applied to the various perfusion maps.
Permanent Link: http://hdl.handle.net/11104/0225236