Timely and successful therapy relies on the correct diagnosis and categorization of brain tumors. In this study, we present a deep learning-based method for the automated identification of brain tumors in MR images. We used a data collection that was available to the public and included both MRI images of brain tumors and normal brain. We down sampled the images, added more data, and normalized the pixel values as preliminary processing. We utilized the cleaned data set to construct a deep learning model based on VGG19. Our model showed a 96.3% accuracy, 96.3% AUC ROC score, 96% precision, 96% recall, and 96% F1 score. To evaluate our model’s performance, we used various metrics such as accuracy, precision, recall, F1 score, confusion matrix, AUC ROC score, and ROC curve. Furthermore, we compared our model’s results with the best performing model from a related study that utilized machine learning algorithms such as Random Forest, SVM, Logistic regression, Gradient boosting, and the achieved accuracy is 92.4%, precision is 85.0%, recall is 94.4%, F1 score of 89.5%, and AUC ROC score touching 97.2%.