Regional Assessment of Facial Nerve Paralysis Using Optical Flow Method
The face composed of variation of facial muscles which are responsible to interact through the expressions. The facial nerve contains approximately 10,000 of fibers and any damage to these facial nerve will affects all of muscles associated with facial expressions. Thus, it is one of the most extensive destruction in peripheral nerve injuries which demanded for rapid and accurate commencement of assessment to a better treatment and rehabilitation. The traditional methods involved the subjective assessment of medical professionals which may lead to observer error and acquired different decisions on treatment method. However, an ideal and good objective assessment system is still have to rely on a standardized scale to make it more fits to clinicians’ use for daily applications. In this study, a diagnosis system for the quantitative assessment of facial nerve paralysis has been proposed using optical flow method which provides the degree of precise movements based on House-Brackmann system on each regional parts of face. The system is not only provided the right-left ratio of facial movement to present the side of paralysis, but also offered the regional score for each movements which lead to total score and afforded the most important highlighted scores, which is the House-Brackmann score for each subjects. The regional scores by using the distance measurement has shown the most outstanding result, at about 98% in classifying the patients and may become a great aid to clinicians in determining the condition of patients from the offset of the paralysis.
KeywordsFacial paralysis Facial nerve assessment Bell’s palsy Optical flow Kanade-Lucas-Tomasi (KLT) House-Brackmann system
This research is funded by Fundamental Research Grant Scheme (RDU160143). Many thanks to Director General of Health Malaysia for giving the authorization to publish this paper. Finally, we thank the Medical Research and Ethics Committee (MREC) of Malaysia for providing the ethical approval to collect the data from Hospital Tuanku Fauziah (Ref. No.: NMRR-12-1195-14374). Finally, thanks also goes to the Ministry of Higher Education (MoHE) for the financial support.
- 2.Singhi, P., Jain, V.: Bell’s palsy in children. Semin. Pediatr. Neurol. Elsevier (2003)Google Scholar
- 5.Minamitani, H., et al.: Computerized diagnosis of facial nerve palsy based on optical flow analysis of facial expressions. In: Engineering in Medicine and Biology Society, 2003. Proceedings of the 25th Annual International Conference of the IEEE, pp. 663–666 (2003)Google Scholar
- 10.Lucas, B.D., Kanade, T.: An iterative image registration technique with an application to stereo vision. In: International Joint Conference on Artificial Intelligence, pp. 674–679 (1981)Google Scholar
- 11.Tomasi, C., Kanade, T.: Detection and tracking of point features, Technical report, CMU-CS-91-132 (1991)Google Scholar
- 12.Ali, S., Shah, M.: A Lagrangian particle dynamics approach for crowd flow segmentation and stability analysis. In: 2007 IEEE Conference on Computer Vision and Pattern Recognition, pp. 1–6 (2007)Google Scholar
- 13.Fradet, M., Robert, P., Pérez, P.: Clustering point trajectories with various life-spans. In: 2009 Conference for Visual Media Production, pp. 7–14 (2009)Google Scholar
- 14.Hu, M., Ali, S., Shah, M.: Detecting global motion patterns in complex videos. In: 19th International Conference on Pattern Recognition ICPR 2008. IEEE, pp. 1–5 (2008)Google Scholar