Deep Convolutional Neural Network-Based Detection of Bone Abnormalities in Musculoskeletal Radiographs
Keywords:
Deep CNN, Musculoskeletal Abnormality, Data Augmentation, Radiographs, MURA, ADAM optimizer and Computer VisionAbstract
Musculoskeletal abnormalities typically rely on radiographic examinations for diagnosis, but even experienced radiologists can miss abnormalities, underscoring the need for improved detection methods. This paper presents a novel approach utilizing Deep Convolutional Neural Networks (Deep CNN) for computer-aided bone abnormality detection. Leveraging the Stanford MURA dataset featuring radiological images of seven upper extremity types, we employ pre-processing techniques such as Histogram Equalization (HE) and Contrastive Limited Adaptive Histogram Equalization (CLAHE) to enhance image quality before inputting them into our proposed 5SET (5S) model. This model accurately classifies images into the seven upper extremity categories and identifies normal or abnormal conditions. Our results demonstrate a remarkable overall accuracy of 92.10%, with a precision of 94% for specific extremities and a Cohen's Kappa score of 91.5%. This proposed model highlights the efficacy of combining preprocessing techniques with Deep CNN for high-precision bone abnormality detection.
Downloads
References
Global, regional, and national incidence, prevalence, and years lived with disability for 328 diseases and injuries for 195 countries, 1990–2016, 2017. A systematic analysis for the global burden of disease Study 2016. Lancet, 390(10100), pp.1211-1259. https://doi.org/10.1016/S0140-6736(17)32154-2.
AJR Am J Roentgenol Kim YW, Mansfield LT. Fool me twice: delayed diagnoses in radiology with emphasis on perpetuated errors. Pages 465–70, 2014. DOI: 10.2214/AJR.13.11493
Berlin, L., 2014. Radiologic errors, past, present and future. Diagnosis, 1(1), pp.79-84. https://doi.org/10.1515/dx-2013-0012
Abujudeh HH. Bruno MA, Walker EA. Understanding and confronting our mistakes: The epidemiology of error in radiology and strategies for error reduction. page 1668–1676. RSNA, 2015. https://doi.org/10.1148/rg.2015150023.
Hani H. Abujudeh, Giles W. Boland, Rathachai Kaewlai, and G. Scott Gazelle James H. Thrall Pavel Rabiner, Elkarn F. Halpern. Abdominal and pelvic computed tomography (ct) interpretation: discrepancy rates among experienced radiologists. pages 1952–7. Springer, 2008.
Worthington M Rennie I McKinstry CS. Briggs GM, Flynn PA. The role of specialist neuroradiology second opinion reporting: is there added value page 791–795. Europe PMC, 2008.
Shoji Kido, Yasusi Hirano and Noriaki Hashimoto, “Detection and Classification of Lung Abnormalities by Use of Convolutional Neural Network (CNN) and Regions with CNN Features (R-CNN)” IEEE 2018.
Rajpurkar, P., Irvin, J., Bagul, A., Ding, D., Duan, T., Mehta, H., Yang, B., Zhu, K., Laird, D., Ball, R.L. and Langlotz, C., 2017. Mura: Large dataset for abnormality detection in musculoskeletal radiographs. arXiv preprint arXiv:1712.06957. https://doi.org/10.48550/arXiv.1712.06957
Mennatallah M.Abdel, Sara H.Awwad, Farah H.Ahmed, Amira G.Wasfi, Taraggy M.Ghanim, Ayman M.Nabil, “Survey: Automatic Recognition of Musculoskeletal Disorders from Radiographs” IEEE 2018.
Azian Azamimi Abdullah, Atieqah Yaakob, and Zunaidi Ibrahim, “Pre- diction of Spinal Abnormalities using Machine Learning Techniques” IEEE 2018.
George, J., Subin, T.K. and Rajeev, K., 2008, November. Detection of temporal bone abnormalities using hybrid wavelet Support Vector Machine classification. In TENCON 2008-2008 IEEE Region 10 Conference (pp. 1-6). IEEE. DOI: 10.1109/TENCON.2008.4766549
Tusher Chandra Mondol, Hasib Iqbal and MMA Hashem, “Deep CNN- Based Ensemble CADx Model for Musculoskeletal Abnormality Detection from Radiographs” 5th International Conference on Advances in Electrical Engineering (ICAEE). IEEE 2019.
Krizhevsky, A., Sutskever, I. and Hinton, G.E., 2012. Imagenet classification with deep convolutional neural networks. Advances in neural information processing systems, 25. DOI: 10.1145/3065386
N. Umadevi, S.N. Geethalakshmi, “Multiple classification system for fracture detection in human bone x-ray images.” In 2012 Third Inter- national Conference on Computing, Communication and Networking Technologies (ICCCNT’12). IEEE, 2012.
Dzierżak, R. and Omiotek, Z., 2022. Application of deep convolutional neural networks in the diagnosis of osteoporosis. Sensors, 22(21), p.8189. https://doi.org/10.3390/s22218189
Deng, J., Dong, W., Socher, R., Li, L.J., Li, K. and Fei-Fei, L., 2009, June. Imagenet: A large-scale hierarchical image database. In 2009 IEEE conference on computer vision and pattern recognition (pp. 248-255). IEEE.
Shin, H.C., Roth, H.R., Gao, M., Lu, L., Xu, Z., Nogues, I., Yao, J., Mollura, D. and Summers, R.M., 2016. Deep convolutional neural networks for computer-aided detection: CNN architectures, dataset characteristics and transfer learning. IEEE transactions on medical imaging, 35(5), pp.1285-1298.
LeCun, Y., Bengio, Y. and Hinton, G. (2015) Deep Learning. Nature, 521, 436-444. http://dx.doi.org/10.1038/nature14539
Salamon, J. and Bello, J.P., 2017. Deep convolutional neural networks and data augmentation for environmental sound classification. IEEE Signal Processing Letters, 24(3), pp.279-283. https://doi.org/10.3390/s23156972
Zhang, B., Yu, K., Ning, Z., Wang, K., Dong, Y., Liu, X., Liu, S., Wang, J., Zhu, C., Yu, Q. and Duan, Y., 2020. Deep learning of lumbar spine X-ray for osteopenia and osteoporosis screening: A multicenter retrospective cohort study. Bone, 140, p.115561.
Chen, J., Kang, X., Liu, Y. and Wang, Z.J., 2015. Median filtering forensics based on convolutional neural networks. IEEE Signal Processing Letters, 22(11), pp.1849-1853.
Li, Z., Tian, Q., Ngamsombat, C., Cartmell, S., Conklin, J., Filho, A.L.M.G., Lo, W.C., Wang, G., Ying, K., Setsompop, K. and Fan, Q., 2022. High‐fidelity fast volumetric brain MRI using synergistic wave‐controlled aliasing in parallel imaging and a hybrid denoising generative adversarial network (HDnGAN). Medical Physics, 49(2), pp.1000-1014. DOI: 10.1002/mp.15427
Smith, L.N., 2017, March. Cyclical learning rates for training neural networks. In 2017 IEEE Winter Conference on Applications of Computer Vision (WACV) (pp. 464-472). IEEE. https://doi.org/10.48550/arXiv.1506.01186
Huang, G., Liu, S., Van der Maaten, L. and Weinberger, K.Q., 2018. Condensenet: An efficient densenet using learned group convolutions. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (pp. 2752-2761). https://doi.org/10.48550/arXiv.1711.09224
Mall, P.K., Singh, P.K., Srivastav, S., Narayan, V., Paprzycki, M., Jaworska, T. and Ganzha, M., 2023. A comprehensive review of deep neural networks for medical image processing: Recent developments and future opportunities. Healthcare Analytics, p.100216. https://doi.org/10.1016/j.health.2023.100216
Ilesanmi, A.E., Ilesanmi, T. and Gbotoso, A.G., 2023. A systematic review of retinal fundus image segmentation and classification methods using convolutional neural networks. Healthcare Analytics, p.100261. https://doi.org/10.1016/j.health.2023.100261
Breit, H.C., Varga-Szemes, A., Schoepf, U.J., Emrich, T., Aldinger, J., Kressig, R.W., Beerli, N., Buser, T.A., Breil, D., Derani, I. and Bridenbaugh, S., 2023. CNN-based evaluation of bone density improves diagnostic performance to detect osteopenia and osteoporosis in patients with non-contrast chest CT examinations. European Journal of Radiology, 161, p.110728.
Eckardt, J.N., Middeke, J.M., Riechert, S., Schmittmann, T., Sulaiman, A.S., Kramer, M., Sockel, K., Kroschinsky, F., Schuler, U., Schetelig, J. and Röllig, C., 2022. Deep learning detects acute myeloid leukemia and predicts NPM1 mutation status from bone marrow smears. Leukemia, 36(1), pp.111-118.
Lee, S.J. and Pickhardt, P.J., 2017. Opportunistic screening for osteoporosis using body CT scans obtained for other indications: the UW experience. Clinical Reviews in Bone and Mineral Metabolism, 15, pp.128-137.
Lorentzon, M., Johansson, H., Harvey, N.C., Liu, E., Vandenput, L., McCloskey, E.V. and Kanis, J.A., 2022. Osteoporosis and fractures in women: the burden of disease. Climacteric, 25(1), pp.4-10.
Zhen, L., Zhang, Y., Yu, K., Kumar, N., Barnawi, A. and Xie, Y., 2021. Early collision detection for massive random access in satellite-based internet of things. IEEE Transactions on Vehicular Technology, 70(5), pp.5184-5189.
Ding, F., Zhu, G., Li, Y., Zhang, X., Atrey, P.K. and Lyu, S., 2021. Anti-forensics for face swapping videos via adversarial training. IEEE Transactions on Multimedia, 24, pp.3429-3441.
Han, S., Oh, J.S. and Lee, J.J., 2022. Diagnostic performance of deep learning models for detecting bone metastasis on whole-body bone scan in prostate cancer. European Journal of Nuclear Medicine and Molecular Imaging, pp.1-11.
Tan, L., Yu, K., Shi, N., Yang, C., Wei, W. and Lu, H., 2021. Towards secure and privacy-preserving data sharing for COVID-19 medical records: A blockchain-empowered approach. IEEE Transactions on Network Science and Engineering, 9(1), pp.271-281.
Grauhan, N.F., Niehues, S.M., Gaudin, R.A., Keller, S., Vahldiek, J.L., Adams, L.C. and Bressem, K.K., 2021. Deep learning for accurately recognizing common causes of shoulder pain on radiographs. Skeletal Radiology, pp.1-8.
Ren, M. and Yi, P.H., 2022. Deep learning detection of subtle fractures using staged algorithms to mimic radiologist search pattern. Skeletal Radiology, pp.1-9.
S. Rani B, G. B, S. G Shivaprasad Yadav, G. Shivakanth and M. B M, "Deep Learning Based Cancer Detection in Bone Marrow using Histopathological Images," 2023 IEEE International Conference on Integrated Circuits and Communication Systems (ICICACS), Raichur, India, 2023, pp. 1-8, doi: 10.1109/ICICACS57338.2023.10100116.
Dimlo, UM Fernandes, R. Umanesan, Jonnadula Narasimharao, N. Senthamilarasi, P. S. Ranjit, B. Balaji, I. Thamarai, and Vijay Kumar Dwivedi. "Optimal Configuration Planning of Multi-Energy Systems using Optimization-based Deep Learning Technique." Electric Power Components and Systems (2023): 1-16.
A. Sathishkumar, S. Majji, T. Radhika Patnala, S. Rao Karanam, A. Kumar and M. Malyadri, "Experimentation Methodology of Orthogonal Frequency Division Multiplexing Signals Process using Radio over Fiber (RoF) system," 2022 International Virtual Conference on Power Engineering Computing and Control: Developments in Electric Vehicles and Energy Sector for Sustainable Future (PECCON), Chennai, India, 2022, pp. 01-05, doi: 10.1109/PECCON55017.2022.9850996.
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
All papers should be submitted electronically. All submitted manuscripts must be original work that is not under submission at another journal or under consideration for publication in another form, such as a monograph or chapter of a book. Authors of submitted papers are obligated not to submit their paper for publication elsewhere until an editorial decision is rendered on their submission. Further, authors of accepted papers are prohibited from publishing the results in other publications that appear before the paper is published in the Journal unless they receive approval for doing so from the Editor-In-Chief.
IJISAE open access articles are licensed under a Creative Commons Attribution-ShareAlike 4.0 International License. This license lets the audience to give appropriate credit, provide a link to the license, and indicate if changes were made and if they remix, transform, or build upon the material, they must distribute contributions under the same license as the original.
