Bone Fracture Detection and Treatment Recommendation Utilizing the YOLOv8 Deep Learning Framework
Keywords:
Bone fracture detection, Clinical decision support system, Deep learning, Medical imaging, Object detection, X-ray analysis, YOLOv8Abstract
Diagnosing bone fractures through X-ray images is essential in emergency and orthopedic settings, yet it often involves lengthy processes and is susceptible to human mistakes. This study introduces a real-time bone fracture detection system utilizing YOLOv8 to accurately pinpoint fracture locations. Unlike traditional classification models that merely display the presence of fractures, this system identifies and marks fracture areas with bounding boxes and confidence scores, enabling accurate spatial analysis of abnormalities. The framework employs sophisticated preprocessing methods and optimized training strategies to improve detection reliability across different image qualities and anatomical areas. Additionally, a rule-based treatment recommendation module offers initial clinical advice based on the identified fracture type and its estimated severity, thus extending the system's functionality from detection to clinical decision support. Experimental findings reveal high detection accuracy, strong mean Average Precision (mAP), favorable precision-recall characteristics, and real-time inference capability with minimal delay. The system serves as an intelligent second-reader tool aimed at aiding radiologists and orthopedic specialists in enhancing diagnostic efficiency, minimizing missed fractures, and standardizing fracture evaluation in high-volume healthcare settings.
References
T. Meena and S. Roy, “Bone Fracture Detection Using Deep Supervised Learning from Radiological Images: A Paradigm Shift,” Diagnostics, vol. 12, no. 10, pp. 2420, Oct. 2022.
M. Kutbi, “Artificial Intelligence-Based Applications for Bone Fracture Detection Using Medical Images: A Systematic Review,” Diagnostics, vol. 14, no. 17, pp. 1879–1879, Aug. 2024.
Z. Su, A. Adam, M. F. Nasrudin, M. Ayob, and G. Punganan, “Skeletal Fracture Detection with Deep Learning: A Comprehensive Review,” Diagnostics, vol. 13, no. 20, pp. 3245, Jan. 2023.
R. Rahman, N. Yagi, K. Hayashi, Akihiro Maruo, Hirotsugu Muratsu, and S. Kobashi, “Enhancing Fracture Diagnosis in Pelvic X-Rays by Deep Convolutional Neural Network with Synthesized Images From 3D-CT,” Scientific Reports, vol. 14, no. 1, Apr. 2024.
İ. Yıldız Potter et al., “Proximal Femur Fracture Detection on Plain Radiography via Feature Pyramid Networks,” Scientific Reports, vol. 14, no. 1, May 2024.
T. Aldhyani et al., “Diagnosis and Detection of Bone Fracture in Radiographic Images Using Deep Learning Approaches,” Frontiers in Medicine, vol. 11, Jan. 2025.
Ç. B. Erdaş, “Automated Fracture Detection in the Ulna and Radius Using Deep Learning on Upper Extremity Radiographs,” Joint Diseases and Related Surgery, vol. 34, no. 3, pp. 598–604, Aug. 2023.
Abdusalomov, S. Mirzakhalilov, O. Ismailov, and Y.-I. Cho, “Lightweight Deep Learning Framework for Accurate Detection of Sports-Related Bone Fractures,” Diagnostics, vol. 15, no. 3, pp. 271–271, Jan. 2025.
Alshahrani and A. Alsairafi, “Bone Fracture Classification Using Convolutional Neural Networks from X-Ray Images,” Engineering, Technology & Applied Science Research, vol. 14, no. 5, pp. 16640–16645, Oct. 2024.
Y. Liu, K. Gan, J. Li, D. Sun, H. Qiu, and D. Liu, “Study on Automatic and Rapid Diagnosis of Distal Radius Fracture by X-Ray,” Journal of Biomedical Engineering, vol. 41, no. 4, pp. 798–806, 2024.
Hassan and I. Afzaal, “AI-Based Applied Innovation for Fracture Detection in X-Rays Using Custom CNN and Transfer Learning Models,” Arxiv.org. 2026.
H. M. Ehsanul et al., “A Modified VGG19-Based Framework for Accurate and Interpretable Real-Time Bone Fracture Detection,” Arxiv.Org. 2026.
Y. L. Thian, Y. Li, P. Jagmohan, D. Sia, V. E. Y. Chan, and R. T. Tan, “Convolutional Neural Networks for Automated Fracture Detection and Localization on Wrist Radiographs,” Radiology: Artificial Intelligence, vol. 1, no. 1, p. e180001, Jan. 2019.
K. He, X. Zhang, S. Ren, and J. Sun, “Deep Residual Learning for Image Recognition,” 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 770–778, Jun. 2016.
Bochkovskiy, C.-Y. Wang, and H.-Y. M. Liao, “YOLOv4: Optimal Speed and Accuracy of Object Detection,” arXiv, vol. 1, Apr. 2020.
