Abstract: Medical image classification is a pattern recognition technique in which different images are categorized into several groups based on some similarity measure. One of the significant applications is the tumor type identification in abnormal MRI brain images. Magnetic resonance image segmentation is widely used by the radiologists to segment the medical images into meaningful regions. The proposed system comprises feature extraction and classification. In feature extraction, the attribute of the co-occurrence matrix and the histogram is represented within this feature vector. In this research, the advantage of both co-occurrence matrix and histogram to extract the texture feature from every segment is used for better classification of images. In classification, the fuzzy logic based hybrid kernel is designed in the classification stage and applied to train of fuzzy logic based support vector machine to perform automatic classification of four different types of brain tumor such as meningioma, glioma, astrocytoma and metastase. The proposed method is validated using k-fold cross validation method. Based on the experimental results, the proposed modified MSD with fuzzy hybrid kernel SVM based brain tumor classification method is more robust than other traditional methods in terms of the evaluation metrics, sensitivity, specificity and accuracy.
A. Prabin and J. Veerappan, 2016. Classification of Multi Class Brain Tumor in Magnetic Resonance Images Using Hybrid Struture Descriptor. Asian Journal of Information Technology, 15: 2880-2886.