Injury classification and level detection of the spinal cord based on the optimized recurrent neural network
-
Munavar Jasim K
and
Thomas Brindha
Abstract
Objectives
Spinal cord damage is one of the traumatic situations in persons that may cause the loss of sensation and proper functioning of the muscles either temporarily or permanently. Hence, steps to assure the recovery through the early functioning and precaution could safe-guard a proper interceptive. To ensure the recovery of spinal cord damage through optimized recurrent neural network.
Methods
The research on the spinal cord injury classification and level detection is done using the CT images, which is initially given to the segmentation that is done using the adaptive thresholding methodology. Once the segments are formed, the disc is localized using the sparse fuzzy C-means clustering approach. In the next step, the features are extracted from the localized disc and the features include the connectivity features, statistical features, image-level features, grid-level features, Histogram of Oriented Gradients (HOG), and Linear Gradient Pattern (LGP). Then, the injury detection is done based on the Crow search Rider Optimization algorithm-based Deep Convolutional Neural Network (CS-ROA-based DCNN). Once the result regarding the presence of the injury is obtained, the injury-level classification is done based on the proposed Deep Recurrent Neural Network (Deep RNN), and in case of the absence of injury, the process is terminated. Therefore, the injury detection classifier derives the level of the injury, such as normal, wedge, biconcavity, and crush.
Results
The experimentation is carried out using an Osteoporotic vertebral fractures database. The performance of the injury level detection based on the proposed model is evaluated based on accuracy, sensitivity, and specificity. The proposed model achieves the maximal accuracy of 0.895, maximal sensitivity of 0.871, and the maximal specificity of 0.933 with respect to K-Fold.
Conclusions
The experimental results show that the proposed model is better than the existing models in terms of accuracy, sensitivity, and specificity.
Research funding: None.
Author contributions: All the authors have accepted responsibility for the entire content of this submitted manuscript and approved submission.
Competing interests: The funding organization(s) played no role in the study design; in the collection, analysis, and interpretation of data; in the writing of the report; or in the decision to submit the report for publication. The authors declare that they have no conflict of interest.
Ethical approval: The conducted research is not related to either human or animal use.
References
1. Talbott, JF, Huie, JR, Ferguson, AR, Bresnahan, JC, Beattie, MS, Dhall, SS. MR imaging for assessing injury severity and prognosis in acute traumatic spinal cord injury. Radiol Clin 2019;57:319–39. https://doi.org/10.1016/j.rcl.2018.09.004.Search in Google Scholar
2. Pranata, YD, Wang, K-C, Wang, J-C, Idram, I, Lai, J-Y, Liu, J-W, et al.. Deep learning and SURF for automated classification and detection of calcaneus fractures in CT images. Comput Methods Progr Biomed 2019;171:27–37. https://doi.org/10.1016/j.cmpb.2019.02.006.Search in Google Scholar
3. Han, Z, Wei, B, Mercado, A, Leung, S, Li, S. Spine-GAN: semantic segmentation of multiple spinal structures. Med Image Anal 2018;50:23–35. https://doi.org/10.1016/j.media.2018.08.005.Search in Google Scholar
4. Ahammad, SKH, Rajesh, V, Rahman, MDZU. Fast and accurate feature extraction-based segmentation framework for spinal cord injury severity classification. IEEE Access 2019;7:46092–103. https://doi.org/10.1109/access.2019.2909583.Search in Google Scholar
5. Tay, B, Hyun, JK, Oh, S. A machine learning approach for specification of spinal cord injuries using fractional anisotropy values obtained from diffusion tensor images. Comput Math Methods Med 2014;2014:276589. https://doi.org/10.1155/2014/276589.Search in Google Scholar
6. Kirshblum, SC, Burns, SP, Biering-Sorensen, F, Donovan, W, Graves, DE, Jha, A, et al.. International standards for neurological classification of spinal cord injury (Revised 2011). J Spinal Cord Med 2011;34:535–46. https://doi.org/10.1179/204577211x13207446293695.Search in Google Scholar
7. Middendorp, JJ, Audige, L, Hanson, B, Chapman, JR, Hosman, AJF. What should an ideal spinal injury classification system consist of? A methodological review and conceptual proposal for future classifications. Eur Spine J 2010;19:1238–49. https://doi.org/10.1007/s00586-010-1415-9.Search in Google Scholar
8. Middendorp, JJ, Audige, L, Bartels, RH, Bolger, C, Deverall, H, Dhoke, P, et al.. The subaxial cervical spine injury classification system: an external agreement validation study. Spine J 2013;13:1055–63. https://doi.org/10.1016/j.spinee.2013.02.040.Search in Google Scholar
9. Wellner, PD. Adaptive thresholding for the digital desk, Technical Report. Cambridge: EPC Copyright Rank Xerox Ltd., Rank Xerox Research Centre Cambridge Laboratory; 1993. 93–110 pp.Search in Google Scholar
10. Chang, X, Wang, Q, Liu, Y, Wang, Y. Sparse regularization in fuzzy c-means for high-dimensional data clustering. IEEE Trans Cybern 2016;47:1–12. https://doi.org/10.1109/TCYB.2016.2627686.Search in Google Scholar
11. Manfredini, D, Stellini, E, Gracco, A, Lombardo, L, Nardini, LG, Siciliani, G. Orthodontics is temporomandibular disorder-neutral. Informationen Aus Orthodontie Und Kieferorthopaedie 2017;49:202–7. https://doi.org/10.1055/s-0043-118188.Search in Google Scholar
12. Cristini, R, Merlin, NRG, Ramanathan, L, Vimala, S. Image forgery detection using back propagation neural network nodel and oarticle swarm optimization algorithm. Multimed Res 2020;3:21–32.10.46253/j.mr.v3i1.a3Search in Google Scholar
13. Bhagyalakshmi, V, Ramchandra, Geeta, D. Arrhythmia classification using cat swarm optimization based support vector neural network. J Netw Commun Syst 2018;1:28–35.10.46253/jnacs.v1i1.a4Search in Google Scholar
14. Vinolin, V, Vinusha, S. Enhancement in biodiesel blend with the aid of neural network and SAPSO. J Comput Mech Power Syst Contr 2018;1:11–7.10.46253/jcmps.v1i1.a2Search in Google Scholar
15. Vojt, BJ. Deep neural networks and their implementation. Department of Theoretical Computer Science and Mathematical Logic; 2016.Search in Google Scholar
16. Binu, D, Kariyappa, BS. RideNN: a new rider optimization agorithm-based neural network for fault dagnosis in analog circuits. IEEE Trans Instrum Meas 2018:1–25.10.1109/TIM.2018.2836058Search in Google Scholar
17. Mukherjee, DP, Cheng, I, Ray, N, Mushahwar, V, Lebel, M, Basu, A. Automatic segmentation of spinal cord MRI using symmetric boundary tracing. IEEE Trans Inf Technol Biomed 2010. https://doi.org/10.1109/TMI.2009.2023362.Search in Google Scholar
18. Huang, SH, Chu, YH, Lai, SH, Novak, CL. Learning-based vertebra detection and iterative normalized-cut segmentation for spinal MRI. IEEE Trans Med Imag 2009:1595–605. https://doi.org/10.1109/TMI.2009.2023362.Search in Google Scholar
19. Tomita, N, Cheung, YY, Hassanpour, S. Deep neural networks for automatic detection of osteoporotic vertebral fractures on CT scans. Comput Biol Med 2018;98:8–15.10.1016/j.compbiomed.2018.05.011Search in Google Scholar PubMed
20. Leener, BD, Cohen-Adad, J, Kadoury, S. Automatic segmentation of the spinal cord and spinal canal coupled with vertebral labeling. IEEE Trans Med Imaging 2015:1705–18.10.1109/TMI.2015.2437192Search in Google Scholar PubMed
21. Klinder, T, Ostermann, J, Ehm, M, Franz, A, Kneser, R, Lorenz, C. Automated model-based vertebra detection, identification, and segmentation in CT images. Med Image Anal 2009:471–82. https://doi.org/10.1016/j.media.2009.02.004.Search in Google Scholar
22. Wang, KSZQ, Lu, L, Wu, D, El-Zehiry, N, Zheng, Y, Shen, D. Automatic segmentation of spinal canals in CT images via iterative topology refinement. IEEE Trans Med Imag 2015:1694–704. https://doi.org/10.1109/tmi.2015.2436693.Search in Google Scholar
23. Lakshmi, ND, Latha, YM, Damodaram, A. Silhouette extraction of a human body based on fusion of HOG and graph-cut segmentation in dynamic backgrounds. In: Third international conference on computational intelligence & communication technology. Mumbai, India: IET; 2013.10.1049/cp.2013.2641Search in Google Scholar
24. Mou, L, Ghamisi, P, Zhu, XX. Deep recurrent neural networks for hyperspectral Image classification. IEEE Trans Geosci Rem Sen 2017.10.1109/TGRS.2016.2636241Search in Google Scholar
25. Jun, B, Choi, I, Kim, D. Local transform features and hybridization for accurate face and human detection. IEEE Trans Pattern Anal Mach Intell 2013:1423–36. https://doi.org/10.1109/tpami.2012.219.Search in Google Scholar
26. Askarzadeh, A. A novel metaheuristic method for solving constrained engineering optimization problems: crow search algorithm. Comput Struct 2016;169:1–12. https://doi.org/10.1016/j.compstruc.2016.03.001.Search in Google Scholar
27. Osteoporotic vertebral fractures [Online]. Available from: http://spineweb.digitalimaginggroup.ca/spineweb/index.php?n=Main.Datasets#Dataset_9.3A_Automatic_vertebral_fracture_analysis_and_identification_from_VFA_by_DXA [Accessed Nov 2019].Search in Google Scholar
28. Giuffrida, JP, Crago, PE. Functional restoration of elbow extension after spinal-cord injury using a neural network-based synergistic FES controller. IEEE Trans Neural Syst Rehabil Eng 2005;13:147–52. https://doi.org/10.1109/tnsre.2005.847375.Search in Google Scholar
© 2020 Walter de Gruyter GmbH, Berlin/Boston
Articles in the same Issue
- Frontmatter
- Short Communication
- The relationship between expression of VIMENTIN and CD146 genes in breast cancer
- Research Articles
- Automated diagnosis of diabetic retinopathy enabled by optimized thresholding-based blood vessel segmentation and hybrid classifier
- Injury classification and level detection of the spinal cord based on the optimized recurrent neural network
- Regularized error function-based extended Kalman filter for estimating the cancer chemotherapy dosage: impact of improved grey wolf optimization
- Bio-algorithms for the modeling and simulation of cancer cells and the immune response
Articles in the same Issue
- Frontmatter
- Short Communication
- The relationship between expression of VIMENTIN and CD146 genes in breast cancer
- Research Articles
- Automated diagnosis of diabetic retinopathy enabled by optimized thresholding-based blood vessel segmentation and hybrid classifier
- Injury classification and level detection of the spinal cord based on the optimized recurrent neural network
- Regularized error function-based extended Kalman filter for estimating the cancer chemotherapy dosage: impact of improved grey wolf optimization
- Bio-algorithms for the modeling and simulation of cancer cells and the immune response
