The document describes a study that uses convolutional neural networks (CNNs) to detect brain tumors in MRI images. Three CNN models are developed and their performance is evaluated using various metrics like accuracy, precision, recall, F1-score, and confusion matrices. The first two models achieve accuracy of up to 94% in detecting tumors, while the third model is able to train and predict tumors with 94% accuracy as well. In total, over 2000 MRI images are used from a public dataset to train and test the models for brain tumor classification.