Authors: Pratik Pandey, Nagendra Patel
Abstract: Brain tumor detection through magnetic resonance imaging (MRI) plays a crucial role in early diagnosis and treatment planning. This study presents a comparative analysis of five deep learning models—CNN, ResNet50, U-Net, YOLOv7, and InceptionResNetV2 for accurate classification of brain tumors. The dataset was preprocessed with cleaning, augmentation, and normalization before training and evaluation. Performance was measured using accuracy, precision, recall, and F1-score. Results demonstrate that all models achieved strong outcomes, but InceptionResNetV2 significantly outperformed others, reaching nearly 100% across all metrics. This superior performance highlights its effectiveness in minimizing false positives and false negatives, thereby offering a robust tool for clinical applications. The findings emphasize the importance of advanced deep learning architectures in medical imaging for reliable tumor detection.
