An Automated Brain Image Analysis System for Brain Cancer using Shearlets

摘要

In this paper, an Automated Brain Image Analysis (ABIA) system thatclassifies the Magnetic Resonance Imaging (MRI) of human brain is presented.The classification of MRI images into normal or low grade or high grade playsa vital role for the early diagnosis. The Non-Subsampled Shearlet Transform(NSST) that captures more visual information than conventional wavelet transformsis employed for feature extraction. As the feature space of NSST is veryhigh, a statistical t-test is applied to select the dominant directional sub-bandsat each level of NSST decomposition based on sub-band energies. A combinationof features that includes Gray Level Co-occurrence Matrix (GLCM) based features,Histograms of Positive Shearlet Coefficients (HPSC), and Histograms ofNegative Shearlet Coefficients (HNSC) are estimated. The combined feature setis utilized in the classification phase where a hybrid approach is designedwith three classifiers; k-Nearest Neighbor (kNN), Naive Bayes (NB) and SupportVector Machine (SVM) classifiers. The output of individual trained classifiersfor a testing input is hybridized to take a final decision. The quantitativeresults of ABIA system on Repository of Molecular Brain Neoplasia Data(REMBRANDT) database show the overall improved performance in comparisonwith a single classifier model with accuracy of 99 for normal/abnormal classificationand 98 for low and high risk classification.