Fuzzy logic color detection: Blue areas in melanoma dermoscopy images

Mounika Lingala; R. Joe Stanley; Ryan K. Rader; Jason Hagerty; Harold S. Rabinovitz; Margaret Oliviero; Iqra Choudhry; William V. Stoecker

doi:10.1016/j.compmedimag.2014.03.007

Fuzzy logic color detection: Blue areas in melanoma dermoscopy images

Mounika Lingala, R. Joe Stanley, Ryan K. Rader, Jason Hagerty, Harold S. Rabinovitz, Margaret Oliviero, Iqra Choudhry, William V. Stoecker

Research output: Contribution to journal › Article › peer-review

28 Scopus citations

Abstract

Fuzzy logic image analysis techniques were used to analyze three shades of blue (lavender blue, light blue, and dark blue) in dermoscopic images for melanoma detection. A logistic regression model provided up to 82.7% accuracy for melanoma discrimination for 866 images. With a support vector machines (SVM) classifier, lower accuracy was obtained for individual shades (79.9-80.1%) compared with up to 81.4% accuracy with multiple shades. All fuzzy blue logic alpha cuts scored higher than the crisp case. Fuzzy logic techniques applied to multiple shades of blue can assist in melanoma detection. These vector-based fuzzy logic techniques can be extended to other image analysis problems involving multiple colors or color shades.

Original language	English (US)
Pages (from-to)	403-410
Number of pages	8
Journal	Computerized Medical Imaging and Graphics
Volume	38
Issue number	5
DOIs	https://doi.org/10.1016/j.compmedimag.2014.03.007
State	Published - Jul 2014
Externally published	Yes

Keywords

Blue area
Dermoscopy
Dysplastic nevi
Fuzzy logic
Image analysis
Melanoma

ASJC Scopus subject areas

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

Access to Document

10.1016/j.compmedimag.2014.03.007

Cite this

@article{123d9f4e5dae457c9f23a80aeaf55556,

title = "Fuzzy logic color detection: Blue areas in melanoma dermoscopy images",

abstract = "Fuzzy logic image analysis techniques were used to analyze three shades of blue (lavender blue, light blue, and dark blue) in dermoscopic images for melanoma detection. A logistic regression model provided up to 82.7% accuracy for melanoma discrimination for 866 images. With a support vector machines (SVM) classifier, lower accuracy was obtained for individual shades (79.9-80.1%) compared with up to 81.4% accuracy with multiple shades. All fuzzy blue logic alpha cuts scored higher than the crisp case. Fuzzy logic techniques applied to multiple shades of blue can assist in melanoma detection. These vector-based fuzzy logic techniques can be extended to other image analysis problems involving multiple colors or color shades.",

keywords = "Blue area, Dermoscopy, Dysplastic nevi, Fuzzy logic, Image analysis, Melanoma",

author = "Mounika Lingala and {Joe Stanley}, R. and Rader, {Ryan K.} and Jason Hagerty and Rabinovitz, {Harold S.} and Margaret Oliviero and Iqra Choudhry and Stoecker, {William V.}",

note = "Funding Information: This publication was made possible by Grant Number SBIR R44 CA-101639-02A2 of the National Institutes of Health (NIH). ",

year = "2014",

month = jul,

doi = "10.1016/j.compmedimag.2014.03.007",

language = "English (US)",

volume = "38",

pages = "403--410",

journal = "Computerized Medical Imaging and Graphics",

issn = "0895-6111",

publisher = "Elsevier Limited",

number = "5",

}

TY - JOUR

T1 - Fuzzy logic color detection

T2 - Blue areas in melanoma dermoscopy images

AU - Lingala, Mounika

AU - Joe Stanley, R.

AU - Rader, Ryan K.

AU - Hagerty, Jason

AU - Rabinovitz, Harold S.

AU - Oliviero, Margaret

AU - Choudhry, Iqra

AU - Stoecker, William V.

N1 - Funding Information: This publication was made possible by Grant Number SBIR R44 CA-101639-02A2 of the National Institutes of Health (NIH).

PY - 2014/7

Y1 - 2014/7

N2 - Fuzzy logic image analysis techniques were used to analyze three shades of blue (lavender blue, light blue, and dark blue) in dermoscopic images for melanoma detection. A logistic regression model provided up to 82.7% accuracy for melanoma discrimination for 866 images. With a support vector machines (SVM) classifier, lower accuracy was obtained for individual shades (79.9-80.1%) compared with up to 81.4% accuracy with multiple shades. All fuzzy blue logic alpha cuts scored higher than the crisp case. Fuzzy logic techniques applied to multiple shades of blue can assist in melanoma detection. These vector-based fuzzy logic techniques can be extended to other image analysis problems involving multiple colors or color shades.

AB - Fuzzy logic image analysis techniques were used to analyze three shades of blue (lavender blue, light blue, and dark blue) in dermoscopic images for melanoma detection. A logistic regression model provided up to 82.7% accuracy for melanoma discrimination for 866 images. With a support vector machines (SVM) classifier, lower accuracy was obtained for individual shades (79.9-80.1%) compared with up to 81.4% accuracy with multiple shades. All fuzzy blue logic alpha cuts scored higher than the crisp case. Fuzzy logic techniques applied to multiple shades of blue can assist in melanoma detection. These vector-based fuzzy logic techniques can be extended to other image analysis problems involving multiple colors or color shades.

KW - Blue area

KW - Dermoscopy

KW - Dysplastic nevi

KW - Fuzzy logic

KW - Image analysis

KW - Melanoma

UR - http://www.scopus.com/inward/record.url?scp=84902104259&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84902104259&partnerID=8YFLogxK

U2 - 10.1016/j.compmedimag.2014.03.007

DO - 10.1016/j.compmedimag.2014.03.007

M3 - Article

C2 - 24786720

AN - SCOPUS:84902104259

SN - 0895-6111

VL - 38

SP - 403

EP - 410

JO - Computerized Medical Imaging and Graphics

JF - Computerized Medical Imaging and Graphics

IS - 5

ER -

Fuzzy logic color detection: Blue areas in melanoma dermoscopy images

Abstract

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this