Related Experiment Video
Updated: Oct 25, 2025
Assessment of Bone Fracture Healing Using Micro-Computed Tomography
Published on: December 9, 2022
Development and Validation of a Convolutional Neural Network for Automated Detection of Scaphoid Fractures on
Nils Hendrix1, Ernst Scholten1, Bastiaan Vernhout1
1Department of Radiology, Jeroen Bosch Ziekenhuis, Henri Dunantstraat 1, 5223 GZ 's-Hertogenbosch, the Netherlands (N.H., B.V., S. Bruijnen, M.d.J., W.H., T.S., M.R.); Jheronimus Academy of Data Science, 's-Hertogenbosch, the Netherlands (N.H., L.L.S.O., E.P.); Department of Imaging, Radboud University Medical Center, Nijmegen, the Netherlands (N.H., E.S., B.V., S. Bruijnen, S.S., M.d.R., W.H., B.v.G., M.R.); Department of Radiology, Ziekenhuis Gelderse Vallei, Ede, the Netherlands (B.M.); Department of Radiology, Sint Maartenskliniek, Nijmegen, the Netherlands (S.D.); Department of Radiology, Groene Hart Ziekenhuis, Gouda, the Netherlands (S. Bollen); Department of Radiology and Nuclear Medicine, Tergooi, Hilversum and Blaricum, the Netherlands (A.S.); and Department of Cognitive Science and Artificial Intelligence, Tilburg University, Tilburg, the Netherlands (L.L.S.O., E.P.).
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.Keywords: Convolutional Neural Network (CNN), Deep Learning Algorithms, Machine Learning Algorithms, Feature Detection-Vision-Application Domain, Computer-Aided DiagnosisSee also the commentary by Li and Torriani in this issue.Supplemental material is available for this article.©RSNA, 2021.
