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 Oct;2(4):044503.
doi: 10.1117/1.JMI.2.4.044503. Epub 2015 Dec 29.

Classification of reticular pattern and streaks in dermoscopic images based on texture analysis

Affiliations

Classification of reticular pattern and streaks in dermoscopic images based on texture analysis

Marlene Machado et al. J Med Imaging (Bellingham). 2015 Oct.

Abstract

The early detection of melanoma is one of the greatest challenges in clinical practice of dermatology, and the reticular pattern is one of the most important dermoscopic structures to improve melanocytic lesion diagnosis. A texture-based approach is developed for the automatic detection of reticular patterns, whose output will assist clinical decision-making. Feature selection was based on the use of two algorithms by means of the classical graylevel co-occurrence matrix and Laws energy masks optimized on a set of 104 dermoscopy images. The AdaBoost (adaptive boosting) approach to machine learning was used within this strategy. Results suggest superiority of LEM for reticular pattern detection in dermoscopic images, achieving a sensitivity of 90.16% and a specificity of 86.67%. The use of automatic classification in dermoscopy to support clinicians is a strong tool to assist diagnosis; however, the use of automatic classification as a complementary tool in clinical routine requires algorithms with high levels of sensitivity and specificity. The results presented in this work will contribute to achieving this goal.

Keywords: dermoscopy; melanoma; pattern recognition; reticular pattern.

PubMed Disclaimer

Figures

Fig. 1
Fig. 1
Examples of reticular pattern in dermoscopy images: (a) Clark nevi, (b) congenital pseudomelanoma, (c) melanoma, and (d) melanoma with streaks.
Fig. 2
Fig. 2
One-dimensional Laws masks of size 3, 5, and 7.
Fig. 3
Fig. 3
Result of reticular pattern finder using graylevel co-occurrence matrix (GLCM) and Laws features. (a and d) Clark nevi, (b and e) congenital pseudomelanoma, and (c and f) melanoma.
Fig. 4
Fig. 4
Performance of Laws masks of different sizes on test set (percentage classified correctly).
Fig. 5
Fig. 5
Performance of Laws masks of different sizes on test set (percentage error).
Fig. 6
Fig. 6
Performance of GLCM, combined Laws features, and combined GLCM and Laws features on test set (percentage classified correctly).
Fig. 7
Fig. 7
Performance of GLCM, combined Laws features, and combined GLCM and Laws features on test set (percentage error).

References

    1. Kasper D. L., Tinsley R. H., Harrison’s Principles of Internal Medicine, McGraw-Hill Companies, Inc., New York: (2005).
    1. Whiteman D. C., Pavan W. J., Bastian B. C., “The melanomas: a synthesis of epidemiological, clinical, histopathological, genetic, and biological aspects, supporting distinct subtypes, causal pathways, and cells of origin,” Pigment Cell Melanoma Res. 24, 879–897 (2011).10.1111/j.1755-148X.2011.00880.x - DOI - PMC - PubMed
    1. Zalaudek I., et al. , “How to diagnose nonpigmented skin tumors: a review of vascular structures seen with dermoscopy: part I. Melanocytic skin tumors,” J. Am. Acad. Dermatol. 63, 361–374 (2010); quiz 375-366.JAADDB10.1016/j.jaad.2009.11.698 - DOI - PubMed
    1. Menzies S. W., Ingvar C., McCarthy W. H., “A sensitivity and specificity analysis of the surface microscopy features of invasive melanoma,” Melanoma Res. 6, 55–62 (1996).MREEEH10.1097/00008390-199602000-00008 - DOI - PubMed
    1. Andreassi L., et al. , “Digital dermoscopy analysis for the differentiation of atypical nevi and early melanoma: a new quantitative semiology,” Arch Dermatol. 135, 1459–1465 (1999).10.1001/archderm.135.12.1459 - DOI - PubMed