this research paper proposes an automated and intelligent classification technique of Magnetic Resonance Imaging (MRI) brain images which is extremely important for medical analysis and interpretation. ECG, CT-scan and MRI images are important ways to diagnose brain diseases efficiently. An abnormal growth of cells without any purposes is called a tumor. Sometimes doctors can tell if a tumor is cancer or isn’t using MRI. MRI also used to find the signs that cancer may have spread from its starting part to another part of the body. Radiologist or physician analyze tumor manually by visual inspection which is a conventional method. This may lead to error in classification while a large number of MRIs are to be analyzed. Brain cancer is the leading cause of death among people which is caused from malignant brain tumor. A benign tumor is one that does not invade nearby tissue but a malignant tumor does. The chances of survival can be increased if the tumor can be detected at its early stage. In this paper a novel method to classify brain tumors as benign (non-cancerous) or malignant (cancerous) is presented. MRI brain image database was used for training and testing. Images were filtered, skull-masked and segmented. The proposed method employed wavelet transform to extract features from several images. Principle component analysis (PCA) was applied to reduce dimensionality of features. Gray Level Co-occurrence Matrix (GLCM) based Features were selected and submitted to a kernel support vector machine (KSVM). To generalize KSVM, k-fold stratified cross validation was applied. Features were extracted from MRI images named gray scale, symmetrical and texture features. The main goal of this paper is to offer an excellent result of MRI brain tumor classification and cancer detection using SVM. Our proposed system achieved classification accuracy of 96% for RBF kernel.

Brain Tumor, Classification, MRI, K-means clustering, PCA, Wavelet, GLCM, SVM

[1] K. B. Vaishnavee and K. Amshakala, “An automated MRI brain image segmentation and tumor detection using SOM-clustering and Proximal Support Vector Machine classifier”, in IEEE International Conference on Engineering and Technology (ICETECH), pp. 1 - 6, 2015.
[2] Ketan Machhale, Hari Babu Nandpuru, Vivek Kapur and Laxmi Kosta, "MRI brain cancer classification using hybrid classifier (SVM-KNN)", in International Conference on Industrial Instrumentation and Control (ICIC), pp. 60-65, 2015.
[3] Hari Babu Nandpuru, S. S. Salankar and V. R. Bora , “MRI brain cancer classification using Support Vector Machine”, in IEEE Students` Conference on Electrical, Electronics and Computer Science (SCEECS), pp. 1 - 6, 2014.
[4] Arashdeep Kaur “An Automatic Brain Tumor Extraction System Using Different Segmentation Methods” International Conference on Computational Intelligence & Communication Technology (CICT), pp. 187-191, 2016.
[5] Y. Zhang and L. Wu, “An MR Brain Images Classifier Via Principal Component Analysis and Kernel Support Vector Machine”, in Progress in Electromagnetics Research(PIER) , Vol. 130, pp. 369-388, 2012.
[6] Sheweta Jain, “Brain Cancer Classification Using GLCM Based Feature Extraction in Artificial Neural Network”, IJCSET, ISSN: 2229-3345, Vol. 4 No. 07 Jul 2013.
[7] Ahmed Kharrat, Mohamed Ben Halima and Mounir Ben Ayed, “MRI brain tumor classification using Support Vector Machines and meta-heuristic method”, International Conference on Intelligent Systems Design and Applications (ISDA), pp. 446-451, 2015.
[8] D. Sridhar and IV. Murali Krishna “Brain Tumor Classification using Discrete Cosine Transform and Probabilistic Neural Network” International Conference on Signal Processing Image Processing & Pattern Recognition (ICSIPR), pp. 1-5, 2013.
[9] Jainy Sachdeva, Vinod Kumar, Indra Gupta; Niranjan Khandelwal and Chirag Kamal Ahuja, “Multiclass Brain Tumor Classification Using GA-SVM”, pp. 182-187, 2011.
[10] Walaa Hussein Ibrahim, Ahmed AbdelRhman, Ahmed Osman and Yusra Ibrahim Mohamed “MRI brain image classification using neural networks”, International Conference on Computing, Electrical and Electronics Engineering (ICCEEE), pp. 253-258, 2013.
[11] G. Kharmega Sundararaj and V. Balamurugan, “Robust classification of primary brain tumor in Computer Tomography images using K-NN and linear SVM”, International Conference on Contemporary Computing and Informatics (IC3I), pp. 1315-1319, 2014.
[12] Ahmed Kharrat, KarimGasmi, et.al, “A Hybrid Approach for Automatic Classification of Brain MRI Using Genetic Algorithm and Support Vector Machine”, Leonardo Journal of Sciences. pp. 71-82, 2010.
[13] P. John, “Brain Tumor classification Using Wavelet and Texture Based Neural Network”, International Journal of Scientific & Engineering Research, Vol. 3, Issue 10, pp. 1-7, 2012.
[14] Janki Naik and Prof Sagar Patel, “Tumor Detection and Classification using Decision Tree in Brain MRI”, IJEDR, ISSN: 2321-9939, 2013.
[15] Mr. Ajaj Khan and Ms. Nikhat Ali Syed, “Image Processing Techniques for Automatic Detection of Tumor in Human Brain Using SVM”, International Journal of Advanced Research in Computer and Communication Engineering (IJARCE), Vol. 4, Issue 4, pp. 541-544, 2015.
[16] Asha Patil, Kalyani Patil, Kalpesh Lad, "Leaf Disease detection using Image Processing Techniques", International Journal of Scientific Research in Computer Science and Engineering, Vol.06, Issue.01, pp.33-36, 2018.
[17] Amey Samant, Sushma Kadge, "Classification of a Retinal Disease based on Different Supervised Learning Techniques", International Journal of Scientific Research in Network Security and Communication, Vol.5, Issue.3, pp.9-13, 2017