Melanoma Detection in Dermoscopic Images using Color Features

Sameena Pathan, Vatsal Aggarwal, K. Gopalakrishna Prabhu, P. C. Siddalingaswamy

Research output: Contribution to journalArticle

Abstract

Color is considered to be a major characteristic feature that is used for distinguishing benign and malignant melanocytic lesions. Most of malignant melanomas are characterized by the presence of six suspicious colors inspired from the ABCD dermoscopic rule. The presence of these suspicious colors histopathologically indicates the presence of melanin in the deeper layers of the epidermis and dermis. The objective of the proposed work is to evaluate the role of color features, a set of fifteen color features have been extracted from the region of interest to determine the role of color in malignancy detection. Further, a set of ensemble classifiers with dynamic selection techniques are used for classification of the extracted features, yielding an average accuracy of 87.5% for classifying benign and malignant lesions.

Original languageEnglish
Pages (from-to)107-115
Number of pages9
JournalBiomedical and Pharmacology Journal
Volume12
Issue number1
DOIs
Publication statusPublished - 01-03-2019

Fingerprint

Melanoma
Color
Melanins
Dermis
Epidermis
Neoplasms

All Science Journal Classification (ASJC) codes

  • Pharmacology

Cite this

Pathan, Sameena ; Aggarwal, Vatsal ; Gopalakrishna Prabhu, K. ; Siddalingaswamy, P. C. / Melanoma Detection in Dermoscopic Images using Color Features. In: Biomedical and Pharmacology Journal. 2019 ; Vol. 12, No. 1. pp. 107-115.
@article{2594c5a31cfc4762bd7ca3d99fba56fd,
title = "Melanoma Detection in Dermoscopic Images using Color Features",
abstract = "Color is considered to be a major characteristic feature that is used for distinguishing benign and malignant melanocytic lesions. Most of malignant melanomas are characterized by the presence of six suspicious colors inspired from the ABCD dermoscopic rule. The presence of these suspicious colors histopathologically indicates the presence of melanin in the deeper layers of the epidermis and dermis. The objective of the proposed work is to evaluate the role of color features, a set of fifteen color features have been extracted from the region of interest to determine the role of color in malignancy detection. Further, a set of ensemble classifiers with dynamic selection techniques are used for classification of the extracted features, yielding an average accuracy of 87.5{\%} for classifying benign and malignant lesions.",
author = "Sameena Pathan and Vatsal Aggarwal and {Gopalakrishna Prabhu}, K. and Siddalingaswamy, {P. C.}",
year = "2019",
month = "3",
day = "1",
doi = "10.13005/bpj/1619",
language = "English",
volume = "12",
pages = "107--115",
journal = "Biomedical and Pharmacology Journal",
issn = "0974-6242",
publisher = "Oriental Scientific Publishing Company",
number = "1",

}

Melanoma Detection in Dermoscopic Images using Color Features. / Pathan, Sameena; Aggarwal, Vatsal; Gopalakrishna Prabhu, K.; Siddalingaswamy, P. C.

In: Biomedical and Pharmacology Journal, Vol. 12, No. 1, 01.03.2019, p. 107-115.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Melanoma Detection in Dermoscopic Images using Color Features

AU - Pathan, Sameena

AU - Aggarwal, Vatsal

AU - Gopalakrishna Prabhu, K.

AU - Siddalingaswamy, P. C.

PY - 2019/3/1

Y1 - 2019/3/1

N2 - Color is considered to be a major characteristic feature that is used for distinguishing benign and malignant melanocytic lesions. Most of malignant melanomas are characterized by the presence of six suspicious colors inspired from the ABCD dermoscopic rule. The presence of these suspicious colors histopathologically indicates the presence of melanin in the deeper layers of the epidermis and dermis. The objective of the proposed work is to evaluate the role of color features, a set of fifteen color features have been extracted from the region of interest to determine the role of color in malignancy detection. Further, a set of ensemble classifiers with dynamic selection techniques are used for classification of the extracted features, yielding an average accuracy of 87.5% for classifying benign and malignant lesions.

AB - Color is considered to be a major characteristic feature that is used for distinguishing benign and malignant melanocytic lesions. Most of malignant melanomas are characterized by the presence of six suspicious colors inspired from the ABCD dermoscopic rule. The presence of these suspicious colors histopathologically indicates the presence of melanin in the deeper layers of the epidermis and dermis. The objective of the proposed work is to evaluate the role of color features, a set of fifteen color features have been extracted from the region of interest to determine the role of color in malignancy detection. Further, a set of ensemble classifiers with dynamic selection techniques are used for classification of the extracted features, yielding an average accuracy of 87.5% for classifying benign and malignant lesions.

UR - http://www.scopus.com/inward/record.url?scp=85064687226&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85064687226&partnerID=8YFLogxK

U2 - 10.13005/bpj/1619

DO - 10.13005/bpj/1619

M3 - Article

VL - 12

SP - 107

EP - 115

JO - Biomedical and Pharmacology Journal

JF - Biomedical and Pharmacology Journal

SN - 0974-6242

IS - 1

ER -