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

Brain tumours are composed of cells where the growth is unrestrained. Though the incidence rate is lower, it is a serious threatening disease to human lives. For effective treatment, an accurate and quick method to classify Magnetic Resonance Imaging (MRI) is required. To identify the meaningful patterns and to interpret images, pattern recognition algorithms are developed. In this work, an extension of Shearlet transform named Bendlets is employed to interpret MRI images and decision making is done by ensemble learning using k-Nearest Neighbor (kNN), Naive Bayesian and Support Vector Machine (SVM) classifiers. The Bendlet and Ensemble Learning (BEL) based system utilizes Bendlet Co-Occurrence Features (BCFs) and Histograms of Positive and Negative Bendlet Coefficients (HPBC & HNBC) from the dominant sub-band as texture descriptors. The rate of classification by the BEL system for the 200 images from REpository of Molecular BRAin Neoplasia DaTa (REMBRANDT) is 99.5% at the initial stage (normal/abnormal classification) and 99% at the final stage (low-risk/high-risk classification). Based on the results, the implementation of BEL system could provide continuous monitoring of the progress of brain tumour very effectively and also offers a real-time response.