Bone Fracture Classification using Convolutional Neural Networks from X-ray Images
Received: 6 June 2024 | Revised: 23 July 2024 and 2 August 2024 | Accepted: 4 August 2024 | Online: 9 August 2024
Corresponding author: Amal Alshahrani
Abstract
This study investigates a bone fracture classification system using deep learning algorithms to determine the best-performing architecture. The primary focus was on training the YOLOv8 model, renowned for its real-time object detection and image segmentation capabilities, as well as the VGG16 model. CNN architectures, known for their effectiveness in image recognition tasks, were chosen for their proven effectiveness in detecting bone fractures from X-ray images. Hyperparameter tuning was used to improve the system's ability to accurately detect and classify bone fractures. The FracAtlas dataset was utilized, which contains 4,083 X-ray images of fractured and non-fractured human bones. Integrating advanced deep learning techniques aims to assist surgeons with more accurate diagnostics. The performance of the developed system was evaluated against existing methods, showcasing its effectiveness in medical diagnostics and fracture treatment. The methodology employed, including data augmentation, extensive model training, and hyperparameter tuning, significantly improved the accuracy of bone fracture detection and classification, demonstrating the potential of deep learning models in aiding medical professionals with more precise and efficient diagnostics.
Keywords:
VGG16, YOLOV8, CNN, bone fracture, classification, deep learningDownloads
References
S. Sharma, "Artificial intelligence for fracture diagnosis in orthopedic X-rays: current developments and future potential," SICOT-J, vol. 9, Art. no. 21.
P. K. Mall et al., "A comprehensive review of deep neural networks for medical image processing: Recent developments and future opportunities," Healthcare Analytics, vol. 4, Dec. 2023, Art. no. 10021
Ultralytics, "YOLOv8 Documantation." https://docs.ultralytics.com/.
N. Kumar, A. Hashmi, M. Gupta, and A. Kundu, "Automatic Diagnosis of Covid-19 Related Pneumonia from CXR and CT-Scan Images," Engineering, Technology & Applied Science Research, vol. 12, no. 1, pp. 7993–7997, Feb. 2022.
E. A. Murphy et al., "Machine learning outperforms clinical experts in classification of hip fractures," Scientific Reports, vol. 12, no. 1, Feb. 2022, Art. no. 2058.
D. P. Yadav and S. Rathor, "Bone Fracture Detection and Classification using Deep Learning Approach," in 2020 International Conference on Power Electronics & IoT Applications in Renewable Energy and its Control (PARC), Mathura, India, Feb. 2020, pp. 282–285.
R. F. A. Marar, D. M. Uliyan, and H. A. Al-Sewadi, "Mandible Bone Osteoporosis Detection using Cone-beam Computed Tomography," Engineering, Technology & Applied Science Research, vol. 10, no. 4, pp. 6027–6033, Aug. 2020.
H. A. Owida, A. Al-Ghraibah, and M. Altayeb, "Classification of Chest X-Ray Images using Wavelet and MFCC Features and Support Vector Machine Classifier," Engineering, Technology & Applied Science Research, vol. 11, no. 4, pp. 7296–7301, Aug. 2021.
Implemented with a Small Sample, De Novo Training, and Multiview Incorporation," Journal of Digital Imaging, vol. 32, no. 4, pp. 672–677, Aug. 2019.
F. Hardalaç et al., "Fracture Detection in Wrist X-ray Images Using Deep Learning-Based Object Detection Models," Sensors, vol. 22, no. 3, Jan. 2022, Art. no. 1285.
S. R. Karanam, Y. Srinivas, and S. Chakravarty, "A Supervised Approach to Musculoskeletal Imaging Fracture Detection and Classification Using Deep Learning Algorithms," Computer Assisted Methods in Engineering and Science, vol. 30, no. 3, pp. 369–385, Mar. 2023.
S. Vironicka and J. G. R. Sathiaseelan, "Classification of Long-Bone Fractures Using Modified Faster RCNN for X-Ray Images," Indian Journal Of Science And Technology, vol. 16, no. 1, pp. 56–65, Jan. 2023.
J. H. F. Oosterhoff et al., "A deep learning approach using an ensemble model to autocreate an image-based hip fracture registry," OTA International, vol. 7, no. 1S, Jan. 2024, Art. no. e283.
R. Y. Ju and W. Cai, "Fracture detection in pediatric wrist trauma X-ray images using YOLOv8 algorithm," Scientific Reports, vol. 13, no. 1, Nov. 2023, Art. no. 20077.
K. Thaiyalnayaki, L. Kavyaa, and J. Sugumar, "Automated Bone Fracture Detection Using Convolutional Neural Network," Journal of Physics: Conference Series, vol. 2471, no. 1, Dec. 2023, Art. no. 012003.
R. Hrubý, D. Kvak, J. Dandár, A. Atakhanova, M. Misař, and D. Dufek, "Cross-Center Validation of Deep Learning Model for Musculoskeletal Fracture Detection in Radiographic Imaging: A Feasibility Study." medRxiv, Art. no. 2024.01.17.24301244, Jan. 17, 2024.
T. Kumar and R. Ponnusamy, "Robust Medical X-Ray Image Classification by Deep Learning with Multi-Versus Optimizer," Engineering, Technology & Applied Science Research, vol. 13, no. 4, pp. 111406–11411, Aug. 2023.
A. Faramawy, "notebook86c6300cc2." https://www.kaggle.com/code/abdelazizfaramawy/notebook86c6300cc2/noteb.
I. Abedeen, M. A. Rahman, F. Z. Prottyasha, A. Tasnim, S. Shatabda, and T. M. Chowdhury, "Fracture Classification Dataset." Kaggle, https://doi.org/10.34740/KAGGLE/DSV/7718956.
A. Al-Shahrani, W. Al-Amoudi, R. Bazaraah, A. Al-Sharief, and H. Farouquee, "An Image Processing-based and Deep Learning Model to Classify Brain Cancer," Engineering, Technology & Applied Science Research, vol. 14, no. 4, pp. 15433–15438, Aug. 2024.
R. Yamashita, M. Nishio, R. K. G. Do, and K. Togashi, "Convolutional neural networks: an overview and application in radiology," Insights into Imaging, vol. 9, no. 4, pp. 611–629, Aug. 2018.
Downloads
How to Cite
License
Copyright (c) 2024 Amal Alshahrani, Alaa Alsairafi
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain the copyright and grant the journal the right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) after its publication in ETASR with an acknowledgement of its initial publication in this journal.
