Diagnosing brain health primarily relies on mag netic resonance imaging (MRI), which provides essential data for healthcare decision-makers. These images serve as a significant source of big data for artificial intelligence applications, facilitating advancements in image classification accuracy a critical subfield of AI. This study focuses on classifying brain tumors, including gliomas, meningiomas, and pituitary tumors, using brain MRI images. We employed convolutional neural networks (CNNs) and transfer learn ing methods, utilizing EfficientNetB3, ResNet50, and VGG16 architectures for classification. The performance of the models was evaluated using metrics such as precision, recall, F1-score, and overall accuracy. The results indicate that both the EfficientNetB3 and ResNet50 models achieved an overall accuracy of 99.4%. These findings underscore the effectiveness of convolutional neural network (CNN) architectures and transfer learning techniques in the early diagnosis and treatment of brain tumors.