Skip to main content

Advertisement

SpringerLink
Log in

Automated Segmentation of Cervical Intervertebral Disks from Videofluorography Using a Convolutional Neural Network and its Performance Evaluation

  • Published:
Journal of Signal Processing Systems Aims and scope Submit manuscript

Abstract

Dysphagia has become an important issue in many countries, and there is a strong need for elucidating the causes of dysphagia. One of the promising ways is to analyze the static and dynamic mechanisms of cervical structures, such as epiglottises, hyoid bones, and cervical vertebral bodies, based on medical images. In this study, we propose an automated segmentation method of cervical intervertebral disks (IDs) from videofluorography (VF) by use of a convolutional neural network (CNN). First, cervical masks are extracted from the frame images of VF, and then a patch-based CNN is applied to the cervical masks to obtain the probability images of ID regions. The sizes of patches are changed in a certain range, and pixel values in the patches are normalized. Morphological image filters are applied to the probability images to eliminate false-positive pixels. The proposed method is applied to VF of 58 participants, consisting of 39 healthy people and 19 patients. The segmentation results are compared with the ground truth as determined by a medical doctor and are evaluated with the pixel-wise F-measure. The F-measure is highest (0.880) when the patch size is 21 × 21 pixels and the both of the pixel value normalization (PVN) and the false positive elimination (FPE) are applied. On the other hand, the F-measure is lowest (0.443) when the patch size is 15 × 15 pixels and neither PVN nor FPE is applied.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Figure 1
Figure 2
Figure 3
Figure 4
Figure 5
Figure 6

Similar content being viewed by others

References

  1. Marik, P.E., & Kaplan, D. (2003). Aspiration Pneumonia and Dysphagia in the Elderly. Chest, 124(1), 328–336.

    Article  Google Scholar 

  2. Ekberg, O., Hamdy, S., Woisard, V., Wuttge-Hannig, A., Ortega, P. (2002). Social and Psychological Burden of Dysphagia; Its Impact on Diagnosis and Treatment. Dysphagia, 17(2), 139–146.

    Article  Google Scholar 

  3. Shigeta, Y., Ogawa, T., Ando, E., Clark, G.T, Enciso, R. (2011). Influence of tongue/mandible volume ratio on oropharyngeal airway in Japanese male patients with obstructive sleep apnea. Oral Surgery, Oral Medicine, Oral Pathology, Oral Radiology, and Endodontology, 111(2), 239–243.

    Article  Google Scholar 

  4. De Assuncao Sampaio, R., & Jackowski, M.P. (2017). Vocal Tract Morphology Using Real-Time Magnetic Resonance Imaging. 2017 30th SIBGRAPI Conference on Graphics, Patterns and Images.

  5. Silva, S., & Teixeira, A. (2015). Unsupervised segmentation of the vocal tract from real-time MRI sequences. Computer Speech and Language, 33(1), 25–46.

    Article  Google Scholar 

  6. Labrunie, M., Badin, P., Voit, D., Joseph, A.A., Frahm, J., Lamalle, L., Vilain, C., Boë, L.-J. (2018). Automatic segmentation of speech articulators from real-time midsagittal MRI based on supervised learning. Speech Communication, 99, 27–46.

    Article  Google Scholar 

  7. ChanLee, J., Seo, H.G., Lee, W.H., Kim, H.C., Han, T.R., Oh, B.-M. (2016). Computer-assisted detection of swallowing difficulty. Computer Methods and Programs in Biomedicine, 134, 79–88.

    Article  Google Scholar 

  8. Yaita, S., Takizawa, H., Mekata, K., Kudo, H. (2018). Tracking of Bodies of Hyoid Bones in Videofluorography by Use of Support Vector Machine. Medical Imaging Technology, 38(5), 209–216.

    Google Scholar 

  9. Zhang, Z., Coyle, J.L., Sejdic, E. (2018). Automatic hyoid bone detection in fluoroscopic images using deep learning. Scientific Reports, 8.

  10. Reinartz, R., Platel, B., Boselie, T., van Mameren, H., van Santbrink, H., ter Haar Romeny, B. (2009). Cervical vertebrae tracking in Video-Fluoroscopy using the normalized gradient field. International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI), 524–531.

  11. Mekata, K., Takizawa, H., Matsubayashi, J., Takigawa, T., Toda, K., Ito, Y., Kudo, H. (2017). A preliminary study on template-matching-based tracking of cervical vertebral bodies in videofluorography during swallowing. International Forum on Medical Imaging in Asia (IFMIA), 190–191.

  12. Mekata, K., Takizawa, H., Takigawa, T., Toda, K., Ito, Y., Kudo, H. (2018). Template-Matching-Based Tracking of cervical spines in videofluorography during swallowing. International Conference on Innovation in Medicine and Healthcare (KES-InMed), 2017, 185–191.

    Google Scholar 

  13. Tan, S., Yao, J., Yao, L., Ward, M.M. (2013). High precision semiautomated computed tomography measurement of lumbar disk and vertebral heights. Medical Physics, 40(1).

    Article  Google Scholar 

  14. Chevrefils, C., Chériet, F., Grimard, G., Aubin, C.-E. (2007). Watershed segmentation of intervertebral disk and spinal canal from MRI images. International Conference Image Analysis and Recognition (ICIAR), 1017–1027.

  15. Tang, Z., & Pauli, J. (2011). Fully automatic extraction of human spine curve from MR images using methods of efficient intervertebral disk extraction and vertebra registration. International Journal of Computer Assisted Radiology and Surgery, 6(1), 21–33.

    Article  Google Scholar 

  16. Ji, X., Zheng, G., Belavy, D., Ni, D. (2016). Automated intervertebral disc segmentation using deep convolutional neural networks. International Workshop on Computational Methods and Clinical Applications for Spine Imaging (CSI), 38–48.

    Google Scholar 

  17. Li, X., Dou, Q., Chen, H., Fu, C.-W., Qi, X., Belavý, D.L., Armbrecht, G., Felsenberg, D., Zheng, G., Heng, P.-A. (2018). 3D multi-scale FCN with random modality voxel dropout learning for Intervertebral Disc Localization and Segmentation from Multi-modality MR Images. Medical Image Analysis, 45, 41–54.

    Article  Google Scholar 

  18. Fischler, MA., & Bolles, R.C. (1981). Random Sample Consensus: A Paradigm for Model Fitting with Applications to Image Analysis and Automated Cartography. Communications of the ACM, 24(6), 381–395.

    Article  MathSciNet  Google Scholar 

  19. The Japanese society of dysphagia rehabilitation. (2014). http://www.jsdr.or.jp/wp-content/uploads/file/doc/VF18-2-p166-186.pdf, Accessed 20 June 2019.

  20. Yasuda, T., Takizawa, H., Okumura, T., Kudo, H., Okada, T. (2017). Structure-by-structure Recognition of Spinal Columns, Ribs, Intervertebral Disks and Vertebrae from Abdominal X-ray CT Images. Journal of Japan Society of Computer Aided Surgery, 19(3), 131–138.

    Article  Google Scholar 

  21. Kim, Y., & Kim, D. (2009). A fully automatic vertebra segmentation method using 3D deformable fences. Computerized Medical Imaging and Graphics, 33(5), 343–352.

    Article  Google Scholar 

  22. Korez, R., Likar, B., Pernuš, F., Vrtovec, T. (2014). Parametric modeling of the intervertebral disc space in 3D: Application to CT images of the lumbar spine. Computerized Medical Imaging and Graphics, 38(7), 596–605.

    Article  Google Scholar 

Download references

Acknowledgements

We are grateful to Dr. Jun Matsubayashi in Department of Human Health Sciences, Graduate School of Medicine, Kyoto University, Dr. Tomoyuki Takigawa in Department of Orthopaedic Surgery, Okayama University Hospital, Dr. Kazukiyo Toda and Dr. Yasuo Ito in Department of Orthopaedic Surgery, Kobe Red Cross Hospital for helpful discussion.

Author information

Authors and Affiliations

  1. University of Tsukuba, 1-1-1 Tennodai, Tsukuba, 305-8573, Japan

    Ayano Fujinaka, Hotaka Takizawa & Hiroyuki Kudo

  2. Department of Rehabilitation, Kobe Red Cross Hospital, 1-3-1 Wakinohamakaigandori, Chuo-ku, Kobe, 651-0073, Japan

    Kojiro Mekata

Authors
  1. Ayano Fujinaka
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Kojiro Mekata
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Hotaka Takizawa
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Hiroyuki Kudo
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Ayano Fujinaka.

Additional information

Publisher’s Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Fujinaka, A., Mekata, K., Takizawa, H. et al. Automated Segmentation of Cervical Intervertebral Disks from Videofluorography Using a Convolutional Neural Network and its Performance Evaluation. J Sign Process Syst 92, 299–305 (2020). https://doi.org/10.1007/s11265-019-01498-x

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11265-019-01498-x

Keywords

Search

Navigation