Melanoma and nevus classification based on asymmetry, border, color, and GLCM texture parameters using deep learning algorithm

Theodore Gautama Chandra; Aulia M.T. Nasution; Iwan Cony Setiadi

doi:10.1063/1.5139389

Melanoma and nevus classification based on asymmetry, border, color, and GLCM texture parameters using deep learning algorithm

Theodore Gautama Chandra^*, Aulia M.T. Nasution, Iwan Cony Setiadi

^*Corresponding author for this work

Institut Teknologi Sepuluh Nopember

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

4 Citations (Scopus)

Abstract

Pattern analysis has been shown to have higher reliability for melanoma and nevus classification. The ABCD method, which is common to be used as a melanoma diagnosis method, has been shown to have inappropriate weighting for each parameter. In addition, pattern analysis has been shown to have a higher success for diagnosing melanoma. In this paper, we choose the Grey Level Co-occurrence Matrix (GLCM) as a texture parameter to represent the pattern of melanoma. We also choose Deep Neural Network (DNN) to retrieve information from the data set. DNN has the capability of analyzing data with a high level of abstraction. Therefore, we choose DNN as a method to classify melanoma and nevus. We use the International Skin Imaging Collaboration (ISIC) archive database as our training and validation data. We use 773 nevi with 870 melanoma images as training data and separate 200 Nevus and 200 Melanoma images as validation data. We achieve 81.75% diagnostic accuracy, 75.5% sensitivity, and 88% specificity.

Original language	English
Title of host publication	4th Biomedical Engineering''s Recent Progress in Biomaterials, Drugs Development, Health, and Medical Devices
Subtitle of host publication	Proceedings of the International Symposium of Biomedical Engineering, ISBE 2019
Editors	Kenny Lischer, Tomy Abuzairi, Siti Fauziyah Rahman, Misri Gozan
Publisher	American Institute of Physics Inc.
ISBN (Electronic)	9780735419445
DOIs	https://doi.org/10.1063/1.5139389
Publication status	Published - 10 Dec 2019
Event	4th International Symposium of Biomedical Engineering�s Recent Progress in Biomaterials, Drugs Development, Health, and Medical Devices, ISBE 2019 - Padang, West Sumatera, Indonesia Duration: 22 Jul 2019 → 24 Jul 2019

Publication series

Name	AIP Conference Proceedings
Volume	2193
ISSN (Print)	0094-243X
ISSN (Electronic)	1551-7616

Conference

Conference	4th International Symposium of Biomedical Engineering�s Recent Progress in Biomaterials, Drugs Development, Health, and Medical Devices, ISBE 2019
Country/Territory	Indonesia
City	Padang, West Sumatera
Period	22/07/19 → 24/07/19

Keywords

Asymmetry
Border
Classification
Color
Deep Neural Network
GLCM Texture
Melanoma
Nevus

Access to Document

10.1063/1.5139389

Cite this

Chandra, T. G., Nasution, A. M. T., & Setiadi, I. C. (2019). Melanoma and nevus classification based on asymmetry, border, color, and GLCM texture parameters using deep learning algorithm. In K. Lischer, T. Abuzairi, S. F. Rahman, & M. Gozan (Eds.), 4th Biomedical Engineering''s Recent Progress in Biomaterials, Drugs Development, Health, and Medical Devices: Proceedings of the International Symposium of Biomedical Engineering, ISBE 2019 Article 050016 (AIP Conference Proceedings; Vol. 2193). American Institute of Physics Inc.. https://doi.org/10.1063/1.5139389

Chandra, Theodore Gautama ; Nasution, Aulia M.T. ; Setiadi, Iwan Cony. / Melanoma and nevus classification based on asymmetry, border, color, and GLCM texture parameters using deep learning algorithm. 4th Biomedical Engineering''s Recent Progress in Biomaterials, Drugs Development, Health, and Medical Devices: Proceedings of the International Symposium of Biomedical Engineering, ISBE 2019. editor / Kenny Lischer ; Tomy Abuzairi ; Siti Fauziyah Rahman ; Misri Gozan. American Institute of Physics Inc., 2019. (AIP Conference Proceedings).

@inproceedings{f9bb8e093b5842bcaa40b290689f4148,

title = "Melanoma and nevus classification based on asymmetry, border, color, and GLCM texture parameters using deep learning algorithm",

abstract = "Pattern analysis has been shown to have higher reliability for melanoma and nevus classification. The ABCD method, which is common to be used as a melanoma diagnosis method, has been shown to have inappropriate weighting for each parameter. In addition, pattern analysis has been shown to have a higher success for diagnosing melanoma. In this paper, we choose the Grey Level Co-occurrence Matrix (GLCM) as a texture parameter to represent the pattern of melanoma. We also choose Deep Neural Network (DNN) to retrieve information from the data set. DNN has the capability of analyzing data with a high level of abstraction. Therefore, we choose DNN as a method to classify melanoma and nevus. We use the International Skin Imaging Collaboration (ISIC) archive database as our training and validation data. We use 773 nevi with 870 melanoma images as training data and separate 200 Nevus and 200 Melanoma images as validation data. We achieve 81.75% diagnostic accuracy, 75.5% sensitivity, and 88% specificity.",

keywords = "Asymmetry, Border, Classification, Color, Deep Neural Network, GLCM Texture, Melanoma, Nevus",

author = "Chandra, {Theodore Gautama} and Nasution, {Aulia M.T.} and Setiadi, {Iwan Cony}",

note = "Publisher Copyright: {\textcopyright} 2019 Author(s).; 4th International Symposium of Biomedical Engineering�s Recent Progress in Biomaterials, Drugs Development, Health, and Medical Devices, ISBE 2019 ; Conference date: 22-07-2019 Through 24-07-2019",

year = "2019",

month = dec,

day = "10",

doi = "10.1063/1.5139389",

language = "English",

series = "AIP Conference Proceedings",

publisher = "American Institute of Physics Inc.",

editor = "Kenny Lischer and Tomy Abuzairi and Rahman, {Siti Fauziyah} and Misri Gozan",

booktitle = "4th Biomedical Engineering''s Recent Progress in Biomaterials, Drugs Development, Health, and Medical Devices",

}

Chandra, TG, Nasution, AMT & Setiadi, IC 2019, Melanoma and nevus classification based on asymmetry, border, color, and GLCM texture parameters using deep learning algorithm. in K Lischer, T Abuzairi, SF Rahman & M Gozan (eds), 4th Biomedical Engineering''s Recent Progress in Biomaterials, Drugs Development, Health, and Medical Devices: Proceedings of the International Symposium of Biomedical Engineering, ISBE 2019., 050016, AIP Conference Proceedings, vol. 2193, American Institute of Physics Inc., 4th International Symposium of Biomedical Engineering�s Recent Progress in Biomaterials, Drugs Development, Health, and Medical Devices, ISBE 2019, Padang, West Sumatera, Indonesia, 22/07/19. https://doi.org/10.1063/1.5139389

Melanoma and nevus classification based on asymmetry, border, color, and GLCM texture parameters using deep learning algorithm. / Chandra, Theodore Gautama; Nasution, Aulia M.T.; Setiadi, Iwan Cony.
4th Biomedical Engineering''s Recent Progress in Biomaterials, Drugs Development, Health, and Medical Devices: Proceedings of the International Symposium of Biomedical Engineering, ISBE 2019. ed. / Kenny Lischer; Tomy Abuzairi; Siti Fauziyah Rahman; Misri Gozan. American Institute of Physics Inc., 2019. 050016 (AIP Conference Proceedings; Vol. 2193).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Melanoma and nevus classification based on asymmetry, border, color, and GLCM texture parameters using deep learning algorithm

AU - Chandra, Theodore Gautama

AU - Nasution, Aulia M.T.

AU - Setiadi, Iwan Cony

PY - 2019/12/10

Y1 - 2019/12/10

N2 - Pattern analysis has been shown to have higher reliability for melanoma and nevus classification. The ABCD method, which is common to be used as a melanoma diagnosis method, has been shown to have inappropriate weighting for each parameter. In addition, pattern analysis has been shown to have a higher success for diagnosing melanoma. In this paper, we choose the Grey Level Co-occurrence Matrix (GLCM) as a texture parameter to represent the pattern of melanoma. We also choose Deep Neural Network (DNN) to retrieve information from the data set. DNN has the capability of analyzing data with a high level of abstraction. Therefore, we choose DNN as a method to classify melanoma and nevus. We use the International Skin Imaging Collaboration (ISIC) archive database as our training and validation data. We use 773 nevi with 870 melanoma images as training data and separate 200 Nevus and 200 Melanoma images as validation data. We achieve 81.75% diagnostic accuracy, 75.5% sensitivity, and 88% specificity.

AB - Pattern analysis has been shown to have higher reliability for melanoma and nevus classification. The ABCD method, which is common to be used as a melanoma diagnosis method, has been shown to have inappropriate weighting for each parameter. In addition, pattern analysis has been shown to have a higher success for diagnosing melanoma. In this paper, we choose the Grey Level Co-occurrence Matrix (GLCM) as a texture parameter to represent the pattern of melanoma. We also choose Deep Neural Network (DNN) to retrieve information from the data set. DNN has the capability of analyzing data with a high level of abstraction. Therefore, we choose DNN as a method to classify melanoma and nevus. We use the International Skin Imaging Collaboration (ISIC) archive database as our training and validation data. We use 773 nevi with 870 melanoma images as training data and separate 200 Nevus and 200 Melanoma images as validation data. We achieve 81.75% diagnostic accuracy, 75.5% sensitivity, and 88% specificity.

KW - Asymmetry

KW - Border

KW - Classification

KW - Color

KW - Deep Neural Network

KW - GLCM Texture

KW - Melanoma

KW - Nevus

UR - http://www.scopus.com/inward/record.url?scp=85076718715&partnerID=8YFLogxK

U2 - 10.1063/1.5139389

DO - 10.1063/1.5139389

M3 - Conference contribution

AN - SCOPUS:85076718715

T3 - AIP Conference Proceedings

BT - 4th Biomedical Engineering''s Recent Progress in Biomaterials, Drugs Development, Health, and Medical Devices

A2 - Lischer, Kenny

A2 - Abuzairi, Tomy

A2 - Rahman, Siti Fauziyah

A2 - Gozan, Misri

PB - American Institute of Physics Inc.

T2 - 4th International Symposium of Biomedical Engineering�s Recent Progress in Biomaterials, Drugs Development, Health, and Medical Devices, ISBE 2019

Y2 - 22 July 2019 through 24 July 2019

ER -

Chandra TG, Nasution AMT , Setiadi IC. Melanoma and nevus classification based on asymmetry, border, color, and GLCM texture parameters using deep learning algorithm. In Lischer K, Abuzairi T, Rahman SF, Gozan M, editors, 4th Biomedical Engineering''s Recent Progress in Biomaterials, Drugs Development, Health, and Medical Devices: Proceedings of the International Symposium of Biomedical Engineering, ISBE 2019. American Institute of Physics Inc. 2019. 050016. (AIP Conference Proceedings). doi: 10.1063/1.5139389

Melanoma and nevus classification based on asymmetry, border, color, and GLCM texture parameters using deep learning algorithm

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this