Segmentation of Gliomas using GLCM Features and Classification of Gliomas in Brain using SVM Classifier

Abstract

Brain Gliomas is one among the biggest threat faced by many people around the globe. According to Inter- national Agency of Research on Cancer (IARC) more than one million people are diagnosed with brain gliomas per year around the globe, with increased fatal rate. During its studies, the occurrence of the abnormal tissues is simple to detect most   of the time; still accurate segmentation and characterization of these abnormalities are not genuine. In the present situation, radiologists have to manually study the reports with the available medical imaging machines and write a report.  This process is time consuming. In fact that, numerous advancement being done, butsegmentation of brain gliomas from MR Images in a rapid, accurate, legitimate and far sighted way is still a demanding role. To overcome this situation a system which can detect the gliomas and will differentiate them as gliomas and non-gliomas has been proposed in this project by using image processing in addition with machine learning, which will help to detect the gliomas and classify them into gliomas or non-gliomas in no time. In this approach, stage by stage techniques for image pre- processing, segmenting brain gliomas using morphological operations, retrieval of gliomas feature using contrast and correlation, classification of the gliomas using SVM is completed with the actual clinical data.