Evaluation of the Facial Paralysis Degree

Abstract

The majority research into human faces in computer vision and pattern recognition is concerned with normal people, i.e. their faces are not affected by any diseases and appear symmetric or approximately symmetric. However, a great number of people in the world are suffering from facial paralysis. Facial Paralysis is a devastating disorder. It is caused when the facial nerve, which sends nerve impulses to the muscles of the face, loses its function. Facial paralysis results in significant psychological and functional disability from the impairment of facial expression, communication and eye protection. For example, it usually affects one side of the face, causing a drooping mouth, drooling, and excessive tearing from one eye. Thus, the evaluation of the degree of paralysis is very important (Beurskens & Heymans , 2003), as different degree requires different medical treatment. For example, as a reliable and effective method, acupuncture doctors may use different needles based on the patient’s paralysis degree. In the past, several evaluation criterions regarding face nerve were proposed. Traditional assessment of facial paralysis is by the House-Brackmann(HB) grading system (House & Brackman, 1985) which was proposed in 1983 and has been adopted as the North American standard for the evaluation of facial paralysis. Grading is achieved by asking the patient to perform certain movements and then using clinical observation and subjective judgment to assign a grade of palsy ranging from grade I (normal) to grade VI (no movement). The advantages of the HB grading scale are its ease of use by clinicians and that it offers a single figure description of facial function. The drawbacks are that it relies on a subjective judgment and it is insensitive to regional differences of function in the different parts of the face. To provide physicians with an objective and quantitative measurement of single-sided facial paralysis, several computer-based methods have been proposed. Maximum static response assay (MSRA) assesses facial function by measuring the displacement of standard reference points of the face (Johnson et al., 1994). The method measures the amplitude of standard facial movements by comparing facial photographs taken at rest and at maximum contraction. For voluntary expressions of a patient, Wang et al present a facial paralysis grading approach based on measuring the patient’s asymmetry (S et al., 2004). Compared with other international grading scales for facial paralysis, such as House-Brackmann and DEFS, the advantages of the approach are that it is objective and can diagnose facial paralysis automatically.