Quantitative texture analysis for Glioblastoma phenotypes discrimination

Author

Chaddad, Ahmad ; Zinn, Pascal O. ; Colen, Rivka R.

Author_Institution

Dept. of Diagnostic Radiol., Univ. of Texas, Houston, TX, USA

fYear

2014

fDate

3-5 Nov. 2014

Firstpage

605

Lastpage

608

Abstract

A quantitative texture analysis for discriminating GBM phenotypes in brain magnetic resonance (MR) images is proposed. GBM phenotypes captured using semi-automatic segmentation based on 3D Slicer Scripts. Segmentation was applied on the registered images considered the T1-Weighted and FLAIR sequence. Texture feature has been extracted from the gray level co-occurrence matrix (GLCM) based on GBM phenotypes. Feature vectors are then used in training a minimum distance classifier based on Mahalanobis distance metric. Simulation results for 13 patients show the highest accuracy of 67% based on the feature extraction from GLCM with offset =1 and 8 phases. Preliminary texture analysis demonstrated that the texture feature based on the GLCM is promising to distinguish GBM phenotypes.

Keywords

biomedical MRI; brain; cancer; feature extraction; image segmentation; image texture; matrix algebra; medical image processing; 3D Slicer Scripts; FLAIR sequence; GBM phenotypes; GLCM; MR images; Mahalanobis distance metric; T1-weighted sequence; brain magnetic resonance; feature extraction; feature vector; glioblastoma phenotypes discrimination; gray level cooccurrence matrix; minimum distance classifier; quantitative texture analysis; semiautomatic segmentation; Accuracy; Cancer; Feature extraction; Image segmentation; Measurement; Three-dimensional displays; Tumors; GBM; GLCM; MRI; Segmentation; Texture;

fLanguage

English

Publisher

ieee

Conference_Titel

Control, Decision and Information Technologies (CoDIT), 2014 International Conference on

Conference_Location

Metz

Type

conf

DOI

10.1109/CoDIT.2014.6996964

Filename

6996964