A Comparative Study of Performance in Bone Fracture Classification from Extremity X-ray Images using Convolutional Neural Networks (CNN)
DOI:
https://doi.org/10.57260/stc.2026.1100Keywords:
Bone fracture classification, Extremity X-ray, Convolutional neural network, Medical image classification, Comparative performance analysisAbstract
This research aims to compare the performance of bone fracture classification from extremity X-ray images using Convolutional Neural Networks (CNN). A total of 10,432 images from the Bone Fracture Multi-Region X-ray dataset were utilized, partitioned into training (70%), validation (20%), and test sets (10%). The methodology consisted of two phases: evaluating six baseline models for feature extraction and optimizing the Fully Connected Layer through 60 variations. The results indicated that the VGG16 and MobileNet model achieved the highest performance among the baselines. By integrating it with an optimized Fully Connected structure (Group 4 + Pattern 3), the model reached an accuracy of 100% with a significant reduction in loss compared to the baseline models. While this perfect accuracy is specific to the characteristics of the current dataset, the findings demonstrate the potential of the developed model as a diagnostic aid for radiologists. This research demonstrates the potential for development into a tool that assists radiologists in preliminary diagnosis, thereby effectively reducing workload and accelerating initial screening.
Downloads
References
Barua, K., Mahmud, T., Barua, A., Sharmen, N., Basnin, N., Islam, D., & Hossain, S. (2023). Explainable AI-based humerus fracture detection and classification from X-ray images. In 2023 26th International Conference on Computer and Information Technology (ICCIT), Cox's Bazar, Bangladesh, (pp. 1-6). IEEE. https://doi.org/10.1109/ICCIT60459.2023.10441124
Chedsom, P., & Kanarkard, W. (2023). Analysis of student engagement in online classroom using Convolutional Neural Networks (CNN). ECTI Transaction on Application Research and Development, 3(3), 39–52. https://doi.org/10.37936/ectiard.2023-3-3.250499
Chedsom, P. (2025). Pneumonia Detection from Chest X-ray Images using Convolutional Neural Networks and Transfer Learning Techniques. Journal of Applied Informatics and Technology, 7(2), 406–431. https://ph01.tci-thaijo.org/index.php/jait/article/view/255187
Islam, M. U., Fathima, A., & Ghosh, D. (2025). An improved technique for bone fracture classification using visual transformers and convolutional neural networks. Proceedings of the International Conference on Innovative Computing & Communication (ICICC 2024). http://dx.doi.org/10.2139/ssrn.5191555
Navale, S. (2023). Bone abnormalities detection and classification using deep learning-Vgg16 algorithm. International Journal for Science Technology and Engineering, 11(7), 122–129. https://doi.org/10.22214/ijraset.2023.54582
Rodrigo, M. (2025). Bone fracture multi-region X-ray data. https://www.kaggle.com/datasets/bmadushanirodrigo/fracture-multi-region-x-ray-data
Sahin, M. E. (2023). Image processing and machine learning‐based bone fracture detection and classification using X‐ray images. International Journal of Imaging Systems and Technology, 33(3), 853–865. https://doi.org/10.1002/ima.22849
Senapati, B., Naeem, A. B., Ghafoor, M. I., Gulaxi, V., Almeida, F., Anand, M. R., & Jaiswal, C. (2024). Wrist Crack Classification Using Deep Learning and X-Ray Imaging. In: Daimi, K., Al Sadoon, A. (eds). Proceedings of the Second International Conference on Advances in Computing Research (ACR’24). ACR 2024. Lecture Notes in Networks and Systems, vol 956. Springer, Cham. https://doi.org/10.1007/978-3-031-56950-0_6
Simonyan, K., & Zisserman, A. (2015). Very Deep Convolutional Networks for Large-Scale Image Recognition. 3rd International Conference on Learning Representations, ICLR 2015, San Diego, 7-9 May 2015, 1-14.
https://arxiv.org/pdf/1409.1556.pdf
Thota, S., Kandukuru, P., Sundaram, M., Ali, A., Basha, S. M., & Bindu, N. H. (2024). "Deep Learning based Bone Fracture Detection," 2024 International Conference on Smart Systems for applications in Electrical Sciences (ICSSES), Tumakuru, India, (pp. 1-7). https://doi.org/10.1109/ICSSES62373.2024.10561360
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Science and Technology to Community
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
1. Articles, information, content, images, etc. that are published in "Science and Technology for Community Journal" is the copyright of science and Technology for Community Journal. Chiang Mai Rajabhat University. If any person or organization wants to distribute all or any part of it or do any action Must have written permission from the science and Technology for Community Journal, Chiang Mai Rajabhat University.
2. Content of articles appearing in the journal is the responsibility of the author of the article. The journal editor is not required to agree or take any responsibility.
