vioft2nntf2t|tblJournal|Abstract_paper|0xf4ff35562b00000040a8020001000400
Medical image process is that the most difficult and rising field these days. To solve various problems in medical imaging such as medical image segmentation, object extraction and image classification etc. This work presents a performance of the rough set based approaches. The detection and identification of brain tumour from MRI is crucial to decrease the speed of casualties. Brain tumor is tough to cure, as a result of the brain feature terribly complicated structure and also the tissues are interconnected with one another during a sophisticated manner. The proposed method uses a novel discriminative framework for multilabel automated brain tumor segmentation. The method selects the most relevant features and segments edema and tumor using a classification algorithm based on Multiple Kernel Learning (MKL). Feature selection and dictionary learning in image segmentation are usually combined with RUSBOOST classifier for identifying the tumor. The RF classifier has increased the classification accuracy as evident by quantitative results of our proposed method which are comparable or higher than the state of the art.