Detection and Classification of Brain Tumors using Convolutional Neural Network

Abstract

According to statistics from WHO, brain tumors will account for roughly 9.5 million deaths globally in the next few decades. Early identification and treatment are the best ways to stop deaths from brain cancer. Brain tumors fall into two categories: benign, which is not cancerous, and malignant, which is cancerous. A brain tumor that originates in a specific location and then metastasizes to other regions of the body, including other areas of the brain, is referred to as a primary tumor. Secondary tumors, commonly referred to as metastatic tumors, arise from primary tumors. It is now possible to more easily analyze medical pictures thanks to the quick development of image processing and soft computing technologies that aid in early detection and therapy. The use of computer-aided diagnostic (CAD) technology for diagnosing illnesses, predicting prognoses, and determining the likelihood of recurrence is expanding as a result of technological improvements. The main area of investigation in this study is the utilization of feature extraction and tumor cell classification for the automatic identification and categorization of brain tumors in magnetic resonance imaging (MRI) scans. Brain tumor detection and classification are done using CNN, and VGG-16 models. Accuracy is obtained by doing a comparative study of these two models. VGG-16 is the best-trained model.