Segmentation of cervical intervertebral disks in videofluorography by CNN, multi-channelization and feature selection



Dysphagia has a large impact on the society because it is a risk factor of malnutrition and aspiration pneumonia, and therefore, it is necessary to elucidate the entire mechanism of dysphagia. In this study, we propose a segmentation method of cervical intervertebral disks (CIDs) in videofluorography (VF) by use of patch-based convolutional neural network (CNN), our multi-channelization (MC) method and image feature selection.


Twenty image filters are individually applied to a VF frame image to generate feature images. One color image, called a multi-channelized image, is generated by setting three selected feature images to its red, green and blue channels. Patch-based CNN is applied to the MC image, and the segmentation accuracy of CIDs is evaluated by the pixel-based F-measure. The combination of the three feature images is optimized by the simulated annealing method.


The proposed method was applied to actual VF dataset consisting of 19 patients and 39 healthy participants. The segmentation accuracy was 59.3% in the F-measure when Sobel and morphological top-hat filters were selected in MC, whereas it was 56.2% when original frame images were used.


The experimental results demonstrated that the proposed method was able to segment CIDs from actual VF and also that the MC method was able to increase the segmentation accuracy by approximately 3%. In this study, LeNet was used as CNN. One of our future tasks is to use other CNNs.

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

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9


  1. 1.

    Marik PE, Kaplan D (2003) Aspiration pneumonia and dysphagia in the elderly. Chest 124(1):328–336

    Article  Google Scholar 

  2. 2.

    Palmer JB, Tanaka E, Ensrud E (2000) Motions of the posterior pharyngeal wall in human swallowing: a quantitative videofluorographic study. Arch Phys Med Rehabil 81(11):1520–1526

    CAS  Article  Google Scholar 

  3. 3.

    Kim Y, Park G-Y, Seo YJ, Im S (2015) Effect of anterior cervical osteophyte in poststroke dysphagia: a case-control study. Arch Phys Med Rehabil 96(7):1269–1276

    Article  Google Scholar 

  4. 4.

    Ryu JS, Lee JH, Kang JY, Kim MY, Shin DE, Shin DA (2012) Evaluation of dysphagia after cervical surgery using laryngeal electromyography. Dysphagia 27(3):318–324

    Article  Google Scholar 

  5. 5.

    Zhang Z, Coyle JL, Sejdić E (2018) Automatic hyoid bone detection in fluoroscopic images using deep learning. Sci Rep 8(1):12310

    Article  Google Scholar 

  6. 6.

    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. In: International conference on medical image computing and computer-assisted intervention (MICCAI 2009), Proceedings. Berlin, pp 524–531

  7. 7.

    Lee JT, Park E, Jung T-D (2019) Automatic detection of the pharyngeal phase in raw videos for the videofluoroscopic swallowing study using efficient data collection and 3d convolutional networks. Sensors 19(18):3873

    Article  Google Scholar 

  8. 8.

    Sa R, Owens W, Wiegand R, Studin M, Capoferri D, Barooha K, Greaux A, Rattray R, Hutton A, Cintineo J, Chaudhary V (2017) Intervertebral disc detection in X-ray images using faster R-CNN. In: 2017 39th annual international conference of the IEEE engineering in medicine and biology society (EMBC). Seogwipo, pp 564–567

  9. 9.

    Fujinaka A, Mekata K, Takizawa H, Kudo H (2019) Preliminary study on intervertebral disk segmentation from videofluorography by multi channelization and CNN. In: The 7th IIAE international conference on intelligent systems and image processing 2019 (ICISIP 2019), Proceedings, Taipei

  10. 10.

    Jadoon MM, Zhang Q, Haq IU, Butt S, Jadoon A (2017) Three-class mammogram classification based on descriptive CNN features. BioMed Res Int 2017:3640901 11 pages

    Article  Google Scholar 

  11. 11.

    Matsuyama E, Lee Y, Takahashi N, Tsai DY (2019) A wavelet coefficient-based convolutional neural network for histological classification of lung cancer in CT images. Med Imag Inf Sci 36(2):64–7

    Google Scholar 

  12. 12.

    The Japanese society of dysphagia rehabilitation. Accessed 18 December 2019

  13. 13.

    Fujinaka A, Saito Y, Mekata K, Takizawa H, Kudo H (2019) Segmentation of intervertebral disks from videofluorographic images using convolutional neural network. In: International forum on medical imaging in asia (IFMIA), Proceedings, Vol 11050, 110501I, Singapore

  14. 14.

    The Swallowing Rehabilitation Research Laboratory. Accessed 9 March 2020

  15. 15.

    Layly J, Marmouset F, Chassagnon G, Bertrand P, Sirinelli D, Cottier J-P, Morel B (2019) Can we reduce frame rate to 15 images per second in pediatric videofluoroscopic swallow studies? Dysphagia 1–5

  16. 16.

    He Q, Perera S, Khalifa Y, Zhang Z, Mahoney AS, Sabry A, Donohue C, Donohue C, Sejdić E (2019) The association of high resolution cervical auscultation signal features with hyoid bone displacement during swallowing. IEEE Trans Neural Syst Rehabil Eng 27(9):1810–1816

    Article  Google Scholar 

Download references


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



Corresponding author

Correspondence to Ayano Fujinaka.

Ethics declarations

Conflict of interest

The authors declare that they have no conflict of interest.

Ethical approval

All procedures performed in studies involving human participants were in accordance with the ethical standards of the institutional and/or national research committee and with the 1964 Helsinki declaration and its later amendments or comparable ethical standards.

Informed consent

Informed consent was obtained from all individual participants included in the study.

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

Verify currency and authenticity via CrossMark

Cite this article

Fujinaka, A., Mekata, K., Takizawa, H. et al. Segmentation of cervical intervertebral disks in videofluorography by CNN, multi-channelization and feature selection. Int J CARS 15, 901–908 (2020).

Download citation


  • Videofluorography
  • Cervical intervertebral disks
  • Multi-channelization
  • CNN
  • Simulated annealing