MULTI CLASS BRAIN TUMOR CLASSIFICATION OF MRI IMAGES USING HYBRID STRUCTURE DESCRIPTOR AND FUZZY LOGIC BASED RBF KERNEL SVM

Document Type: Research Paper

Authors

1 Department of CSE, PSN College of Engineering and Technology, Tirunelveli, India

2 Department of EEE, Syed Ammal Engineering College, Ramanathapuram,India

Abstract

Medical Image segmentation is to partition the image into a set of regions that are visually obvious and consistent with respect to some properties such as gray level, texture or color. Brain tumor classification is an imperative and difficult task in cancer radiotherapy. The objective of this research is to examine the use of pattern classification methods for distinguishing different types of brain tumors, such as primary gliomas from metastases, and also for grading of gliomas. Manual classification results look better because it involves human intelligence but the disadvantage is that the results may differ from one person to another person and takes long time. MRI image based automatic diagnosis method is used for early diagnosis and treatment of brain tumors. In this article, fully automatic, multi class brain tumor classification approach using hybrid structure descriptor and Fuzzy logic based Pair of RBF kernel support vector machine is developed. The method was applied to a population of 102 brain tumors histologically diagnosed as Meningioma (115), Metastasis (120), Gliomas grade II (65) and Gliomas grade II (70). Classification accuracy of proposed system in class 1(Meningioma) type tumor is 98.6\%, class 2 (Metastasis) is 99.29\%, class 3(Gliomas grade II) is 97.87\% and class 4(Gliomas grade III) is 98.6\%.

Keywords


[1] S. Bauer S, L. P. Nolte and M. Reyes, Fully automatic segmentation of brain tumor im-
ages using support vector machine classi cation in combination with hierarchical conditional
random eld regularization, Med Image Comput Assist Interv., 14(3) (2011), 354{361.
[2] C. J. C. Burges., A tutorial on support vector machines for pattern recognition, Data Mining
and Knowledge Discovery, 2 (1998), 121{167.
[3] S. Chaplot , L. M. Patnai and N. R. Jagannathan , Classi cation of magnetic resonance brain
images using wavelets as input to support vector machine and neural network, Biomedical
Signal Processing and Control, 1(1) (2006), 86{92.
[4] J. Chunming Li, R. Huang, Z. Ding and J. Chris Gatenby, A level set method for image
segmentation in the presence of intensity in-homogeneities with application to MRI, IEEE
Trans Image Process, 20 (2011), 2007{2016.

[5] R. Dhanasekaran and A. Jayachandranm, Brain tumor detection using fuzzy support vector
machine classi cation based on a texton Co-occurrence matrix, Journal of imaging Science
and Technology, 57(1) (2013), 10507-1{10507-7.
[6] S. R. Dubey, S. K. Singh, and R. K. Singh, Rotation and scale invariant hybrid image
descriptor and retrieval, Computers & Electrical Engineering, 46(8) (2015), 288{302.
[7] N. E. Ibrahim, S. Khalid and M. Manaf, Seed-Based region growing (SBRG) vs adaptive
network-based inference system (ANFIS) vs fuzzy c-means(FCM) - brain abnormalities seg-
mentation, World Acad. Sci. Eng. Technol., 68 (2010), 425{435.
[8] A. Jayachandran and R. Dhanasekaran, Automatic detection of brain tumor in magnetic
resonance images using multi-texton histogram and support vector machinel, International
Journal of Imaging Systems and Technology, 23(2) (2013), 97{103.
[9] A. Jayachandran and R. Dhanasekaran, Severity analysis of brain tumor in MRI images uses
modi ed multi-texton structure descriptor and kernel- SVM, The Arabian Journal of science
and engineering, 39(10) (2014), 7073{7086.
[10] B. Julesz, Textons|the elements of texture perception and their interactions, Nature, 290
(1981), 91{97.
[11] G. Kharmega Sundararaj and A. Jayachandran, Abnormality segmentation and classi ca-
tion of multi-class brain tumor in MR images using fuzzy logic-based hybrid kernel SVM,
International journal of Fuzzy System, 17(3) (2015), 434{443.
[12] J. S. Lin, K. S. Cheng and C. W. Mao, Segmentation of multispectral magnetic resonance im-
age using penalized fuzzy competitive learning network, Journal of Computers and Biomedical
Research, 29(4) (1996), 314{326.
[13] G. H. Liu, L. Zhang, Yingkun Hou, Zuoyong Li and Jing-Yu Yang, Image retrieval based on
multi-texton histogram, Pattern Recognition, 43(7) (2010), 2380{2389.
[14] C. L. P. Long-Chen, Philip Chen and L. U. Mingzhu, A multiple-kernel fuzzy C-means algo-
rithm for image segmentation, IEEE Transactions On Systems, Man, and Cybernetics{Part
B: Cybernetics, 41(5) (2011), 1263{1274.
[15] T. Wang and H. M. Chiang, Fuzzy support vector machine for multi-class text categorization,
Information Processing and Management, 43 (2007), 914{929.
[16] R. J. Young and E. A. Knopp, Brain MRI: tumor evaluation, Journal of Magnetic Resonance
Imaging, 24 (2006), 709{724.
[17] E. I. Zacharaki, S. Wang, S. Chawla, E. R. Melhem and C. Davatzikos, Classi cation of brain
tumor type and grade using MRI texture in a machine learning technique, Magn. Reson. Med.,
62 (2009), 1609{1618.
[18] K. Zhang, H. X. Cao and H. Yan, Application of support vector machines on network abnor-
mal intrusion detection, Application Research of Computers, 5 (2006), 98{100.
[19] C. Zhu and T. Jiang, Multi context fuzzy clustering for separation of brain tissues in magnetic
resonance images, Neuro lmage, 18(3) (2003), 685 {696.
[20] W. Zhu, N. Zeng and N. Wang, Sensitivity, speci city, accuracy, associated con dence in-
terval and ROC analysis with practical SAS implementations, In: Proceedings of the SAS
Conference, NESUG 210, November 14{17, Baltimore, Maryland, 2010.