Cervical spondylosis detection using deep dense auxiliary inception network

Document Type : Research Paper

Authors

1 GHRCOE, Nagpur, India

2 GHRIEAT, Nagpur, India

Abstract

Cervical Spondylosis is a recurring spinal syndrome in which the spine progressively tightens and that can eventually become fully rigid. Early diagnosis is really an efficient way of improving the recovery rate and reducing costs. Due to the difficult and comprehensive procedure for recognizing cervical spondylosis in the initial stages, this area is untreated. Strong correlations of the vertebrae make the automatic detection procedure challenging. These minor variations in the X-ray image make visual interpretation a challenging task involving skilled explorers. Even after this, the problem still remains untreated and also the feasibility of even an automatic detection framework has still not been addressed for this application. Thus, the Deep learning-based method was used to predict some potential relevance of Cervical Spondylosis has. The proposed system can be used to detect the onset of cervical spondylosis in the early stages using deep learning techniques.

Keywords

[1] P. Bailey and L. Casamajor, Osteo-arthritis of the spine as a cause of compression of the spinal cord and its roots,
J. Nerv. Ment. Dis. 38(10) (1911) 588–609.[2] W.R. Brain, G.C. Knight and J.W.D. Bull, Discussion on rupture of the intervertebral disc in the cervical region,
Proc. R. Soc. Med. 41 (1948) 509–516.
[3] W.R. Brain, D. Northfield and M. Wilkinson, The neurologic manifestations of cervical spondylosis, Brain 75
(1952) 187–225.
[4] P.B. Chanda, A. Paul, A. Paul and S. Sarkar, Spondylosis detection and classification Of cervical images using
ATMFCMC based medical image segmentation methods, Proc. Int. Conf. Adv. Electron. Elect. Comput. Intell.
2019, Available at SSRN: https://ssrn.com/abstract=3575474 or http://dx.doi.org/10.2139/ssrn.3575474.
[5] H. Chen, C. Shen, J. Qin, D. Ni, L. Shi, J.C. Cheng and P.A. Heng, Automatic localization and identification of
vertebrae in spine CT via a joint learning model with deep neural networks, in Medical Image Computing and
Computer-Assisted Intervention–MICCAI, Springer, (2015) 515–522.
[6] P. Chitte and U.M. Gokhale, Analysis of different methods for identification and classification of cervical spondylosis (CS): A survey, Int. J. Appl. Engin. Res. 12 (2017) 11727–11737.
[7] B.M. McCormack and P.R. Weinstein, Cervical spondylosis. An update, West J. Med. 165(1-2) (1996) 43–51.
[8] X. Glorot, A. Bordes and Y. Bengio, Deep sparse rectifier neural networks[C], Int. Conf. Artificial Intell. Stat.
(2011) 315–323.
[9] G.E. Hinton, N. Srivastava, A. Krizhevsky, I. Sutskever and R. Salakhutdinov, Improving neural networks by
preventing co-adaptation of feature detectors, CoRR, abs/1207.0580, 2012.
[10] R. Janssens, G. Zeng and G. Zheng, Fully automatic segmentation of lumbar vertebrae from CT images using
cascaded 3D fully convolutional networks, 2018 IEEE 15th Int. Symp. Biomed. Imaging (ISBI 2018), Washington,
DC, USA, (2018) 893–897.
[11] H. Jin Bae, H. jung Hyun, Y. Byeon, K. Shin, Y. Cho, Y. Ji Song, S. Yi, S. Kuh, J. S. Yeom and N. Kim, Fully
automated 3D segmentation and separation of multiple cervical vertebrae in CT images using a 2D convolutional
neural network, Computer Meth. Prog. Biomed. 184 (105119) (2020).
[12] B. Kara, A. Celik, S. Karadereler, L. Ulusoy, K. Ganiyusufoglu, L. Onat, A. Mutlu, I. Ornek, M. Sirvanci and A.
Hamzaoglu, The role of DTI in early detection of cervical spondylotic myelopathy: a preliminary study with 3-T
MRI, Neuroradiology 53 (2011) 609-–616.
[13] A. Krizhevsky, I. Sutskever and G. Hinton, Imagenet classification with deep convolutional neural networks, Adv.
Neural Inf. Proces. Syst. 25 (2012) 1106—1114.
[14] C. Kuok, J. Hsue, T. Shen, B. Huang, C. Chen and Y. Sun, An effective CNN approach for vertebrae segmentation
from 3D CT images, 2018 Pacific Neighborhood Consortium Annual Conference and Joint Meetings (PNC), San
Francisco, CA, USA, (2018) 1–6.
[15] M. Lin, Q. Chen and S. Yan. Network in network, CoRR abs/1312.4400, 2013.
[16] M. McDonnell and P. Lucas, Cervical spondylosis, stenosis, and rheumatoid arthritis, Med. Health, Rhode Island
95(4) (2012) 105—109.
[17] Y. Li, W. Liang, Y. Zhang, H. An and J. Tan, Automatic Lumbar vertebrae detection based on feature fusion
deep learning for partial occluded C-arm X-ray images, 2016 38th Annual International Conference of the IEEE
Engineering in Medicine and Biology Society (EMBC), Orlando, FL, USA, (2016) 647–650.
[18] A. Paul and P.B. Chanda, Detection and classification of cervical spondylosis using image segmentation techniques,
Inf. Photon. Commun. Lecture Notes in Networks and Systems, Springer, Singapore, 79 (2020) 145–154.
[19] R. Sa, W. Owens, R. Wiegand, M. Studin, D. Capoferri, K. Barooha, A. Greaux, R. Rattray, A. Hutton, J.
Cintineo and Vipin Chaudhary, Intervertebral disc detection in X-ray images using faster R-CNN, 39th Annual
Int. Conf. IEEE Engin. Med. Bio. Soc. Jeju, Korea (South), (2017) 564–567.
[20] P. Sermanet, D. Eigen, X. Zhang, M. Mathieu, R. Fergus and Y. LeCun, Overfeat: Integrated recognition,
localization and detection using convolutional networks, 2nd Int. Conf. Learning Represent. ICLR 2014, Banff,
Canada.
[21] S. Singh, D. Kumar and S. Kumar, Risk factors in cervical spondylosis, J. Clinical Orthopaed. Trauma 5(4) (2014)
221–226.
[22] J. Sola and J. Sevilla, Importance of input data normalization for the application of neural networks to complex
industrial problems[J], IEEE Trans. Nuclear Sci. 44(3) (1997) 1464–1468.
[23] M. Sreeraj, Jestin Joy, Manu Jose, Meenu Varghese and T.J. Rejoice, Comparative analysis of Machine Learning
approaches for early stage Cervical Spondylosis detection, J. King Saud Univ. Comput. Inf. Sci. (2020).
[24] A. Suzani, A. Seitel, Y. Liu, S. Fels, R. N. Rohling and P. Abolmaesumi, Fast automatic vertebrae detection and
localization in pathological ct scans-a deep learning approach, Medical Image Computing and Computer-Assisted
Intervention–MICCAI, Springer, (2015) 678–686.
[25] A. Suzani, A. Rasoulian, A. Seitel, S. Fels, R. N. Rohling and P. Abolmaesumi, Deep learning for automatic
localization, identification, and segmentation of vertebral bodies in volumetric MR images, In SPIE MedicalImaging. Int. Soc. Optic. Photon. (2015) 514—941.
[26] A. Voorhies and M. Rand, Cervical Spondylosis: Recognition, Differential Diagnosis, and Managemen, Ochsner
J. 3(2) (2001) 78–84.
[27] N. Wang, L. Cui, X. Huang, Y. Xiang and J. Xiao, EasiCSDeep: A deep learning model for cervical spondylosis
identification using surface electromyography signal, arXiv:1812.04912 [cs.LG].
[28] X. Yu and L. Xiang, Classifying Cervical Spondylosis Based on Fuzzy Calculation, Abstr. Appl. Anal. 2014 (2014)
Article ID 182956.
[29] M.D. Zeiler and R. Fergus, Visualizing and Understanding Convolutional Networks, In: ECCV, Lecture Notes
Comput. Sci. 2014.
[30] L. Zhang and H. Wang, A novel segmentation method for cervical vertebrae based on PointNet++ and converge
segmentation, Comput. Meth. Prog. Biomed. 200 (105798) (2021).
Volume 12, Special Issue
December 2021
Pages 1595-1604
  • Receive Date: 01 August 2021
  • Revise Date: 23 September 2021
  • Accept Date: 16 November 2021