Artificial Intelligence analysis of over half a million European and Chinese women reveals striking differences in the facial skin ageing process.
Chinese
European
artificial intelligence
deep learning
skin ageing
Journal
Journal of the European Academy of Dermatology and Venereology : JEADV
ISSN: 1468-3083
Titre abrégé: J Eur Acad Dermatol Venereol
Pays: England
ID NLM: 9216037
Informations de publication
Date de publication:
Jul 2022
Jul 2022
Historique:
revised:
28
01
2022
received:
22
11
2021
accepted:
23
02
2022
pubmed:
14
3
2022
medline:
22
6
2022
entrez:
13
3
2022
Statut:
ppublish
Résumé
Artificial Intelligence (A.I) and deep learning-based algorithms are increasingly being used in dermatology following the emergence of powerful smartphones with high-resolution cameras. To use an A.I-based algorithm, validated by dermatologists, to compare the evolution of the skin ageing process among Chinese and European women. Selfie images were taken by 465 587 European and 79 016 Chinese women ranging from 18 to 85 and 18 to 69 years old, respectively, without facial skin diseases and who had access to a smartphone with a high-resolution camera (≥4 Megapixels). The selfies were analysed by facial skin diagnostic using a smartphone application to grade the severity of 9 facial signs (including wrinkles, sagging, vascular, pigmentation signs, pores). Wrinkles/texture, ptosis and sagging increased linearly with age in European women compared to lower scores and more gradual increase in the younger age-classes in Chinese women. In Chinese women, pigmentation signs increased regularly between 18 and 40 years, plateaued between 40 and 60 years, then increased in the over 60s compared to lower scores and a slower more regular increase with age in European women. Vascularization signs increased steadily with age in European women compared to no significant change in Chinese women. Marked differences were observed in the skin ageing process between European and Chinese populations, both in the prevalence of each facial ageing sign and their kinetics. Automatic grading performed on selfies and analysed by A.I is a fast and confidential method for quantifying signs of facial ageing and identifying the main issues for each population and age-class, which is of practical interest, as it will allow the development of tailored prevention and therapeutic measures.
Sections du résumé
BACKGROUND
BACKGROUND
Artificial Intelligence (A.I) and deep learning-based algorithms are increasingly being used in dermatology following the emergence of powerful smartphones with high-resolution cameras.
OBJECTIVES
OBJECTIVE
To use an A.I-based algorithm, validated by dermatologists, to compare the evolution of the skin ageing process among Chinese and European women.
METHODS
METHODS
Selfie images were taken by 465 587 European and 79 016 Chinese women ranging from 18 to 85 and 18 to 69 years old, respectively, without facial skin diseases and who had access to a smartphone with a high-resolution camera (≥4 Megapixels). The selfies were analysed by facial skin diagnostic using a smartphone application to grade the severity of 9 facial signs (including wrinkles, sagging, vascular, pigmentation signs, pores).
RESULTS
RESULTS
Wrinkles/texture, ptosis and sagging increased linearly with age in European women compared to lower scores and more gradual increase in the younger age-classes in Chinese women. In Chinese women, pigmentation signs increased regularly between 18 and 40 years, plateaued between 40 and 60 years, then increased in the over 60s compared to lower scores and a slower more regular increase with age in European women. Vascularization signs increased steadily with age in European women compared to no significant change in Chinese women.
CONCLUSIONS
CONCLUSIONS
Marked differences were observed in the skin ageing process between European and Chinese populations, both in the prevalence of each facial ageing sign and their kinetics. Automatic grading performed on selfies and analysed by A.I is a fast and confidential method for quantifying signs of facial ageing and identifying the main issues for each population and age-class, which is of practical interest, as it will allow the development of tailored prevention and therapeutic measures.
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
1136-1142Subventions
Organisme : L'Oréal
Commentaires et corrections
Type : CommentIn
Informations de copyright
© 2022 European Academy of Dermatology and Venereology.
Références
Schwalbe N, Wahl B. Artificial intelligence and the future of global health. Lancet 2020; 395: 1579-1586.
Esteva A, Kuprel B, Novoa RA et al. Dermatologist-level classification of skin cancer with deep neural networks. Nature 2017; 542: 115-118.
Tschandl P, Codella N, Akay BN et al. Comparison of the accuracy of human readers versus machine-learning algorithms for pigmented skin lesion classification: an open, web-based, international, diagnostic study. Lancet Oncol 2019; 20: 938-947.
Tschandl P, Rinner C, Apalla Z et al. Human-computer collaboration for skin cancer recognition. Nat Med 2020; 26: 1229-1234.
Du-Harpur X, Watt FM, Luscombe NM, Lynch MD. What is AI? Applications of artificial intelligence to dermatology. Br J Dermatol 2020; 183: 423-430.
Bobrov E, Georgievskaya A, Kiselev K et al. PhotoAgeClock: deep learning algorithms for development of non-invasive visual biomarkers of aging. Aging 2018; 10: 3249-3259.
Jiang R, Kezele I, Levinshtein A et al. A new procedure, free from human assessment that automatically grades some facial skin structural signs. Comparison with assessments by experts, using referential atlases of skin ageing. Int J Cosmet Sci 2019; 41: 67-78.
Zhang Y, Jiang R, Kezele I et al. A new procedure, free from human assessment, that automatically grades some facial skin signs in men from selfie pictures. Application to changes induced by a severe aerial chronic urban pollution. Int J Cosmet Sci 2020; 42: 185-197.
Flament F, Hofmann M, Roo E et al. An automatic procedure that grades some facial skin structural signs: agreements and validation with clinical assessments made by dermatologists. Int J Cosmet Sci 2019; 41: 472-478.
Flament F, Lee YW, Lee DH et al. The continuous development of a complete and objective automatic grading system of facial signs from selfie pictures: Asian validation study and application to women of three ethnic origins, differently aged. Skin Res Technol 2021; 27: 183-190.
Genomes Project C, Auton A, Brooks LD et al. A global reference for human genetic variation. Nature 2015; 526: 68-74.
Le Clerc S, Taing L, Ezzedine K et al. A genome-wide association study in Caucasian women points out a putative role of the STXBP5L gene in facial photoaging. J Invest Dermatol 2013; 133: 929-935.
Zhang M, Song F, Liang L et al. Genome-wide association studies identify several new loci associated with pigmentation traits and skin cancer risk in European Americans. Hum Mol Genet 2013; 22: 2948-2959.
Law MH, Medland SE, Zhu G et al. Genome-wide association shows that pigmentation genes play a role in skin aging. J Invest Dermatol 2017; 137: 1887-1894.
Endo C, Johnson TA, Morino R et al. Genome-wide association study in Japanese females identifies fifteen novel skin-related trait associations. Sci Rep 2018; 8: 8974.
Liu Y, Gao W, Koellmann C et al. Genome-wide scan identified genetic variants associated with skin aging in a Chinese female population. J Dermatol Sci 2019; 96: 42-49.
Flament F, Velleman D, Yamashita E et al. Japanese experiment of a complete and objective automatic grading system of facial signs from selfie pictures: Validation with dermatologists and characterization of changes due to age and sun exposures. Skin Res Technol 2021; 27: 544-553.
Flament F, Maudet A, Ye C et al. Comparing the self-perceived effects of a facial anti-aging product to those automatically detected from selfie images of Chinese women of different ages and cities. Skin Res Technol 2021; 27: 880-890.
Flament F, Zhang Y, Jiang R et al. Objective and automatic grading system of facial signs from selfie pictures of South African women: characterization of changes with age and sun-exposures. Skin Res Technol 2022; https://doi.org/10.1111/srt.13153.
Nouveau-Richard S, Yang Z, Mac-Mary S et al. Skin ageing: a comparison between Chinese and European populations. A pilot study. J Dermatol Sci 2005; 40: 187-193.
Vierkotter A, Huls A, Yamamoto A et al. Extrinsic skin ageing in German, Chinese and Japanese women manifests differently in all three groups depending on ethnic background, age and anatomical site. J Dermatol Sci 2016; 83: 219-225.
Bazin R, Doublet E. Skin Aging Atlas. Volume 1, Caucasian Type. Paris: Editions Med'Com; 2007.
Bazin R, Flament F. Skin Aging Atlas. Volume 2, Asian Type. Paris: Editions Med’Com; 2010.
Bazin R, Flament F, Giron F. Skin Aging Atlas. Volume 3, Afro-American Type. Paris: Editions Med’Com; 2012.
Bazin R, Flament F, Rubert V. Skin Aging Atlas. Volume 4, Indian Type. Paris: Editions Med’Com; 2015.
Flament F, Bazin R, Qiu H. Skin Aging Atlas. Volume 5, Photo-aging Face & Body. Paris: Editions Med’Com; 2017.
Flament F, Francois G, Qiu H et al. Facial skin pores: a multiethnic study. Clin Cosmet Invest Dermatol 2015; 8: 85-93.
Krutmann J, Bouloc A, Sore G, Bernard BA, Passeron T. The skin aging exposome. J Dermatol Sci 2017; 85: 152-161.
Passeron T, Krutmann J, Andersen ML, Katta R, Zouboulis CC. Clinical and biological impact of the exposome on the skin. J Eur Acad Dermatol Venereol 2020; 34(Suppl 4): 4-25.