Detecting Anomalies present in Brain MRI

A brain tumor is a mass of unnecessary cells growing in the brain. Brain tissue classification from magnetic resonance images (MRI) is of great importance for research and clinical studies of the normal and diseased human brain. In just a few decades, the use of magnetic resonance imaging (MRI) scanners has grown enormously. An MRI scan is the best way to see inside the human body without cutting it open. It uses strong magnetic fields and non-ionizing radiation in the radio frequency range. Brain tumor effects may not be the same for each. Brain tumors can have a variety of shapes and sizes person. In This Paper, We have take two dimension MRI jpeg image, then Normalized cut segmentation is performed on it after that we get three different images. First one is colour image for separating different parts of images. If any anomalies are present in the brain then it should be seen also. Second one is image noise must be removed from the image. And last part is edges are detected from image after that we are taking the color image and converting those images into matrix format. Then we get some vector value on the basis of that vector value classification must be performed by using the approach of ANN. Key Words— Magnetic Resonance Images (MRI), Brain Tumor Detection, brain MRI classification, Artificial Neural Network (ANN), Normalized cut segmentation