A Smartphone Application for Skin Lesion Detection and Classification with Deep Learning Algorithms

X. Anitha Mary; Peniel Winifred; C. Suganthi Evangeline; Vinoth Babu Kumaravelu; C. Karthik; Subrata Chowdhury; Khaled Rabie; Bui Thi Thu; Vu Duong Tung

A Smartphone Application for Skin Lesion Detection and Classification with Deep Learning Algorithms

X. Anitha Mary^*, Peniel Winifred, C. Suganthi Evangeline, Vinoth Babu Kumaravelu, C. Karthik, Subrata Chowdhury, Khaled Rabie, Bui Thi Thu, Vu Duong Tung

^*Corresponding author for this work

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

1 Scopus citations

Abstract

The Skin Lesion (SL) classification has recently received a lot of attention. Because of the significant resemblance between these skin lesions, physicians spend a lot of time analyzing them. A Deep Learning (DL) based automated categorization system can help clinicians recognize the type of SL and improve the patient's health. In this research, DL approaches such as VGG-16, ResNet-50 and customized model are employed to detect the SL using a smartphone application. These models are trained on the SL classification dataset from the International Skin Imaging Collaboration (ISIC) 2019. The customized model over fits the other two models with a validation accuracy of 86.21%, whereas the validation accuracy of VGG-16 and ResNet-50 is 85.15% and 84.82%, respectively. Physicians will save time and have a higher precision rate in the automatic classification of SL utilizing DL.

Original language	English
Pages (from-to)	34-39
Number of pages	6
Journal	International Journal of Intelligent Systems and Applications in Engineering
Volume	10
Issue number	3
State	Published - Oct 2022
Externally published	Yes

Bibliographical note

Publisher Copyright:
© 2022, Ismail Saritas. All rights reserved.

Keywords

Application development
Customized model
Deep models
Skin lesion classification
Tensor Flow Lite (TFL)
Validation accuracy

ASJC Scopus subject areas

Control and Systems Engineering
Information Systems
Computer Graphics and Computer-Aided Design
Artificial Intelligence

Cite this

@article{d7562c5e5040474fa8efda619da0ff8c,

title = "A Smartphone Application for Skin Lesion Detection and Classification with Deep Learning Algorithms",

abstract = "The Skin Lesion (SL) classification has recently received a lot of attention. Because of the significant resemblance between these skin lesions, physicians spend a lot of time analyzing them. A Deep Learning (DL) based automated categorization system can help clinicians recognize the type of SL and improve the patient's health. In this research, DL approaches such as VGG-16, ResNet-50 and customized model are employed to detect the SL using a smartphone application. These models are trained on the SL classification dataset from the International Skin Imaging Collaboration (ISIC) 2019. The customized model over fits the other two models with a validation accuracy of 86.21\%, whereas the validation accuracy of VGG-16 and ResNet-50 is 85.15\% and 84.82\%, respectively. Physicians will save time and have a higher precision rate in the automatic classification of SL utilizing DL.",

keywords = "Application development, Customized model, Deep models, Skin lesion classification, Tensor Flow Lite (TFL), Validation accuracy",

author = "Mary, \{X. Anitha\} and Peniel Winifred and Evangeline, \{C. Suganthi\} and Kumaravelu, \{Vinoth Babu\} and C. Karthik and Subrata Chowdhury and Khaled Rabie and Thu, \{Bui Thi\} and Tung, \{Vu Duong\}",

year = "2022",

month = oct,

language = "English",

volume = "10",

pages = "34--39",

journal = "International Journal of Intelligent Systems and Applications in Engineering",

issn = "2147-6799",

publisher = "Auricle Global Society of Education and Research",

number = "3",

}

TY - JOUR

T1 - A Smartphone Application for Skin Lesion Detection and Classification with Deep Learning Algorithms

AU - Mary, X. Anitha

AU - Winifred, Peniel

AU - Evangeline, C. Suganthi

AU - Kumaravelu, Vinoth Babu

AU - Karthik, C.

AU - Chowdhury, Subrata

AU - Rabie, Khaled

AU - Thu, Bui Thi

AU - Tung, Vu Duong

PY - 2022/10

Y1 - 2022/10

N2 - The Skin Lesion (SL) classification has recently received a lot of attention. Because of the significant resemblance between these skin lesions, physicians spend a lot of time analyzing them. A Deep Learning (DL) based automated categorization system can help clinicians recognize the type of SL and improve the patient's health. In this research, DL approaches such as VGG-16, ResNet-50 and customized model are employed to detect the SL using a smartphone application. These models are trained on the SL classification dataset from the International Skin Imaging Collaboration (ISIC) 2019. The customized model over fits the other two models with a validation accuracy of 86.21%, whereas the validation accuracy of VGG-16 and ResNet-50 is 85.15% and 84.82%, respectively. Physicians will save time and have a higher precision rate in the automatic classification of SL utilizing DL.

AB - The Skin Lesion (SL) classification has recently received a lot of attention. Because of the significant resemblance between these skin lesions, physicians spend a lot of time analyzing them. A Deep Learning (DL) based automated categorization system can help clinicians recognize the type of SL and improve the patient's health. In this research, DL approaches such as VGG-16, ResNet-50 and customized model are employed to detect the SL using a smartphone application. These models are trained on the SL classification dataset from the International Skin Imaging Collaboration (ISIC) 2019. The customized model over fits the other two models with a validation accuracy of 86.21%, whereas the validation accuracy of VGG-16 and ResNet-50 is 85.15% and 84.82%, respectively. Physicians will save time and have a higher precision rate in the automatic classification of SL utilizing DL.

KW - Application development

KW - Customized model

KW - Deep models

KW - Skin lesion classification

KW - Tensor Flow Lite (TFL)

KW - Validation accuracy

UR - https://www.scopus.com/pages/publications/85139142901

M3 - Article

AN - SCOPUS:85139142901

SN - 2147-6799

VL - 10

SP - 34

EP - 39

JO - International Journal of Intelligent Systems and Applications in Engineering

JF - International Journal of Intelligent Systems and Applications in Engineering

IS - 3

ER -

A Smartphone Application for Skin Lesion Detection and Classification with Deep Learning Algorithms

Abstract

Bibliographical note

Keywords

ASJC Scopus subject areas

Fingerprint

Cite this