Identification And Classification Of Brain Tumor From MRI Using Transfer Learning Approach

Brain tumor is one of the most common causes of death. The early detection of a brain tumor is essential for a quicker course of treatment, and numerous approaches are employed to identify a brain tumor from the imaging modality of Magnetic Resonance Imaging (MRI). Convolutional Neural Network (CNN) approach, on the other hand, is the state-of-the-art technology employed in recent years to solve various medical image-related challenges, such as classification. In this study, three different forms of brain tumors—glioma, meningioma, and pituitary gland—were identified and categorized using ResNet50. There are 1861 images in the dataset utilized for this study. The proposed approach is developed using transfer learning technique and it accurately identifies the classes of brain tumors with 99% testing accuracy.