Detection of the Pharyngeal Phase in the Videofluoroscopic Swallowing Study Using Inflated 3D Convolutional Networks

  • Jong Taek LeeEmail author
  • Eunhee Park
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11046)


Videofluoroscopic swallowing study (VFSS) is a standard diagnostic tool for dysphagia. Previous computer assisted analysis of VFSS required manual preparation to mark several anatomical structures and to select time intervals of interest such as a pharyngeal phase during swallowing. These processes were still costly and challenging for clinicians. In this study, we present a novel approach to detect the pharyngeal phase of swallowing through whole of VFSS video clips using Inflated 3D Convolutional Networks (I3D) without additional manual annotations.


Action classification Dysphagia Inflated 3D convolutional networks Videofluoroscopic swallowing study 


  1. 1.
    Aung, M., Goulermas, J., Stanschus, S., Hamdy, S., Power, M.: Automated anatomical demarcation using an active shape model for videofluoroscopic analysis in swallowing. Med. Eng. Phys. 32(10), 1170–1179 (2010)CrossRefGoogle Scholar
  2. 2.
    Carreira, J., Zisserman, A.: Quo vadis, action recognition? a new model and the kinetics dataset. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4724–4733. IEEE (2017)Google Scholar
  3. 3.
    Dengel, G., Robbins, J., Rosenbek, J.C.: Image processing in swallowing and speech research. Dysphagia 6(1), 30–39 (1991)CrossRefGoogle Scholar
  4. 4.
    Kay, W., et al.: The kinetics human action video dataset. arXiv preprint arXiv:1705.06950 (2017)
  5. 5.
    Kellen, P.M., Becker, D.L., Reinhardt, J.M., Van Daele, D.J.: Computer-assisted assessment of hyoid bone motion from videofluoroscopic swallow studies. Dysphagia 25(4), 298–306 (2010)CrossRefGoogle Scholar
  6. 6.
    Lee, J.C., Nam, K.W., Jang, D.P., Paik, N.J., Ryu, J.S., Kim, I.Y.: A supporting platform for semi-automatic hyoid bone tracking and parameter extraction from videofluoroscopic images for the diagnosis of dysphagia patients. Dysphagia 32(2), 315–326 (2017)CrossRefGoogle Scholar
  7. 7.
    Logemann, J., Kahrilas, P., Begelman, J., Dodds, W., Pauloski, B.: Interactive computer program for biomechanical analysis of videoradiographic studies of swallowing. Am. J. Roentgenol. 153(2), 277–280 (1989)CrossRefGoogle Scholar
  8. 8.
    Logemann, J.A., Pauloski, B.R., Rademaker, A.W., Kahrilas, P.J.: Oropharyngeal swallow in younger and older women: videofluoroscopic analysis. J. Speech Lang. Hear. Res. 45(3), 434–445 (2002)CrossRefGoogle Scholar
  9. 9.
    Marik, P.E.: Aspiration pneumonitis and aspiration pneumonia. New Engl. J. Med. 344(9), 665–671 (2001)CrossRefGoogle Scholar
  10. 10.
    Molfenter, S.M., Steele, C.M.: Kinematic and temporal factors associated with penetration-aspiration in swallowing liquids. Dysphagia 29(2), 269–276 (2014)CrossRefGoogle Scholar
  11. 11.
    Noorwali, S.: Semi-automatic tracking of the hyoid bone and the epiglottis movements in digital videofluoroscopic images (2013)Google Scholar
  12. 12.
    Palmer, J.B., Kuhlemeier, K.V., Tippett, D.C., Lynch, C.: A protocol for the videofluorographic swallowing study. Dysphagia 8(3), 209–214 (1993)CrossRefGoogle Scholar
  13. 13.
    Pérez, J.S., Meinhardt-Llopis, E., Facciolo, G.: Tv-l1 optical flow estimation. Image Process. On Line 2013, 137–150 (2013)CrossRefGoogle Scholar
  14. 14.
    Zach, C., Pock, T., Bischof, H.: A Duality Based Approach for Realtime TV-L1 Optical Flow. In: Hamprecht, Fred A., Schnörr, Christoph, Jähne, Bernd (eds.) DAGM 2007. LNCS, vol. 4713, pp. 214–223. Springer, Heidelberg (2007). Scholar

Copyright information

© Springer Nature Switzerland AG 2018

Authors and Affiliations

  1. 1.Electronics and Telecommunications Research InstituteDaeguSouth Korea
  2. 2.Department of Rehabilitation MedicineKyungpook National University Chilgok HospitalDaeguSouth Korea
  3. 3.Department of Rehabilitation MedicineSchool of Medicine, Kyungpook National UniversityDaeguSouth Korea

Personalised recommendations