Classification Of Brain Tumor using Deep Learning CNN

Brain tumors are a common and serious illness that, at their most advanced stages, can reduce life expectancy to a few years. Therefore, coming up with a treatment plan is essential to improving patients’ quality of life. To assess malignancies in the brain, lungs, liver, breast, and prostate, among other parts of the body, methods including computed tomography (CT), magnetic resonance imaging (MRI), and ultrasound are commonly used. Certain forms of brain cancer can be detected with MRI in particular. However, it might be difficult to differentiate between tumor and non-neoplastic regions due to the large amount of data produced by MRI scans, and the lack of images can result in errors. A trustworthy and automated technique for tumor separation is necessary to get around this. Automatically distinguishing between brain tumors is a particularly difficult endeavor, especially when dealing with huge regions and the intricate differences in tumor morphologies. Convolutional Neural Networks (CNNs) are used in this study to automatically detect brain tumors. Small, intricate structures can be processed by the network architecture. A brain tumor is a malignant development brought on by aberrant and unchecked cell partition. Medical diagnosis has benefited greatly from developments in deep learning for pictures of medical conditions. This field makes extensive use of machine learning methods, particularly those that employ sight-based learning or image perception (CNNs).