Related Experiment Video
Updated: Aug 14, 2025
Design and Analysis for Fall Detection System Simplification
Published on: April 6, 2020
Detecting pediatric wrist fractures using deep-learning-based object detection
John R Zech1, Giuseppe Carotenuto2, Zenas Igbinoba3
1Department of Radiology, Columbia University Irving Medical Center/New York Presbyterian Hospital, 622 W 168th St., New York, NY, 10032, USA. jrz2111@columbia.edu.
Background:
Missed fractures are the leading cause of diagnostic error in the emergency department, and fractures of pediatric bones, particularly subtle wrist fractures, can be misidentified because of their varying characteristics and responses to injury.
Objective:
This study evaluated the utility of an object detection deep learning framework for classifying pediatric wrist fractures as positive or negative for fracture, including subtle buckle fractures of the distal radius, and evaluated the performance of this algorithm as augmentation to trainee radiograph interpretation.
Materials And Methods:
We obtained 395 posteroanterior wrist radiographs from unique pediatric patients (65% positive for fracture, 30% positive for distal radial buckle fracture) and divided them into train (n = 229), tune (n = 41) and test (n = 125) sets. We trained a Faster R-CNN (region-based convolutional neural network) deep learning object-detection model. Two pediatric and two radiology residents evaluated radiographs initially without the artificial intelligence (AI) assistance, and then subsequently with access to the bounding box generated by the Faster R-CNN model.
Results:
The Faster R-CNN model demonstrated an area under the curve (AUC) of 0.92 (95% confidence interval [CI] 0.87-0.97), accuracy of 88% (n = 110/125; 95% CI 81-93%), sensitivity of 88% (n = 70/80; 95% CI 78-94%) and specificity of 89% (n = 40/45, 95% CI 76-96%) in identifying any fracture and identified 90% of buckle fractures (n = 35/39, 95% CI 76-97%). Access to Faster R-CNN model predictions significantly improved average resident accuracy from 80 to 93% in detecting any fracture (P < 0.001) and from 69 to 92% in detecting buckle fracture (P < 0.001). After accessing AI predictions, residents significantly outperformed AI in cases of disagreement (73% resident correct vs. 27% AI, P = 0.002).
Conclusion:
An object-detection-based deep learning approach trained with only a few hundred examples identified radiographs containing pediatric wrist fractures with high accuracy. Access to model predictions significantly improved resident accuracy in diagnosing these fractures.
