Saif, A. F. M. 
ORCID: https://orcid.org/0000-0002-7443-8844, Shahnaz, Celia, Zhu, Wei-Ping ORCID: https://orcid.org/0000-0001-7955-7044 and Ahmad, M. Omair ORCID: https://orcid.org/0000-0002-2924-6659
(2019)
Abnormality Detection in Musculoskeletal Radiographs Using Capsule Network.
IEEE Access, 7
.
pp. 81494-81503.
ISSN 2169-3536
Preview |
Text (application/pdf)
5MBZhu-IEEE Access-2019.pdf - Published Version Available under License Spectrum Terms of Access. |
Official URL: http://dx.doi.org/10.1109/ACCESS.2019.2923008
Abstract
To treat the diseases or injuries of the joints, bones, muscles, and spine in both adult and pediatric imaging the musculoskeletal radiographs bring a significant depth of expertise. Abnormality detection in the musculoskeletal study is backbreaking as more than 1.7 billion people are affected by musculoskeletal condition (BMU, 2017). Hence if we want to create enough opportunity to treat a maximum amount of patients, machine learning and deep learning can play a crucial role. CNN is an excellent deep learning method for image classification and other computer vision tasks. But CNN has exhibited some serious limitations when the images are rotated and deformed. Hence capsule network architecture is introduced in this paper for musculoskeletal radiographs abnormality detection and this capsnet architecture has shown very promising features that can help to vanquish the limitations of CNN. In addition, this capsule network has scored 10% higher kappa score than 169 layer densenet using less training data in the case of musculoskeletal radiographs abnormality detection. This feature of capsule network can help to use deep learning in such cases where an aggregate of a large amount of data is not possible. For image quality investigation, blind image spatial quality evaluator (BRISQUE) and naturalness image quality evaluator (NIQE) scores are measured and it is found that when the pixel size of the resized images are more close to the pixel size of the original images, we get a better approximation. Hence in the case of musculoskeletal radiographs abnormality detection, our method outperforms state-of-the-art method using a less amount of training data.
| Divisions: | Concordia University > Gina Cody School of Engineering and Computer Science > Electrical and Computer Engineering |
|---|---|
| Item Type: | Article |
| Refereed: | Yes |
| Authors: | Saif, A. F. M. and Shahnaz, Celia and Zhu, Wei-Ping and Ahmad, M. Omair |
| Journal or Publication: | IEEE Access |
| Date: | 2019 |
| Funders: |
|
| Digital Object Identifier (DOI): | 10.1109/ACCESS.2019.2923008 |
| Keywords: | Capsule network, routing-by-agreement, squashing, margin loss, Cohen’s kappa statistic |
| ID Code: | 986103 |
| Deposited By: | Krista Alexander |
| Deposited On: | 21 Nov 2019 20:12 |
| Last Modified: | 21 Nov 2019 20:12 |
References:
1. A. Criminisi, J. Shotton, E. Konukoglu, "Decision forests: A unified framework for classification regression density estimation manifold learning and semi-supervised learning", Found. Trends Comput. Graph. Vis., vol. 7, no. 3, pp. 81-227, Feb. 2012.2. E. Ricci, R. Perfetti, "Retinal blood vessel segmentation using line operators and support vector classification", IEEE Trans. Med. Imag., vol. 26, no. 10, pp. 1357-1365, Oct. 2007.
3. I. El-Naqa, Y. Yang, M. N. Wernick, N. P. Galatsanos, R. M. Nishikawa, "A support vector machine approach for detection of microcalcifications", IEEE Trans. Med. Imag., vol. 21, no. 12, pp. 1552-1563, Dec. 2002.
4. H. P. Ng, S. H. Ong, K. W. C. Foong, P. S. Goh, W. L. Nowinski, "Medical image segmentation using k-means clustering and improved watershed algorithm", Proc. IEEE Southwest Symp. Image Anal. Interpretation, pp. 61-65, Mar. 2006.
5. E. I. Zacharaki, Sumei Wang, S. Chawla, D. S. Yoo, R. Wolf, E. R. Melhem, C. Davatzikos, "Classification of brain tumor type and grade using MRI texture and shape in a machine learning scheme", Magn. Reson. Med., vol. 62, no. 6, pp. 1609-1618, Dec. 2009.
6. B. N. Li, C. K. Chui, S. Chang, S. H. Ong, "Integrating spatial fuzzy clustering with level set methods for automated medical image segmentation", Comput. Biol. Med., vol. 41, no. 1, pp. 1-10, 2011.
7. R. J. Martis, C. Chakraborty, A. K. Ray, "A two-stage mechanism for registration and classification of ECG using Gaussian mixture model", Pattern Recognit., vol. 42, no. 11, pp. 2979-2988, Nov. 2009.
8. A. Krizhevsky, I. Sutskever, G. E. Hinton, "ImageNet classification with deep convolutional neural networks", Proc. NIPS, pp. 1097-1105, Dec. 2012.
9. K. He, X. Zhang, S. Ren, J. Sun, "Deep residual learning for image recognition", Proc. IEEE CVPR, pp. 770-778, Jun. 2016.
10. S. Sabour, N. Frosst, G. E. Hinton, "Dynamic routing between capsules", Proc. Adv. Neural Inf. Process. Syst., pp. 3859-3869, 2017.
11. G. E. Hinton, A. Krizhevsky, S. D. Wang, T. Honkela, W. Duch, M. Girolami, S. Kaski, "Transforming auto-encoders" in Artificial Neural Networks and Machine Learning, Berlin, Germany:Springer, pp. 44-51, 2011.
12. P. Rajpurkar, J. Irvin, A. Bagul, D. Ding, T. Duan, H. Mehta, B. Yang, K. Zhu, D. Laird, R. L. Ball, C. Langlotz, K. Shpanskaya, M. P. Lungren, A. Y. Ng, "MURA: Large dataset for abnormality detection in musculoskeletal radiographs", Proc. 1st Conf. Med. Imag. Deep Learn. (MIDL), pp. 1-10, 2017, [online] Available: https://arxiv.org/abs/1712.06957.
13. P. Afshar, A. Mohammadi, K. N. Plataniotis, "Brain tumor type classification via capsule networks", arXiv:1802.10200, Mar. 2018, [online] Available: https://arxiv.org/abs/1802.10200.
14. R. LaLonde, U. Bagci, "Capsules for object segmentation", arXiv:1804.04241, Apr. 2018, [online] Available: https://arxiv.org/abs/1804.04241.
15. A. Mittal, A. K. Moorthy, A. C. Bovik, "No-reference image quality assessment in the spatial domain", IEEE Trans. Image Process., vol. 21, no. 12, pp. 4695-4708, Dec. 2012.
16. A. Mittal, R. Soundararajan, A. C. Bovik, "Making a ‘completely blind’ image quality analyzer", IEEE Signal Process. Letters., vol. 20, no. 3, pp. 209-212, Mar. 2013.
17. J. Sim, C. C. Wright, "The kappa statistic in reliability studies: Use interpretation and sample size requirements", Phys. Therapy, vol. 85, no. 3, pp. 257-268, Mar. 2005.
18. A. J. Viera, J. M. Garrett, "Understanding interobserver agreement: The kappa statistic", Fam Med, vol. 37, no. 5, pp. 360-363, 2005.
19. G. Huang, Z. Liu, L. van der Maaten, K. Q. Weinberger, "Densely connected convolutional networks", arXiv:1608.06993, Sep. 2016, [online] Available: https://arxiv.org/abs/1608.06993.
20. L. Berlin, "Liability of interpreting too many radiographs", Amer. J. Roentgenol., vol. 175, no. 1, pp. 17-22, 2000.
21. J. Deng, W. Dong, R. Socher, L.-J. Li, K. Li, L. Fei-Fei, "Imagenet: A large-scale hierarchical image database", Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), pp. 248-255, Jun. 2009.
22. W. Gale, L. Oakden-Rayner, G. Carneiro, A. P. Bradley, L. J. Palmer, "Detecting hip fractures with radiologist-level performance using deep neural networks", arXiv:1711.06504, Nov. 2017, [online] Available: https://arxiv.org/abs/1711.06504.
23. D. P. Kingma, J. Ba, "Adam: A method for stochastic optimization", arXiv:1412.6980, Dec. 2014, [online] Available: https://arxiv.org/abs/1412.6980.
24. B. Zhou, A. Khosla, A. Lapedriza, A. Oliva, A. Torralba, "Learning deep features for discriminative localization", Proc. IEEE Conf. Comput. Vis. Pattern Recognit., pp. 2921-2929, Jun. 2016.
25. A. D. Woolf, B. Pflege, "Burden of major musculoskeletal conditions", Bull. World Health Org., vol. 81, no. 9, pp. 646-656, 2003.
26. I. Goodfellow, Y. Bengio, A. Courville, Deep Learning, Cambridge, MA, USA:MIT Press, 2016.
Repository Staff Only: item control page
Download Statistics
Download Statistics