Abstract: One of the leading causes of cancer-related deaths globally is brain tumors. The categorization of brain tumors is a challenging scientific problem. Brain tumors come in a wide range of sizes, shapes, and intensities. It's possible for tumors from different pathological classifications to look similar. Brain tumors can be classified and diagnosed using a variety of imaging methods. Fortunately, due to its superior image quality and lack of ionizing radiation, Magnetic Resonance Imaging (MRI) is frequently used. Recent developments in deep learning have made it possible for radiologists to quickly analyse medical images using artificial intelligence (AI) techniques. In order to classify various types of brain tumors, CNN models can assist physicians and radiologists in validating their initial screening.

Keywords: Convolutional neural network , Deep learning ,Grid search, Hyper-parameter optimization, Tumor grading.

| DOI: 10.17148/IARJSET.2023.10221