An Automatic Method to Locate Tumor from MRI Brain Images Using Wavelet Packet Based Feature Set

This paper developed a fully automatic method to locate the brain tumor from Magnetic resonance imaging (MRI) head scans using wavelet packet transformation (WPT) based feature set. WPT is used to extract high frequency data from all sub bands of MRI images. Modulus maximum is used to detect singularities among these high frequency features and thus isolates the hyper intense nature of tumors. These tumor areas are detected by preparing a mask of modulated images and then compared it with the original scans. This method does not require any preprocessing operations like seed selection, initialization and skull stripped scans of existing methods. Experiments were done with the sample images collected from popular hospitals and clinics. The results were visually inspected for the outputs. The quantitative validation was done with the Chi-square test. It performed significance study to identify the goodness of fit, the probability of fitness is above 0.75.

[1]  Karuppana Gounder Somasundaram,et al.  Fully automatic brain extraction algorithm for axial T2-weighted magnetic resonance images , 2010, Comput. Biol. Medicine.

[2]  Shiwei Ma,et al.  Life System Modeling and Intelligent Computing, International Conference on Life System Modeling and Simulation, LSMS 2010, and International Conference on Intelligent Computing for Sustainable Energy and Environment, ICSEE 2010, Wuxi, China, September 17-20, 2010, Proceedings, Part II , 2010, LSMS/ICSEE.

[3]  Stéphane Mallat,et al.  Characterization of Signals from Multiscale Edges , 2011, IEEE Trans. Pattern Anal. Mach. Intell..

[4]  Irene Cheng,et al.  Fluid Vector Flow and Applications in Brain Tumor Segmentation , 2009, IEEE Transactions on Biomedical Engineering.

[5]  S. Bauer,et al.  A survey of MRI-based medical image analysis for brain tumor studies , 2013, Physics in medicine and biology.

[6]  Kathleen M Schmainda,et al.  Computer‐aided detection of brain tumor invasion using multiparametric MRI , 2009, Journal of magnetic resonance imaging : JMRI.

[7]  Vinod Kumar,et al.  A novel content-based active contour model for brain tumor segmentation. , 2012, Magnetic resonance imaging.

[8]  Lawrence O. Hall,et al.  Automatic segmentation of non-enhancing brain tumors in magnetic resonance images , 2001, Artif. Intell. Medicine.

[9]  S. Vijayalakshmi,et al.  A Novel Self Initiating Brain Tumor Boundary Detection for MRI , 2012 .

[10]  Banghua Yang,et al.  Wavelet Packet-Based Feature Extraction for Brain-Computer Interfaces , 2010, LSMS/ICSEE.

[11]  R. Uthayakumar,et al.  Mathematical Modelling and Scientific Computation , 2012, Communications in Computer and Information Science.

[12]  Wen-Liang Hwang,et al.  Analysis of singularities from modulus maxima of complex wavelets , 2005, IEEE Trans. Inf. Theory.

[13]  Guido Gerig,et al.  Level-set evolution with region competition: automatic 3-D segmentation of brain tumors , 2002, Object recognition supported by user interaction for service robots.

[14]  Russell Greiner,et al.  Quick detection of brain tumors and edemas: A bounding box method using symmetry , 2012, Comput. Medical Imaging Graph..

[15]  Bernhard Schölkopf,et al.  Learning with Kernels: Support Vector Machines, Regularization, Optimization, and Beyond , 2005, IEEE Transactions on Neural Networks.

[16]  Peng Wang,et al.  Computer‐aided detection of metastatic brain tumors using automated three‐dimensional template matching , 2010, Journal of magnetic resonance imaging : JMRI.