<abstract xmlns="http://www.w3.org/1999/xhtml"><p> This work focuses on fully automatic detection of brain tumors. The first aim is to determine, whether the image contains a brain with a tumor, and if it does, localize it. The goal of this work is not the exact segmentation of tumors, but the localization of their approximate position. The test database contains 203 T2-weighted images of which 131 are images of healthy brain and the remaining 72 images contain brain with pathological area. The estimation, whether the image shows an afflicted brain and where a pathological area is, is done by multi resolution symmetry analysis. The first goal was tested by five-fold cross-validation technique with 100 repetitions to avoid the result dependency on sample order. This part of the proposed method reaches the true positive rate of 87.52% and the true negative rate of 93.14% for an afflicted brain detection. The evaluation of the second part of the algorithm was carried out by comparing the estimated location to the true tumor location. The detection of the tumor location reaches the rate of 95.83% of correct anomaly detection and the rate 87.5% of correct tumor location.</p></abstract>

This work focuses on fully automatic detection of brain tumors. The first aim is to determine, whether the image contains a brain with a tumor, and if it does, localize it. The goal of this work is not the exact segmentation of tumors, but the localization of their approximate position. The test database contains 203 T2-weighted images of which 131 are images of healthy brain and the remaining 72 images contain brain with pathological area. The estimation, whether the image shows an afflicted brain and where a pathological area is, is done by multi resolution symmetry analysis. The first goal was tested by five-fold cross-validation technique with 100 repetitions to avoid the result dependency on sample order. This part of the proposed method reaches the true positive rate of 87.52% and the true negative rate of 93.14% for an afflicted brain detection. The evaluation of the second part of the algorithm was carried out by comparing the estimated location to the true tumor location. The detection of the tumor location reaches the rate of 95.83% of correct anomaly detection and the rate 87.5% of correct tumor location.

Automatic Brain Tumor Detection in T2-weighted Magnetic Resonance Images

Deptartment of Telecommunications, Faculty of Electrical Engineering and Communication, Brno University of Technology, Technicka 12, 612 00 Brno, Czech Republic

Institute of Scientific Instruments of the ASCR, v.v.i., Kralovopolska 147, 612 64 Brno, Czech Republic

Pattern Recognition and Image Processing Group, Institute of Computer Graphics and Algorithms, Faculty of Informatics, Vienna University of Technology, Favoritenstr. 9/186-3, A-1040 Vienna, Austria

Measurement Science Review

{"article-title":"Automatic Brain Tumor Detection in T2-weighted Magnetic Resonance Images"}

This work focuses on fully automatic detection of brain tumors. The first aim is to determine, whether the image contains a brain with a tumor, and if it does,...

Automatic Brain Tumor Detection in T2-weighted Magnetic Resonance Images

Published Online: Nov 02, 2013

Page range: 223 - 230

DOI: https://doi.org/10.2478/msr-2013-0034

Keywords
Brain tumor, brain tumor detection, symmetry analysis

This content is open access.

Automatic Brain Tumor Detection in T2-weighted Magnetic Resonance Images

Published Online: Nov 02, 2013

Page range: 223 - 230

DOI: https://doi.org/10.2478/msr-2013-0034

KeywordsBrain tumor, brain tumor detection, symmetry analysis

This content is open access.

Keywords
Brain tumor, brain tumor detection, symmetry analysis