Medical Imaging 2025-07-31
Deep Learning for Shoulder Fracture Detection
A deep learning-based ensemble system for automated shoulder fracture detection in clinical radiographs, addressing the need for rapid and accurate fracture identification in emergency and orthopedic settings.
5C Network Research Team · arXiv · DOI: 10.48550/arXiv.2507.13408
Key Findings
- Ensemble approach combining multiple deep learning architectures achieves higher fracture detection accuracy than any single model
- System identifies subtle and occult shoulder fractures that are frequently missed in emergency department workflows
- Clinically validated on real-world radiographs from Indian hospitals with diverse imaging equipment
- Decision support output includes fracture localization to aid radiologist confirmation
