A CNN-Based Strategy to Classify MRI-Based Brain Tumors Using Deep Convolutional Network

Brain tumor is a severe health condition that kills many lives every year, and several of those casualties are from rural areas. However, the technology to diagnose brain tumors at an early stage not as efficient expected. Therefore, we sought create reliable system can help medical professionals identify tumors. Although studies being conducted on this issue, attempted establish much more error-free classification method, which trained with comparatively substantial number real datasets rather than augmented data. Using modified VGG-16 (Visual Geometry Group) architecture 10,153 MRI (Magnetic Resonance Imaging) images 3 different classes (Glioma, Meningioma, Pituitary), network performs significantly well. It achieved precision 99.4% for Glioma, 96.7% 100% Pituitary, overall accuracy 99.5%. also attained better results other existing CNN architectures state-of-the-art work.