Brain Tumor Identification and Classification of MRI Images Using Deep Learning Techniques

Brain tumor detection from Magnetic Resonance Imaging (MRI) is a critical task in medical diagnosis, as early identification can significantly improve treatment outcomes. This paper presents a Brain Tumor Identification and Classification System using deep learning techniques implemented on a Raspberry Pi platform. A USB camera module is used to capture MRI scan images, which are then processed using a trained YOLO (You Only Look Once) deep learning model to detect the presence or absence of a brain tumor. The classification result is displayed on an LCD screen with visual and audio alerts provided via LEDs and a buzzer. The proposed system offers a compact, cost-effective, and portable solution for preliminary brain tumor screening, suitable for educational, research, and assistive diagnostic applications. The system achieved confidence scores of 0.93–0.94 for normal brain classification and approximately 0.73 for tumor detection.