Fuzzy logic techniques for blotch feature evaluation in dermoscopy images

Azmath Khan, Kapil Gupta, R. J. Stanley, William V. Stoecker, Randy H. Moss, Giuseppe Argenziano, H. Peter Soyer, Harold S. Rabinovitz, Armand B. Cognetta

Research output: Contribution to journalArticle

22 Citations (Scopus)

Abstract

Blotches, also called structureless areas, are critical in differentiating malignant melanoma from benign lesions in dermoscopy skin lesion images. In this paper, fuzzy logic techniques are investigated for the automatic detection of blotch features for malignant melanoma discrimination. Four fuzzy sets representative of blotch size and relative and absolute blotch colors are used to extract blotchy areas from a set of dermoscopy skin lesion images. Five previously reported blotch features are computed from the extracted blotches as well as four new features. Using a neural network classifier, malignant melanoma discrimination results are optimized over the range of possible alpha-cuts and compared with results using crisp blotch features. Features computed from blotches using the fuzzy logic techniques based on three plane relative color and blotch size yield the highest diagnostic accuracy of 81.2%.

Original languageEnglish
Pages (from-to)50-57
Number of pages8
JournalComputerized Medical Imaging and Graphics
Volume33
Issue number1
DOIs
Publication statusPublished - Jan 2009

Fingerprint

Fuzzy Logic
Dermoscopy
Fuzzy logic
Melanoma
Skin
Color
Fuzzy sets
Classifiers
Neural networks

Keywords

  • Asymmetric blotches
  • Dermoscopy
  • Fuzzy logic
  • Image analysis
  • Malignant melanoma
  • Neural network

ASJC Scopus subject areas

  • Radiology Nuclear Medicine and imaging
  • Health Informatics
  • Radiological and Ultrasound Technology
  • Computer Graphics and Computer-Aided Design
  • Computer Vision and Pattern Recognition

Cite this

Khan, A., Gupta, K., Stanley, R. J., Stoecker, W. V., Moss, R. H., Argenziano, G., ... Cognetta, A. B. (2009). Fuzzy logic techniques for blotch feature evaluation in dermoscopy images. Computerized Medical Imaging and Graphics, 33(1), 50-57. https://doi.org/10.1016/j.compmedimag.2008.10.001

Fuzzy logic techniques for blotch feature evaluation in dermoscopy images. / Khan, Azmath; Gupta, Kapil; Stanley, R. J.; Stoecker, William V.; Moss, Randy H.; Argenziano, Giuseppe; Soyer, H. Peter; Rabinovitz, Harold S.; Cognetta, Armand B.

In: Computerized Medical Imaging and Graphics, Vol. 33, No. 1, 01.2009, p. 50-57.

Research output: Contribution to journalArticle

Khan, A, Gupta, K, Stanley, RJ, Stoecker, WV, Moss, RH, Argenziano, G, Soyer, HP, Rabinovitz, HS & Cognetta, AB 2009, 'Fuzzy logic techniques for blotch feature evaluation in dermoscopy images', Computerized Medical Imaging and Graphics, vol. 33, no. 1, pp. 50-57. https://doi.org/10.1016/j.compmedimag.2008.10.001
Khan, Azmath ; Gupta, Kapil ; Stanley, R. J. ; Stoecker, William V. ; Moss, Randy H. ; Argenziano, Giuseppe ; Soyer, H. Peter ; Rabinovitz, Harold S. ; Cognetta, Armand B. / Fuzzy logic techniques for blotch feature evaluation in dermoscopy images. In: Computerized Medical Imaging and Graphics. 2009 ; Vol. 33, No. 1. pp. 50-57.
@article{0a56259747bf43e0894369b356e4cfed,
title = "Fuzzy logic techniques for blotch feature evaluation in dermoscopy images",
abstract = "Blotches, also called structureless areas, are critical in differentiating malignant melanoma from benign lesions in dermoscopy skin lesion images. In this paper, fuzzy logic techniques are investigated for the automatic detection of blotch features for malignant melanoma discrimination. Four fuzzy sets representative of blotch size and relative and absolute blotch colors are used to extract blotchy areas from a set of dermoscopy skin lesion images. Five previously reported blotch features are computed from the extracted blotches as well as four new features. Using a neural network classifier, malignant melanoma discrimination results are optimized over the range of possible alpha-cuts and compared with results using crisp blotch features. Features computed from blotches using the fuzzy logic techniques based on three plane relative color and blotch size yield the highest diagnostic accuracy of 81.2{\%}.",
keywords = "Asymmetric blotches, Dermoscopy, Fuzzy logic, Image analysis, Malignant melanoma, Neural network",
author = "Azmath Khan and Kapil Gupta and Stanley, {R. J.} and Stoecker, {William V.} and Moss, {Randy H.} and Giuseppe Argenziano and Soyer, {H. Peter} and Rabinovitz, {Harold S.} and Cognetta, {Armand B.}",
year = "2009",
month = "1",
doi = "10.1016/j.compmedimag.2008.10.001",
language = "English",
volume = "33",
pages = "50--57",
journal = "Computerized Medical Imaging and Graphics",
issn = "0895-6111",
publisher = "Elsevier Limited",
number = "1",

}

TY - JOUR

T1 - Fuzzy logic techniques for blotch feature evaluation in dermoscopy images

AU - Khan, Azmath

AU - Gupta, Kapil

AU - Stanley, R. J.

AU - Stoecker, William V.

AU - Moss, Randy H.

AU - Argenziano, Giuseppe

AU - Soyer, H. Peter

AU - Rabinovitz, Harold S.

AU - Cognetta, Armand B.

PY - 2009/1

Y1 - 2009/1

N2 - Blotches, also called structureless areas, are critical in differentiating malignant melanoma from benign lesions in dermoscopy skin lesion images. In this paper, fuzzy logic techniques are investigated for the automatic detection of blotch features for malignant melanoma discrimination. Four fuzzy sets representative of blotch size and relative and absolute blotch colors are used to extract blotchy areas from a set of dermoscopy skin lesion images. Five previously reported blotch features are computed from the extracted blotches as well as four new features. Using a neural network classifier, malignant melanoma discrimination results are optimized over the range of possible alpha-cuts and compared with results using crisp blotch features. Features computed from blotches using the fuzzy logic techniques based on three plane relative color and blotch size yield the highest diagnostic accuracy of 81.2%.

AB - Blotches, also called structureless areas, are critical in differentiating malignant melanoma from benign lesions in dermoscopy skin lesion images. In this paper, fuzzy logic techniques are investigated for the automatic detection of blotch features for malignant melanoma discrimination. Four fuzzy sets representative of blotch size and relative and absolute blotch colors are used to extract blotchy areas from a set of dermoscopy skin lesion images. Five previously reported blotch features are computed from the extracted blotches as well as four new features. Using a neural network classifier, malignant melanoma discrimination results are optimized over the range of possible alpha-cuts and compared with results using crisp blotch features. Features computed from blotches using the fuzzy logic techniques based on three plane relative color and blotch size yield the highest diagnostic accuracy of 81.2%.

KW - Asymmetric blotches

KW - Dermoscopy

KW - Fuzzy logic

KW - Image analysis

KW - Malignant melanoma

KW - Neural network

UR - http://www.scopus.com/inward/record.url?scp=57449101617&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=57449101617&partnerID=8YFLogxK

U2 - 10.1016/j.compmedimag.2008.10.001

DO - 10.1016/j.compmedimag.2008.10.001

M3 - Article

C2 - 19027266

AN - SCOPUS:57449101617

VL - 33

SP - 50

EP - 57

JO - Computerized Medical Imaging and Graphics

JF - Computerized Medical Imaging and Graphics

SN - 0895-6111

IS - 1

ER -