BIOMAT Database Logo BIOMAT Database Logo

Detecting pediatric wrist fractures using deep-learning-based object detection. 2023

John R Zech, and Giuseppe Carotenuto, and Zenas Igbinoba, and Clement Vinh Tran, and Elena Insley, and Alyssa Baccarella, and Tony T Wong
Department of Radiology, Columbia University Irving Medical Center/New York Presbyterian Hospital, 622 W 168th St., New York, NY, 10032, USA. jrz2111@columbia.edu.

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. 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. 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. 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). 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.

UI MeSH Term Description Entries
D002648 Child A person 6 to 12 years of age. An individual 2 to 5 years old is CHILD, PRESCHOOL. Children
D006801 Humans Members of the species Homo sapiens. Homo sapiens,Man (Taxonomy),Human,Man, Modern,Modern Man
D000077321 Deep Learning Supervised or unsupervised machine learning methods that use multiple layers of data representations generated by nonlinear transformations, instead of individual task-specific ALGORITHMS, to build and train neural network models. Hierarchical Learning,Learning, Deep,Learning, Hierarchical
D000092503 Wrist Fractures Fractures of the CARPAL BONES, the distal ULNA and/or RADIUS at the WRIST. Distal Forearm Fractures,Distal Radius Fractures,Distal Radius and Ulna Fractures,Distal Ulna Fractures,Distal Ulna and Radius Fractures,Radial Styloid Fractures,Smith Fracture,Distal Forearm Fracture,Distal Radius Fracture,Distal Ulna Fracture,Forearm Fracture, Distal,Fracture, Distal Forearm,Fracture, Distal Radius,Fracture, Distal Ulna,Fracture, Radial Styloid,Fracture, Smith,Fracture, Wrist,Radial Styloid Fracture,Radius Fracture, Distal,Styloid Fracture, Radial,Ulna Fracture, Distal,Wrist Fracture
D001185 Artificial Intelligence Theory and development of COMPUTER SYSTEMS which perform tasks that normally require human intelligence. Such tasks may include speech recognition, LEARNING; VISUAL PERCEPTION; MATHEMATICAL COMPUTING; reasoning, PROBLEM SOLVING, DECISION-MAKING, and translation of language. AI (Artificial Intelligence),Computer Reasoning,Computer Vision Systems,Knowledge Acquisition (Computer),Knowledge Representation (Computer),Machine Intelligence,Computational Intelligence,Acquisition, Knowledge (Computer),Computer Vision System,Intelligence, Artificial,Intelligence, Computational,Intelligence, Machine,Knowledge Representations (Computer),Reasoning, Computer,Representation, Knowledge (Computer),System, Computer Vision,Systems, Computer Vision,Vision System, Computer,Vision Systems, Computer
D014954 Wrist Injuries Injuries to the wrist or the wrist joint. Injuries, Wrist,Injury, Wrist,Wrist Injury
D016571 Neural Networks, Computer A computer architecture, implementable in either hardware or software, modeled after biological neural networks. Like the biological system in which the processing capability is a result of the interconnection strengths between arrays of nonlinear processing nodes, computerized neural networks, often called perceptrons or multilayer connectionist models, consist of neuron-like units. A homogeneous group of units makes up a layer. These networks are good at pattern recognition. They are adaptive, performing tasks by example, and thus are better for decision-making than are linear learning machines or cluster analysis. They do not require explicit programming. Computational Neural Networks,Connectionist Models,Models, Neural Network,Neural Network Models,Neural Networks (Computer),Perceptrons,Computational Neural Network,Computer Neural Network,Computer Neural Networks,Connectionist Model,Model, Connectionist,Model, Neural Network,Models, Connectionist,Network Model, Neural,Network Models, Neural,Network, Computational Neural,Network, Computer Neural,Network, Neural (Computer),Networks, Computational Neural,Networks, Computer Neural,Networks, Neural (Computer),Neural Network (Computer),Neural Network Model,Neural Network, Computational,Neural Network, Computer,Neural Networks, Computational,Perceptron
D050723 Fractures, Bone Breaks in bones. Bone Fractures,Broken Bones,Spiral Fractures,Torsion Fractures,Bone Fracture,Bone, Broken,Bones, Broken,Broken Bone,Fracture, Bone,Fracture, Spiral,Fracture, Torsion,Fractures, Spiral,Fractures, Torsion,Spiral Fracture,Torsion Fracture

Related Publications

John R Zech, and Giuseppe Carotenuto, and Zenas Igbinoba, and Clement Vinh Tran, and Elena Insley, and Alyssa Baccarella, and Tony T Wong
Fracture Detection in Wrist X-ray Images Using Deep Learning-Based Object Detection Models.
February 2022, Sensors (Basel, Switzerland),
John R Zech, and Giuseppe Carotenuto, and Zenas Igbinoba, and Clement Vinh Tran, and Elena Insley, and Alyssa Baccarella, and Tony T Wong
Automatic detection of midfacial fractures in facial bone CT images using deep learning-based object detection models.
May 2024, Journal of stomatology, oral and maxillofacial surgery,
John R Zech, and Giuseppe Carotenuto, and Zenas Igbinoba, and Clement Vinh Tran, and Elena Insley, and Alyssa Baccarella, and Tony T Wong
Detecting Distal Radius Fractures Using a Segmentation-Based Deep Learning Model.
April 2023, Journal of digital imaging,
John R Zech, and Giuseppe Carotenuto, and Zenas Igbinoba, and Clement Vinh Tran, and Elena Insley, and Alyssa Baccarella, and Tony T Wong
Deep learning-based small object detection: A survey.
February 2023, Mathematical biosciences and engineering : MBE,
John R Zech, and Giuseppe Carotenuto, and Zenas Igbinoba, and Clement Vinh Tran, and Elena Insley, and Alyssa Baccarella, and Tony T Wong
Object Detection at Level Crossing Using Deep Learning.
November 2020, Micromachines,
John R Zech, and Giuseppe Carotenuto, and Zenas Igbinoba, and Clement Vinh Tran, and Elena Insley, and Alyssa Baccarella, and Tony T Wong
Anonymizing Radiographs Using an Object Detection Deep Learning Algorithm.
November 2023, Radiology. Artificial intelligence,
John R Zech, and Giuseppe Carotenuto, and Zenas Igbinoba, and Clement Vinh Tran, and Elena Insley, and Alyssa Baccarella, and Tony T Wong
Automated detection of acute appendicular skeletal fractures in pediatric patients using deep learning.
November 2022, Skeletal radiology,
John R Zech, and Giuseppe Carotenuto, and Zenas Igbinoba, and Clement Vinh Tran, and Elena Insley, and Alyssa Baccarella, and Tony T Wong
Detection of ankle fractures using deep learning algorithms.
December 2022, Foot and ankle surgery : official journal of the European Society of Foot and Ankle Surgeons,
John R Zech, and Giuseppe Carotenuto, and Zenas Igbinoba, and Clement Vinh Tran, and Elena Insley, and Alyssa Baccarella, and Tony T Wong
Multiple Object Detection Based on Clustering and Deep Learning Methods.
August 2020, Sensors (Basel, Switzerland),
John R Zech, and Giuseppe Carotenuto, and Zenas Igbinoba, and Clement Vinh Tran, and Elena Insley, and Alyssa Baccarella, and Tony T Wong
Cooperative Object Transportation Using Curriculum-Based Deep Reinforcement Learning.
July 2021, Sensors (Basel, Switzerland),
Copied contents to your clipboard!