Development and Validation of a Convolutional Neural Network for Automated Detection of Scaphoid Fractures on Conventional Radiographs

Nils Hendrix*, Ernst Scholten, Bastiaan Vernhout, Stefan Bruijnen, Bas Maresch, Mathijn de Jong, Suzanne Diepstraten, Stijn Bollen, Steven Schalekamp, Maarten de Rooij, Alexander Scholtens, Ward Hendrix, Tijs Samson, Sharon Ong, Eric Postma, Bram van Ginneken, Matthieu Rutten

*Corresponding author for this work

Research output: Contribution to journalArticleScientificpeer-review

Abstract

Purpose: To compare the performance of a convolutional neural network (CNN) to that of 11 radiologists in detecting scaphoid bone fractures on conventional radiographs of the hand, wrist, and scaphoid. Materials and Methods: At two hospitals (hospitals A and B), three datasets consisting of conventional hand, wrist, and scaphoid radiographs were retrospectively retrieved: a dataset of 1039 radiographs (775 patients [mean age, 48 years ± 23 {standard deviation}; 505 female patients], period: 2017–2019, hospitals A and B) for developing a scaphoid segmentation CNN, a dataset of 3000 radiographs (1846 patients [mean age, 42 years ± 22; 937 female patients], period: 2003–2019, hospital B) for developing a scaphoid fracture detection CNN, and a dataset of 190 radiographs (190 patients [mean age, 43 years ± 20; 77 female patients], period: 2011–2020, hospital A) for testing the complete fracture detection system. Both CNNs were applied consecutively: The segmentation CNN localized the scaphoid and then passed the relevant region to the detection CNN for fracture detection. In an observer study, the performance of the system was compared with that of 11 radiologists. Evaluation metrics included the Dice similarity coefficient (DSC), Hausdorff distance (HD), sensitivity, specificity, positive predictive value (PPV), and area under the receiver operating characteristic curve (AUC). Results: The segmentation CNN achieved a DSC of 97.4% ± 1.4 with an HD of 1.31 mm ± 1.03. The detection CNN had sensitivity of 78% (95% CI: 70, 86), specificity of 84% (95% CI: 77, 92), PPV of 83% (95% CI: 77, 90), and AUC of 0.87 (95% CI: 0.81, 0.91). There was no difference between the AUC of the CNN and that of the radiologists (0.87 [95% CI: 0.81, 0.91] vs 0.83 [radiologist range: 0.79–0.85]; P = .09). Conclusion: The developed CNN achieved radiologist-level performance in detecting scaphoid bone fractures on conventional radiographs of the hand, wrist, and scaphoid.

Original languageEnglish
Article numbere200260
Pages (from-to)e200260
JournalRadiology: Artificial Intelligence
Volume3
Issue number4
DOIs
Publication statusPublished - Jul 2021

Keywords

  • Computer-aided diagnosis
  • Convolutional neural network (CNN)
  • Deep learning algorithms
  • Feature detection-vision-application domain
  • Machine learning algorithms

Fingerprint

Dive into the research topics of 'Development and Validation of a Convolutional Neural Network for Automated Detection of Scaphoid Fractures on Conventional Radiographs'. Together they form a unique fingerprint.

Cite this