BrainNet-7: A CNN Model for Diagnosing Brain Tumors from MRI Images based on an Ablation Study

Tumors in the brain are masses or clusters of abnormal cells that may spread to other tissues nearby and pose a danger patient. The main imaging technique used determine extent tumors is magnetic resonance imaging, which ensures an accurate diagnosis. A sizable amount data for model training advances designs provide better approximations supervised environment likely account most growth Deep Learning techniques computer vision applications. learning approaches have shown promising results increasing precision tumor identification classification using (MRI). This study’s purpose describe robust deep-learning categorizes MRI images into four classes based on convolutional neural network (CNN). By removing artefacts, reducing noise, enhancing image, unwanted areas deleted, quality improved, highlighted. Several CNN architectures, including VGG16, VGG19, MobileNet, MobileNetV2, InceptionV3, investigated compare get best model. After getting model, hyper parameter ablation study was performed Proposed BrainNet-7 achieved with 99.01% test accuracy 99.21% validation accuracy.