Detecting Glioma, Meningioma, and Pituitary Tumors, and Normal Brain Tissues based on Yolov11 and Yolov8 Deep Learning Models

TL;DR

The study tackles the problem of rapid, accurate MRI-based classification of brain tissue into No-Tumor, Glioma, Meningioma, and Pituitary tumors. It systematically compares YOLOv8, YOLOv11, and a customized CNN on a multi-source dataset using transfer learning and data augmentation to assess performance. Key findings show YOLOv8 and YOLOv11 achieving near-perfect accuracies (approximately 99%+) on training and validation, while the customized CNN also performs strongly (around 98% accuracy), underscoring that optimized CNNs can surpass some pre-trained models in domain-specific tasks. The work provides benchmark evidence and demonstrates the potential for real-time, reliable brain-tumor diagnostics in clinical practice by combining advanced YOLO architectures with tailored CNN design and diverse MRI datasets.

Abstract

Accurate and quick diagnosis of normal brain tissue Glioma, Meningioma, and Pituitary Tumors is crucial for optimal treatment planning and improved medical results. Magnetic Resonance Imaging (MRI) is widely used as a non-invasive diagnostic tool for detecting brain abnormalities, including tumors. However, manual interpretation of MRI scans is often time-consuming, prone to human error, and dependent on highly specialized expertise. This paper proposes an advanced AI-driven technique to detecting glioma, meningioma, and pituitary brain tumors using YoloV11 and YoloV8 deep learning models. Methods: Using a transfer learning-based fine-tuning approach, we integrate cutting-edge deep learning techniques with medical imaging to classify brain tumors into four categories: No-Tumor, Glioma, Meningioma, and Pituitary Tumors. Results: The study utilizes the publicly accessible CE-MRI Figshare dataset and involves fine-tuning pre-trained models YoloV8 and YoloV11 of 99.49% and 99.56% accuracies; and customized CNN accuracy of 96.98%. The results validate the potential of CNNs in achieving high precision in brain tumor detection and classification, highlighting their transformative role in medical imaging and diagnostics.

Figures (7)

• Figure 1: The framework of our study
• Figure 2: YOLOv8 Accuracy & Loss
• Figure 3: YOLOv11 Accuracy & Loss
• Figure 4: YOLOv8 Confusion Matrix
• Figure 5: YOLOv11 Confusion Matrix