Image classification is one of the typical computational applications widely used in the medical field, especially for abnormality detection in magnetic resonance (MR) brain images. Medical image classification is a pattern recognition technique in which different images are categorized into several groups based on some similarity measures. One of the significant applications is the tumor type identification in abnormal MR brain images. The proposed multi-class brain tumor classification system comprises feature extraction and classification. In feature extraction, the attributes of the co-occurrence matrix and the histogram are represented within the feature vector. In this work, the advantage of both co-occurrence matrix and histogram to extract the texture feature from every segment is used for better classification. In classification, the fuzzy logic-based hybrid kernel is designed and applied to train the support vector machine for automatic classification of four different types of brain tumors such as Meningioma, Glioma, Astrocytoma, and Metastases. Based on the experimental results, the proposed brain tumor classification method is more robust than other traditional methods in terms of the evaluation metrics, sensitivity, specificity, and accuracy.

Segmentation is the process of labeling objects in image data. It is a decisive phase in several medical imaging processing tasks for operation planning, radio therapy or diagnostics, and widely useful for studying the differences of healthy persons and persons with tumor. Magnetic Resonance Imaging brain tumor segmentation is a complicated task due to the variance and intricacy of tumors. In this article, a tumor segmentation scheme is presented, which focuses on the structural analysis on both tumorous and normal tissues. Our proposed method hits the target with the aid of the following major steps: (i) Tumor Region Location, (ii) Feature Extraction using Multi-texton Technique, and (iii) Final Classification using support vector machine (SVM). The results for the tumor detection are validated through evaluation metrics such as, sensitivity, specificity, and accuracy. The comparative analysis is carried out by Radial Basis Function neural network and Feed Forward Neural Network. The obtained results depict that the proposed Multi-texton histogram and support vector machine based brain tumor detection approach is more robust than the other classifiers in terms of sensitivity, specificity, and accuracy.

No abstract

No abstract

No abstract