Utilizing deep learning for dermal matrix quality assessment on in vivo line-field confocal optical coherence tomography images.
deep learning
dermal fibers
dermal matrix quality
in vivo
line-field confocal optical coherence tomography
Journal
Skin research and technology : official journal of International Society for Bioengineering and the Skin (ISBS) [and] International Society for Digital Imaging of Skin (ISDIS) [and] International Society for Skin Imaging (ISSI)
ISSN: 1600-0846
Titre abrégé: Skin Res Technol
Pays: England
ID NLM: 9504453
Informations de publication
Date de publication:
Jan 2023
Jan 2023
Historique:
received:
22
08
2022
accepted:
08
10
2022
pubmed:
12
11
2022
medline:
31
1
2023
entrez:
11
11
2022
Statut:
ppublish
Résumé
Line-field confocal optical coherence tomography (LC-OCT) is an imaging technique providing non-invasive "optical biopsies" with an isotropic spatial resolution of ∼1 μm and deep penetration until the dermis. Analysis of obtained images is classically performed by experts, thus requiring long and fastidious training and giving operator-dependent results. In this study, the objective was to develop a new automated method to score the quality of the dermal matrix precisely, quickly, and directly from in vivo LC-OCT images. Once validated, this new automated method was applied to assess photo-aging-related changes in the quality of the dermal matrix. LC-OCT measurements were conducted on the face of 57 healthy Caucasian volunteers. The quality of the dermal matrix was scored by experts trained to evaluate the fibers' state according to four grades. In parallel, these images were used to develop the deep learning model by adapting a MobileNetv3-Small architecture. Once validated, this model was applied to the study of dermal matrix changes on a panel of 36 healthy Caucasian females, divided into three groups according to their age and photo-exposition. The deep learning model was trained and tested on a set of 15 993 images. Calculated on the test data set, the accuracy score was 0.83. As expected, when applied to different volunteer groups, the model shows greater and deeper alteration of the dermal matrix for old and photoexposed subjects. In conclusion, we have developed a new method that automatically scores the quality of the dermal matrix on in vivo LC-OCT images. This accurate model could be used for further investigations, both in the dermatological and cosmetic fields.
Sections du résumé
BACKGROUND
BACKGROUND
Line-field confocal optical coherence tomography (LC-OCT) is an imaging technique providing non-invasive "optical biopsies" with an isotropic spatial resolution of ∼1 μm and deep penetration until the dermis. Analysis of obtained images is classically performed by experts, thus requiring long and fastidious training and giving operator-dependent results. In this study, the objective was to develop a new automated method to score the quality of the dermal matrix precisely, quickly, and directly from in vivo LC-OCT images. Once validated, this new automated method was applied to assess photo-aging-related changes in the quality of the dermal matrix.
MATERIALS AND METHODS
METHODS
LC-OCT measurements were conducted on the face of 57 healthy Caucasian volunteers. The quality of the dermal matrix was scored by experts trained to evaluate the fibers' state according to four grades. In parallel, these images were used to develop the deep learning model by adapting a MobileNetv3-Small architecture. Once validated, this model was applied to the study of dermal matrix changes on a panel of 36 healthy Caucasian females, divided into three groups according to their age and photo-exposition.
RESULTS
RESULTS
The deep learning model was trained and tested on a set of 15 993 images. Calculated on the test data set, the accuracy score was 0.83. As expected, when applied to different volunteer groups, the model shows greater and deeper alteration of the dermal matrix for old and photoexposed subjects.
CONCLUSIONS
CONCLUSIONS
In conclusion, we have developed a new method that automatically scores the quality of the dermal matrix on in vivo LC-OCT images. This accurate model could be used for further investigations, both in the dermatological and cosmetic fields.
Identifiants
pubmed: 36366860
doi: 10.1111/srt.13221
pmc: PMC9838780
doi:
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
e13221Informations de copyright
© 2022 SILAB. Skin Research and Technology published by John Wiley & Sons Ltd.
Références
Maturitas. 2011 Jul;69(3):249-56
pubmed: 21612880
Skin Res Technol. 2018 Nov;24(4):570-586
pubmed: 29575271
J Cell Commun Signal. 2018 Mar;12(1):35-43
pubmed: 29455303
Ann Transl Med. 2020 Jun;8(11):713
pubmed: 32617333
G Ital Dermatol Venereol. 2015 Dec;150(6):665-74
pubmed: 26349926
Sci Rep. 2022 Jan 10;12(1):481
pubmed: 35013485
Skin Res Technol. 2020 May;26(3):398-404
pubmed: 31799766
J Cosmet Dermatol. 2020 Jan;19(1):190-198
pubmed: 31131982
J Clin Med. 2022 Jan 14;11(2):
pubmed: 35054123
Skin Res Technol. 2013 Feb;19(1):e217-22
pubmed: 22724561
Skin Res Technol. 2023 Jan;29(1):e13221
pubmed: 36366860
Semin Plast Surg. 2021 Aug;35(3):145-152
pubmed: 34526861
Int J Mol Sci. 2022 May 30;23(11):
pubmed: 35682813
Int J Epidemiol. 2002 Apr;31(2):439-46
pubmed: 11980813
Biophys Rev. 2022 Apr 6;14(2):463-481
pubmed: 35528030
Int J Cosmet Sci. 2019 Feb;41(1):67-78
pubmed: 30664236
Am J Clin Dermatol. 2018 Apr;19(2):139-144
pubmed: 28891036
Front Pharmacol. 2019 Jul 09;10:759
pubmed: 31354480
J Photochem Photobiol B. 2006 Dec 1;85(3):198-204
pubmed: 16963272
JID Innov. 2021 Jun 25;1(3):100039
pubmed: 34909735
Biomed Opt Express. 2019 Jan 22;10(2):694-706
pubmed: 30800509
Med Image Anal. 2021 Jan;67:101841
pubmed: 33142135
Prim Care. 2022 Mar;49(1):99-118
pubmed: 35125161
Arch Dermatol Res. 2014 Jan;306(1):1-9
pubmed: 24113905
Adv Wound Care (New Rochelle). 2013 Feb;2(1):5-10
pubmed: 24527317
J Am Acad Dermatol. 2019 Apr;80(4):1114-1120
pubmed: 30528311
Skin Res Technol. 2021 May;27(3):340-352
pubmed: 33085784
J Med Imaging (Bellingham). 2019 Apr;6(2):024003
pubmed: 31065567
J Biophotonics. 2022 Feb;15(2):e202100236
pubmed: 34608756
Cutis. 2017 Sep;100(3):163-166
pubmed: 29121130
Medicina (Kaunas). 2022 Mar 31;58(4):
pubmed: 35454342
J Biomed Opt. 2018 Oct;23(10):1-9
pubmed: 30353716
Mech Ageing Dev. 2019 Jan;177:150-156
pubmed: 29548941
J Am Acad Dermatol. 2019 Apr;80(4):1121-1131
pubmed: 30528310
Biomed Opt Express. 2013 Sep 16;4(10):2179-86
pubmed: 24156073
Entropy (Basel). 2021 Oct 22;23(11):
pubmed: 34828081
Gerontology. 2015;61(5):427-34
pubmed: 25660807
Opt Express. 2018 Dec 24;26(26):33534-33542
pubmed: 30650800
J Invest Dermatol. 2020 Jun;140(6):1214-1222
pubmed: 31838127
Arch Dermatol. 2008 Feb;144(2):217-22
pubmed: 18283179