Abstract

Due to its complex and time consuming nature, magnetic resonance imaging (MRI) can be an accurate method for classifying and independently detecting brain cancers, but it can also cause difficulties and errors. A thorough examination including several modules is required, which is the main reason for the intricacy of the brain tumor detection process. An apparent answer to this problem has been made possible by the development of deep learning (DL), which has enabled auto- mated medical image processing and diagnosis systems to occur. An important approach in visual learning and picture classification is the use of convolutional neural networks (CNNs). The suggested model is combined with a unique methodology presented in this paper, which combines two picture enhancing techniques: Adaptive Histogram Equalization (CLAHE) and Gaussian-blur-based sharpening. With this method, various types of brain tu mors are intended to be accurately classified.