EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

DeepSmile: Anomaly Detection Software for Facial Movement Assessment

Eder A Rodríguez Martínez iD, Olga Polezhaeva, Félix Marcellin iD, Émilien Colin iD, Lisa Boyaval, François-Régis Sarhan iD, Stéphanie Dakpé

Diagnostics · 10.01.2023 · 13 (2) · 254

DOI: 10.3390/diagnostics13020254 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Diagnostics, online erschienen am 10.01.2023. Verfasst von Eder A Rodríguez Martínez und 6 weiteren Autor:innen. Beteiligte Einrichtung: UR 7516 Laboratory CHIMERE, University of Picardie Jules Verne, 80039 Amiens, France. Die Arbeit wurde bisher 13-mal zitiert (Crossref) und nennt 68 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: European Regional Development Fund, Fondation Gueules Cassees, Picardie Council.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

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.

Schlagwörter

Stichwörter der Autor:innen

anomaly detectiondeep learningfacial paralysislong-short term memory

Autor:innen und Institutionen

  • UR 7516 Laboratory CHIMERE, University of Picardie Jules Verne, 80039 Amiens, France.
  • Institut Faire Faces, 80000 Amiens, France.
  • Faculty of Odontology, University of Reims Champagne-Ardenne, 51097 Reims, France.
  • Maxillofacial Surgery, CHU Amiens-Picardie, 80000 Amiens, France.
  • Physiotherapy School, CHU Amiens-Picardie, 80000 Amiens, France.

ORCID-Profile: Eder A Rodríguez Martínez, Félix Marcellin, Émilien Colin, François-Régis Sarhan

Förderung

  • European Regional Development Fund
  • Fondation Gueules Cassees
  • Picardie Council
  • Agence Nationale de Recherche
  • the Picardie Council, the Fondation. des Gueules Cassées
  • FiGuRES EquipEx program

Zitieren

APA

Rodríguez Martínez, E. A., Polezhaeva, O., Marcellin, F., Colin, É., Boyaval, L., Sarhan, F. R., & Dakpé, S. (2023). DeepSmile: Anomaly Detection Software for Facial Movement Assessment. Diagnostics, 13(2), 254. https://doi.org/10.3390/diagnostics13020254

Vancouver

Rodríguez Martínez EA, Polezhaeva O, Marcellin F, Colin É, Boyaval L, Sarhan FR, et al. DeepSmile: Anomaly Detection Software for Facial Movement Assessment. Diagnostics. 2023;13(2):254. doi:10.3390/diagnostics13020254

BibTeX
@article{RodrguezMartnez2023,
  author = {Rodríguez Martínez, Eder A and Polezhaeva, Olga and Marcellin, Félix and Colin, Émilien and Boyaval, Lisa and Sarhan, François-Régis and Dakpé, Stéphanie},
  title = {DeepSmile: Anomaly Detection Software for Facial Movement Assessment},
  journal = {Diagnostics},
  year = {2023},
  volume = {13},
  number = {2},
  pages = {254},
  doi = {10.3390/diagnostics13020254}
}
Kostenlos starten →