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
. 2008 Aug;14(3):347-53.
doi: 10.1111/j.1600-0846.2008.00301.x.

Border detection in dermoscopy images using statistical region merging

M Emre Celebi  1 , Hassan A Kingravi, Hitoshi Iyatomi, Y Alp Aslandogan, William V Stoecker, Randy H Moss, Joseph M Malters, James M Grichnik, Ashfaq A Marghoob, Harold S Rabinovitz, Scott W Menzies
Affiliations

Border detection in dermoscopy images using statistical region merging

M Emre Celebi et al. Skin Res Technol. 2008 Aug.

Abstract

Background: As a result of advances in skin imaging technology and the development of suitable image processing techniques, during the last decade, there has been a significant increase of interest in the computer-aided diagnosis of melanoma. Automated border detection is one of the most important steps in this procedure, because the accuracy of the subsequent steps crucially depends on it.

Methods: In this article, we present a fast and unsupervised approach to border detection in dermoscopy images of pigmented skin lesions based on the statistical region merging algorithm.

Results: The method is tested on a set of 90 dermoscopy images. The border detection error is quantified by a metric in which three sets of dermatologist-determined borders are used as the ground-truth. The proposed method is compared with four state-of-the-art automated methods (orientation-sensitive fuzzy c-means, dermatologist-like tumor extraction algorithm, meanshift clustering, and the modified JSEG method).

Conclusion: The results demonstrate that the method presented here achieves both fast and accurate border detection in dermoscopy images.

PubMed Disclaimer

Figures

Fig. 1
Fig. 1
(a) Original image, (b) SRM segmentation result, (c) initial border detection result (E = 11.499%), (d) majority filtering (E = 11.477%), (e) morphological dilation (E = 7.081%), and (f) distance transform (E = 7.486%). Green, manual border; blue, automatic border; E, error.
Fig. 2
Fig. 2
Comparison of the post-processing methods.
Fig. 3
Fig. 3
Error = (a) 4.186% (melanoma), (b) 5.216% (melanoma), (c) 5.285% (melanoma), (d) 8.290% (benign), (e) 10.245% (benign), and (f) 10.419% (melanoma).
See this image and copyright information in PMC

Similar articles

See all similar articles

Cited by

See all "Cited by" articles

References

    1. Jemal A, Siegel R, Ward E, Murray T, Xu J, Thun MJ. Cancer Statistics 2007. Cancer J Clin. 2007;57:43–66. - PubMed
    1. Menzies SW, Crotty KA, Ingwar C, McCarthy WH. An atlas of surface microscopy of pigmented skin lesions: dermoscopy. Sydney, Australia: McGraw-Hill; 2003.
    1. Steiner K, Binder M, Schemper M, Wolff K, Pehamberger H. Statistical evaluation of epiluminescence dermoscopy criteria for melanocytic pigmented lesions. J Am Acad Dermatol. 1993;29:581–588. - PubMed
    1. Binder M, Schwarz M, Winkler A, Steiner A, Kaider A, Wolff K, Pehamberger H. Epiluminescence microscopy. A useful tool for the diagnosis of pigmented skin lesions for formally trained dermatologists. Arch Dermatol. 1995;131:286–291. - PubMed
    1. Fleming MG, Steger C, Zhang J, Gao J, Cognetta AB, Pollak I, Dyer CR. Techniques for a structural analysis of dermatoscopic imagery. Comput Med Imaging Graphics. 1998;22:375–389. - PubMed

Publication types

MeSH terms