The site of the Media Sphera Publishers contains materials intended solely for healthcare professionals.
By closing this message, you confirm that you are a certified medical professional or a student of a medical educational institution.

Login
EN
+7 (495) 482-4118
+7 (495) 482-0604
+8 800 101-59-87
  • (toll-free number for subscriptions)
    Mon-Fri from 10 a.m. to 6 p.m.

  • © 1998-2025
+7 (495) 482-43-29
EN
All journals
Journal
Year
Year
Search result: 0

Khryanin A.A.

Novosibirsk State Medical University;
Association of obstetrician-gynecologists and dermatologists

Bocharova V.K.

Pavlov First Saint Petersburg State Medical University

Artificial intelligence in dermatology: opportunities and prospects

Authors:

Khryanin A.A., Bocharova V.K.

More about the authors

Journal: Russian Journal of Clinical Dermatology and Venereology. 2024;23(3): 246‑252

DOI: 10.17116/klinderma202423031246

Views: 744

Downloaded: 11

Buy for 200₽
Contact the author
Table of contents

To cite this article:

Khryanin AA, Bocharova VK. Artificial intelligence in dermatology: opportunities and prospects. Russian Journal of Clinical Dermatology and Venereology. 2024;23(3):246‑252. (In Russ.)
https://doi.org/10.17116/klinderma202423031246

Подписка 2025 (Russian Journal of Clinical Dermatology and Venereology)
 
МСФ на ЯМ
Close metadata
Recommended articles:
Labo­ratory diagnosis of «key» sexually transmitted infe­ctions. Part II. Russian Journal of Clinical Dermatology and Vene­reology. 2024;(1):6-11
Labo­ratory diagnosis of neurosyphilis: opti­mization ways. Part II. Current approaches and biomarkers. Russian Journal of Clinical Dermatology and Vene­reology. 2024;(1):28-36
Ptychotropic poro­keratosis (porokeratosis ptychotropica): features of clinical and histological mani­festations. Russian Journal of Clinical Dermatology and Vene­reology. 2024;(1):56-62
Diagnostics of HIV-infection in the Chechen Repu­blic: current state and prospects. Russian Journal of Preventive Medi­cine. 2024;(1):17-24
Digi­tal healthcare of the Russian Fede­ration: basic concepts for practitioners. Russian Journal of Preventive Medi­cine. 2024;(1):97-105
Prevention of type 1 diabetes mellitus in children and adolescents. Russian Journal of Preventive Medi­cine. 2024;(1):115-120
Endo­bronchial hama­rtoma. P.A. Herzen Journal of Onco­logy. 2024;(1):59-62
Surgery for mediastinal tera­toma containing pancreatic tissue. Piro­gov Russian Journal of Surgery. 2024;(2):75-83
Arti­ficial neural network in intravascular imaging. Russian Journal of Cardiology and Cardiovascular Surgery. 2024;(1):77-81
Algo­rithm of the symptom-based headache diagnostic. Russian Journal of Preventive Medi­cine. 2024;(2):77-85

Artificial intelligence (AI) is becoming the most discussed technology in the world in recent years. AI based on neural network models makes significant progress in teledermatology. The problem is of critical importance and relevance, because telemedicine and AI, which are used in dermatology, make it possible to improve both the quality of health care for the population and the working process of medical professionals. The authors present a modern review of opportunities, prospects and problems related to the AI integration into the dermatologist’s clinical practice. For example, non-melanoma skin cancers (NMSCs) are known to be the most common cancers in the world, and melanoma is the most malignant form of skin cancer. Dermoscopy has increased the accuracy of NMSCs diagnosis by doctors, but, unfortunately, it remains relatively low. AI could provide invaluable help in early assessment and diagnosis of NMSCs. Studies have found that convolution neural network algorithms can classify skin lesions by dermoscopic images with very high or at least equivalent performance compared to clinicians. In this case, qualitative data and specialist’s feedback lead to a significant quality leap in the AI model. Nevertheless, despite the advantages and development speed of AI-based technologies, there are problems related to: a) the need to improve cybersecurity; b) the need to pay more attention to medico-legal and ethical issues; c) The need to standardize international and local regulations. The objective of the review article is to provide an analysis of the current achievements and limitations of AI in dermatology, paying special attention to the relevance of application in clinical practice.

Keywords:

artificial intelligence
machine learning
teledermatology
dermoscopy
skin cancers
melanoma
diagnosis
prevention

Authors:

Khryanin A.A.

Novosibirsk State Medical University;
Association of obstetrician-gynecologists and dermatologists

Bocharova V.K.

Pavlov First Saint Petersburg State Medical University

Received:

06.08.2023

Accepted:

13.03.2024

List of references:

  1. Artificial Intelligence. Oxford Dictionary.
  2. Vermesan O, Eisenhauer M, Sundmaeker H, et al. Internet of things cognitive transformation technology research trends and applications. Cognitive Hyperconnected Digital Transformation, June 2017;20-25.  https://doi.org/10.1201/9781003337584-3
  3. Bini SA. Artificial intelligence, machine learning, deep learning, and cognitive computing: what do these terms mean and how will they impact health care? J Arthroplast. 2018;33(8):2358-2361. https://doi.org/10.1016/j.arth.2018.02.067
  4. Erickson BJ, Korfiatis P, Akkus Z, Kline TL. Machine learning for medical imaging. Radiographics. 2017;37(2):505-515.  https://doi.org/10.1148/rg.2017160130
  5. Hogarty DT, Mackey DA, Hewitt AW. Current state and future prospects of artificial intelligence in ophthalmology: a review. Clin Exp Ophthalmol. 2019; 47(1):128-139.  https://doi.org/10.1111/ceo.13381
  6. Hogarty DT, Su JC, Phan K, et al. Artificial intelligence in dermatology — where we are and the way to the future: a review. Am J Clin Dermatol. 2020; 21(1):41-47.  https://doi.org/10.1007/s40257-019-00462-6
  7. Krizhevsky A, Sutskever I, Hinton GE. ImageNet classification with deep convolutional neural networks. Communications of the ACM. June 2017; 60(6):84-90.  https://doi.org/10.1145/3065386
  8. Lee JG, Jun S, Cho YW, et al. Deep learning in medical imaging: General overview. Korean J Radiol. 2017;18(4):570-584.  https://doi.org/10.3348/kjr.2017.18.4.570
  9. Tschandl P. Artificial intelligence for melanoma diagnosis. Ital J Dermatol Venereol. 2021;156(3):289-299.  https://doi.org/10.23736/S2784-8671.20.06753-X
  10. Benjamens S, Dhunnoo P, Meskó B. The state of artificial intelligence-based FDA-approved medical devices and algorithms: an online database. NPJ Digit Med. 2020;3:118.  https://doi.org/10.1038/s41746-020-00324-0
  11. Abraham SB, Arunachalam S, Zhong A, et al. Improved real-world glycemic control with continuous glucose monitoring system predictive alerts. J Diabetes Sci Technol. 2019;15(1):91-97.  https://doi.org/10.1177/1932296819859334
  12. van der Heijden AA, Abramoff MD, Verbraak F, et al. Validation of automated screening for referable diabetic retinopathy with the IDx-DR device in the Hoorn Diabetes Care System. Acta Ophthalmol. 2018;96(1):63-68.  https://doi.org/10.1111/aos.13613
  13. Escobar GJ, Turk BJ, Ragins A, et al. Piloting electronic medical record-based early detection of inpatient deterioration in community hospitals. J Hosp Med. 2016;11:S18-S24.  https://doi.org/10.1002/jhm.2652
  14. Singh G. Artificial intelligence in colorectal cancer: a review. Siberian Journal of Oncology. 2023;22(3):99-107.  https://doi.org/10.21294/1814-4861-2023-22-3-99-107
  15. Sun T, Niu X, He Q, et al. Artificial Intelligence in microbiomes analysis: A review of applications in dermatology. Front Microbiol. 2023 Feb 1;14: 1112010. https://doi.org/10.3389/fmicb.2023.1112010
  16. Rajkomar A, Dean J, Kohane I. Machine learning in medicine. N Engl J Med. 2019;380(14):1347-1358. https://doi.org/10.1056/nejmra1814259
  17. Kulkarni PA, Singh H. Artificial Intelligence in Clinical Diagnosis: Opportunities, Challenges, and Hype. JAMA. Published online. 2023;330(4): 317-318.  https://doi.org/10.1001/jama.2023.11440
  18. Tschandl P, Rinner C, Apalla Z, et al. Human—computer collaboration for skin cancer recognition. Nat Med. 2020;26(8):1229-1234. https://doi.org/10.1038/s41591-020-0942-0
  19. Esteva A, Kuprel B, Novoa RA, et al. Dermatologist-level classification of skin cancer with deep neural networks. Nature. 2017;542(7639):115-118.  https://doi.org/10.1038/nature21056
  20. Haggenmüller S, Maron RC, Hekler A, et al. Skin cancer classification via convolutional neural networks: systematic review of studies involving human experts. Eur J Cancer. 2021;156:202-216.  https://doi.org/10.1016/j.ejca.2021.06.049
  21. Tschandl P, Rosendahl C, Akay BN, et al. Expert-level diagnosis of nonpigmented skin cancer by combined convolutional neural networks. JAMA Dermatol. 2019;155(1):58-65.  https://doi.org/10.1001/jamadermatol.2018.4378
  22. Combalia M, Codella N, Rotemberg V, et al. Validation of artificial intelligence prediction models for skin cancer diagnosis using dermoscopy images: the 2019 International Skin Imaging Collaboration Grand Challenge. Lancet Digit Health. 2022;4(5):e330-e339. https://doi.org/10.1016/S2589-7500(22)00021-8
  23. National Cancer Institute Melanoma of the Skin-Cancer Stat Facts. Published May 2022. Accessed 18 May 2022.
  24. Swetter SM, Tsao H, Bichakjian CK, et al. Guidelines of care for the management of primary cutaneous melanoma. J Am Acad Dermatol. 2019;80(1): 208-250.  https://doi.org/10.1016/j.jaad.2018.08.055
  25. Pan Y, Gareau DS, Scope A, et al. Polarized and nonpolarized dermoscopy: the explanation for the observed differences. Arch Dermatol. 2008;144(6): 828-829.  https://doi.org/10.1001/archderm.144.6.828
  26. Pehamberger H, Steiner A, Wolff K. In vivo epiluminescence microscopy of pigmented skin lesions. I. Pattern analysis of pigmented skin lesions. J Am Acad Dermatol. 1987;17(4):571-583.  https://doi.org/10.1016/S0190-9622(87)70239-4
  27. Kittler H, Pehamberger H, Wolff K, Binder M. Diagnostic accuracy of dermoscopy. Lancet Oncol. 2002;3(3):159-165.  https://doi.org/10.1016/S1470-2045(02)00679-4
  28. Argenziano G, Cerroni L, Zalaudek I, et al. Accuracy in melanoma detection: a 10-year multicenter survey. J Am Acad Dermatol. 2012;67(1):54-59.  https://doi.org/10.1016/j.jaad.2011.07.019
  29. Jiang A, Jefferson IS, Robinson SK, et al. Skin cancer discovery during total body skin examinations. Int J Womens Dermatol. 2021;7(4):411-414.  https://doi.org/10.1016/j.ijwd.2021.05.005
  30. Argenziano G, Zalaudek I, Hofmann-Wellenhof R, et al. Total body skin examination for skin cancer screening in patients with focused symptoms. J Am Acad Dermatol. 2012;66(2):212-219.  https://doi.org/10.1016/j.jaad.2010.12.039
  31. Avilés-Izquierdo JA, Molina-López I, Rodríguez-Lomba E, et al. Who detects melanoma? Impact of detection patterns on characteristics and prognosis of patients with melanoma. J Am Acad Dermatol. 2016;75(5):967-974.  https://doi.org/10.1016/j.jaad.2016.07.009
  32. Scheetz J, Rothschild P, McGuinness M, et al. A survey of clinicians on the use of artificial intelligence in ophthalmology, dermatology, radiology and radiation oncology. Sci Rep. 2021;51:93.  https://doi.org/10.1038/s41598-021-84698-5
  33. International Skin Imaging Collaboration (ISIC) Archive.
  34. Navarrete-Dechent C, Dusza SW, Liopyris K, et al. Automated dermatological diagnosis: hype or reality? J Investig Dermatol. 2018;138(10):2277-2279. https://doi.org/10.1016/j.jid.2018.04.040
  35. Okur E, Turkan M. A survey on automated melanoma detection. Eng Appl Artif Intell. 2018;73:50-67.  https://doi.org/10.1016/j.engappai.2018.04.028
  36. Narla A, Kuprel B, Sarin K, et al. Automated classification of skin lesions: from pixels to practice. J Investig Dermatol. 2018;138(10):2108-2110. https://doi.org/10.1016/j.jid.2018.06.175
  37. Winkler JK, Fink C, Toberer F, et al. Association between surgical skin markings in dermoscopic images and diagnostic performance of a deep learning convolutional neural network for melanoma recognition. JAMA Dermatol. 2019;155(10):1135-1141. https://doi.org/10.1001/jamadermatol.2019.1735
  38. Navarrete-Dechent C, Liopyris K, Marchetti MA. Multiclass artificial intelligence in dermatology: progress but still room for improvement. J Investig Dermatol. 2021;141(5):1325-1328. https://doi.org/10.1016/j.jid.2020.06.040
  39. Haenssle HA, Winkler JK, Fink C, et al. Skin lesions of face and scalp—classification by a market-approved convolutional neural network in comparison with 64 dermatologists. Eur J Cancer. 2021;144:192-199.  https://doi.org/10.1016/j.ejca.2020.11.034
  40. Yu C, Yang S, Kim W, et al. Acral melanoma detection using a convolutional neural network for dermoscopy images. PLoS One. 2018;13(4):e0196621. https://doi.org/10.1371/journal.pone.0193321
  41. Abbas Q, Ramzan F, Ghani MU. Acral melanoma detection using dermoscopic images and convolutional neural networks. Vis Comput Ind Biomed Art. 2021;25: without pages. https://doi.org/10.1186/s42492-021-00091-z
  42. 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(7):938-947.  https://doi.org/10.1016/S1470-2045(19)30333-X
  43. Adamson AS, Smith A. Machine learning and health care disparities in dermatology. JAMA Dermatol. 2018;154(11):1247-1248. https://doi.org/10.1001/jamadermatol.2018.2348
  44. Chartrand G, Cheng PM, Vorontsov E, et al. Deep learning: a primer for radiologists. Radiographics. 2017;37(7):2113-2131. https://doi.org/10.1148/rg.2017170077
  45. Gaudy-Marqueste C, Wazaefi Y, Bruneu Y, et al. Ugly duckling sign as a major factor of efficiency in melanoma detection. JAMA Dermatol. 2017;153(4): 279-284.  https://doi.org/10.1001/jamadermatol.2016.5500
  46. Mascaro JM. The dermatologist’s position concerning nevi: a vision ranging from «the ugly duckling» to «“little red riding hood» Arch Dermatol. 1998;134(11):1484-1485.
  47. Zalaudek I, Docimo G, Argenziano G. Using dermoscopic criteria and patient-related factors for the management of pigmented melanocytic nevi. Arch Dermatol. 2009;145(7):816-826.  https://doi.org/10.1001/archdermatol.2009.115
  48. Carli P, De Giorgi V, Argenziano G, et al. Pre-operative diagnosis of pigmented skin lesions: in vivo dermoscopy performs better than dermoscopy on photographic images. J Eur Acad Dermatol Venereol. 2002;16(4):339-346.  https://doi.org/10.1046/j.1468-3083.2002.00470.x
  49. Kutzner H, Jutzi TB, Krahl D, et al. Overdiagnosis of melanoma—causes, consequences and solutions. JDDG J German Soc Dermatol. 2020;18(11): 1236-1243. https://doi.org/10.1111/ddg.14233
  50. Bell KJL, Mehta Y, Turner RM, et al. Fear of new or recurrent melanoma after treatment for localised melanoma. Psychooncology. 2017;26(11): 1784-1791. https://doi.org/10.1002/pon.4366
  51. Linos E, Parvataneni R, Stuart SE, et al. Treatment of nonfatal conditions at the end of life: nonmelanoma skin cancer. JAMA Intern Med. 2013;173(11): 1006-1012. https://doi.org/10.1001/jamainternmed.2013.639
  52. Han SS, Kim MS, Lim W, et al. Classification of the clinical images for benign and malignant cutaneous tumors using a deep learning algorithm. J Investig Dermatol. 2018;138(7):1529-1538. https://doi.org/10.1016/j.jid.2018.01.028
  53. Ward-Peterson M, Acuña JM, Alkhalifah MK, et al. Association Between Race/Ethnicity and Survival of Melanoma Patients in the United States Over 3 Decades: A Secondary Analysis of SEER Data. Medicine (Baltimore). 2016;95(17):e3315. https://doi.org/10.1097/MD.0000000000003315
  54. Yap J, Yolland W, Tschandl P. Multimodal skin lesion classification using deep learning. Exp Dermatol. 2018;27(11):1261-1267. https://doi.org/10.1111/exd.13777
  55. Jameson JL, Longo DL. Precision medicine--personalized, problematic, and promising. N Engl J Med. 2015;372(23):2229-2234. https://doi.org/10.1056/NEJMsb1503104
  56. Lee KJ, Betz-Stablein B, Stark MS, et al. The Future of Precision Prevention for Advanced Melanoma. Front Med (Lausanne). 2022 Jan 17;8:818096. https://doi.org/10.3389/fmed.2021.818096
  57. Smithers BM, Dunn J, Soyer HP. Whither melanoma in Australia? Med J Aust. 2017;207(8):330-331.  https://doi.org/10.5694/mja17.00740
  58. Marchetti MA, Codella NCF, Dusza SW, et al. Results of the 2016 international skin imaging collaboration international symposium on biomedical imaging challenge: comparison of the accuracy of computer algorithms to dermatologists for the diagnosis of melanoma from dermoscopic images. J Am Acad Dermatol. 2018;78:270-277.e1.  https://doi.org/10.1016/j.jaad.2017.08.016
  59. Han SS, Park I, Eun Chang S, et al. Augmented intelligence dermatology: deep neural networks empower medical professionals in diagnosing skin cancer and predicting treatment options for 134 skin disorders. J Investig Dermatol. 2020;140(9):1753-1761. https://doi.org/10.1016/j.jid.2020.01.019

Close metadata

Contact the author
Email
Message
The publishing house "Media Sphere" does not provide treatment services, does not give recommendations on contacting medical institutions and specific specialists, on the prescription of medicines and dietary supplements.

Email Confirmation

An email was sent to test@gmail.com with a confirmation link. Follow the link from the letter to complete the registration on the site.

Email Confirmation

Contact us
If you have any questions, complaints or suggestions, please use this feedback form.
Email
Message
The publishing house "Media Sphere" does not provide treatment services, does not give recommendations on contacting medical institutions and specific specialists, on the prescription of medicines and dietary supplements.
Submit Application

You can become an author of one of our magazines, send a request and we will consider it in during the day.

Name
Phone
E-mail
Message
Login
Registration
E-mail
Password
Forgot Password?

Log in to the site using your account in one of the services

Password recovery
E-mail
Login
Register


We use cооkies to improve the performance of the site. By staying on our site, you agree to the terms of use of cооkies. To view our Privacy and Cookie Policy, please. click here.