Facial movements are crucial for human interaction because they provide relevant information on verbal and non-verbal communication and social interactions. From a clinical point of view, the analysis of facial movements is important for diagnosis, follow-up, drug therapy, and surgical treatment. Current methods of assessing facial palsy are either (i) objective but inaccurate, (ii) subjective and, thus, depending on the clinician’s level of experience, or (iii) based on static data. To address the aforementioned problems, we implemented a deep learning algorithm to assess facial movements during smiling. Such a model was trained on a dataset that contains healthy smiles only following an anomaly detection strategy. Generally speaking, the degree of anomaly is computed by comparing the model’s suggested healthy smile with the person’s actual smile. The experimentation showed that the model successfully computed a high degree of anomaly when assessing the patients’ smiles. Furthermore, a graphical user interface was developed to test its practical usage in a clinical routine. In conclusion, we present a deep learning model, implemented on open-source software, designed to help clinicians to assess facial movements.

Orthognathic surgery affects both function and aesthetics. An important aesthetic complication is the nasal alteration that can result from Le Fort I osteotomy. A common method for countering this complication is the alar base cinch suture technique. Although the method for this suture has been standardized, the results vary and are inconsistent; further improvements are therefore required. The objective of this study was to review the literature data on the alar base cinch suture technique and associated results. In this review, the PubMed, Ovid, and Ichushi-Web electronic databases were searched using logical combinations of keywords related to the perinasal musculature and alar base cinch suture technique. Following screening of the results, 42 publications were included. The review findings prompted several conclusions. The anatomy of the myrtiformis muscle and depressor septi nasalis may differ between ethnicities, and it is essential to take certain factors related to ethnicity into account when implementing the alar base cinch suture technique. It is also important to consider factors such as the patient's aesthetic preferences.

Background: Peripheral facial palsy (PFP) affects up to 30 people per 100,000 person-years, leading to functional, aesthetic and social implications in patients. The aim of this study was to measure the attention paid to paralyzed faces versus healthy faces using a dynamic eye-tracking percept. Methods: Thirty observers watched video sequences of patients and healthy volunteers performing four facial movements, and their gaze was recorded. Results: In all cases, the observers focused their attention on the face’s central triangle and particularly on the eyes. Still, more attention was paid to the patients’ eyes (54.3 ± 25.0 s vs. 49.8 ± 26.4, p = 0.001) and mouth (27.1 ± 13.9 s vs. 23.3 ± 14.2, p = 0.002) and less to their nose (24.6 ± 17.9 s vs. 31.3 ± 22.4, p < 0.001). Gaze analysis of bisected faces revealed an attentional bias towards the right visual field, particularly for healthy faces (64.21 ± 24.56 s vs. 45.97 ± 23.91 for the left visual field, p < 0.05), while more attention was still paid to the paralyzed side of patients (117.50 ± 29.40 s vs. 105.99 ± 24.68 for the non-paralyzed side, p < 0.01), and in particular to the mouth (31.54 ± 16.36 s vs. 24.48 ± 11.97, p < 0.01). Conclusions: The visual exploration process differed between healthy and paralyzed faces, as more attention was paid to the face’s mobile units and to the paralyzed side in patients. In the future, this protocol could be applied to various diseases and allow clinicians to improve their patients’ treatment and follow-up.