UV Irradiation of Nevi: Impact on Performance of Electrical Impedance Spectroscopy and a Convolution Neural Network

Julia K. Winkler; Holger A. Haenssle; Lorenz Uhlmann; Anissa Schweizer-Rick; Christine Fink

doi:10.5826/dpc.1204a164

UV Irradiation of Nevi: Impact on Performance of Electrical Impedance Spectroscopy and a Convolution Neural Network

Authors

Julia K. Winkler Department of Dermatology, University of Heidelberg, Heidelberg, Germany
Holger A. Haenssle Department of Dermatology, University of Heidelberg, Heidelberg, Germany
Lorenz Uhlmann Novartis Pharma GmbH, Basel, Switzerland
Anissa Schweizer-Rick Department of Dermatology, University of Heidelberg, Heidelberg, Germany
Christine Fink Department of Dermatology, University of Heidelberg, Heidelberg, Germany

Keywords:

electrical impedance spectroscopy, dermoscopy, convolution neural network, UV irradiation

Abstract

Introduction: UV irradiation of nevi induces transient melanocytic activation with dermoscopic and histological changes.

Objectives:We investigated whether UV irradiation of nevi may influence electrical impedance spectroscopy (EIS) or convolution neural networks (CNN).

Methods: Prospective, controlled trial in 50 patients undergoing phototherapy (selective UV phototherapy (SUP), UVA1, SUP/UVA1, or PUVA). EIS (Nevisense, SciBase AB, Sweden) and CNN scores (Moleanalyzer-Pro, FotoFinder Systems, Germany) of nevi were assessed before (V1) and after UV irradiation (V2). One nevus (nevus_irr) was exposed to UV light, another UV-shielded (nevus_non-_irr).

Results: There were no significant differences in EIS scores of nevus_irr before (2.99 [2.51-3.47]) and after irradiation (3.32 [2.86-3.78]; p=0.163), which was on average 13.28 (range 4-47) days later. Similarly, UV-shielded nevus_non-_irr did not show significant changes of EIS scores (V1: 2.65 [2.19-3.11]), V2: 2.92 [2.50-3.34]; p=0.094). Subgroup analysis by irradiation revealed a significant increase of EIS scores of nevus_irr (V1: 2.69 [2.21-3.16], V2: 3.23 [2.72-3.73]; p=0.044) and nevus_non-_irr (V1: 2.57 [2.07-3.07], V2: 3.03 [2.48-3.57]; p=0.033) for patients receiving SUP. In contrast, CNN scores of nevus_irr (p=0.995) and nevus_non-_irr (p=0.352) showed no significant differences before and after phototherapy.

Conclusions: For the tested EIS system increased EIS scores were found in nevi exposed to SUP. In contrast, CNN results were more robust against UV exposure.

References

Arnold, M., et al., Trends in incidence and predictions of cutaneous melanoma across Europe up to 2015. Journal of the European Academy of Dermatology and Venereology, 2014. 28(9): p. 1170-1178.

Fink, C. and H. Haenssle, Non‐invasive tools for the diagnosis of cutaneous melanoma. Skin Research and Technology, 2017. 23(3): p. 261-271.

Mohr, P., et al., Electrical impedance spectroscopy as a potential adjunct diagnostic tool for cutaneous melanoma. Skin Research and Technology, 2013. 19(2): p. 75-83.

Ceder, H., et al., Evaluation of electrical impedance spectroscopy as an adjunct to dermoscopy in short-term monitoring of atypical melanocytic lesions. Dermatology practical & conceptual, 2016. 6(4): p. 1.

Rocha, L., et al., Analysis of an electrical impedance spectroscopy system in short‐term digital dermoscopy imaging of melanocytic lesions. British Journal of Dermatology, 2017. 177(5): p. 1432-1438.

Malvehy, J., et al., Clinical performance of the Nevisense system in cutaneous melanoma detection: an international, multicentre, prospective and blinded clinical trial on efficacy and safety. Br J Dermatol, 2014. 171(5): p. 1099-107.

Esteva, A., et al., Dermatologist-level classification of skin cancer with deep neural networks. Nature, 2017. 542(7639): p. 115-118.

Haenssle, H.A., et al., Man against machine: diagnostic performance of a deep learning convolutional neural network for dermoscopic melanoma recognition in comparison to 58 dermatologists. Ann Oncol, 2018. 29(8): p. 1836-1842.

Haenssle, H.A., et al., Man against machine reloaded: performance of a market-approved convolutional neural network in classifying a broad spectrum of skin lesions in comparison with 96 dermatologists working under less artificial conditions. Annals of Oncology, 2020. 31(1): p. 137-143.

De Gruijl, F.J.E.J.o.C., Skin cancer and solar UV radiation. 1999. 35(14): p. 2003-2009.

Tronnier, M., J. Smolle, and H.H. Wolff, Ultraviolet irradiation induces acute changes in melanocytic nevi. Journal of investigative dermatology, 1995. 104(4): p. 475-478.

Hofmann-Wellenhof, R., et al., Ultraviolet radiation of melanocytic nevi: a dermoscopic study. 1998. 134(7): p. 845-850.

Hofmann-Wellenhof, R., et al., Influence of UVB therapy on dermoscopic features of acquired melanocytic nevi. J Am Acad Dermatol, 1997. 37(4): p. 559-63.

Tronnier, M., J. Smolle, and H.H.J.J.o.i.d. Wolff, Ultraviolet irradiation induces acute changes in melanocytic nevi. 1995. 104(4): p. 475-478.

Tronnier, M. and H.H. Wolff, UV-irradiated melanocytic nevi simulating melanoma in situ. The American journal of dermatopathology, 1995. 17(1): p. 1-6.

R Core Team (2021). R: A language and environment for statistical computing. . R Foundation for Statistical Computing, Vienna, Austria.; Available from: https://www.R-project.org.

Pinheiro J, B.D., DebRoy S, Sarkar D. R Core Team (2021). _nlme: Linear and Nonlinear Mixed Effects Models_.R package version 3.1-152.; Available from: https://CRAN.R-project.org/package=nlme.

Welti, M., et al., Evaluation of the minimal erythema dose for UVB and UVA in context of skin phototype and nature of photodermatosis. Photodermatol Photoimmunol Photomed, 2020. 36(3): p. 200-207.

Cicchetti, D.V.J.P.a., Guidelines, criteria, and rules of thumb for evaluating normed and standardized assessment instruments in psychology. 1994. 6(4): p. 284.

Koo, T.K. and M.Y.J.J.o.c.m. Li, A guideline of selecting and reporting intraclass correlation coefficients for reliability research. 2016. 15(2): p. 155-163.

Hofmann-Wellenhof, R., et al., Ultraviolet radiation of melanocytic nevi: a dermoscopic study. Archives of dermatology, 1998. 134(7): p. 845-850.

Ceder, H., et al., Evaluation of electrical impedance spectroscopy as an adjunct to dermoscopy in short-term monitoring of atypical melanocytic lesions. 2016. 6(4): p. 1.

Carrera, C., et al., Development of a human in vivo method to study the effect of ultraviolet radiation and sunscreens in melanocytic nevi. Dermatology, 2008. 217(2): p. 124-36.

Carrera, C., et al., Impact of sunscreens on preventing UVR-induced effects in nevi: in vivo study comparing protection using a physical barrier vs sunscreen. 2013. 149(7): p. 803-813.

Zaher, H., et al., Dermoscopic and immunohistochemical changes in acquired melanocytic nevi following narrow-band ultraviolet B therapy. Dermatology, 2016. 232(3): p. 273-278.

Ghani-Nejad, H., et al., Dermoscopic Changes of Melanocytic Nevi after Psoralen-Ultraviolet A and Narrow-Band Ultraviolet B Phototherapy. Indian J Dermatol, 2016. 61(1): p. 118.

Kilinc Karaarslan, I., et al., Changes in the dermoscopic appearance of melanocytic naevi after photochemotherapy or narrow-band ultraviolet B phototherapy. J Eur Acad Dermatol Venereol, 2007. 21(4): p. 526-31.

Stierner, U., et al., UVB irradiation induces melanocyte increase in both exposed and shielded human skin. J Invest Dermatol, 1989. 92(4): p. 561-4.

Krutmann, Combined, Simultaneous Exposure to Radiation Within and Beyond the UV Spectrum: A Novel Approach to Better Understand Skin Damage by Natural Sunlight. .

Slominski, A.T., et al., How ultraviolet light touches the brain and endocrine system through skin, and why.

Nachbar, F., et al., The ABCD rule of dermatoscopy. High prospective value in the diagnosis of doubtful melanocytic skin lesions. J Am Acad Dermatol, 1994. 30(4): p. 551-9.

Oikarinen, A., et al., Connective tissue alterations in skin exposed to natural and therapeutic UV-radiation. Photo-dermatology, 1985. 2(1): p. 15-26.