International Research Journal of Education and Technology

Brain tumors are the most common and deadly cancer, with just a few months to live in the most advanced stages. As a result, therapy planning is a crucial step in improving the quality of life of patients. Tumors in the brain, lung, liver, breast, prostate, and other organs are regularly assessed using several image modalities such as computed tomography (CT), magnetic resonance imaging (MRI), and ultrasound pictures. In this study, MRI images are used to diagnose brain tumor in particular. An MRI scan, on the other hand, collects so much data that manual classification of tumor vs. non-tumor in a given period is unfeasible. It does, however, have some drawbacks (for example, reliable quantitative measures are only available for a restricted number of photos). As a result, to lower the rate of human fatalities, a reliable and automatic classification technique is necessary. Due to the large geographical and structural variety of the brain tumor’s surrounding environment, automatic brain tumor classification is a difficult task. This research proposes the use of Convolutional Neural Networks (CNN) classification for automatic brain tumor identification. If a tumor is discovered, the system classifies it and informs the patient about the stage of the tumor he is likely to experience. Our system gets 99.25% accuracy.

Keywords: CNN classifier, MRI image processing, Brain tumor detection.