An Experimental Analysis of Brain Tumor Detection Using Contemporize CNN Models

A growth of brain tumor or abnormal cells leads to the cancerous. Cells in a brain tumor proliferate rapidly and indefinitely, and the tumor's pace of growth is uncontrollable. Deep learning has been proposed as a potential solution to the challenges of diagnosing and treating brain cancer. Deep learning and machine learning algorithms provide a quicker prediction of a brain tumor, and a better degree of accuracy facilitates patient care. The goal of this study was to develop a contemporize convolutional neural network (CNN) model framework and provide training and accuracy prediction parameters. Our suggested technique was tested on a dataset for brain tumor diagnosis using MRI images showing 150 tumors. In the testing data, the algorithm achieved remarkable accuracy of 94%, validation accuracy of 92.34%, and test accuracy of 94.5%, surpassing current conventional methods for brain cancer detection.