Volume 12, Issue 5 (May 2025), Pages: 68-81

----------------------------------------------

 Original Research Paper

Enhancing diagnostic accuracy in bone fracture detection: A comparative study of customized and pre-trained deep learning models on X-ray images

 Author(s): 

 Abdulmajeed Alsufyani *

 Affiliation(s):

 Department of Computer Science, College of Computers and Information Technology, Taif University, Taif, Saudi Arabia

 Full text

    Full Text - PDF

 * Corresponding Author. 

   Corresponding author's ORCID profile:  https://orcid.org/0000-0001-6110-3642

 Digital Object Identifier (DOI)

  https://doi.org/10.21833/ijaas.2025.05.008

 Abstract

This study examines the performance of several deep learning models for detecting bone fractures from X-ray images. Traditional radiological methods depend on manual interpretation, which can lead to mistakes. Deep learning provides a useful alternative by automating the process of fracture detection. In this research, five models were tested: one custom Convolutional Neural Network (CNN) and four pre-trained models — AlexNet, DenseNet121, ResNet152, and EfficientNetB3. The models were trained on a dataset containing 10,581 X-ray images, which were labeled as either fractured or non-fractured. The models’ performance was measured using accuracy, precision, recall, and F1-score. Among these models, EfficientNetB3 achieved the best results, with 99.20% accuracy and perfect recall, showing its high potential for use in clinical practice. ResNet152 and the custom CNN also performed well, although with slightly lower accuracy. The findings of this study emphasize the value of using advanced deep learning architectures for medical image analysis.

 © 2025 The Authors. Published by IASE.

 This is an open access article under the CC BY-NC-ND license ( http://creativecommons.org/licenses/by-nc-nd/4.0/).

 Keywords

 Bone fractures, X-ray images, Deep learning, Fracture detection, Medical imaging

 Article history

 Received 15 November 2024, Received in revised form 25 April 2025, Accepted 30 April 2025

 Acknowledgment

No Acknowledgment.

  Compliance with ethical standards

  Conflict of interest: The author(s) declared no potential conflicts of interest with respect to the research, authorship, and/or publication of this article.

 Citation:

 Alsufyani A (2025). Enhancing diagnostic accuracy in bone fracture detection: A comparative study of customized and pre-trained deep learning models on X-ray images. International Journal of Advanced and Applied Sciences, 12(5): 68-81

  Permanent Link to this page

 Figures

  Fig. 1  Fig. 2  Fig. 3  Fig. 4 

 Tables

  Table 1  Table 2  Table 3  Table 4  Table 5  Table 6  Table 7 

----------------------------------------------   

 References (21)

1. Aso-Escario J, Sebastián C, Aso-Vizán A, Martínez-Quiñones JV, Consolini F, and Arregui R (2019). Delay in diagnosis of thoracolumbar fractures. Orthopedic Reviews, 11(2): 7774.  https://doi.org/10.4081/or.2019.7774    [Google Scholar] PMid:31210909 PMCid:PMC6551460
2. Cowan PT, Launico MV, and Kahai P (2020). Anatomy, bones. StatPearls Publishing, Treasure Island, USA.    [Google Scholar]
3. Gan K, Xu D, Lin Y, Shen Y, Zhang T, Hu K, Zhou K, Bi M, Pan L, Wu W, and Liu Y (2019). Artificial intelligence detection of distal radius fractures: A comparison between the convolutional neural network and professional assessments. Acta Orthopaedica, 90(4): 394–400.  https://doi.org/10.1080/17453674.2019.1600125    [Google Scholar] PMid:30942136 PMCid:PMC6718190
4. Goodfellow I (2016). Deep learning. MIT Press, Cambridge, USA.    [Google Scholar]
5. Hardalaç F, Uysal F, Peker O, Çiçeklidağ M, Tolunay T, Tokgöz N, Kutbay U, Demirciler B, and Mert F (2022). Fracture detection in wrist X-ray images using deep learning-based object detection models. Sensors, 22(3): 1285.  https://doi.org/10.3390/s22031285    [Google Scholar] PMid:35162030 PMCid:PMC8838335
6. He K, Zhang X, Ren S, and Sun J (2016). Deep residual learning for image recognition. In the Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, IEEE, Las Vegas, USA: 770–778.  https://doi.org/10.1109/CVPR.2016.90    [Google Scholar] PMid:26180094
7. Huang G, Liu Z, Van Der Maaten L, and Weinberger KQ (2017). Densely connected convolutional networks. In the Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, IEEE, Honolulu, USA: 4700-4708.  https://doi.org/10.1109/CVPR.2017.243    [Google Scholar] PMCid:PMC5598342
8. Jones RM, Sharma A, Hotchkiss R, Sperling JW, Hamburger J, Ledig C, O'Toole R, and Gardner M et al. (2020). Assessment of a deep-learning system for fracture detection in musculoskeletal radiographs. NPJ Digital Medicine, 3(1): 144.  https://doi.org/10.1038/s41746-020-00352-w    [Google Scholar] PMid:33145440 PMCid:PMC7599208
9. Krizhevsky A, Sutskever I, and Hinton GE (2017). ImageNet classification with deep convolutional neural networks. Advances in Neural Information Processing Systems, 25: 1097–1105.    [Google Scholar]
10. Mohanty S and Senapati MR (2023). Fracture detection from X-ray images using different machine learning techniques. In the 1 ^st International Conference on Circuits, Power and Intelligent Systems, IEEE, Bhubaneswar, India: 1-6.  https://doi.org/10.1109/CCPIS59145.2023.10291652    [Google Scholar]
11. Nishiyama M, Ishibashi K, Ariji Y, Fukuda M, Nishiyama W, Umemura M, Katsumata A, Fujita H, and Ariji E (2021). Performance of deep learning models constructed using panoramic radiographs from two hospitals to diagnose fractures of the mandibular condyle. Dentomaxillofacial Radiology, 50(7): 20200611.  https://doi.org/10.1259/dmfr.20200611    [Google Scholar] PMid:33769840 PMCid:PMC8474128
12. Nwankpa C, Ijomah W, Gachagan A, and Marshall S (2018). Activation functions: Comparison of trends in practice and research for deep learning. Arxiv Preprint Arxiv:1811.03378.  https://doi.org/10.48550/arXiv.1811.03378     [Google Scholar]
13. Rodrigo M (2024). Bone fracture multi-region x-ray data. Available online at:  https://www.kaggle.com/datasets/bmadushanirodrigo/fracture-multi-region-x-ray-data 
14. Sharma S (2023). Artificial intelligence for fracture diagnosis in orthopedic X-rays: Current developments and future potential. SICOT Journal, 9: 21.  https://doi.org/10.1051/sicotj/2023018    [Google Scholar] PMid:37409882 PMCid:PMC10324466
15. Son DM, Yoon YA, Kwon HJ, An CH, and Lee SH (2021). Automatic detection of mandibular fractures in panoramic radiographs using deep learning. Diagnostics, 11(6): 933.  https://doi.org/10.3390/diagnostics11060933    [Google Scholar] PMid:34067462 PMCid:PMC8224557
16. Su Z, Adam A, Nasrudin MF, Ayob M, and Punganan G (2023). Skeletal fracture detection with deep learning: A comprehensive review. Diagnostics, 13(20): 3245.  https://doi.org/10.3390/diagnostics13203245    [Google Scholar] PMid:37892066 PMCid:PMC10606060
17. Tan M and Le Q (2019). EfficientNet: Rethinking model scaling for convolutional neural networks. In the International Conference on Machine Learning, PMLR, Long Beach, USA: 6105-6114.    [Google Scholar]
18. Tanzi L, Vezzetti E, Moreno R, and Moos S (2020). X-ray bone fracture classification using deep learning: A baseline for designing a reliable approach. Applied Sciences, 10(4): 1507.  https://doi.org/10.3390/app10041507    [Google Scholar]
19. Taylor-Phillips S and Stinton C (2019). Fatigue in radiology: A fertile area for future research. The British Journal of Radiology, 92(1099): 20190043. https://doi.org/10.1259/bjr.20190043    [Google Scholar] PMid:30933540 PMCid:PMC6636274
20. Wang X, Xu Z, Tong Y, Xia L, Jie B, Ding P, Bai H, Zhang Y, and He Y (2022). Detection and classification of mandibular fracture on CT scan using deep convolutional neural network. Clinical Oral Investigations, 26(6): 4593-4601.  https://doi.org/10.1007/s00784-022-04427-8    [Google Scholar] PMid:35218428
21. Yadav DP, Sharma A, Athithan S, Bhola A, Sharma B, and Dhaou IB (2022). Hybrid SFNet model for bone fracture detection and classification using ML/DL. Sensors, 22(15): 5823.  https://doi.org/10.3390/s22155823    [Google Scholar] PMid:35957380 PMCid:PMC9371081