Multi-class multi-level classification algorithm for skin lesions classification using machine learning techniques

Nazia Hameed, Antesar M. Shabut, Miltu K. Ghosh, M.A. Hossain

Research output: Contribution to journalArticle

Abstract

Skin diseases remain a major cause of disability worldwide and contribute approximately 1.79% of the global burden of disease measured in disability-adjusted life years. In the United Kingdom alone, 60% of the population suffer from skin diseases during their lifetime. In this paper, we propose an intelligent digital diagnosis scheme to improve the classification accuracy of multiple diseases. A Multi-Class Multi-Level (MCML) classification algorithm inspired by the “divide and conquer” rule is explored to address the research challenges. The MCML classification algorithm is implemented using traditional machine learning and advanced deep learning approaches. Improved techniques are proposed for noise removal in the traditional machine learning approach. The proposed algorithm is evaluated on 3672 classified images, collected from different sources and the diagnostic accuracy of 96.47% is achieved. To verify the performance of the proposed algorithm, its metrics are compared with the Multi-Class Single-Level classification algorithm which is the main algorithm used in most of the existing literature. The results also indicate that the MCML classification algorithm is capable of enhancing the classification performance of multiple skin lesions.
Original languageEnglish
Article number112961
JournalExpert Systems with Applications
Volume141
Early online date18 Sep 2019
DOIs
Publication statusE-pub ahead of print - 18 Sep 2019

Fingerprint

Learning systems
Skin

Cite this

@article{115cd447caa04c308155ee8ceb419ff3,
title = "Multi-class multi-level classification algorithm for skin lesions classification using machine learning techniques",
abstract = "Skin diseases remain a major cause of disability worldwide and contribute approximately 1.79{\%} of the global burden of disease measured in disability-adjusted life years. In the United Kingdom alone, 60{\%} of the population suffer from skin diseases during their lifetime. In this paper, we propose an intelligent digital diagnosis scheme to improve the classification accuracy of multiple diseases. A Multi-Class Multi-Level (MCML) classification algorithm inspired by the “divide and conquer” rule is explored to address the research challenges. The MCML classification algorithm is implemented using traditional machine learning and advanced deep learning approaches. Improved techniques are proposed for noise removal in the traditional machine learning approach. The proposed algorithm is evaluated on 3672 classified images, collected from different sources and the diagnostic accuracy of 96.47{\%} is achieved. To verify the performance of the proposed algorithm, its metrics are compared with the Multi-Class Single-Level classification algorithm which is the main algorithm used in most of the existing literature. The results also indicate that the MCML classification algorithm is capable of enhancing the classification performance of multiple skin lesions.",
author = "Nazia Hameed and Shabut, {Antesar M.} and Ghosh, {Miltu K.} and M.A. Hossain",
year = "2019",
month = "9",
day = "18",
doi = "10.1016/j.eswa.2019.112961",
language = "English",
volume = "141",
journal = "Expert Systems With Applications.",
issn = "0957-4174",
publisher = "Elsevier",

}

Multi-class multi-level classification algorithm for skin lesions classification using machine learning techniques. / Hameed, Nazia; Shabut, Antesar M.; Ghosh, Miltu K.; Hossain, M.A.

In: Expert Systems with Applications, Vol. 141, 112961, 01.03.2020.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Multi-class multi-level classification algorithm for skin lesions classification using machine learning techniques

AU - Hameed, Nazia

AU - Shabut, Antesar M.

AU - Ghosh, Miltu K.

AU - Hossain, M.A.

PY - 2019/9/18

Y1 - 2019/9/18

N2 - Skin diseases remain a major cause of disability worldwide and contribute approximately 1.79% of the global burden of disease measured in disability-adjusted life years. In the United Kingdom alone, 60% of the population suffer from skin diseases during their lifetime. In this paper, we propose an intelligent digital diagnosis scheme to improve the classification accuracy of multiple diseases. A Multi-Class Multi-Level (MCML) classification algorithm inspired by the “divide and conquer” rule is explored to address the research challenges. The MCML classification algorithm is implemented using traditional machine learning and advanced deep learning approaches. Improved techniques are proposed for noise removal in the traditional machine learning approach. The proposed algorithm is evaluated on 3672 classified images, collected from different sources and the diagnostic accuracy of 96.47% is achieved. To verify the performance of the proposed algorithm, its metrics are compared with the Multi-Class Single-Level classification algorithm which is the main algorithm used in most of the existing literature. The results also indicate that the MCML classification algorithm is capable of enhancing the classification performance of multiple skin lesions.

AB - Skin diseases remain a major cause of disability worldwide and contribute approximately 1.79% of the global burden of disease measured in disability-adjusted life years. In the United Kingdom alone, 60% of the population suffer from skin diseases during their lifetime. In this paper, we propose an intelligent digital diagnosis scheme to improve the classification accuracy of multiple diseases. A Multi-Class Multi-Level (MCML) classification algorithm inspired by the “divide and conquer” rule is explored to address the research challenges. The MCML classification algorithm is implemented using traditional machine learning and advanced deep learning approaches. Improved techniques are proposed for noise removal in the traditional machine learning approach. The proposed algorithm is evaluated on 3672 classified images, collected from different sources and the diagnostic accuracy of 96.47% is achieved. To verify the performance of the proposed algorithm, its metrics are compared with the Multi-Class Single-Level classification algorithm which is the main algorithm used in most of the existing literature. The results also indicate that the MCML classification algorithm is capable of enhancing the classification performance of multiple skin lesions.

UR - http://www.scopus.com/inward/record.url?scp=85072713000&partnerID=8YFLogxK

U2 - 10.1016/j.eswa.2019.112961

DO - 10.1016/j.eswa.2019.112961

M3 - Article

VL - 141

JO - Expert Systems With Applications.

JF - Expert Systems With Applications.

SN - 0957-4174

M1 - 112961

ER -