Title :
Multiresolution texture models for brain tumor segmentation in MRI
Author :
Iftekharuddin, Khan M. ; Ahmed, Shaheen ; Hossen, Jakir
fDate :
Aug. 30 2011-Sept. 3 2011
Abstract :
In this study we discuss different types of texture features such as Fractal Dimension (FD) and Multifractional Brownian Motion (mBm) for estimating random structures and varying appearance of brain tissues and tumors in magnetic resonance images (MRI). We use different selection techniques including KullBack - Leibler Divergence (KLD) for ranking different texture and intensity features. We then exploit graph cut, self organizing maps (SOM) and expectation maximization (EM) techniques to fuse selected features for brain tumors segmentation in multimodality T1, T2, and FLAIR MRI. We use different similarity metrics to evaluate quality and robustness of these selected features for tumor segmentation in MRI for real pediatric patients. We also demonstrate a non-patient-specific automated tumor prediction scheme by using improved AdaBoost classification based on these image features.
Keywords :
Brownian motion; biomedical MRI; expectation-maximisation algorithm; feature extraction; image classification; image resolution; image segmentation; image texture; learning (artificial intelligence); medical image processing; paediatrics; tumours; AdaBoost classification; FLAIR MRI; KullBack-Leibler divergence technique; MRI; brain tissues; brain tumor segmentation; expectation maximization technique; fractal dimension; graph cut; magnetic resonance images; multifractional Brownian motion; multimodality T1; multimodality T2; multiresolution texture model; nonpatient-specific automated tumor prediction scheme; pediatric patients; self organizing maps; texture feature; Biomedical imaging; Feature extraction; Fractals; Image segmentation; Magnetic resonance imaging; Training; Tumors; Algorithms; Brain; Brain Neoplasms; Child; Computer Graphics; Computers; Fractals; Humans; Image Processing, Computer-Assisted; Magnetic Resonance Imaging; Models, Statistical; Models, Theoretical; Motion; Multivariate Analysis; Principal Component Analysis; ROC Curve; Software;
Conference_Titel :
Engineering in Medicine and Biology Society, EMBC, 2011 Annual International Conference of the IEEE
Conference_Location :
Boston, MA
Print_ISBN :
978-1-4244-4121-1
Electronic_ISBN :
1557-170X
DOI :
10.1109/IEMBS.2011.6091766