The Comparative Analysis of Brain Tumor Identification on MRI Image by Probabilistic Neural Networks – A Preview

Abstract

Brain tumor is a collection or mass of abnormal cells in the brain. Contemporarily, brain tumor is turning out a major cause of death of many persons. The earnestness of mind tumor is vast among all kinds of cancers. Consequently, human life can be saved by the immediate detection of tumor and proper treatment to be done. Due to the abnormal formations of tumor cell, their detection becomes a complex task. It is very necessary to analyze mind tumor from MRI therapy. Brain tumor is classified into three types: Normal, Benign and Malignant. The neural network will be used to classify the phase of brain tumor that is benign, malignant or normal. Extraction of features can be done by the help of gray- level co-occurrence matrix (GLCM). Picture compression and picture recognition can be done with the help of Principal Component Analysis method (PCA) and also reduced the dimensionality of data. Classification of mind tumor is done by the help of probabilistic neural network (PNN). K-means clustering algorithm is used for Segmentation process and the detection of mind tumor spread region to be done. Numbers of defect cells are finding in the spread regions. PNN is quick process and also gives better classification accuracy. Simulation is done via MATLAB software.