Brain tumors are abnormal growths of cells in the brain that can be life-threatening if not diagnosed and treated promptly. Early and accurate detection of brain tumors is crucial for effective treatment planning and improvingpatientsurvival rates. Traditional methods of tumor diagnosis rely heavily on manual inspection of Magnetic Resonance Imaging (MRI) scans by radiologists, which can be time consuming, subjective, and prone to human error. With the advancement of artificial intelligence and deep learning techniques, automated systems have emerged as an effective solution to support medical professionals in accurate and faster diagnosis. This project focuses on developing an automated brain tumor classification system using MRI images and deep learning   models,   particularly Convolutional Neural Networks (CNNs). The system is designed to classify brain MRI scans into four categories: glioma tumor, meningioma tumor, pituitary tumor, and normal (no tumor). The methodology involves several key stages: image acquisition, preprocessing to enhance image quality and reduce noise, feature extraction using CNN layers, and  multi-class classification. The CNN model automatically learns hierarchical features from the MRI scans, capturing subtle patterns and variations that may not be easily visible to the human eye. To evaluate the performance of the proposed system, the model is trained and tested on a labeled dataset of brain MRI images. Metrics such as accuracy, precision, recall, F1-score, and confusion matrix analysis are used to assess the model’s effectiveness. The proposed automated system offers several advantages: it reduces the workload of radiologists, minimizes the chances of diagnostic errors, and accelerates the overall diagnostic process. By integrating deep learning techniques with medical image processing, this project not only enhances diagnostic accuracy but also contributes to the broader field of computer-aided medical diagnosis,ultimately improving healthcare outcome