This paper introduces the application of YOLOv9, the latest version of the You Only Look Once (YOLO) series, to the task of fracture detection in pediatric wrist trauma X-ray images. The authors trained the YOLOv9 model on the GRAZPEDWRI-DX dataset, a dataset containing 20,327 X-ray images of pediatric wrist trauma, and extended the training set using data augmentation techniques to improve model performance. The experimental results show that the YOLOv9 model achieved a mean average precision (mAP) 50-95 of 43.73%, an improvement of 3.7% over the current state-of-the-art (SOTA) model. The paper highlights the effectiveness of YOLOv9 in real-time object detection and its potential as a computer-assisted diagnosis (CAD) tool for radiologists and surgeons. The implementation code is publicly available on GitHub. The main contributions of the paper include the first application of YOLOv9 to fracture detection, addressing information loss in X-ray images, and achieving SOTA performance on the GRAZPEDWRI-DX dataset. The paper also discusses the limitations of the model in predicting "bone anomaly" and "soft tissue" classes due to insufficient data and suggests future research directions to enhance these areas.This paper introduces the application of YOLOv9, the latest version of the You Only Look Once (YOLO) series, to the task of fracture detection in pediatric wrist trauma X-ray images. The authors trained the YOLOv9 model on the GRAZPEDWRI-DX dataset, a dataset containing 20,327 X-ray images of pediatric wrist trauma, and extended the training set using data augmentation techniques to improve model performance. The experimental results show that the YOLOv9 model achieved a mean average precision (mAP) 50-95 of 43.73%, an improvement of 3.7% over the current state-of-the-art (SOTA) model. The paper highlights the effectiveness of YOLOv9 in real-time object detection and its potential as a computer-assisted diagnosis (CAD) tool for radiologists and surgeons. The implementation code is publicly available on GitHub. The main contributions of the paper include the first application of YOLOv9 to fracture detection, addressing information loss in X-ray images, and achieving SOTA performance on the GRAZPEDWRI-DX dataset. The paper also discusses the limitations of the model in predicting "bone anomaly" and "soft tissue" classes due to insufficient data and suggests future research directions to enhance these areas.