Feature Extraction from Segmented Brain MRI Images using Traditional Methods and Classification Analysis of Brain Tumor using Machine Learning Classifiers

Objectives: To determine the most effective traditional method for feature extraction and Machine Learning (ML) classifier for classification of segmented brain MRI images. Methods: The dataset of brain MRI images are segmented using the Morphological Active Contour Boltzmann Monte Carlo Method (MACB) model from our previous work. The feature extraction analysis of the segmented brain MRI images is done using the traditional feature extraction methods viz. shape, Gray Level Co-occurrence Matrix (GLCM), wavelet, Local Binary Pattern (LBP) and intensity. After feature extraction, the classification of brain tumor using the ML classifiers such as Support Vector Machine, Logistic Regression, Linear Discriminant Analysis, Decision Tree (DT), Random Forest, AdaBoost, K-Nearest Neighbours and Naive-Bayes are carried out in the segmented brain MRI images. An extensive classification analysis is made to find the best feature extraction method and best ML classifier for segmented brain MRI images. The public multi-class dataset of brain MRI images available in Kaggle website are used in this work, it contains 7023 images (5712 training and 1311 testing images). Findings: The 31 features, extracted using various combinations of 5 traditional feature extraction methods, are inputted to 8 ML classifiers and performance analysis is done. It is found from the analysis that the DT classifier achieves the highest classification accuracy of 96.05%. Novelty: The key novelty of the proposed approach depends on the tumor segmentation technique using our MACB model for segmenting brain tumors in MRI images, since the MACB model has itself demonstrated better performance in providing better quality tumor delineation, as compared to traditional segmentation methods. From the dataset of MACB segmented brain MRI images, 31 features, extracted using various combinations of 5 traditional feature extraction methods, are inputted to 8 ML classifiers and a performance analysis is done. It is concluded that the DT classifier achieves higher accuracy. Keywords: Image segmentation, Feature extraction, Machine Learning classifiers, Brain tumor classification