BRAIN CANCER CLASSIFICATION USING MACHINE LEARNING

ABSTRACT Brain cancer remains one of the most life-threatening diseases, requiring timely and accurate diagnosis to improve patient survival rates. Traditional diagnostic techniques such as manual MRI interpretation are often time-consuming and prone to human error. This research focuses on the development of a machine learning-based system for brain cancer classification using magnetic resonance imaging (MRI). The system leverages deep learning techniques, specifically a Convolutional Neural Network (CNN) model, trained on a Kaggle dataset containing over 3,000 MRI images categorized into glioma, meningioma, pituitary, and no tumor classes. The model was trained using TensorFlow and Keras frameworks, employing image preprocessing, augmentation, and normalization to improve classification accuracy. Experimental results demonstrated that the developed model achieved high precision and accuracy in detecting and classifying different brain tumor types. The system provides an automated, reliable, and efficient diagnostic tool that can assist radiologists in early tumor detection, reduce diagnostic delays, and enhance clinical decision-making. This study underscores the potential of machine learning in advancing medical image analysis and improving healthcare outcomes for brain cancer patients.