CoChat
Sign Up
Cited by 13Skin Protection and AgingOptical Coherence Tomography ApplicationsFace recognition and analysis

Evaluating facial dermis aging in healthy Caucasian females with LC-OCT and deep learning

Open access
Assi, Ali, Fischman, Sébastien, Lopez, Colombe, Pedrazzani, Mélanie, Grignon, Guénolé, Missodey, Raoul, Korichi, Rodolphe, Cauchard, Jean-Hubert +2 more·2024·Scientific Reports
DOI 10.1038/s41598-024-74370-zPMC PMC11480100
Open this paper in CoChat — free accountOpen PDF

Abstract

Recent advancements in high-resolution imaging have significantly improved our understanding of microstructural changes in the skin and their relationship to the aging process. Line Field Confocal Optical Coherence Tomography (LC-OCT) provides detailed 3D insights into various skin layers, including the papillary dermis and its fibrous network. In this study, a deep learning model utilizing a 3D ResNet-18 network was trained to predict chronological age from LC-OCT images of 100 healthy Caucasian female volunteers, aged 20 to 70 years. The AI-based protocol focused on regions of interest delineated between the segmented dermal-epidermal junction and the superficial dermis, exploiting complex patterns within the collagen network for age prediction. The model achieved a mean absolute error of 4.2 years and exhibited a Pearson correlation coefficient of 0.937 with actual ages. Furthermore, there was a notable correlation (r = 0.87) between quantified clinical scoring, encompassing parameters such as firmness, elasticity, density, and wrinkle appearance, and the ages predicted by deep learning model. This strong correlation underscores how integrating emerging imaging technologies with deep learning can accelerate aging research and deepen our understanding of how alterations in skin microstructure are related to visible signs of aging.

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1038/s41598-024-74370-z

Cites

7 of 7 references verified0 citation errors · 0 not checkable

Statistics

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

  • Applying tomography and AI to reconstruct 3D epidermal cross-sections to indicate a lesion or an anomalous vascularization is possible.

    “the possibility of applying tomography and AI to reconstruct 3D epidermal cross-sections to indicate a lesion [54,55,56] or an anomalous vascularization [57,58].”

    From Artificial Intelligence in the Histopathological Assessment of Non-Neoplastic Skin Disorders: A Narrative Review with Future Perspectives (2025) · cites this paper as [55]

    The Introduction describes LC-OCT as a 3D skin-imaging tool that supports diagnosis of skin disorders, and Methods (Dermis-epidermis junction detection) describes AI-based segmentation of 3D image stacks. The paper studies healthy skin aging, however, and does not show that its AI reconstruction identifies lesions or anomalous vascularization. (LLM, conf=0.84)

    Experimental — accuracy not yet measured

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Cites

Flagged first, then by citations

Research works printed but not linked: 52

  1. [1]Bielfeldt, S., Springmann, G., Seise, M., Wilhelm, K. P. & Callaghan, T. An updated review of clinical methods in the assessment of ageing skin – new perspectives and evaluation for claims support. Int. J. Cosmet. Sci. 40, 348–355 (2018). 30047989 · DOI
  2. [2]Dobos, G., Lichterfeld, A., Blume-Peytavi, U. & Kottner, J. Evaluation of skin ageing: A systematic review of clinical scales. Br. J. Dermatol.Bold">172, 1249–1261 (2015). 25363020 · DOI
  3. [4]Vierkötter, A. et al. The SCINEXA: Anovel, validated score to simultaneously assess and differentiate between intrinsic and extrinsic skin ageing. J. Dermatol. Sci. 53, 207–211 (2009). 19059763 · DOI
  4. [5]Costello, L. et al. Quantitative morphometric analysis of intrinsic and extrinsic skin ageing in individuals with Fitzpatrick skin types II–III. Exp. Dermatol. 32, 620–631 (2023). 36695185 PMC10947487 · DOI
  5. [6]Guida, S., Pellacani, G., Ciardo, S. & Longo, C. Reflectance confocal microscopy of aging skin and skin cancer. Dermatol. Pract. Concept. 11, e2021068 (2021). 34123564 PMC8172052 · DOI
  6. [7]Chen, K., Wang, Z., Han, Y. & Cui, Y. In vivo detection of healthy skin: Comparison of multiphoton microscopy and reflectance confocal microscopy. Ski Res. Technol. 29, e13340 (2023). PMC10156995 37231920 · DOI
  7. [8]Pezzini, C. et al. Skin ageing: Clinical aspects and in vivo microscopic patterns observed with reflectance confocal microscopy and optical coherence tomography. Exp. Dermatol. 32, 348–358 (2023). 36394180 · DOI
  8. [9]Pena, A. M. et al. In vivo multiphoton multiparametric 3D quantification of human skin aging on forearm and face. Sci. Rep. 12, 14863 (2022). 36050338 PMC9437074 · DOI
  9. [10]Koehler, M. J. et al. Morphological skin ageing criteria by multiphoton laser scanning tomography: Non-invasive in vivo scoring of the dermal fibre network. Exp. Dermatol. 17, 519–523 (2008). 18201192 · DOI
  10. [11]Raphael, A. P. et al. Computational characterization of reflectance confocal microscopy features reveals potential for automated photoageing assessment. Exp. Dermatol. 22, 458–463 (2013). 23800056 · DOI
  11. [12]Hames, S. C., Bradley, A. P., Ardigo, M., Soyer, H. P. & Prow, T. W. Towards data-driven quantification of skin ageing using reflectance confocal microscopy. Int. J. Cosmet. Sci. 43, 466–473 (2021). 34133771 · DOI
  12. [13]Donelli, C. et al. Line-field Confocal Optical Coherence Tomography for the diagnosis of skin carcinomas: Real-Life Data over three years. Curr. Oncol. 30, 8853–8864 (2023). 37887539 PMC10604937 · DOI
  13. [14]Perez-Anker, J. et al. Criteria for melanocytic lesions in LC‐OCT. J. Eur. Acad. Dermatol. Venereol. 10.1111/jdv.20079 (2024). 38727525 · DOI
  14. [15]Orsini, C. et al. Line-field confocal optical coherence tomography: New insights for psoriasis treatment monitoring. J. Eur. Acad. Dermatol. Venereol. 38, 325–331 (2024). 37823360 · DOI
  15. [16]Ruini, C. et al. In-Vivo LC-OCT evaluation of the Downward Proliferation Pattern of keratinocytes in Actinic Keratosis in comparison with histology: First impressions from a pilot study. Cancers 13, 2856 (2021). 34201052 PMC8228287 · DOI
  16. [17]Dubois, A. et al. Line-field confocal time-domain optical coherence tomography with dynamic focusing. Opt. Express 26, 33534–33542 (2018). 30650800 · DOI
  17. [18]Ogien, J., Levecq, O., Azimani, H. & Dubois, A. Dual-mode line-field confocal optical coherence tomography for ultrahigh-resolution vertical and horizontal section imaging of human skin in vivo. Biomed. Opt. Express 11, 1327 (2020). 32206413 PMC7075601 · DOI
  18. [19]Río-Sancho, S., del, Gallay, C., Ventéjou, S. & Christen‐Zaech, S. In vivo evaluation of skin of children with LC‐OCT: An objective assessment. J. Eur. Acad. Dermatol. Venereol. 37, 1897–1905 (2023). 37147895 · DOI
  19. [20]Chauvel-Picard, J. et al. Line‐field confocal optical coherence tomography as a tool for three‐dimensional in vivo quantification of healthy epidermis: A pilot study. J. Biophoton. 15, e202100236 (2022). 34608756 · DOI
  20. [21]Pedrazzani, M. et al. Comparison of line-field confocal optical coherence tomography images with histological sections: Validation of a new method for in vivo and non‐invasive quantification of superficial dermis thickness. Ski Res. Technol. 26, 398–404 (2020). 31799766 · DOI
  21. [22]Breugnot, J. et al. Utilizing deep learning for dermal matrix quality assessment on in vivo line-field confocal optical coherence tomography images. Ski Res. Technol. 29, e13221 (2023). PMC9838780 36366860 · DOI
  22. [23]Ayadh, M. et al. Investigation of the link between the human skin relief and the dermal fibers network by coupling topographic analysis and LC-OCT imaging before and during folding tests. 4open 6, 6 (2023). · DOI
  23. [24]Bonnier, F. et al. Line-field confocal optical coherence tomography coupled with artificial intelligence algorithms to identify quantitative biomarkers of facial skin ageing. Sci. Rep. 13, 13881 (2023). 37620374 PMC10449778 · DOI
  24. [25]Haydont, V., Bernard, B. A. & Fortunel, N. O. Age-related evolutions of the dermis: Clinical signs, fibroblast and extracellular matrix dynamics. Mech. Ageing Dev. 177, 150–156 (2019). 29548941 · DOI
  25. [27]He, T., Fisher, G. J., Kim, A. J. & Quan, T. Age-related changes in dermal collagen physical properties in human skin. PLoS ONE 18, e0292791 (2023). 38064445 PMC10707495 · DOI
  26. [28]Kadoya, K. et al. Fibulin-5 deposition in human skin: Decrease with ageing and ultraviolet B exposure and increase in solar elastosis. Br. J. Dermatol. 153, 607–612 (2005). 16120151 · DOI
  27. [30]Cinotti, E. et al. Comparison of reflectance confocal microscopy and line-field optical coherence tomography for the identification of keratinocyte skin tumours. Ski Res. Technol. 29, e13215 (2023). PMC9838760 36424847 · DOI
  28. [31]Neerken et al. Comparison of confocal laser scanning microscopy and optical coherence tomography. 949–971 (2004). 10.1007/0-387-29989-0_22 · DOI
  29. [32]de Rigal, J. et al. Assessment of Aging of the human skin by in vivo Ultrasonic Imaging. J. Investig Dermatol. 93, 621–625 (1989). 2677155 · DOI
  30. [33]Nicolescu, A. C. et al. Subepidermal low-echogenic band—its utility in clinical practice: A systematic review. Diagnostics 13, 970 (2023). 36900113 PMC10000591 · DOI
  31. [34]Czajkowska, J. et al. High-frequency ultrasound in anti-aging skin therapy monitoring. Sci. Rep.Bold">13, 17799 (2023). 37853086 PMC10584894 · DOI
  32. [35]Cinotti, E. et al. Structural skin changes in elderly people investigated by reflectance confocal microscopy. J. Eur. Acad. Dermatol. Venereol. 34, 2652–2658 (2020). 32294278 · DOI
  33. [36]Wurm, E. M. T. et al. In vivo assessment of chronological ageing and photoageing in forearm skin using reflectance confocal microscopy. Br. J. Dermatol. 167, 270–279 (2012). 22428802 · DOI
  34. [37]Koehler, M. J., König, K., Elsner, P., Bückle, R. & Kaatz, M. In vivo assessment of human skin aging by multiphoton laser scanning tomography. Opt. Lett. 31, 2879–2881 (2006). 16969409 · DOI
  35. [38]Kröger, M. et al. In vivo non-invasive staining-free visualization of dermal mast cells in healthy, allergy and mastocytosis humans using two-photon fluorescence lifetime imaging. Sci. Rep. 10, 14930 (2020). 32913196 PMC7484787 · DOI
  36. [40]Hames, S. C., Ardigò, M., Soyer, H. P., Bradley, A. P. & Prow, T. W. Automated segmentation of skin strata in Reflectance Confocal Microscopy depth stacks. PLoS ONE 11, e0153208 (2016). 27088865 PMC4835045 · DOI
  37. [41]Fischman, S. et al. Non-invasive scoring of cellular atypia in keratinocyte cancers in 3D LC-OCT images using deep learning. Sci. Rep. 12, 481 (2022). 35013485 PMC8748986 · DOI
  38. [42]Kaur, P., Dana, K. J., Cula, G. O. & Mack, M. C. Hybrid deep learning for reflectance confocal microscopy skin images. In 23rd International Conference on Pattern Recognition (ICPR) 1466–1471 (2016). 10.1109/icpr.2016.7899844 · DOI
  39. [43]Robic, J. et al. Clinical validation of a computer-based approach for the quantification of the skin ageing process of women using in vivo confocal microscopy. J. Eur. Acad. Dermatol. Venereol. 35, e68–e70 (2021). 32645231 · DOI
  40. [45]Lin, C. H. et al. Rapid measurement of epidermal thickness in OCT images of skin. Sci. Rep. 14, 2230 (2024). 38278852 PMC10817904 · DOI
  41. [46]Pinto-Coelho, L. How Artificial Intelligence is shaping medical imaging technology: A survey of innovations and applications. Bioengineering 10, 1435 (2023). 38136026 PMC10740686 · DOI
  42. [48]Meng, D., Zhang, S., Huang, Y., Mao, K. & Han, J. D. J. Application of AI in biological age prediction. Curr. Opin. Struct. Biol. 85, 102777 (2024). 38310737 · DOI
  43. [49]Bortz, J. et al. Biological age estimation using circulating blood biomarkers. Commun. Biol. 6, 1089 (2023). 37884697 PMC10603148 · DOI
  44. [51]Bobrov, E. et al. PhotoAgeClock: Deep learning algorithms for development of non-invasive visual biomarkers of aging. Aging (Albany NY) 10, 3249–3259 (2018). 30414596 PMC6286834 · DOI
  45. [52]Park, S. et al. Facial age evaluated by artificial intelligence system, Dr.AMORE ®: An objective, intuitive, and reliable new skin diagnosis technology. J. Cosmet. Dermatol. 23, 1510–1512 (2024). 38149689 · DOI
  46. [53]ELKarazle, K., Raman, V. & Then, P. Facial age estimation using machine learning techniques: An overview. Big Data Cogn. Comput. 6, 128 (2022). · DOI
  47. [54]Cho, C. et al. Evaluation of facial skin age based on biophysical properties in vivo. J. Cosmet. Dermatol. 21, 3546–3554 (2022). 34859944 · DOI
  48. [55]Dias, H. C., Manco, L., Real, F. C. & Cunha, E. A blood–bone–tooth model for Age Prediction in forensic contexts. Biology 10, 1312 (2021). 34943227 PMC8698317 · DOI
  49. [56]Dubois, A. et al. Line-field confocal optical coherence tomography for high-resolution noninvasive imaging of skin tumors. J. Biomed. Opt. 23, 106007–106007 (2018). 30353716 · DOI
  50. [57]Ogien, J., Tavernier, C., Fischman, S. & Dubois, A. Line-field confocal optical coherence tomography (LC-OCT): Principles and practical use. Ital. J. Dermatol. Venereol. 158, 171–179 (2023). 37278495 · DOI
  51. [58]Ogien, J., Daures, A., Cazalas, M., Perrot, J. L. & Dubois, A. Line-field confocal optical coherence tomography for three-dimensional skin imaging. Front. Optoelectron. 13, 381–392 (2020). 36641566 PMC9743950 · DOI
  52. [59]Daxenberger, F. et al. Innovation in actinic keratosis assessment: Artificial Intelligence-based approach to LC-OCT PRO score evaluation. Cancers 15, 4457 (2023). 37760425 PMC10527366 · DOI

Cited by

Sorted by citations

Authors
Assi, A., Fischman, S., Lopez, C., Pedrazzani, M., Grignon, G., Missodey, R., Korichi, R., Cauchard, J.-H., Ralambondrainy, S., & Bonnier, F.
Affiliations
LVMH (France) (FR)
Corresponding author
Bonnier, Franck
ORCID
Venue
Scientific Reports
Publisher
Springer Science and Business Media LLC
Published
2024-10-15
Volume
14
Issue
1
Pages
24113-24113
ISSN
2045-2322 (ISSN-L)
DOI
10.1038/s41598-024-74370-z
PMC
PMC11480100
OpenAlex
W4403436250
Cited by
13
References
7
Citations by year
2026: 7 · 2025: 5 · 2024: 1
FWCI
5.31
Type
journal article
Language
en
Open access
Licence
Locations
  • Scientific Reports (publishedVersion, cc-by-nc-nd)
  • PubMed Central (publishedVersion, cc-by-nc-nd)
  • PubMed (publishedVersion)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
Topics
  • Health Sciences › Medicine › Dermatology › Skin Protection and Aging
  • Physical Sciences › Engineering › Biomedical Engineering › Optical Coherence Tomography Applications
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Face recognition and analysis
Keywords
facial skin aging, dermis, line-field confocal optical coherence tomography, chronological age estimation, collagen network, basement membrane zone, skin microstructure
MeSH terms
Deep Learning, Adult, Aged, Aging, Face, Female, Humans, Middle Aged, Skin Aging, Dermis, Tomography, Optical Coherence, White People, Young Adult, Healthy Volunteers

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review