Deep learning for pediatric femoral neck fracture detection in a multicenter study.

Journal: iScience
Published Date: Dec 8, 2025

Abstract

Pediatric femoral neck fractures (FNFs) are uncommon but may result in severe complications if undiagnosed. This study developed a deep learning model for automated detection and localization of FNFs on pediatric hip radiographs. The model was trained on 2,594 hip radiographs from 2,116 patients across eight centers. The optimal model (YOLOv11s) achieved a mean average precision at 0.5 IoU threshold ([email protected]) of 90.6% and an AUC of 0.921 on the internal test set, and a [email protected] of 96.8% and an AUC of 0.968 on the external test set. To our knowledge, this represents one of the most comprehensive multicenter AI diagnostic studies for detecting pediatric FNFs. In a single-center reader study, AI assistance significantly improved diagnostic performance among emergency department orthopedic surgeons, particularly those with limited experience. These findings suggest the potential clinical utility of this model for supporting decision-making in emergency settings.

Authors

  • Xiaoliang Chen
    State Key Laboratory for Manufacturing Systems Engineering, Xi'an Jiaotong University, No.28, Xianning West Road, Xi'an, Shaanxi 710049, P.R. China.
  • Mingdi Xue
    Department of Orthopedics Surgery, Union Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan 430022, China.
  • Xudong Wang
    Department of Maxillofacial and Otorhinolaryngology Oncology, National Clinical Research Center for Cancer, Key Laboratory of Cancer Prevention and Therapy of Tianjin, Tianjin Medical University Cancer Institute and Hospital, Tianjin Medical University, Tianjin, China.
  • Lei Jiang
    Department of Thoracic Surgery, Shanghai Pulmonary Hospital, Tongji University, Shanghai 200433, China.
  • Tao Zhang
    Department of Traumatology, Chongqing Emergency Medical Center, Chongqing University Central Hospital, School of Medicine, Chongqing University, Chongqing, 40044, People's Republic of China.
  • Ning Ling
    National Key Laboratory of Multispectral Information Intelligent Processing Technology, School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan 430074, China.
  • Haocheng Xu
    School of Electrical Engineering and Telecommunications, University of New South Wales, High St, Kensington, NSW 2052, Australia.
  • Weihang Gao
    Department of Orthopedics Surgery, Union Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan 430022, China.
  • Lek Hang Cheang
    Department of Orthopedic Surgery, Centro Hospitalar Conde de Sao Januario, Macau 999078, China.
  • Jiaming Yang
    Jiangsu Key Lab of Big Data Security & Intelligent Processing, School of Computer Science, Nanjing University of Posts and Telecommunications, Nanjing 210023, China.
  • Wa Hou Tai
    Department of Neurosurgery, Centro Hospitalar Conde de Sao Januario, Macau 999078, China.
  • Jialang Hu
    Department of Orthopedics, Wuhan Pu'ai Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan 430010, China.
  • Pengran Liu
    Department of Orthopedics Surgery, Union Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China. [email protected].
  • Tongtong Huo
    Department of Orthopedics, Union Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China.
  • Zhewei Ye
    Department of Orthopedics, Union Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China. [email protected].

Keywords

No keywords available for this article.

External Resources

Popular Topics
Recent Journals