Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2024 Sep 11;4(1):177.
doi: 10.1038/s43856-024-00598-5.

Prospective multicenter study using artificial intelligence to improve dermoscopic melanoma diagnosis in patient care

Lukas Heinlein #  1 , Roman C Maron #  1 , Achim Hekler #  1 , Sarah Haggenmüller  1 , Christoph Wies  1   2 , Jochen S Utikal  3   4   5 , Friedegund Meier  6   7 , Sarah Hobelsberger  6 , Frank F Gellrich  6 , Mildred Sergon  6 , Axel Hauschild  8 , Lars E French  9   10 , Lucie Heinzerling  9   11 , Justin G Schlager  9 , Kamran Ghoreschi  12 , Max Schlaak  12 , Franz J Hilke  12 , Gabriela Poch  12 , Sören Korsing  12 , Carola Berking  11 , Markus V Heppt  11 , Michael Erdmann  11 , Sebastian Haferkamp  13 , Konstantin Drexler  13 , Dirk Schadendorf  14 , Wiebke Sondermann  14 , Matthias Goebeler  15 , Bastian Schilling  15 , Eva Krieghoff-Henning  1 , Titus J Brinker  16
Affiliations

Prospective multicenter study using artificial intelligence to improve dermoscopic melanoma diagnosis in patient care

Lukas Heinlein et al. Commun Med (Lond). .

Abstract

Background: Early detection of melanoma, a potentially lethal type of skin cancer with high prevalence worldwide, improves patient prognosis. In retrospective studies, artificial intelligence (AI) has proven to be helpful for enhancing melanoma detection. However, there are few prospective studies confirming these promising results. Existing studies are limited by low sample sizes, too homogenous datasets, or lack of inclusion of rare melanoma subtypes, preventing a fair and thorough evaluation of AI and its generalizability, a crucial aspect for its application in the clinical setting.

Methods: Therefore, we assessed "All Data are Ext" (ADAE), an established open-source ensemble algorithm for detecting melanomas, by comparing its diagnostic accuracy to that of dermatologists on a prospectively collected, external, heterogeneous test set comprising eight distinct hospitals, four different camera setups, rare melanoma subtypes, and special anatomical sites. We advanced the algorithm with real test-time augmentation (R-TTA, i.e., providing real photographs of lesions taken from multiple angles and averaging the predictions), and evaluated its generalization capabilities.

Results: Overall, the AI shows higher balanced accuracy than dermatologists (0.798, 95% confidence interval (CI) 0.779-0.814 vs. 0.781, 95% CI 0.760-0.802; p = 4.0e-145), obtaining a higher sensitivity (0.921, 95% CI 0.900-0.942 vs. 0.734, 95% CI 0.701-0.770; p = 3.3e-165) at the cost of a lower specificity (0.673, 95% CI 0.641-0.702 vs. 0.828, 95% CI 0.804-0.852; p = 3.3e-165).

Conclusion: As the algorithm exhibits a significant performance advantage on our heterogeneous dataset exclusively comprising melanoma-suspicious lesions, AI may offer the potential to support dermatologists, particularly in diagnosing challenging cases.

Plain language summary

Melanoma is a type of skin cancer that can spread to other parts of the body, often resulting in death. Early detection improves survival rates. Computational tools that use artificial intelligence (AI) can be used to detect melanoma. However, few studies have checked how well the AI works on real-world data obtained from patients. We tested a previously developed AI tool on data obtained from eight different hospitals that used different types of cameras, which also included images taken of rare melanoma types and from a range of different parts of the body. The AI tool was more likely to correctly identify melanoma than dermatologists. This AI tool could be used to help dermatologists diagnose melanoma, particularly those that are difficult for dermatologists to diagnose.

PubMed Disclaimer

Conflict of interest statement

Jochen S. Utikal is on the advisory board or has received honoraria and travel support from Amgen, Bristol Myers Squibb, GSK, Immunocore, LeoPharma, Merck Sharp and Dohme, Novartis, Pierre Fabre, Roche, and Sanofi outside the submitted work. Friedegund Meier has received travel support and/or speaker’s fees and/or advisor’s honoraria by Novartis, Roche, BMS, MSD and Pierre Fabre and research funding from Novartis and Roche. Sarah Hobelsberger reports clinical trial support from Almirall and speaker’s honoraria from Almirall, UCB, and AbbVie and has received travel support from the following companies: UCB, Janssen Cilag, Almirall, Novartis, Lilly, LEO Pharma and AbbVie outside the submitted work. Sebastian Haferkamp reports advisory roles for or has received honoraria from Pierre Fabre Pharmaceuticals, Novartis, Roche, BMS, Amgen, and MSD outside the submitted work. Konstantin Drexler has received honoraria from Pierre Fabre Pharmaceuticals and Novartis. Axel Hauschild reports clinical trial support, speaker’s honoraria, or consultancy fees from the following companies: Agenus, Amgen, BMS, Dermagnostix, Highlight Therapeutics, Immunocore, Incyte, IO Biotech, Merck Pfizer, MSD, NercaCare, Novartis, Philogen, Pierre Fabre, Regeneron, Roche, Sanofi-Genzyme, Seagen, Sun Pharma and Xenthera outside the submitted work. Lars E. French is on the advisory board or has received consulting/speaker honoraria from Galderma, Janssen, Leo Pharma, Eli Lilly, Almirall, Union Therapeutics, Regeneron, Novartis, Amgen, AbbVie, UCB, Biotest, and InflaRx. Max Schlaak reports advisory roles for Bristol-Myers Squibb, Novartis, MSD, Roche, Pierre Fabre, Kyowa Kirin, Immunocore, and Sanofi-Genzyme. Wiebke Sondermann reports grants, speaker’s honoraria, or consultancy fees from medi GmbH Bayreuth, AbbVie, Almirall, Amgen, Bristol-Myers Squibb, Celgene, GSK, Janssen, LEO Pharma, Lilly, MSD, Novartis, Pfizer, Roche, Sanofi Genzyme and UCB outside the submitted work. Bastian Schilling reports advisory roles for or has received honoraria from Sanofi, Pierre Fabre Pharmaceuticals, SUN Pharma, and BMS, and research funding from Novartis, all outside the submitted work. Matthias Goebeler has received speaker’s honoraria and/or has served as a consultant and/or member of advisory boards for Almirall, Argenx, Biotest, Eli Lilly, Janssen Cilag, Leo Pharma, Novartis, and UCB outside the submitted work. Michael Erdmann declares honoraria and travel support from Bristol-Myers Squibb, Immunocore Novartis, Pierre Farbe, and Sanofi outside the submitted work. Jakob N. Kather reports consulting services for Owkin, France, Panakeia, UK, and DoMore Diagnostics, Norway, and has received honoraria for lectures by MSD, Eisai, and Fresenius. Titus J. Brinker reports owning a company that develops mobile apps (Smart Health Heidelberg GmbH, Handschuhsheimer Landstr. 9/1, 69120 Heidelberg). The remaining authors declare no competing interests.

Figures

Fig. 1
Fig. 1. Feature distribution of our dataset.
The feature distribution of our dataset (n = 11460) using t-distributed Stochastic Neighbor Embedding (2 components, 1000 iterations). The features are colored according to their type (melanoma or non-melanoma).
See this image and copyright information in PMC

Similar articles

See all similar articles

Cited by

  • Artificial Intelligence in the Non-Invasive Detection of Melanoma.
    İsmail Mendi B, Kose K, Fleshner L, Adam R, Safai B, Farabi B, Atak MF. İsmail Mendi B, et al. Life (Basel). 2024 Dec 4;14(12):1602. doi: 10.3390/life14121602. Life (Basel). 2024. PMID: 39768310 Free PMC article. Review.
  • Skin Photodamage and Melanomagenesis: A Comprehensive Review.
    Manganelli M, Stabile G, Scharf C, Podo Brunetti A, Paolino G, Giuffrida R, Bigotto GD, Damiano G, Mercuri SR, Sallustio F, Mangano E, Bordoni R, De Nardi P, Guida G, Foti C, Argenziano G, Longo C, Pellacani G, Rizzo N, Russo V, Guida S, Rongioletti F. Manganelli M, et al. Cancers (Basel). 2025 May 26;17(11):1784. doi: 10.3390/cancers17111784. Cancers (Basel). 2025. PMID: 40507265 Free PMC article. Review.

References

    1. Guy et al. Vital signs: melanoma incidence and mortality trends and projections—United States, 1982-2030. MMWR Morb. Mortal. Wkly Rep.64, 591–596 (2015). - PMC - PubMed
    1. Matthews, N. H., Li, W.-Q., Qureshi, A. A., Weinstock, M. A. & Cho, E. Epidemiology of Melanoma. (Exon Publications; 2017) pp. 3–22. - PubMed
    1. Lens, M. B. & Dawes, M. Global perspectives of contemporary epidemiological trends of cutaneous malignant melanoma. Br. J. Dermatol.150, 179–185 (2004). 10.1111/j.1365-2133.2004.05708.x - DOI - PubMed
    1. Petrie, T., Samatham, R., Witkowski, A. M., Esteva, A. & Leachman, S. A. Melanoma early detection: big data, bigger picture. J. Invest. Dermatol.139, 25–30 (2019). 10.1016/j.jid.2018.06.187 - DOI - PMC - PubMed
    1. Rigel, D. S., Russak, J. & Friedman, R. The evolution of melanoma diagnosis: 25 years beyond the ABCDs. CA Cancer J. Clin.60, 301–316 (2010). 10.3322/caac.20074 - DOI - PubMed

LinkOut - more resources