A deep learning model accurately identifies hard-to-detect physeal fractures in children's wrist x-rays.
Key Details
- 1AI model developed using 2,103 x-rays from 1,082 pediatric patients (mean age 10)
- 2Best performing model (EfficientNet-B2) achieved 84% accuracy, 81% precision, 89% recall, and F1-score of 0.86 on test data
- 3Model uses Grad-CAM for interpretability, highlighting regions contributing to decisions
- 4Physeal fractures are often misdiagnosed (up to 46% rate), risking later growth deformities
- 5Proposed use as decision-support tool in urgent care and ER settings; potential to reduce missed diagnoses
Why It Matters
Missed pediatric fracture diagnoses can cause significant long-term harm. AI decision-support could help frontline clinicians recognize subtle injuries and improve outcomes, addressing a known gap in pediatric musculoskeletal radiology.
Source
AuntMinnie
Related News
•AuntMinnie
Paul Chang Discusses Foundation Models and Agentic AI at RSNA 2025
Dr. Paul Chang shares his insights on the role of foundation models and agentic AI in radiology at RSNA 2025.
•AuntMinnie
Toronto Study: LLMs Must Cite Sources for Radiology Decision Support
University of Toronto researchers found that large language models (LLMs) such as DeepSeek V3 and GPT-4o offer promising support for radiology decision-making in pancreatic cancer when their recommendations cite guideline sources.
•AuntMinnie
AI Model Using Mammograms Enhances Five-Year Breast Cancer Risk Assessment
A new image-only AI model more accurately predicts five-year breast cancer risk than breast density alone, according to multinational research presented at RSNA 2025.