A Supervised Approach to Musculoskeletal Imaging Fracture Detection and Classification Using Deep Learning Algorithms

  • Santoshachandra Rao Karanam Centurion University of Technology and Management, Odisha, India
  • Y. Srinivas Information Technology, GITAM University, Visakhapatnam, India
  • S. Chakravarty Centurion University of Technology and Management, Odisha, India

Abstract

Bone fractures break bone continuity. Impact or stress causes numerous bone fractures. Fracture misdiagnosis is the most frequent mistake in emergency rooms, resulting in treatment delays and permanent impairment. According to the Indian population studies, fractures are becoming more common. In the last three decades, there has been a growth of 480 000, and by 2022, it will surpass 600 000. Classifying X-rays may be challenging, particularly in an emergency room when one must act quickly. Deep learning techniques have recently become more popular for image categorization. Deep neural networks (DNNs) can classify images and solve challenging problems. This research aims to build and evaluate a deep learning system for fracture identification and bone fracture classification (BFC). This work proposes an image-processing system that can identify bone fractures using X-rays. Images from the dataset are pre-processed, enhanced, and extracted. Then, DNN classifiers ResNeXt101, InceptionResNetV2, Xception, and NASNetLarge separate the images into the ones with unfractured and fractured bones (normal, oblique, spiral, comminuted, impacted, transverse, and greenstick). The most accurate model is InceptionResNetV2, with an accuracy of 94.58%.

Keywords

musculoskeletal images, image processing, image enhancement, fracture diagnosis, fracture classification, deep neural networks,

References

1. L. Berlin, Defending the “missed” radiographic diagnosis, American Journal of Roentgenology, 176(2): 317–322, 2001, doi: 10.2214/ajr.176.2.1760317.
2. H.R. Guly, Diagnostic errors in an accident and emergency department, Emergency Medicine Journal, 18(4): 263–269, 2001, doi: 10.1136/emj.18.4.263.
3. P. Hallas, T. Ellingsen, Errors in fracture diagnoses in the emergency department characteristics of patients and diurnal variation, BMC Emergency Medicine, 6, article number 4, 2006, doi: 10.1186/1471-227X-6-4.
4. C.-J. Wei, W.-C. Tsai, C.-M. Tiu, H.-T. Wu, H.-J. Chiou, C.-Y. Chang, Systematic analysis of missed extremity fractures in emergency radiology, Acta Radiologica, 47(7): 710–717, 2006, doi: 10.1080/02841850600806340.
5. J.C. He, W.K. Leou, T.S. Howe, Hierarchical classifiers for detection of fractures in X-ray images, [in:] W.G. Kropatsch, M. Kampel, A. Hanbury [Eds.], Computer analysis of images and patterns. CAIP 2007. Lecture Notes in Computer Science, vol. 4673, Springer, Berlin, 2007, doi: 10.1007/978-3-540-74272-2_119.
6. J. Liang, B.-C. Pan, Y.-H. Huang, X.-Y. Fan, Fracture identification of X-ray image, [in:] 2010 International Conference on Wavelet Analysis and Pattern Recognition, pp. 67–73, 2010, doi: 10.1109/ICWAPR.2010.5576438.
7. O. Bandyopadhyay, B. Chanda, B.B. Bhattacharya, Entropy-based automatic segmentation of bones in digital X-ray images, [in:], S.O. Kuznetsov, D.P. Mandal, M.K. Kundu, S.K. Pal [Eds.], Pattern Recognition and Machine Intelligence, PReMI 2011, Lecture Notes in Computer Science, Vol. 6744, Springer, Berlin, Heidelberg, 2011, doi: 10.1007/978-3-642-21786-9_22.
8. H.Y. Chai, L.K. Wee, T.T. Swee, S. Salleh, A.K. Ariff, Kamarulafizam, Gray-level cooccurrence matrix bone fracture detection, American Journal of Applied Sciences, 8(1): 26–32, 2011, doi: 10.3844/ajassp.2011.26.32.
9. S.K. Mahendran, I.K. Shereef, An enhanced tibia fracture detection tool using image processing and classification fusion techniques in X-ray images, Global Journal of Computer Science and Technology, 11(14): 23–28, 2011.
10. A. Krizhevsky, I. Sutskever, G.E. Hinton, ImageNet classification with deep convolutional neural networks, Communications of the ACM, 60(6): 84–90, 2017, doi: 10.1145/3065386.
11. M. Al-Ayyoub, I. Hmeidi, H. Rababah, Detecting handand bone fractures in X-ray images, Journal of Multimedia Processing and Technologies (JMPT), 4(3): 155–168, 2013, doi: 10.13140/RG.2.1.2645.8327.
12. H.R. Roth, Y. Wang, J. Yao, L. Lu, J.E, Burns, R.M. Summers, Deep convolutional networks for automated detection of posterior-element fractures on spine CT, [in:] Proceedings SPIE 9785, Medical Imaging 2016: Computer-Aided Diagnosis, 97850P, 2016, doi: 10.1117/12.2217146.
13. K. Dimililer, IBFDS: Intelligent bone fracture detection system, Procedia Computer Science, 120: 260–267, 2017, doi: 10.1016/j.procs.2017.11.237.
14. J. Olczak et al., Artificial intelligence for analyzing orthopedic trauma radiographs, Acta Orthopaedica, 88(6): 581–586, 2017, doi: 10.1080/17453674.2017.1344459.
15. P. Rajpurkar et al., MURA: Large dataset for abnormality detection in musculoskeletal radiographs, arXiv:1712.06957v4, 2017, doi: 10.48550/arXiv.1712.06957.
16. S.W. Chung et al., Automated detection and classification of the proximal humerus fracture by using deep learning algorithm, Acta Orthopaedica, 89(4): 468–473, 2018, doi: 10.1080/17453674.2018.1453714.
17. R. Lindsey et al., Deep neural network improves fracture detection by clinicians, Proceedings of the National Academy of Sciences of the United States of America, 115(45): 11591–11596, 2018, doi: 10.1073/pnas.1806905115.
18. D.H. Kim, T. MacKinnon, Artificial intelligence in fracture detection: transfer learning from deep convolutional neural networks, Clinical Radiology, 73(5): 439–445, 2018, doi: 10.1016/j.crad.2017.11.015.
19. G. Kitamura, C. Chung, B.E. Moore, Ankle fracture detection utilizing a convolutional neural network ensemble implemented with a small sample, de novo training, and multiview incorporation, Journal of Digital Imaging, 32(4): 672–677, 2019, doi: 10.1007/s10278-018-0167-7.
20. C.-T. Cheng et al., Application of a deep learning algorithm for detection and visualization of hip fractures on plain pelvic radiographs, European Radiology, 29(10): 5469–5477, 2019, doi: 10.1007/s00330-019-06167-y.
21. A. Jiménez-Sánchez et al., Precise proximal femur fracture classification for interactive training and surgical planning, International Journal for Computer Assisted Radiology and Surgery, 15(5): 847–857, 2020, doi: 10.1007/s11548-020-02150-x.
22. G. Zdolsek, Y. Chen, H.P. Bögl, C. Wang, M. Woisetschläger, J. Schilcher, Deep neural networks with promising diagnostic accuracy for the classification of atypical femoral fractures, Acta Orthopaedica, 92(4): 394–400, 2021, doi: 10.1080/17453674.2021.1891512.
23. G. Chada, Machine learning models for abnormality detection in musculoskeletal radiographs, Reports, 2(4): 26, 2019, doi: 10.3390/reports2040026.
24. L. Tanzi, E. Vezzetti, R. Moreno, S. Moos, X-ray bone fracture classification using deep learning: a baseline for designing a reliable approach, Applied Sciences, 10(4): 1507, 2020, doi: 10.3390/app10041507.
25. A. Oyeranmi, B. Ronke, R. Mohammed, A. Edwin, Detection of fracture bones in X-ray images categorization, Journal of Advances in Mathematics and Computer Science, 35(4): 1–11, 2020, doi: 10.9734/JAMCS/2020/v35i430265.
26. D. Joshi, T.P. Singh, A survey of fracture detection techniques in bone X-ray images, Artificial Intelligence Review, 53: 4475–4517, 2020, doi: 10.1007/s10462-019-09799-0.
27. R.M. Jones et al., Assessment of a deep-learning system for fracture detection in musculoskeletal radiographs, NPJ Digitital Medicine, 3: 144, 2020, doi: 10.1038/s41746-020-00352-w.
28. I. Kandel, M. Castelli, A. Popovic, Musculoskeletal images classification for detection of fractures using transfer learning, Journal of Imaging, 6(11): 127, 2020, doi: 10.3390/jimaging6110127.
29. T. Bergs, C. Holst, P. Gupta, T. Augspurger, Digital image processing with deep learning for automated cutting tool wear detection, Procedia Manufacturing, 48: 947–958, 2020, doi: 10.1016/j.promfg.2020.05.134.
30. L. Jin et al., Deep-learning-assisted detection and segmentation of rib fractures from CT scans: Development and validation of FracNet, eBioMedicine, 62: 103106, 2020, doi: 10.1016/j.ebiom.2020.103106.
31. H.-Y. Chen et al., Application of deep learning algorithm to detect and visualize vertebral fractures on plain frontal radiographs, PLoS ONE, 16(1): e0245992, 2021, doi: 10.1371/journal.pone.0245992.
32. Y. Ma, Y. Luo, Bone fracture detection through the two-stage system of crack-sensitive convolutional neural network, Informatics in Medicine Unlocked, 22: 100452, 2021, doi: 10.1016/j.imu.2020.100452.
33. S.R. Karanam, Y. Srinivas, S. Chakravarty, A systematic review on approach and analysis of bone fracture classification, Materials Today: Proceedings, 2021, doi: 10.1016/j.matpr.2021.06.408.
34. S.R. Karanam, Y. Srinivas, S. Chakravarty, A systematic approach to diagnosis and categorization of bone fractures in X-ray imagery, International Journal of Healthcare Management, pp. 1–12, 2022, doi: 10.1080/20479700.2022.2097765.
35. S.R. Karanam, Y. Srinivas, S. Chakravarty, A statistical model approach based on the Gaussian Mixture Model for the diagnosis and classification of bone fractures, International Journal of Healthcare Management, pp. 1–12, 2023, doi: 10.1080/20479700.2022.2161146.
Published
Mar 16, 2023
How to Cite
KARANAM, Santoshachandra Rao; SRINIVAS, Y.; CHAKRAVARTY, S.. A Supervised Approach to Musculoskeletal Imaging Fracture Detection and Classification Using Deep Learning Algorithms. Computer Assisted Methods in Engineering and Science, [S.l.], v. 30, n. 3, p. 369–385, mar. 2023. ISSN 2956-5839. Available at: <https://cames.ippt.pan.pl/index.php/cames/article/view/682>. Date accessed: 17 apr. 2024. doi: http://dx.doi.org/10.24423/cames.682.
Section
Articles