Automated detection of smiles as discrete episodes.
orthodontics
smiling
validation studies
Journal
Journal of oral rehabilitation
ISSN: 1365-2842
Titre abrégé: J Oral Rehabil
Pays: England
ID NLM: 0433604
Informations de publication
Date de publication:
Dec 2022
Dec 2022
Historique:
revised:
25
07
2022
received:
27
02
2022
accepted:
22
08
2022
pubmed:
8
10
2022
medline:
15
11
2022
entrez:
7
10
2022
Statut:
ppublish
Résumé
Patients seeking restorative and orthodontic treatment expect an improvement in their smiles and oral health-related quality of life. Nonetheless, the qualitative and quantitative characteristics of dynamic smiles are yet to be understood. To develop, validate, and introduce open-access software for automated analysis of smiles in terms of their frequency, genuineness, duration, and intensity. A software script was developed using the Facial Action Coding System (FACS) and artificial intelligence to assess activations of (1) cheek raiser, a marker of smile genuineness; (2) lip corner puller, a marker of smile intensity; and (3) perioral lip muscles, a marker of lips apart. Thirty study participants were asked to view a series of amusing videos. A full-face video was recorded using a webcam. The onset and cessation of smile episodes were identified by two examiners trained with FACS coding. A Receiver Operating Characteristic (ROC) curve was then used to assess detection accuracy and optimise thresholding. The videos of participants were then analysed off-line to automatedly assess the features of smiles. The area under the ROC curve for smile detection was 0.94, with a sensitivity of 82.9% and a specificity of 89.7%. The software correctly identified 90.0% of smile episodes. While watching the amusing videos, study participants smiled 1.6 (±0.8) times per minute. Features of smiles such as frequency, duration, genuineness, and intensity can be automatedly assessed with an acceptable level of accuracy. The software can be used to investigate the impact of oral conditions and their rehabilitation on smiles.
Sections du résumé
BACKGROUND
BACKGROUND
Patients seeking restorative and orthodontic treatment expect an improvement in their smiles and oral health-related quality of life. Nonetheless, the qualitative and quantitative characteristics of dynamic smiles are yet to be understood.
OBJECTIVE
OBJECTIVE
To develop, validate, and introduce open-access software for automated analysis of smiles in terms of their frequency, genuineness, duration, and intensity.
MATERIALS AND METHODS
METHODS
A software script was developed using the Facial Action Coding System (FACS) and artificial intelligence to assess activations of (1) cheek raiser, a marker of smile genuineness; (2) lip corner puller, a marker of smile intensity; and (3) perioral lip muscles, a marker of lips apart. Thirty study participants were asked to view a series of amusing videos. A full-face video was recorded using a webcam. The onset and cessation of smile episodes were identified by two examiners trained with FACS coding. A Receiver Operating Characteristic (ROC) curve was then used to assess detection accuracy and optimise thresholding. The videos of participants were then analysed off-line to automatedly assess the features of smiles.
RESULTS
RESULTS
The area under the ROC curve for smile detection was 0.94, with a sensitivity of 82.9% and a specificity of 89.7%. The software correctly identified 90.0% of smile episodes. While watching the amusing videos, study participants smiled 1.6 (±0.8) times per minute.
CONCLUSIONS
CONCLUSIONS
Features of smiles such as frequency, duration, genuineness, and intensity can be automatedly assessed with an acceptable level of accuracy. The software can be used to investigate the impact of oral conditions and their rehabilitation on smiles.
Identifiants
pubmed: 36205621
doi: 10.1111/joor.13378
pmc: PMC9828522
doi:
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
1173-1180Subventions
Organisme : Colgate-Palmolive Company
Organisme : Sir John Walsh Research Institute
Informations de copyright
© 2022 The Authors. Journal of Oral Rehabilitation published by John Wiley & Sons Ltd.
Références
Ann N Y Acad Sci. 2003 Dec;1000:205-21
pubmed: 14766633
Infancy. 2009 May 1;14(3):285-305
pubmed: 19885384
Behav Res Methods. 2015 Dec;47(4):1136-1147
pubmed: 25488104
Stat Med. 2004 Aug 30;23(16):2537-50
pubmed: 15287083
Am J Orthod Dentofacial Orthop. 2003 Jul;124(1):4-12
pubmed: 12867893
J Nonverbal Behav. 2009 Mar 1;33(1):17-34
pubmed: 19554208
IEEE Trans Syst Man Cybern B Cybern. 2006 Feb;36(1):96-105
pubmed: 16468569
Front Psychol. 2018 Oct 26;9:2052
pubmed: 30416473
J Neural Eng. 2020 Apr 09;17(2):026025
pubmed: 32271717
J Pers Soc Psychol. 1990 Feb;58(2):342-53
pubmed: 2319446
PLoS One. 2017 Apr 19;12(4):e0173942
pubmed: 28422963
Int Conf Affect Comput Intell Interact Workshops. 2019 Sep;2019:594-599
pubmed: 32363090
Eur J Orthod. 2009 Oct;31(5):459-66
pubmed: 19541798
Am J Orthod Dentofacial Orthop. 2013 Jun;143(6):819-27
pubmed: 23726332
PLoS Med. 2007 Oct 16;4(10):e297
pubmed: 17941715
Emotion. 2009 Dec;9(6):807-20
pubmed: 20001124
J Pers Assess. 2019 Jan-Feb;101(1):4-15
pubmed: 29087223
J Esthet Restor Dent. 2018 Mar;30(2):160-167
pubmed: 29285853
Cortex. 2011 May;47(5):569-74
pubmed: 20537620
J Oral Rehabil. 2022 Dec;49(12):1173-1180
pubmed: 36205621
Eur J Orthod. 2008 Aug;30(4):366-73
pubmed: 18632836
Kidney Int. 2008 Jan;73(2):148-53
pubmed: 17978812
Psychol Bull. 2003 Mar;129(2):305-34
pubmed: 12696842
J Prosthet Dent. 2020 May;123(5):739-746
pubmed: 31383523
Emotion. 2008 Feb;8(1):1-12
pubmed: 18266511
Front Psychol. 2020 Jul 28;11:1126
pubmed: 32848960
Angle Orthod. 2004 Feb;74(1):43-50
pubmed: 15038490
BDJ Open. 2020 May 05;6:6
pubmed: 32411387
Radiology. 2018 Mar;286(3):800-809
pubmed: 29309734