Brain Tumor Detection in MRI Images with YOLOv12

The precise identification of brain tumors via MRI imaging continues to pose a considerable challenge within the domain of medical diagnostics. Although conventional deep learning models have shown effectiveness, they often encounter difficulties in detecting accuracy and efficiency in various types of tumors. In this research, we introduce an enhanced approach for brain tumor detection that employs the latest YOLOv12 object detection framework. We assess and contrast the performance of YOLOv12 with several other leading models, illustrating its supe- rior detection accuracy. The YOLOv12n model notably achieves the highest mAP@50 of 93.3%, outperforming previous YOLO versions and conventional techniques. The model is trained and evaluated using a comprehensive MRI dataset that includes various tumour types, thereby ensuring its generalisability and robustness. These findings highlight YOLOv12’s potential as a reliable, quick, and accurate method for real-time brain tumor diagnosis and medical picture analysis.