Brain Tumor Detection using modified VGG-19 and Inception ResnetV2 models

A brain tumor is characterized as an aggregation of abnormal cells within the brain. These tumors can be classified into two categories: malignant and benign. Malignant is cancerous whereas benign is not. Both tumors are very hazardous as they grow rapidly and attack different parts of the cerebrum. Even after extensive research, the cause of the brain tumor is unknown. In this paper, a VGG-19 and an Inception-Resnet V2 model are presented for detecting brain tumor by employing images of MRI scans. The dataset is gathered from Kaggle and preprocessed using Keras Image Data Generator. The VGG-19 model provided an accuracy of 99.71% and the Inception-Resnet V2 provided an accuracy of 99.28%. The proposed models performed well to achieve the task.