Brain Tumor Classification Accuracy Enhancement via DenseNet201 Compared to Four Alternative Models

Early brain tumor staging is critical to the success of currently available treatment planning and modalities. Magnetic Resonance Imaging (MRI) is a necessary method for treatment planning and early diagnosis. Most current classification methods do not achieve a high level of classification accuracy, which may result in some tumor cases being misclassified or classified as suspicious. In our proposed work, we leverage the DenseNet201 deep learning architecture as the foundation for classifying brain tumors. A dataset in this methodology consisted of MRI scans, which included four unique types of tumors: meningioma, pituitary tumor, no tumor, and glioma. To improve classification precision, improve generalization, and reduce overfitting, we employed three strategies (a1, a2, and a3) during the classification process. When our model was evaluated on unseen test data, it achieved an impressive 99.77\% accuracy. The proposed technique effectively classifies malignant brain tumors, despite the similarities within classes and the varying tumor morphologies. There are four state-of-the-art techniques of deep learning that we compared our results with: ResNetRS50, ResNet50, VGG19, and EfficientNetV2, which achieved accuracies of 99.77\%, 98.71\%, 96.88\%, and 96.58\%, respectively. In the field of brain tumor classification, our approach has outperformed others in terms of performance, highlighting its potential for clinical applications.