 This paper proposes a novel approach to detect and classify brain tumors using deep learning techniques. It uses a combination of convolutional neural networks, CNNs, and residual networks, ResNets, which are both well-known methods in computer vision. The CNNs are used to detect the presence of tumors in the image, while the ResNets are used to classify the tumor into benign or malignant. Additionally, the UNET model is used to segment the tumor region more precisely. The model was tested on a publicly available dataset consisting of 120 patients, and it achieved high accuracy rates of up to 95%. This article was authored by Abdullah Asairi, Ahmad Shaf, Tariq Ali, and others.