Classification of MRI Brain Tumor Images using Deep Learning Segment Anything Model for segmentation and Deep Convolution Neural Network

Brain tumors pose a significant health challenge by putting pressure on healthy parts of the brain or spreading into other areas and blocking the flow of fluid around the brain. Thus, identifying and categorizing the tumor is crucial for delivering effective treatment, especially if detected early. This means the tumor is smaller, and treatment is more effective, less invasive, and has fewer side effects. In recent years, many researchers have developed computer vision, and more specifically, deep learning methods, to automate the analysis of brain MRI scans. These methods enable efficient processing and improve the accuracy of detecting small tumors. This paper aims to propose a deep-learning method for classifying brain tumors. In this work, the input image goes through two subprocesses: first, object detection to identify the tumor's location. Then, a fine-tuned Segment Anything Model (SAM) was applied to extract the lesion from the background. Finally, deep learning Convolution Neural Network (CNN), is applied to the cropped image for classification. This method will help doctors and researchers detect tumors at the initial stages