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.

No abstract

In this paper a new tumor classification system has been designed and developed for MRI systems. The MR imaging is a mostly used scheme for high excellence in medical imaging, it gives clear imageing capability especially in brain imaging where the soft-tissues contrast and non invasiveness is a clear advantage. The proposed method consists of three stages namely pre-processing, feature extraction and classification. In the first stage, gausian filter is applied for extracting the noise for experimental image. In the second stage, Statistical texture features are extracted for the purpose of classification. Finally, the decision tree classifier is used to classify the type of tumor image. In our proposed system classification has two divisions: i) training stage and ii) testing stage. In the training stage, various features are extracted from the tumor and non tumor images. In testing stage, based on the knowledge base, the classifier classify the image into tumor and non-tumor. Thus, the proposed system has been evaluated on a dataset of 40 patients. The proposed system was found efficient in classification with a sucesss of more than 95% of accuracy.

No abstract