Automatic Assessment of Facial Nerve Function Based on Infrared Thermal Imaging
LIU Xu-long1, 2, FU Bin-rui1, 2, XU Li-wen1, LU Ning2, YU Chang-yong2, BAI Lu-yi2
1. Department of Biomedical Engineering, Northeastern University at Qinhuangdao, Qinhuangdao 066004, China 2. College of Information Science and Engineering, Northeastern University, Shenyang 110819, China
Abstract：Facial paralysis which is mainly caused by facial nerve dysfunction is a common clinical entity. It seriously devastates a patient’s daily life and interpersonal relationships. A method of automatic assessment of facial nerve function is of critical importance for the diagnosis and treatment of facial paralysis. The contralateral asymmetry of facial temperature distribution is one of the newly symptoms of facial paralysis patients which can be captured by infrared thermography. This paper presents a novel framework for objective measurement of facial paralysis based on the automatic analysis of infrared thermal image. Facial infrared thermal image is automatically divided into eight regional areas based on facial temperature distribution specificity and edge detection, the facial temperature distribution features are extracted automatically, including the asymmetry degree of facial temperature distribution, effective thermal area ratio and temperature difference. The automatic classifier is used to assess facial nerve function based on radial basis function neural network (RBFNN). This method comprehensively utilizes the correlation and specificity of the facial temperature distribution，extracts efficiently the facial temperature contralateral asymmetry of facial paralysis in the infrared thermal imaging. In our experiments, 390 infrared thermal images were collected from subjects with unilateral facial paralysis. The results show: the average classification accuracy rate of our proposed method was 94.10%. It has achieved a better classification rate which is above 9.31% than K nearest neighbor (kNN) classifier and 4.87% above Support vector machine (SVM). This experiment results is superior to traditional House-Brackmann facial neural function assessment method. The classification accuracy of facial nerve function with the method is full compliance with the clinical application standard. A complete set of automated techniques for the computerized assessment of thermal images has been developed to assess thermal dysfunction caused by facial paralysis, and the clinical diagnosis and treatment of facial paralysis also will benefit by this method.
刘旭龙1, 2，付斌瑞1, 2，许沥文1，鲁 宁2，于长永2, 柏禄一2. 红外热成像辅助面神经功能自动评估方法研究[J]. 光谱学与光谱分析, 2016, 36(05): 1445-1450.
LIU Xu-long1, 2, FU Bin-rui1, 2, XU Li-wen1, LU Ning2, YU Chang-yong2, BAI Lu-yi2. Automatic Assessment of Facial Nerve Function Based on Infrared Thermal Imaging. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2016, 36(05): 1445-1450.
[1] Holland N J, Weiner G M. BMJ, 2004, 329(7465): 553. [2] Chan J Y K, Byrne P J. Facial Plastic Surgery, 2011, 27(4): 346. [3] Lamina S, Hanif S. African Health Sciences, 2013, 12(4): 514. [4] Henstrom D K, Skilbeck C J, Weinberg J, et al. The Laryngoscope, 2011, 121(1): 47. [5] Lee H Y, Park M S, Byun J Y, et al. Clinical and Experimental Otorhinolaryngology, 2013, 6(3): 135. [6] Wachtman G S, Cohn J F, VanSwearingen J M, et al. Plastic and Reconstructive Surgery, 2001, 107(5): 1124. [7] Mitre E I, Lazarini P R, Dolci J E L. American Journal of Otolaryngology, 2008, 29(1): 51. [8] He S, Soraghan J J, O’Reilly B F. EURASIP J Image Video Process, 2007, 2007(4): 81282. [9] He S, Soraghan J J, O’Reilly B F, et al. IEEE Trans. Biomed. Eng., 2009, 56(7): 1864. [10] GAO Yu-hong, XUE Yi-long, LUO Yun, et al(高宇红, 薛毅珑, 罗 芸, 等). Chinese Journal of Laser Medicine & Surgery(中国激光医学杂志), 2008, 17(1): 50. [11] Zhang D. The American Journal of Chinese Medicine, 2007, 35(6): 967. [12] LIU Xu-long, HONG Wen-xue, ZHANG Tao, et al(刘旭龙, 洪文学, 张 涛, 等). Journal of Biomedical Engineering(生物医学工程学杂志), 2013, 30(1): 34. [13] Nosaka R, Fukui K. Pattern Recognition, 2014, 47(7): 2428. [14] Luqman H, Mahmoud S A, Awaida S. Pattern Recognition, 2014, 47(6): 2231. [15] O’Reilly B F, Soraghan J J, McGrenary S, et al. Otology & Neurotology, 2010, 31(3): 486.
