Brain Tumor Classification using Principal Component Analysis and Probabilistic Neural Network

growth of the cell in the brain is the brain tumor. Brain tumor is common and serious disease. The proposed method for tumor classification in magnetic resonance brain image is the human inspection. Magnetic Resonance Imaging (MRI) plays an intrinsic role in the brain tumor disease diagnostic application. Various types of tumor that leads decision complicated. So that correct classification of brain tumor is important to detect the types of tumor. In this paper, Probabilistic Neural network (PNN) is used for brain tumor classification. Decision making was performed in two steps: 1) Feature extraction using Principal Component Analysis (PCA). And 2) Classification is done by Probabilistic neural network (PNN). Brain tumor is classified into three classes: Normal, Benign and Malignant. Again malignant tumor is classified as Glioma and Meningioma. PNN is faster and provide good classification accuracy.

[1]  Chong-Ho Choi,et al.  Input feature selection for classification problems , 2002, IEEE Trans. Neural Networks.

[2]  D. Sridhar,et al.  Brain Tumor Classification using Discrete Cosine Transform and Probabilistic Neural Network , 2013, 2013 International Conference on Signal Processing , Image Processing & Pattern Recognition.

[3]  George C. Kagadis,et al.  Non-linear Least Squares Features Transformation for Improving the Performance of Probabilistic Neural Networks in Classifying Human Brain Tumors on MRI , 2007, ICCSA.

[4]  Jiawei Han,et al.  Data Mining: Concepts and Techniques , 2000 .

[5]  Mohd Ariffanan Mohd Basri,et al.  Probabilistic Neural Network for Brain Tumor Classification , 2011, 2011 Second International Conference on Intelligent Systems, Modelling and Simulation.

[6]  Vinod Kumar,et al.  Classification of brain tumors using PCA-ANN , 2011, 2011 World Congress on Information and Communication Technologies.

[7]  S. Sumathi,et al.  Introduction to neural networks using MATLAB 6.0 , 2006 .