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
. 2015:2015:579282.
doi: 10.1155/2015/579282. Epub 2015 Nov 26.

Computer-Aided Decision Support for Melanoma Detection Applied on Melanocytic and Nonmelanocytic Skin Lesions: A Comparison of Two Systems Based on Automatic Analysis of Dermoscopic Images

Kajsa Møllersen  1 , Herbert Kirchesch  2 , Maciel Zortea  3 , Thomas R Schopf  1 , Kristian Hindberg  3 , Fred Godtliebsen  3
Affiliations

Computer-Aided Decision Support for Melanoma Detection Applied on Melanocytic and Nonmelanocytic Skin Lesions: A Comparison of Two Systems Based on Automatic Analysis of Dermoscopic Images

Kajsa Møllersen et al. Biomed Res Int. 2015.

Abstract

Commercially available clinical decision support systems (CDSSs) for skin cancer have been designed for the detection of melanoma only. Correct use of the systems requires expert knowledge, hampering their utility for nonexperts. Furthermore, there are no systems to detect other common skin cancer types, that is, nonmelanoma skin cancer (NMSC). As early diagnosis of skin cancer is essential, there is a need for a CDSS that is applicable to all types of skin lesions and is suitable for nonexperts. Nevus Doctor (ND) is a CDSS being developed by the authors. We here investigate ND's ability to detect both melanoma and NMSC and the opportunities for improvement. An independent test set of dermoscopic images of 870 skin lesions, including 44 melanomas and 101 NMSCs, were analysed by ND. Its sensitivity to melanoma and NMSC was compared to that of Mole Expert (ME), a commercially available CDSS, using the same set of lesions. ND and ME had similar sensitivity to melanoma. For ND at 95% melanoma sensitivity, the NMSC sensitivity was 100%, and the specificity was 12%. The melanomas misclassified by ND at 95% sensitivity were correctly classified by ME, and vice versa. ND is able to detect NMSC without sacrificing melanoma sensitivity.

PubMed Disclaimer

Figures

Figure 1
Figure 1
(a) Receiver operating characteristic curves for Nevus Doctor and Mole Expert. (b) Nonmelanoma skin cancer sensitivity as a function of melanoma sensitivity.
Figure 2
Figure 2
Boxplots for (a) Nevus Doctor and (b) Mole Expert. The horizontal lines inside the boxes are the medians; the boxes are defined by the 25th and 75th percentiles. The whiskers are situated at two standard deviations from the mean. The crosses indicate outlier observations.
Figure 3
Figure 3
(a)–(d) Lesions photographed with Canon/DermLite. (e)–(h) Lesions photographed with DermoGenius. ((a)-(b) and (e)-(f)) The two melanomas misclassified by ND at 95% melanoma sensitivity. ((c)-(d) and (g)-(h)) The two melanomas misclassified by ME at 95% melanoma sensitivity.
Figure 4
Figure 4
Receiver operating characteristic curves for Nevus Doctor and Mole Expert. Upper right part of Figure 1(a).
Figure 5
Figure 5
Receiver operating characteristic curves for Nevus Doctor, Mole Expert, and the combination classifier. Melanocytic lesions only.
Figure 6
Figure 6
Lesion (a) was clinically diagnosed as naevus, whereas lesion (b) was clinically diagnosed as melanoma.
See this image and copyright information in PMC

References

    1. Garbe C., Eigentler T. K., Keilholz U., Hauschild A., Kirkwood J. M. Systematic review of medical treatment in melanoma: current status and future prospects. The Oncologist. 2011;16(1):5–24. doi: 10.1634/theoncologist.2010-0190. - DOI - PMC - PubMed
    1. Niezgoda A., Niezgoda P., Czajkowski R. Novel approaches to treatment of advanced melanoma: a review on targeted therapy and immunotherapy. BioMed Research International. 2015;2015:16. doi: 10.1155/2015/851387.851387 - DOI - PMC - PubMed
    1. American Cancer Society. American Cancer Society; 2014. Cancer facts & figures 2014.
    1. Cancer Registry of Norway. Cancer Registry of Norway; 2015. Cancer in Norway 2013—cancer incidence, mortality, survival and prevalence in Norway.
    1. Kittler H., Pehamberger H., Wolff K., Binder M. Diagnostic accuracy of dermoscopy. The Lancet Oncology. 2002;3(3):159–165. doi: 10.1016/s1470-2045(02)00679-4. - DOI - PubMed