Application and Improvement of YOLO11 for Brain Tumor Detection in Medical Images

Weijuan Han^1*Xinjie Dong²Guixia Wang¹Yuwen Ding³Aolin Yang⁴

• ¹Zhongyuan Institute of Science and Technology, Zhengzhou, China
• ²Henan Public Security Department, zhengzhou, China
• ³Henan Medical College, Zhengzhou, China
• ⁴Henan University of Economics and Law, Zhengzhou, China

Brain tumors pose a critical threat to human health, and early detection is essential for improving patient outcomes. While magnetic resonance imaging (MRI) is the standard diagnostic tool, manual interpretation is labor-intensive and subject to human error. Object detection methods based on deep learning, especially the YOLO (You Only Look Once) series, have shown promise for automated tumor detection. However, challenges remain in balancing detection accuracy, computational efficiency, and real-time applicability, particularly in clinical environments with constrained hardware. This study presents two key enhancements to the YOLOv11 architecture aimed at improving brain tumor detection from MRI images. First, we integrated a set of novel attention modules (Shuffle3D and Dualchannel attention) into the network to enhance its feature extraction capability. Second, we modified the loss function by combining the Complete Intersection over Union (CIoU) with a Hook function (HKCIoU) to better penalize low-quality predictions and accelerate convergence. Experiments conducted on a public Kaggle dataset demonstrated that our improved model reduced parameters and computations by 2.7% and 7.8%, respectively, while achieving mAP50 and mAP50-95 improvements of 1.0% and 1.4%, respectively, over the baseline. Comparative analysis with existing models validated the robustness and accuracy of our approach. The model's balance of detection accuracy and computational efficiency renders it particularly suitable for deployment in clinical environments with hardware constraints.