Application of artificial intelligence technologies in dermatology
- Authors: Ruksha T.G.1, Lapkina E.Z.1
-
Affiliations:
- Professor V.F. Voino-Yasenetsky Krasnoyarsk State Medical University
- Issue: Vol 28, No 4 (2025)
- Pages: 429-436
- Section: DERMATOLOGY
- URL: https://bakhtiniada.ru/1560-9588/article/view/350471
- DOI: https://doi.org/10.17816/dv678577
- EDN: https://elibrary.ru/LKDQID
- ID: 350471
Cite item
Abstract
Dermatology represents a field of medicine with extensive potential for analyzing pathological changes directly in the lesion site, which is reflected in the widespread use of morphological studies for diagnosing skin diseases. With the rapid integration of artificial intelligence technologies into medicine, dermatology has once again become a promising area for the testing and implementation of neural network- and machine learning-based methods for practical medical applications.
This article provides a review of scientific publications reporting the use of artificial intelligence technologies in dermatology. For this purpose, 120 research studies published between 2020 and 2025 and indexed in the PubMed database were analyzed.
The analysis established that artificial intelligence technologies can be used for the differential diagnosis of malignant skin neoplasms. A large number of images is critical for developing artificial intelligence-based platforms for skin melanoma due to the high heterogeneity of both the clinical and morphological presentation of neoplasms. At the same time, in some cases, image augmentation processes may enhance the effectiveness of the developed methods. In addition to neoplasms, machine learning methods have been applied to develop differential diagnostic algorithms for chronic dermatologic conditions such as atopic dermatitis, psoriasis, alopecia areata, rosacea, and acne. Along with clinical applications, the use of artificial intelligence in dermatology education has also been reported.
At the same time, the use of artificial intelligence raises patients’ concerns regarding ethical issues as well as the accuracy of diagnostic and therapeutic strategies; therefore, patients currently view these technologies primarily as complementary to physicians' work.
Full Text
##article.viewOnOriginalSite##About the authors
Tatiana G. Ruksha
Professor V.F. Voino-Yasenetsky Krasnoyarsk State Medical University
Author for correspondence.
Email: tatyana_ruksha@mail.ru
ORCID iD: 0000-0001-8142-4283
SPIN-code: 5412-2148
MD, Dr. Sci. (Medicine), Professor
Russian Federation, 1 P. Zeleznyak st, Krasnoyarsk, 660022Ekaterina Z. Lapkina
Professor V.F. Voino-Yasenetsky Krasnoyarsk State Medical University
Email: e.z.lapkina@mail.ru
ORCID iD: 0000-0002-7226-9565
SPIN-code: 7656-8584
Cand. Sci. (Biology), Assistant Professor
Russian Federation, 1 P. Zeleznyak st, Krasnoyarsk, 660022References
- Stanton RB. Artificial intelligence. Nature. 1971;234:279–280. doi: 10.1038/234279b0
- Wang H, Fu T, Du Y, et al. Scientific discovery in the age of artificial intelligence. Nature. 2023;620(7972):47–60. doi: 10.1038/s41586-023-06221-2 EDN: DNMAKR
- Shanahan M, McDonell K, Reynolds L. Role play with large language models. Nature. 2023;623(7987):493–498. doi: 10.1038/s41586-023-06647-8 EDN: RGHFTH
- Feng J, Wang Q, Qiu H, Liu L. Retrieval in decoder benefits generative models for explainable complex question answering. Neural Netw. 2025;181:106833. doi: 10.1016/j.neunet.2024.106833
- Ananthaswamy А. How close is AI to human-level intelligence? Nature. 2024;636(8041):22–25. doi: 10.1038/d41586-024-03905-1 EDN: WEDYSK
- Zhang M, Yang Q, Lou J, et al. A new strategy to HER2-specific antibody discovery through artificial intelligence-powered phage display screening based on the Trastuzumab framework. Biochim Biophys Acta Mol Basis Dis. 2025;1871(5):167772. doi: 10.1016/j.bbadis.2025.167772
- King А. Four ways to power-up AI for drug discovery. Nature. 2025 Feb 27. doi: 10.1038/d41586-025-00602-5
- Nordmann TM, Anderton H, Hasegawa A, et al. Spatial proteomics identifies JAKi as treatment for a lethal skin disease. Nature. 2024;635(8040):1001–1009. doi: 10.1038/s41586-024-08061-0
- Modiri O, Ebriani J, Davis J. Can AI models assist patients in screening for non-melanoma skin cancer? Evaluating diagnostic accuracy of ChatGPT and Gemini using clinical images. Arch Dermatol Res. 2025;317(1):555. doi: 10.1007/s00403-025-04062-9
- Maher NG, Danaei Mehr H, Cong C, et al. Weakly supervised deep learning image analysis can differentiate melanoma from naevi on haematoxylin and eosin-stained histopathology slides. J Eur Acad Dermatol Venereol. 2024;38(12):2250–2258. doi: 10.1111/jdv.20307
- Mudhar HS, Milman T, Stevenson S, et al. PRAME expression by immunohistochemistry and reverse transcription quantitative PCR in conjunctival melanocytic lesions-a comprehensive clinicopathologic study of 202 cases and correlation of cytogenetics with PRAME expression in challenging conjunctival melanocytic lesions. Hum Pathol. 2023;134:1–18. doi: 10.1016/j.humpath.2023.02.002
- Cui Y, Li Y, Miedema JR, et al. Region of interest detection in melanocytic skin tumor whole slide images-nevus and melanoma. Cancers (Basel). 2024;16(15):2616. doi: 10.3390/cancers16152616
- Esimbekova AR, Palkina NV, Zinchenko IS, et al. Focal adhesion alterations in G0-positive melanoma cells. Cancer Med. 2023;12(6):7294–7308. doi: 10.1002/cam4.5510
- Komina AV, Palkina NV, Aksenenko MB, et al. Semaphorin-5A downregulation is associated with enhanced migration and invasion of BRAF-positive melanoma cells under vemurafenib treatment in melanomas with heterogeneous BRAF status. Melanoma Res. 2019;29(5):544–548. doi: 10.1097/CMR.0000000000000621
- Azimi A, Bi L, Bonfil A, et al. Integrated analysis of proteomic and dermoscopy imaging data improves non-invasive classification of benign nevi and melanoma. J Invest Dermatol. 2025;145(8):2108–2111.e5. doi: 10.1016/j.jid.2025.01.022
- Kuppanda PM, Janda M, Soyer HP, Caffery LJ. What are patients’ perceptions and attitudes regarding the use of artificial intelligence in skin cancer screening and diagnosis? Narrative review. J Invest Dermatol. 2025;145(8):1858–1865. doi: 10.1016/j.jid.2025.01.013
- Kimball AB, Jemec GB, Alavi A, et al. Secukinumab in moderate-to-severe hidradenitis suppurativa (SUNSHINE and SUNRISE): week 16 and week 52 results of two identical, multicentre, randomised, placebo-controlled, double-blind phase 3 trials. Lancet. 2023;401(10378):747–761. doi: 10.1016/S0140-6736(23)00022-3
- Demirel Öğüt N, Ayanoğlu MA, Koç Yıldırım S, et al. Are IL-17 inhibitors superior to IL-23 inhibitors in reducing systemic inflammation in moderate-to-severe plaque psoriasis? A retrospective cohort study. Arch Dermatol Res. 2025;317(1):232. doi: 10.1007/s00403-024-03768-6
- Zhang Y, Qian H, Kuang YH, et al. Evaluation of the inflammatory parameters as potential biomarkers of systemic inflammation extent and the disease severity in psoriasis patients. Arch Dermatol Res. 2024;316(6):229. doi: 10.1007/s00403-024-02972-8
- Hawro M, Sahin E, Steć M, et al. A comprehensive, tri-national, cross-sectional analysis of characteristics and impact of pruritus in psoriasis. J Eur Acad Dermatol Venereol. 2022;36(11):2064–2075. doi: 10.1111/jdv.18330
- Aggarwal SL. Data augmentation in dermatology image recognition using machine learning. Skin Res Technol. 2019;25(6):815–820. doi: 10.1111/srt.12726
- Greenfield DA, Feizpour A, Evans CL. Quantifying inflammatory response and drug-aided resolution in an atopic dermatitis model with deep learning. J Invest Dermatol. 2023;143(8):1430–1438. doi: 10.1016/j.jid.2023.01.026
- Eskandari A, Sharbatdar M. Efficient diagnosis of psoriasis and lichen planus cutaneous diseases using deep learning approach. Sci Rep. 2024;14(1):9715. doi: 10.1038/s41598-024-60526-4
- Achararit P, Manaspon C, Jongwannasiri C, et al. Artificial intelligence-based diagnosis of oral lichen planus using deep convolutional neural networks. Eur J Dent. 2023;17(4):1275–1282. doi: 10.1055/s-0042-1760300
- Kaya G, Tak AY. Evaluation of SALT score severity in correlation with trichoscopic findings in alopecia areata: a study of 303 patients. Arch Dermatol Res. 2025;317(1):523. doi: 10.1007/s00403-025-04026-z
- Bhardwaj V, Rodgers N, Harth O, Harth Y. Artificial intelligence-based personalization of treatment regimen for hair loss: a 6-month clinical trial. J Drugs Dermatol. 2025;24(3):233–238. doi: 10.36849/JDD.8611
- Cortez CD, Fakih A, Bruet M, et al. Impact of dermoscopy training associated with artificial intelligence on general practitioner residents. J Eur Acad Dermatol Venereol. 2024;38(12):2323–2325. doi: 10.1111/jdv.20328
- Khawaja Z, Adhoni MZ, Byrnes KG. Generative artificial intelligence powered chatbots in urology. Curr Opin Urol. 2025;35(3):243–249. doi: 10.1097/MOU.0000000000001280
- Ananthaswamy A. How close is AI to human-level intelligence? Nature. 2024;636(8041):22–25. doi: 10.1038/d41586-024-03905-1 EDN: WEDYSK
- Villalobos P, Ho A, Sevilla J, et al. Will we run out of data? Limits of LLM scaling based on human-generated data. arXiv. 2024. doi: 10.48550/arXiv.2211.04325
- Muñoz JM, Bernacer J, Noë A, Thompson E. Why AI will never be able to acquire human-level intelligence. Nature. 2025;637(8047):794. doi: 10.1038/d41586-025-00170-8
Supplementary files


