Enhancing Brain Tumor Classification Using Deep Learning

Abstract

This study aims to enhance the classification of brain tumors using advanced deep learning models applied to magnetic resonance imaging (MRI) images. The methodology involves applying pre-trained Convolutional Neural Networks (CNNs) including ResNet50, MobileNet, and Inception v2, and transformer models such as Vision Transformer (ViT) and Shifted Window (Swin). A hybrid model combining MobileNet and Swin was developed to improve classification accuracy. Data augmentation and image enhancement techniques were applied to optimize model performance. The models were rigorously evaluated using metrics such as accuracy, precision, recall, and F1-score. Among the models tested, MobileNet-Swin achieved the highest classification with accuracy of 99.65 and precision of 99.82 and recall of 99.82 and F1-score of 99.82. The findings support the effectiveness of hybrid deep learning models in assisting radiologists and improving clinical decision-making for brain tumor classification. Future work should focus on expanding the dataset and exploring additional deep learning architectures to further enhance classification accuracy.