BRAIN TUMOR CLASSIFICATION IN MRI USING NEURAL NETWORKS

Abstract

Accurate classification of brain tumors is essential for diagnosis, treatment planning, and prognosis assessment. Manual interpretation of MRI scans is time-consuming and subject to inter-observer variability, which can affect clinical decision-making. Neural network-based approaches, particularly convolutional neural networks (CNNs) and deep learning architectures, have demonstrated significant potential in automating brain tumor classification with high accuracy. This paper reviews current methodologies for MRI-based brain tumor classification using neural networks, discussing model architectures, performance metrics, challenges such as limited annotated datasets and imaging variability, and clinical applicability. The study highlights how AI-driven classification systems can support radiologists, improve diagnostic efficiency, and contribute to personalized neuro-oncology care.