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
Comment
. 2018 Oct;138(10):2277-2279.
doi: 10.1016/j.jid.2018.04.040. Epub 2018 Jun 1.

Automated Dermatological Diagnosis: Hype or Reality?

Affiliations
Comment

Automated Dermatological Diagnosis: Hype or Reality?

Cristian Navarrete-Dechent et al. J Invest Dermatol. 2018 Oct.
No abstract available

PubMed Disclaimer

Conflict of interest statement

CONFLICT OF INTEREST

The authors state no conflict of interest.

Figures

Figure 1.
Figure 1.. Modification of the web app classification output by image manipulation.
(a, b) Basal cell carcinoma. The original image (a) was modified by zooming in (b). The two images gave different classifications: (a) lentigo (99.2% confidence); (b) intraepithelial carcinoma (96.9% confidence). (c, d) Melanoma. The original image (c) was modified by changing the contrast and brightness settings (d). The two images gave different classifications: (c) melanoma (99% confidence); (d) hemangioma (98% confidence). (e, f) Melanoma. The original image (e) was modified by flipping the image vertically (f). The two images gave different classifications: (e) lentigo (74% confidence), melanoma (12% confidence), nevus (5% confidence); (f) melanoma (40.5% confidence), lentigo (32% confidence), nevus (24% confidence). All images come from the International Skin Imaging Collaboration Archive (https://isic-archive.com/#images, dataset name: 2018 JID Editorial Images).

Comment in

Comment on

Similar articles

Cited by

References

    1. Castelvecchi D Can we open the black box of AI? Nature 2016;538:20–3. - PubMed
    1. Esteva A, Kuprel B, Novoa RA, Ko J, Swetter SM, Blau HM, et al. Dermatologist-level classification of skin cancer with deep neural networks. Nature 2017;542:115–8. - PMC - PubMed
    1. Ferris LK, Harkes JA, Gilbert B, Winger DG, Golubets K, Akilov O, et al. Computer-aided classification of melanocytic lesions using dermoscopic images. J Am Acad Dermatol 2015;73: 769–76. - PubMed
    1. Han SS, Kim MS, Lim W, Park GH, Park I, Chang SE. Classification of the clinical images for benign and malignant cutaneous tumors using a deep learning algorithm. J Invest Dermatol 2018. - PubMed
    1. Linos E, Schroeder SA, Chren MM. Potential overdiagnosis of basal cell carcinoma in older patients with limited life expectancy. JAMA 2014;312:997–8. - PubMed