ResNet-50 Based Intelligent System for Brain Tumor Detection

Detection of brain tumors via MRI scans is a healthcare imperative complicated by the enormous variationin the shapes and locations of the tumors. This project proposes the application of deep learning using the ResNet-50convolutional neural network to automatically classify brain tumors from MRI scans. The system not only aims for highdiagnostic accuracy but also incorporates Grad-CAM heatmaps to provide visual interpretation of the model’spredictions, enhancing transparency in clinical decision-making. Through extensive preprocessing, data augmentationduring model training, and a user-friendly web interface, the system is designed to be both powerful and practical forreal-world medical use