Multiclass Brain Tumor Classification from MRI Images Using a Lightweight CNN Model

Early and accurate classification of brain tumors is critical for effective diagnosis and treatment planning. In this work, a convolutional neural network (CNN)-based approach for multiclass classification of brain tumors using magnetic resonance imaging (MRI) is demonstrated. The proposed model classifies brain MRI images into four categories: glioma, meningioma, pituitary tumor, and no tumor. The network is trained end-to-end using normalized MRI images and evaluated using accuracy, precision, recall, F1-score, confusion matrix analysis, and receiver operating characteristic (ROC) curves. Experimental results demonstrate strong generalization performance, achieving high classification accuracy and near-perfect class separability, highlighting the effectiveness of lightweight CNN architectures for medical image analysis.