Klasifikasi Hasil Mri Tumor Otak Dengan Ektraksi Fitur Gray Level Co-Occurance Matrix (Glcm)

Abstract

An important part of the body is the brain which is the source of all the body's organs in the skull cavity. Brain tumors are one of the diseases that can attack it. Detection of brain tumors is one aspect that is considered important in medical diagnosis. This research aims to implement GLCM (Gray Level Co-occurrence Matrix) feature extraction on MRI images of brain tumors and to find the best algorithm performance for detecting brain tumors using these MRI images. The data used in this research is public data originating from kaggle.com. The feature extraction process in pictures used in this research is GLCM, which has the function of calculating the frequency of pixel intensity values ​​that are spaced between images using parameters 0o, 45o, 90o, and 135o. The next stage in this research is to carry out preprocessing steps and then look for classification values ​​from the MRI results using the Naïve Bayes, C4.5, and Neural Network algorithms. The results obtained show that Naïve Bayes has the best algorithm performance compared to C4.5 and Neural Network, namely with an accuracy of the Naïve Bayes algorithm of 96.8%, while for the C4.5 algorithm it is 41.5% and the Neural Network is 38.25%. Apart from this, this study proves that GLCM feature extraction has proven effective in capturing texture information from MRI images which is very important in brain tumor classification.