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
Review
. 2024 Apr 8;16(7):1443.
doi: 10.3390/cancers16071443.

Performance of Commercial Dermatoscopic Systems That Incorporate Artificial Intelligence for the Identification of Melanoma in General Practice: A Systematic Review

Ian Miller  1   2   3 , Nedeljka Rosic  1   2 , Michael Stapelberg  1   2   3 , Jeremy Hudson  2   4 , Paul Coxon  2   4 , James Furness  5 , Joe Walsh  6   7 , Mike Climstein  1   2   8
Affiliations
Review

Performance of Commercial Dermatoscopic Systems That Incorporate Artificial Intelligence for the Identification of Melanoma in General Practice: A Systematic Review

Ian Miller et al. Cancers (Basel). .

Abstract

Background: Cutaneous melanoma remains an increasing global public health burden, particularly in fair-skinned populations. Advancing technologies, particularly artificial intelligence (AI), may provide an additional tool for clinicians to help detect malignancies with a more accurate success rate. This systematic review aimed to report the performance metrics of commercially available convolutional neural networks (CNNs) tasked with detecting MM.

Methods: A systematic literature search was performed using CINAHL, Medline, Scopus, ScienceDirect and Web of Science databases.

Results: A total of 16 articles reporting MM were included in this review. The combined number of melanomas detected was 1160, and non-melanoma lesions were 33,010. The performance of market-approved technology and clinician performance for classifying melanoma was highly heterogeneous, with sensitivity ranging from 16.4 to 100.0%, specificity between 40.0 and 98.3% and accuracy between 44.0 and 92.0%. Less heterogeneity was observed when clinicians worked in unison with AI, with sensitivity ranging between 83.3 and 100.0%, specificity between 83.7 and 87.3%, and accuracy between 86.4 and 86.9%.

Conclusion: Instead of focusing on the performance of AI versus clinicians for classifying melanoma, more consistent performance has been obtained when clinicians' work is supported by AI, facilitating management decisions and improving health outcomes.

Keywords: computer-aided diagnosis; convolutional neural network; deep learning; dermatology; detection; diagnosis; epidemiology; machine learning; skin cancer; total body photography.

PubMed Disclaimer

Conflict of interest statement

Professor Mike Climstein is a section editor for PeerJ (Sports Medicine and Rehabilitation). Adjunct Professor Michael Stapelberg is self-employed operating at John Flynn Hospital Specialist Centre. The Adjunct Professor Jeremy Hudson and Dr. Paul Coxon are employed at North Queensland Skin Centre. The authors declare no conflicts of interest.

Figures

Figure 1
Figure 1
A visual representation of sensitivity and specificity.
Figure 2
Figure 2
PRISMA flow diagram.
Figure 3
Figure 3
Detection techniques captured in this systematic review. Traditional methods involve either opportunistic or routine skin examination via dermatoscopy. Emerging technologies include mobile applications, bedside convolutional neural networks and serial monitoring with the aid of total body photography.
Figure 4
Figure 4
(top) Describes the country location of publication; (bottom) describes the year the included studies were published.
See this image and copyright information in PMC

Similar articles

See all similar articles

Cited by

References

    1. Arnold M., Singh D., Laversanne M., Vignat J., Vaccarella S., Meheus F., Cust A.E., de Vries E., Whiteman D.C., Bray F. Global Burden of Cutaneous Melanoma in 2020 and Projections to 2040. JAMA Dermatol. 2022;158:495–503. doi: 10.1001/jamadermatol.2022.0160. - DOI - PMC - PubMed
    1. Olsen C.M., Green A.C., Pandeya N., Whiteman D.C. Trends in Melanoma Incidence Rates in Eight Susceptible Populations through 2015. J. Investig. Dermatol. 2019;139:1392–1395. doi: 10.1016/j.jid.2018.12.006. - DOI - PubMed
    1. Watts C.G., Dieng M., Morton R.L., Mann G.J., Menzies S.W., Cust A.E. Clinical practice guidelines for identification, screening and follow-up of individuals at high risk of primary cutaneous melanoma: A systematic review. Br. J. Dermatol. 2015;172:33–47. doi: 10.1111/bjd.13403. - DOI - PubMed
    1. Whiteman D.C., Olsen C.M., MacGregor S., Law M.H., Thompson B., Dusingize J.C., Green A.C., Neale R.E., Pandeya N., Study Q.S. The effect of screening on melanoma incidence and biopsy rates. Br. J. Dermatol. 2022;187:515–522. doi: 10.1111/bjd.21649. - DOI - PMC - PubMed
    1. Henrikson N.B., Ivlev I., Blasi P.R., Nguyen M.B., Senger C.A., Perdue L.A., Lin J.S. Skin Cancer Screening: Updated Evidence Report and Systematic Review for the US Preventive Services Task Force. JAMA. 2023;329:1296–1307. doi: 10.1001/jama.2023.3262. - DOI - PubMed

LinkOut - more resources