<![CDATA[Magnetic Resonance Imaging (MRI) is an imaging modality that uses a non-ionising magnetic field, so it does not cause radiation exposure. However, a high magnetic field strength still poses a significant safety risk due to projectile effects, so screening is necessary to verify that standard MRI objects are present. This study aims to develop an MRI-safe Label Detection using You Only Look Once version 11 (YOLOv11) Framework. The YOLOv11 is one of the Deep Learning algorithms that is used for Real-time Object Detection with Medical Imaging Standardization. The dataset used consists of a standard MRI bed image and a normal patient bed obtained from several MRI facilities, with an image size of 640 pixels, and divided into four classes. The results show that the model achieves an accuracy of 97,5%, a precision of 99,1%, a recall of 98,8%, an F1-Score of 98,9%, and an mAP50 of 98,9%, which indicates excellent detection performance. The Loss curve analysis shows a stable training process without any indication of significant overfitting. In addition, the confusion matrix shows high classification ability in each class. This research aims to develop an automated safety screening system for zone three MRI to reduce the risk of accidents. However, limitations include the small number of datasets and the limited variety of objects. Therefore, further development is recommended by increasing the variety of object data and integrating real-time systems and supporting hardware.]]>
