Facial Paresis Index Prediction by Exploiting Active Appearance Models for Compact Discriminative Features

Luise Modersohn, Joachim Denzler

2016

Abstract

In the field of otorhinolaryngology, the dysfunction of the facial nerve is a common disease which results in a paresis of usually one half of the patients face. The grade of paralysis is measured by physicians with rating scales, e.g. the Stennert Index or the House-Brackmann scale. In this work, we propose a method to analyse and predict the severity of facial paresis on the basis of single images. We combine feature extraction methods based on a generative approach (Active Appearance Models) with a fast non-linear classifier (Random Decision Forests) in order to predict the patients grade of facial paresis. In our proposed framework, we make use of highly discriminative features based on the fitting parameters of the Active Appearance Model, Action Units and Landmark distances. We show in our experiments that it is possible to correctly predict the grade of facial paresis in many cases, although the visual appearance is strongly varying. The presented method creates new opportunities to objectively document the patients progress in therapy.

References

  1. Alberti, P. W. and Biagioni, E. (1972). Facial paralysis in children. a review of 150 cases. The Laryngoscope, 82:1013-1020.
  2. Bradski, G. (2000). The OpenCV Library. Dr. Dobb's Journal of Software Tools.
  3. Breiman, L. (2001). Random trees. Machine Learning, 95(1):5-32.
  4. Cootes, T., Edwards, G., and Taylor, C. (2001). Active appearance models. Transactions on Pattern Analysis and Machine Intelligence, 23(6):681-685.
  5. Coulson, S., Croxson, G., Adams, R., and O'Dwyer, N. (2005). Reliability of the ”sydney,” ”sunnybrook,” and ”house brackmann” facial grading systems to assess voluntary movement and synkinesis after facial nerve paralysis. OtolaryngologyHead and Neck Surgery, 132(4):143-149.
  6. de Ru, J., Braunius, W., van Benthem, P., Busschers, W., and Hordijk, G. (2006). Grading facial nerve function: why a new grading system, the moress, should be proposed. Otology and Neurotology, 27:1030-1036.
  7. Delannoy, J. and Ward, T. (2010). A preliminary investigation into the use of machine vision techniques for automating facial paralysis rehabilitation therapy. Signals and Systems Conference (ISSC), pages 228-232.
  8. Ekman, P. and Friesen, W. (1978). Facial action coding system: A technique for the measurement of facial movement. Consulting Psychologists Press.
  9. Gebhard, A., Paulus, D., Suchy, B., Fucak, I., Wolf, S., and Niemann, H. (2001). Automatische graduierung von gesichtsparesen. In Bildverarbeitung fr die Medizin 2001, Informatik aktuell, pages 352-356. Springer Berlin Heidelberg.
  10. Gebhard, A., Paulus, D., Suchy, B., and Wolf, S. (2000). A system for diagnosis support of patients with facialis paresis. German Journal on Artificial Intelligence, 3.
  11. Guntinas-Lichius, O., Straesser, A., and Streppel, M. (2007). Quality of life after facial nerve repair. The Laryngoscope, 117(3):421-426.
  12. Haase, D., Kemmler, M., Guntinas-Lichius, O., and Denzler, J. (2013). Efficient measuring of facial action unit activation intensities using active appearance models. Proceedings of the 13th IAPR International Conference on Machine Vision Applications (MVA), pages 141-144.
  13. Haase, D., Minnigerode, L., Volk, G., Denzler, J., and Guntinas-Lichius, O. (2015). Automated and objective action coding of facial expressions in patients with acute facial palsy. European Archives of OtoRhino-Laryngology, 272(5):1259-1267.
  14. Haase, D., Nyakatura, J. A., and Denzler, J. (2014). Comparative large-scale evaluation of human and active appearance model based tracking performance of anatomical landmarks in x-ray locomotion sequences. Pattern Recognition and Image Analysis (PRIA), 24(1):86-92.
  15. He, S., Soraghan, J., O'Reilly, B., and Dongshan, X. (2009). Quantitative analysis of facial paralysis using local binary patterns in biomedical videos. Transactions on Biomedical Engineering, 56(7).
  16. House, J. and Brackmann, D. (1985). Facial nerve grading system. OtolaryngologyHead and Neck Surgery, 93:146-147.
  17. Matthews, I. and Baker, S. (2004). Active appearance models revisited. International Journal of Computer Vision, 60(2):135-164.
  18. Peitersen, E. (2002). Bell's palsy: The spontaneous course of 2,500 peripheral facial nerve palsies of different etiologies. Acta Oto-Laryngologica, 122(7):4-30.
  19. Song, I., Nguwi, Y., Vong, J., Diederich, J., and Yellowlees, P. (2013). Profiling bell's palsy based on house-brackmann score. Symposium on Computational Intelligence in Healthcare and e-health (CICARE), pages 1-6.
  20. Song, Q., Montillo, A., Bhagalia, R., and Srikrishnan, V. (2014). Organ localization using joint ap/lat view landmark consensus detection and hierarchical active appearance models. Medical Computer Vision. Large Data in Medical Imaging, 8331:138-147.
  21. Stennert, E., Limberg, C., and Frentrup, K. (1977). Parese und defektheilungsindex; ein leicht anwendbares schema zur objektiven bewertung von therapieerfolgen bei fazialisparesen. HNO, 25:238-245.
  22. Vincent, G., Wolstenholme, C., Scott, I., and Bowes, M. (2010). Fully automatic segmentation of the knee joint using active appearance models. Medical Image Analysis for the Clinic: A Grand Challenge, pages 224- 230.
  23. Wachtman, G., Cohn, J., VanSwearingen, J., and Manders, E. (2001). Automated tracking of facial features in patients with facial neuromuscular dysfunction. Plastic and Reconstructive Surgery, 107(5):1124-1133.
  24. Wang, S. and Qi, F. (2005). Compute aided diagnosis of facial paralysis based on pface. Engineering in Medicine and Biology Society, pages 4353-4356.
Download


Paper Citation


in Harvard Style

Modersohn L. and Denzler J. (2016). Facial Paresis Index Prediction by Exploiting Active Appearance Models for Compact Discriminative Features . In Proceedings of the 11th Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 4: VISAPP, (VISIGRAPP 2016) ISBN 978-989-758-175-5, pages 271-278. DOI: 10.5220/0005787602710278


in Bibtex Style

@conference{visapp16,
author={Luise Modersohn and Joachim Denzler},
title={Facial Paresis Index Prediction by Exploiting Active Appearance Models for Compact Discriminative Features},
booktitle={Proceedings of the 11th Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 4: VISAPP, (VISIGRAPP 2016)},
year={2016},
pages={271-278},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0005787602710278},
isbn={978-989-758-175-5},
}


in EndNote Style

TY - CONF
JO - Proceedings of the 11th Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 4: VISAPP, (VISIGRAPP 2016)
TI - Facial Paresis Index Prediction by Exploiting Active Appearance Models for Compact Discriminative Features
SN - 978-989-758-175-5
AU - Modersohn L.
AU - Denzler J.
PY - 2016
SP - 271
EP - 278
DO - 10.5220/0005787602710278