Median Filter Based Denoising And Classification of MRI Brain Tumor using Convolutional Neural Networks

One of today's sensitive topic is the categorization of brain tumors. And they are very difficult task to find the tumors and take a treatment decision based on their classes. There are many issues related to this subject, such as poor image resolution, classification and the ability to predict tumors in new brain images. There are various types of imaging techniques are used to find the tumors. But,MRI is a commonly used technique to detect the tumor. Since MRI images have poor contrast, it can be challenging to classify and find the position of the tumor.Consequently, an image first undergoes preprocessing, which usually involves image, which typically includes image enhancement, finding the best with the help of parameter estimation will make classification simpler. The proposed work beginwith enhancing the image with the aid of six type of filters. Then, in order to determine the best filter for high-quality images, parameter estimation techniques is done using SNR and PSNR in MATLAB. After that, use Convolutional Neural Networks (CNN) to categorize the different types of brain tumors. Meningioma, glioma, and pituitary tumors are the three groups into which tumors are classified by CNN. It also displays the tumor's position, type, size and location.