A Neural Network Model for Intelligent Classification of Distal Radius Fractures Using Statistical Shape Model Extraction Features

Abstract

Objective: Distal radius fractures account for 12%–17% of all fractures, with accurate classification being crucial for proper treatment planning. Studies have shown that in emergency settings, the misdiagnosis rate of hand/wrist fractures can reach up to 29%, particularly among non-specialist physicians due to a high workload and limited experience. While existing AI methods can detect fractures, they typically require large training datasets and are limited to fracture detection without type classification. Therefore, there is an urgent need for an efficient and accurate method that can both detect and classify different types of distal radius fractures. To develop and validate an intelligent classifier for distal radius fractures by combining a statistical shape model (SSM) with a neural network (NN) based on CT imaging data.

Methods: From August 2022 to May 2023, a total of 80 CT scans were collected, including 43 normal radial bones and 37 distal radius fractures (17 Colles', 12 Barton's, and 8 Smith's fractures). We established the distal radius SSM by combining mean values with PCA (Principal Component Analysis) features and proposed six morphological indicators across four groups. The intelligent classifier (SSM + NN) was trained using SSM features as input data and different fracture types as output data. Four-fold cross-validations were performed to verify the classifier's robustness. The SSMs for both normal and fractured distal radius were successfully established based on CT data. Analysis of variance revealed significant differences in all six morphological indicators among groups (p < 0.001). The intelligent classifier achieved optimal performance when using the first 15 PCA-extracted features, with a cumulative variance contribution rate exceeding 75%. The classifier demonstrated excellent discrimination capability with a mean area under the curve (AUC) of 0.95 in four-fold cross-validation, and achieved an overall classification accuracy of 97.5% in the test set. The optimal prediction threshold range was determined to be 0.2–0.4.

Results: The SSMs for both normal and fractured distal radius were successfully established based on CT data. Analysis of variance revealed significant differences in all six morphological indicators among groups (p < 0.001). The intelligent classifier achieved optimal performance when using the first 15 PCA-extracted features, with a cumulative variance contribution rate exceeding 75%. The classifier demonstrated excellent discrimination capability with a mean AUC of 0.95 in four-fold cross-validation and achieved an overall classification accuracy of 97.5% in the test set. The optimal prediction threshold range was determined to be 0.2–0.4.

Conclusion: The CT-based SSM + NN intelligent classifier demonstrated excellent performance in identifying and classifying different types of distal radius fractures. This novel approach provides an efficient, accurate, and automated tool for clinical fracture diagnosis, which could potentially improve diagnostic efficiency and treatment planning in orthopedic practice.

Keywords

artificial intelligence / computer-aided diagnosis / distal radius fracture / principal component analysis / statistical shape model

References

[1] T. Heimann and H.-P. Meinzer, “Statistical Shape Models for 3D Medical Image Segmentation: A Review,” Medical Image Analysis 13 (2009): 543-563.

[2] L. Grassi, S. P. Väänänen, and H. Isaksson, “Statistical Shape and Appearance Models: Development Towards Improved Osteoporosis Care,” Current Osteoporosis Reports 19 (2021): 676-687.

[3] I. T. Jolliffe and J. Cadima, “Principal Component Analysis: A Review and Recent Developments,” Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences 374 (2016): 20150202.

[4] P. R. Atkins, P. Agrawal, J. D. Mozingo, et al., “Prediction of Femoral Head Coverage From Articulated Statistical Shape Models of Patients With Developmental Dysplasia of the Hip,” Journal of Orthopaedic Research 40 (2022): 2113-2126.

[5] F. Jazinizadeh, J. D. Adachi, and C. E. Quenneville, “Advanced 2D Image Processing Technique to Predict Hip Fracture Risk in an Older Population Based on Single DXA Scans,” Osteoporosis International 31 (2020): 1925-1933.

[6] B. Vafaeian, H. T. Riahi, H. Amoushahi, N. M. Jomha, and S. Adeeb, “A Feature-Based Statistical Shape Model for Geometric Analysis of the Human Talus and Development of Universal Talar Prostheses,” Journal of Anatomy 240 (2022): 305-322.

[7] D. W. G. Langerhuizen, S. J. Janssen, W. H. Mallee, et al., “What Are the Applications and Limitations of Artificial Intelligence for Fracture Detection and Classification in Orthopaedic Trauma Imaging? A Systematic Review,” Clinical Orthopaedics and Related Research 477, no. 11 (2019): 2482-2491, https://doi.org/10.1097/CORR.0000000000000848.

[8] P. H. S. Kalmet, S. Sanduleanu, S. Primakov, et al., “Deep Learning in Fracture Detection: A Narrative Review,” Acta Orthopaedica 91 (2020): 215-220.

[9] J. Olczak, F. Emilson, A. Razavian, T. Antonsson, A. Stark, and M. Gordon, “Ankle Fracture Classification Using Deep Learning: Automating Detailed AO Foundation/Orthopedic Trauma Association (AO/OTA) 2018 Malleolar Fracture Identification Reaches a High Degree of Correct Classification,” Acta Orthopaedica 92 (2021): 102-108.

[10] T. T. Anttila, T. V. Karjalainen, T. O. Mäkelä, et al., “Detecting Distal Radius Fractures Using a Segmentation-Based Deep Learning Model,” Journal of Digital Imaging 36, no. 2 (2023): 679-687, https://doi.org/10.1007/s10278-022-00741-5.

[11] M. A. Badgeley, J. R. Zech, L. Oakden-Rayner, et al., “Deep Learning Predicts Hip Fracture Using Confounding Patient and Healthcare Variables,” npj Digital Medicine 2 (2019): 31.

[12] C. T. Cheng, T. Y. Ho, T. Y. Lee, et al., “Application of a Deep Learning Algorithm for Detection and Visualization of Hip Fractures on Plain Pelvic Radiographs,” European Radiology 29 (2019): 5469-5477.

[13] C. I. Hsieh, K. Zheng, C. Lin, et al., “Automated Bone Mineral Density Prediction and Fracture Risk Assessment Using Plain Radiographs via Deep Learning,” Nature Communications 12 (2021): 5472.

[14] S. W. Chung, S. S. Han, J. W. Lee, et al., “Automated Detection and Classification of the Proximal Humerus Fracture by Using Deep Learning Algorithm,” Acta Orthopaedica 89 (2018): 468-473.

[15] J. F. Dipnall, J. Lu, B. J. Gabbe, et al., “Comparison of State-Of-The-Art Machine and Deep Learning Algorithms to Classify Proximal Humeral Fractures Using Radiology Text,” European Journal of Radiology 153 (2022): 110366.

[16] F. Hardalaç, F. Uysal, O. Peker, et al., “Fracture Detection in Wrist X-Ray Images Using Deep Learning-Based Object Detection Models,” Sensors 22 (2022): 1285.

[17] A. M. Raisuddin, E. Vaattovaara, M. Nevalainen, et al., “Critical Evaluation of Deep Neural Networks for Wrist Fracture Detection,” Scientific Reports 11 (2021): 6006.

[18] N. Kriegeskorte and T. Golan, “Neural Network Models and Deep Learning,” Current Biology 29 (2019): R231-R236.

[19] S. M. Anwar, M. Majid, A. Qayyum, M. Awais, M. Alnowami, and M. K. Khan, “Medical Image Analysis Using Convolutional Neural Networks: A Review,” Journal of Medical Systems 42 (2018): 226.

[20] S. Soffer, A. Ben-Cohen, O. Shimon, M. M. Amitai, H. Greenspan, and E. Klang, “Convolutional Neural Networks for Radiologic Images: A Radiologist's Guide,” Radiology 290 (2019): 590-606.

[21] K. Oka, R. Shiode, Y. Yoshii, H. Tanaka, T. Iwahashi, and T. Murase, “Artificial Intelligence to Diagnosis Distal Radius Fracture Using Biplane Plain X-Rays,” Journal of Orthopaedic Surgery and Research 16 (2021): 694.

[22] T. Suzuki, S. Maki, T. Yamazaki, et al., “Detecting Distal Radial Fractures From Wrist Radiographs Using a Deep Convolutional Neural Network With an Accuracy Comparable to Hand Orthopedic Surgeons,” Journal of Digital Imaging 35 (2022): 39-46.

[23] B. Katt, D. Seigerman, K. Lutsky, and P. Beredjiklian, “Distal Radius Malunion,” Journal of Hand Surgery 45 (2020): 433-442.

[24] A. Christersson, J. Nysjö, L. Berglund, et al., “Comparison of 2D Radiography and a Semi-Automatic CT-Based 3D Method for Measuring Change in Dorsal Angulation Over Time in Distal Radius Fractures,” Skeletal Radiology 45 (2016): 763-769.

[25] A. Lawson, J. M. Naylor, R. Buchbinder, et al., “Surgical Plating vs Closed Reduction for Fractures in the Distal Radius in Older Patients: A Randomized Clinical Trial,” JAMA Surgery 156, no. 3 (2021): 229-237, https://doi.org/10.1001/jamasurg.2020.5672.

[26] T. S. P. Singh, A. N. Sadagatullah, and A. H. Yusof, “Morphology of Distal Radius Curvatures: A CT-Based Study on the Malaysian Malay Population,” Singapore Medical Journal 56 (2015): 562-566.

[27] R. Fernholm, K. Pukk Härenstam, C. Wachtler, G. H. Nilsson, M. J. Holzmann, and A. C. Carlsson, “Diagnostic Errors Reported in Primary Healthcare and Emergency Departments: A Retrospective and Descriptive Cohort Study of 4830 Reported Cases of Preventable Harm in Sweden,” European Journal of General Practice 25, no. 3 (2019): 128-135, https://doi.org/10.1080/13814788.2019.1625886.

[28] A. E. Freeland and K. T. Luber, “Biomechanics and Biology of Plate Fixation of Distal Radius Fractures,” Hand Clinics 21 (2005): 329-339.

[29] A. Pinto, A. Reginelli, F. Pinto, et al., “Errors in Imaging Patients in the Emergency Setting,” British Journal of Radiology 89, no. 1061 (2016): 20150914, https://doi.org/10.1259/bjr.20150914.

[30] Y. Chen and G. Medioni, “Object Modeling by Registration of Multiple Range Images,” Image and Vision Computing 10 (1992): 145-155.

[31] S. F. Baumbach, J. Binder, A. Synek, et al., “Analysis of the Three-Dimensional Anatomical Variance of the Distal Radius Using 3D Shape Models,” BMC Medical Imaging 17 (2017): 23.

[32] K. Gan, D. Xu, Y. Lin, et al., “Artificial Intelligence Detection of Distal Radius Fractures: A Comparison Between the Convolutional Neural Network and Professional Assessments,” Acta Orthopaedica 90 (2019): 394-400.

[33] H. Min, Y. Rabi, A. Wadhawan, et al., “Automatic Classification of Distal Radius Fracture Using a Two-Stage Ensemble Deep Learning Framework,” Physical and Engineering Sciences in Medicine 46, no. 2 (2023): 877-886, https://doi.org/10.1007/s13246-023-01261-4.

[34] P. G. Anderson, G. L. Baum, N. Keathley, et al., “Deep Learning Assistance Closes the Accuracy Gap in Fracture Detection Across Clinician Types,” Clinical Orthopaedics and Related Research® 481, no. 3 (2023): 580-588.

RIGHTS & PERMISSIONS

2025 The Author(s). Orthopaedic Surgery published by Tianjin Hospital and John Wiley & Sons Australia, Ltd.