Clin Exp Emerg Med.  2021 Jun;8(2):120-127. 10.15441/ceem.20.091.

Application of convolutional neural networks for distal radio-ulnar fracture detection on plain radiographs in the emergency room

Affiliations
  • 1Department of Emergency Medicine, Hallym University Sacred Heart Hospital, Hallym University Medical Center, Anyang, Korea
  • 2Medical Artificial Intelligence Center, Hallym University Sacred Heart Hospital, Hallym University Medical Center, Anyang, Korea
  • 3Department of Neurology, Hallym University Sacred Heart Hospital, Hallym University Medical Center, Anyang, Korea
  • 4Department of Ophthalmology, Hallym University Sacred Heart Hospital, Hallym University Medical Center, Anyang, Korea

Abstract


Objective
Recent studies have suggested that deep-learning models can satisfactorily assist in fracture diagnosis. We aimed to evaluate the performance of two of such models in wrist fracture detection.
Methods
We collected image data of patients who visited with wrist trauma at the emergency department. A dataset extracted from January 2018 to May 2020 was split into training (90%) and test (10%) datasets, and two types of convolutional neural networks (i.e., DenseNet-161 and ResNet-152) were trained to detect wrist fractures. Gradient-weighted class activation mapping was used to highlight the regions of radiograph scans that contributed to the decision of the model. Performance of the convolutional neural network models was evaluated using the area under the receiver operating characteristic curve.
Results
For model training, we used 4,551 radiographs from 798 patients and 4,443 radiographs from 1,481 patients with and without fractures, respectively. The remaining 10% (300 radiographs from 100 patients with fractures and 690 radiographs from 230 patients without fractures) was used as a test dataset. The sensitivity, specificity, positive predictive value, negative predictive value, and accuracy of DenseNet-161 and ResNet-152 in the test dataset were 90.3%, 90.3%, 80.3%, 95.6%, and 90.3% and 88.6%, 88.4%, 76.9%, 94.7%, and 88.5%, respectively. The area under the receiver operating characteristic curves of DenseNet-161 and ResNet-152 for wrist fracture detection were 0.962 and 0.947, respectively.
Conclusion
We demonstrated that DenseNet-161 and ResNet-152 models could help detect wrist fractures in the emergency room with satisfactory performance.

Keyword

Wrist; Fractures, bone; Deep learning; Neural networks, computer
Full Text Links
  • CEEM
Actions
Cited
CITED
export Copy
Close
Share
  • Twitter
  • Facebook
Similar articles
Copyright © 2024 by Korean Association of Medical Journal Editors. All rights reserved.     E-mail: koreamed@kamje.or.kr