A basis function feature-based approach for skin lesion discrimination in dermatology dermoscopy images

R. Joe Stanley, William V. Stoecker, Randy H. Moss, Harold S. Rabinovitz, Armand B. Cognetta, Giuseppe Argenziano, H. Peter Soyer

Research output: Contribution to journalArticle

19 Citations (Scopus)

Abstract

Background: Skin lesion color is an important feature for diagnosing malignant melanoma. New basis function correlation features are proposed for discriminating malignant melanoma lesions from benign lesions in dermoscopy images. The proposed features are computed based on correlating the luminance histogram of melanoma or benign labeled relative colors from a specified portion of the skin lesion with a set of basis functions. These features extend previously developed statistical and fuzzy logic-based relative color histogram analysis techniques for automated mapping of colors representative of melanoma and benign skin lesions from a training set of lesion images. Methods: Using the statistical and fuzzy logic-based approaches for relative color mapping, melanoma and benign color features are computed over skin lesion region of interest, respectively. Luminance histograms are obtained from the melanoma and benign mapped colors within the lesion region of interest and are correlated with a set of basis functions to quantify the distribution of colors. The histogram analysis techniques and feature calculations are evaluated using a data set of 279 malignant melanomas and 442 benign dysplastic nevi images. Results: Experimental test results showed that combining existing melanoma and benign color features with the proposed basis function features found from the melanoma mapped colors yielded average correct melanoma and benign lesion discrimination rates as high as 86.45% and 83.35%, respectively. Conclusions: The basis function features provide an alternative approach to melanoma discrimination that quantifies the variation and distribution of colors characteristic of melanoma and benign skin lesions.

Original languageEnglish
Pages (from-to)425-435
Number of pages11
JournalSkin Research and Technology
Volume14
Issue number4
DOIs
Publication statusPublished - 2008

Fingerprint

Dermoscopy
Dermatology
Melanoma
Color
Skin
Fuzzy Logic
Dysplastic Nevus Syndrome
Skin Pigmentation

Keywords

  • Basis function
  • Color
  • Fuzzy logic
  • Histogram
  • Image processing
  • Malignant melanoma

ASJC Scopus subject areas

  • Dermatology

Cite this

Joe Stanley, R., Stoecker, W. V., Moss, R. H., Rabinovitz, H. S., Cognetta, A. B., Argenziano, G., & Peter Soyer, H. (2008). A basis function feature-based approach for skin lesion discrimination in dermatology dermoscopy images. Skin Research and Technology, 14(4), 425-435. https://doi.org/10.1111/j.1600-0846.2008.00307.x

A basis function feature-based approach for skin lesion discrimination in dermatology dermoscopy images. / Joe Stanley, R.; Stoecker, William V.; Moss, Randy H.; Rabinovitz, Harold S.; Cognetta, Armand B.; Argenziano, Giuseppe; Peter Soyer, H.

In: Skin Research and Technology, Vol. 14, No. 4, 2008, p. 425-435.

Research output: Contribution to journalArticle

Joe Stanley, R, Stoecker, WV, Moss, RH, Rabinovitz, HS, Cognetta, AB, Argenziano, G & Peter Soyer, H 2008, 'A basis function feature-based approach for skin lesion discrimination in dermatology dermoscopy images', Skin Research and Technology, vol. 14, no. 4, pp. 425-435. https://doi.org/10.1111/j.1600-0846.2008.00307.x
Joe Stanley, R. ; Stoecker, William V. ; Moss, Randy H. ; Rabinovitz, Harold S. ; Cognetta, Armand B. ; Argenziano, Giuseppe ; Peter Soyer, H. / A basis function feature-based approach for skin lesion discrimination in dermatology dermoscopy images. In: Skin Research and Technology. 2008 ; Vol. 14, No. 4. pp. 425-435.
@article{65f1f43f78394bd48d3de901fc8dc91b,
title = "A basis function feature-based approach for skin lesion discrimination in dermatology dermoscopy images",
abstract = "Background: Skin lesion color is an important feature for diagnosing malignant melanoma. New basis function correlation features are proposed for discriminating malignant melanoma lesions from benign lesions in dermoscopy images. The proposed features are computed based on correlating the luminance histogram of melanoma or benign labeled relative colors from a specified portion of the skin lesion with a set of basis functions. These features extend previously developed statistical and fuzzy logic-based relative color histogram analysis techniques for automated mapping of colors representative of melanoma and benign skin lesions from a training set of lesion images. Methods: Using the statistical and fuzzy logic-based approaches for relative color mapping, melanoma and benign color features are computed over skin lesion region of interest, respectively. Luminance histograms are obtained from the melanoma and benign mapped colors within the lesion region of interest and are correlated with a set of basis functions to quantify the distribution of colors. The histogram analysis techniques and feature calculations are evaluated using a data set of 279 malignant melanomas and 442 benign dysplastic nevi images. Results: Experimental test results showed that combining existing melanoma and benign color features with the proposed basis function features found from the melanoma mapped colors yielded average correct melanoma and benign lesion discrimination rates as high as 86.45{\%} and 83.35{\%}, respectively. Conclusions: The basis function features provide an alternative approach to melanoma discrimination that quantifies the variation and distribution of colors characteristic of melanoma and benign skin lesions.",
keywords = "Basis function, Color, Fuzzy logic, Histogram, Image processing, Malignant melanoma",
author = "{Joe Stanley}, R. and Stoecker, {William V.} and Moss, {Randy H.} and Rabinovitz, {Harold S.} and Cognetta, {Armand B.} and Giuseppe Argenziano and {Peter Soyer}, H.",
year = "2008",
doi = "10.1111/j.1600-0846.2008.00307.x",
language = "English",
volume = "14",
pages = "425--435",
journal = "Skin Research and Technology",
issn = "0909-752X",
publisher = "Wiley-Blackwell",
number = "4",

}

TY - JOUR

T1 - A basis function feature-based approach for skin lesion discrimination in dermatology dermoscopy images

AU - Joe Stanley, R.

AU - Stoecker, William V.

AU - Moss, Randy H.

AU - Rabinovitz, Harold S.

AU - Cognetta, Armand B.

AU - Argenziano, Giuseppe

AU - Peter Soyer, H.

PY - 2008

Y1 - 2008

N2 - Background: Skin lesion color is an important feature for diagnosing malignant melanoma. New basis function correlation features are proposed for discriminating malignant melanoma lesions from benign lesions in dermoscopy images. The proposed features are computed based on correlating the luminance histogram of melanoma or benign labeled relative colors from a specified portion of the skin lesion with a set of basis functions. These features extend previously developed statistical and fuzzy logic-based relative color histogram analysis techniques for automated mapping of colors representative of melanoma and benign skin lesions from a training set of lesion images. Methods: Using the statistical and fuzzy logic-based approaches for relative color mapping, melanoma and benign color features are computed over skin lesion region of interest, respectively. Luminance histograms are obtained from the melanoma and benign mapped colors within the lesion region of interest and are correlated with a set of basis functions to quantify the distribution of colors. The histogram analysis techniques and feature calculations are evaluated using a data set of 279 malignant melanomas and 442 benign dysplastic nevi images. Results: Experimental test results showed that combining existing melanoma and benign color features with the proposed basis function features found from the melanoma mapped colors yielded average correct melanoma and benign lesion discrimination rates as high as 86.45% and 83.35%, respectively. Conclusions: The basis function features provide an alternative approach to melanoma discrimination that quantifies the variation and distribution of colors characteristic of melanoma and benign skin lesions.

AB - Background: Skin lesion color is an important feature for diagnosing malignant melanoma. New basis function correlation features are proposed for discriminating malignant melanoma lesions from benign lesions in dermoscopy images. The proposed features are computed based on correlating the luminance histogram of melanoma or benign labeled relative colors from a specified portion of the skin lesion with a set of basis functions. These features extend previously developed statistical and fuzzy logic-based relative color histogram analysis techniques for automated mapping of colors representative of melanoma and benign skin lesions from a training set of lesion images. Methods: Using the statistical and fuzzy logic-based approaches for relative color mapping, melanoma and benign color features are computed over skin lesion region of interest, respectively. Luminance histograms are obtained from the melanoma and benign mapped colors within the lesion region of interest and are correlated with a set of basis functions to quantify the distribution of colors. The histogram analysis techniques and feature calculations are evaluated using a data set of 279 malignant melanomas and 442 benign dysplastic nevi images. Results: Experimental test results showed that combining existing melanoma and benign color features with the proposed basis function features found from the melanoma mapped colors yielded average correct melanoma and benign lesion discrimination rates as high as 86.45% and 83.35%, respectively. Conclusions: The basis function features provide an alternative approach to melanoma discrimination that quantifies the variation and distribution of colors characteristic of melanoma and benign skin lesions.

KW - Basis function

KW - Color

KW - Fuzzy logic

KW - Histogram

KW - Image processing

KW - Malignant melanoma

UR - http://www.scopus.com/inward/record.url?scp=54049131233&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=54049131233&partnerID=8YFLogxK

U2 - 10.1111/j.1600-0846.2008.00307.x

DO - 10.1111/j.1600-0846.2008.00307.x

M3 - Article

C2 - 18937777

AN - SCOPUS:54049131233

VL - 14

SP - 425

EP - 435

JO - Skin Research and Technology

JF - Skin Research and Technology

SN - 0909-752X

IS - 4

ER -