Hip surgeries require precise and timely interpretation of X-ray images to identify structures, implants, and abnormalities. This research focuses on reducing surgery time by automating the annotation of hip X-rays using deep learning models, specifically YOLOv8 and YOLOv7, which are optimized for object detection in medical imaging. The models accurately identify and label key anatomical features and abnormalities, assisting surgeons with real-time insights that streamline both preoperative planning and intraoperative procedures. By automating annotations, this approach minimizes manual workload, reduces surgery duration, and enhances the precision of surgical interventions, ultimately aiming to improve patient outcomes and surgical efficiency in orthopedic practices.