Brain Tumor Detection and Localization with YOLOv8
A comprehensive approach for brain tumor detection using the BR35h dataset and the YOLOv8 algorithm is proposed, and the evaluation of loss values highlights the potential of the model as a valuable tool for accurate and efficient brain tumors detection, which may help physicians make more informed decisions efficiently.
Abstract
Brain tumor detection plays a crucial role in the early diagnosis as well as treatment planning of neuro-oncological conditions. Accurate localization and identification of brain tumors using magnetic resonance imaging (MRI) images are essential for guiding medical interventions. In this paper, a comprehensive approach for brain tumor detection using the BR35h dataset and the YOLOv8 algorithm is proposed. BR35h dataset consists 800 of magnetic resonance images (MRI), with tumor perimeters annotated. Hence, this study's goal is to employ the latest version of YOLO, which is YOLOv8, to create a model that locates and detects brain tumors in a given MRI image. Through various evaluations, the suggested model achieves high performance with a mean average precision (mAP) of 97.6%. Additionally, the evaluation of loss values is discussed, showcasing the model's progress in detecting and localizing brain tumors. The outcomes highlight the potential of the model as a valuable tool for accurate and efficient brain tumor detection, which may help physicians make more informed decisions efficiently.