<![CDATA[Brain tumors are a serious neurological disease that require rapid and accurate diagnosis to improve treatment success. However, conventional interpretation of brain MRI images is often time-consuming and highly dependent on radiologists’ expertise, which may lead to diagnostic inconsistency. This study aims to develop a brain tumor detection and classification model from MRI images using a Convolutional Neural Network (CNN) approach. The dataset consists of four classes, namely glioma, meningioma, pituitary, and no tumor. The research stages include data collection, image preprocessing, model training, and evaluation using accuracy, loss, precision, recall, and F1-score. The results show that the CNN model achieved a training accuracy of 1.0000 at the final epoch, while the testing phase produced an accuracy of 58.75% with a loss value of 1.9600. These findings indicate that the model was able to learn important patterns from MRI images, although the gap between training and testing performance suggests overfitting. This study contributes to the development of AI-based medical image classification for brain tumor identification and shows that CNN has potential as a supportive tool for assisting medical personnel in brain tumor diagnosis. Further improvements can be achieved through data augmentation, hyperparameter tuning, and optimization of model architecture.]]>
Copyrights © 2026
