Brain Tumor Classification Using Computer Vision and Deep Learning Techniques

Abstract

This research addresses the critical task of brain tumor detection and classification by leveraging advanced neural networks and deep learning techniques. The study focuses on detecting three prevalent types of brain tumors—glioma, meningioma, and pituitary tumors—as well as identifying cases without tumors. Two cutting-edge deep learning models, You Only Look Once version 11 (YOLOv11) and Visual Geometry Group 19 (VGG19), were utilized for precise detection and classification. The methods were tested on an expanded dataset, which contributed to improved accuracy and robustness in model training and evaluation. Comparative analysis with earlier algorithms and older neural network models demonstrated significant enhancements in detection accuracy, classification speed, and overall system performance. These improvements highlight the potential of YOLOv11 and VGG19 for early brain tumor detection, which is vital for timely diagnosis and better patient outcomes. Our findings suggest that the application of these models in medical imaging can lead to more effective and accurate diagnoses, presenting a promising direction for future advancements in brain tumor detection.