SkNet: A Convolutional Neural Networks Based Classification Approach for Skin Cancer Classes

Afsana Ahsan Jeny; Abu Noman Md Sakib; Masum Shah Junayed; Khadija Akter Lima; Ikhtiar Ahmed; Md Baharul Islam

doi:10.1109/ICCIT51783.2020.9392716

SkNet: A Convolutional Neural Networks Based Classification Approach for Skin Cancer Classes

Afsana Ahsan Jeny, Abu Noman Md Sakib, Masum Shah Junayed, Khadija Akter Lima, Ikhtiar Ahmed, Md Baharul Islam

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

18 Citations (Scopus)

Abstract

Skin Cancer is one of the most common types of cancer. A solution for this globally recognized health problem is much required. Machine Learning techniques have brought revolutionary changes in the field of biomedical researches. Previously, It took a significant amount of time and much effort in detecting skin cancers. In recent years, many works have been done with Deep Learning which made the process a lot faster and much more accurate. In this paper, We have proposed a novel Convolutional Neural Networks (CNN) based approach that can classify four different types of Skin Cancer. We have developed our model SkNet consisting of 19 convolution layers. In previous works, the highest accuracy gained on 1000 images was 80.52%. Our proposed model exceeded that previous performance and achieved an accuracy of 95.26% on a dataset of 4800 images which is the highest acquired accuracy.

Original language	English
Title of host publication	ICCIT 2020 - 23rd International Conference on Computer and Information Technology, Proceedings
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9781665422444
DOIs	https://doi.org/10.1109/ICCIT51783.2020.9392716
Publication status	Published - 19 Dec 2020
Externally published	Yes
Event	23rd International Conference on Computer and Information Technology, ICCIT 2020 - Virtual, Dhaka, Bangladesh Duration: 19 Dec 2020 → 21 Dec 2020

Publication series

Name	ICCIT 2020 - 23rd International Conference on Computer and Information Technology, Proceedings

Conference

Conference	23rd International Conference on Computer and Information Technology, ICCIT 2020
Country/Territory	Bangladesh
City	Virtual, Dhaka
Period	19/12/20 → 21/12/20

Keywords

Artificial Intelligence
CNN
Classification
Deep Learning
Skin Cancer Classes

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1109/ICCIT51783.2020.9392716

Cite this

Jeny, A. A., Sakib, A. N. M., Junayed, M. S., Lima, K. A., Ahmed, I., & Islam, M. B. (2020). SkNet: A Convolutional Neural Networks Based Classification Approach for Skin Cancer Classes. In ICCIT 2020 - 23rd International Conference on Computer and Information Technology, Proceedings Article 9392716 (ICCIT 2020 - 23rd International Conference on Computer and Information Technology, Proceedings). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICCIT51783.2020.9392716

Jeny, Afsana Ahsan ; Sakib, Abu Noman Md ; Junayed, Masum Shah et al. / SkNet : A Convolutional Neural Networks Based Classification Approach for Skin Cancer Classes. ICCIT 2020 - 23rd International Conference on Computer and Information Technology, Proceedings. Institute of Electrical and Electronics Engineers Inc., 2020. (ICCIT 2020 - 23rd International Conference on Computer and Information Technology, Proceedings).

@inproceedings{3b48544a1610463c9396f7cd15424786,

title = "SkNet: A Convolutional Neural Networks Based Classification Approach for Skin Cancer Classes",

abstract = "Skin Cancer is one of the most common types of cancer. A solution for this globally recognized health problem is much required. Machine Learning techniques have brought revolutionary changes in the field of biomedical researches. Previously, It took a significant amount of time and much effort in detecting skin cancers. In recent years, many works have been done with Deep Learning which made the process a lot faster and much more accurate. In this paper, We have proposed a novel Convolutional Neural Networks (CNN) based approach that can classify four different types of Skin Cancer. We have developed our model SkNet consisting of 19 convolution layers. In previous works, the highest accuracy gained on 1000 images was 80.52%. Our proposed model exceeded that previous performance and achieved an accuracy of 95.26% on a dataset of 4800 images which is the highest acquired accuracy.",

keywords = "Artificial Intelligence, CNN, Classification, Deep Learning, Skin Cancer Classes",

author = "Jeny, {Afsana Ahsan} and Sakib, {Abu Noman Md} and Junayed, {Masum Shah} and Lima, {Khadija Akter} and Ikhtiar Ahmed and Islam, {Md Baharul}",

note = "Publisher Copyright: {\textcopyright} 2020 IEEE.; 23rd International Conference on Computer and Information Technology, ICCIT 2020 ; Conference date: 19-12-2020 Through 21-12-2020",

year = "2020",

month = dec,

day = "19",

doi = "10.1109/ICCIT51783.2020.9392716",

language = "English",

series = "ICCIT 2020 - 23rd International Conference on Computer and Information Technology, Proceedings",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

booktitle = "ICCIT 2020 - 23rd International Conference on Computer and Information Technology, Proceedings",

}

Jeny, AA, Sakib, ANM, Junayed, MS, Lima, KA, Ahmed, I & Islam, MB 2020, SkNet: A Convolutional Neural Networks Based Classification Approach for Skin Cancer Classes. in ICCIT 2020 - 23rd International Conference on Computer and Information Technology, Proceedings., 9392716, ICCIT 2020 - 23rd International Conference on Computer and Information Technology, Proceedings, Institute of Electrical and Electronics Engineers Inc., 23rd International Conference on Computer and Information Technology, ICCIT 2020, Virtual, Dhaka, Bangladesh, 19/12/20. https://doi.org/10.1109/ICCIT51783.2020.9392716

SkNet: A Convolutional Neural Networks Based Classification Approach for Skin Cancer Classes. / Jeny, Afsana Ahsan; Sakib, Abu Noman Md; Junayed, Masum Shah et al.
ICCIT 2020 - 23rd International Conference on Computer and Information Technology, Proceedings. Institute of Electrical and Electronics Engineers Inc., 2020. 9392716 (ICCIT 2020 - 23rd International Conference on Computer and Information Technology, Proceedings).

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

TY - GEN

T1 - SkNet

T2 - 23rd International Conference on Computer and Information Technology, ICCIT 2020

AU - Jeny, Afsana Ahsan

AU - Sakib, Abu Noman Md

AU - Junayed, Masum Shah

AU - Lima, Khadija Akter

AU - Ahmed, Ikhtiar

AU - Islam, Md Baharul

PY - 2020/12/19

Y1 - 2020/12/19

N2 - Skin Cancer is one of the most common types of cancer. A solution for this globally recognized health problem is much required. Machine Learning techniques have brought revolutionary changes in the field of biomedical researches. Previously, It took a significant amount of time and much effort in detecting skin cancers. In recent years, many works have been done with Deep Learning which made the process a lot faster and much more accurate. In this paper, We have proposed a novel Convolutional Neural Networks (CNN) based approach that can classify four different types of Skin Cancer. We have developed our model SkNet consisting of 19 convolution layers. In previous works, the highest accuracy gained on 1000 images was 80.52%. Our proposed model exceeded that previous performance and achieved an accuracy of 95.26% on a dataset of 4800 images which is the highest acquired accuracy.

AB - Skin Cancer is one of the most common types of cancer. A solution for this globally recognized health problem is much required. Machine Learning techniques have brought revolutionary changes in the field of biomedical researches. Previously, It took a significant amount of time and much effort in detecting skin cancers. In recent years, many works have been done with Deep Learning which made the process a lot faster and much more accurate. In this paper, We have proposed a novel Convolutional Neural Networks (CNN) based approach that can classify four different types of Skin Cancer. We have developed our model SkNet consisting of 19 convolution layers. In previous works, the highest accuracy gained on 1000 images was 80.52%. Our proposed model exceeded that previous performance and achieved an accuracy of 95.26% on a dataset of 4800 images which is the highest acquired accuracy.

KW - Artificial Intelligence

KW - CNN

KW - Classification

KW - Deep Learning

KW - Skin Cancer Classes

UR - http://www.scopus.com/inward/record.url?scp=85104556557&partnerID=8YFLogxK

U2 - 10.1109/ICCIT51783.2020.9392716

DO - 10.1109/ICCIT51783.2020.9392716

M3 - Conference contribution

AN - SCOPUS:85104556557

T3 - ICCIT 2020 - 23rd International Conference on Computer and Information Technology, Proceedings

BT - ICCIT 2020 - 23rd International Conference on Computer and Information Technology, Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

Y2 - 19 December 2020 through 21 December 2020

ER -

Jeny AA, Sakib ANM, Junayed MS, Lima KA, Ahmed I, Islam MB. SkNet: A Convolutional Neural Networks Based Classification Approach for Skin Cancer Classes. In ICCIT 2020 - 23rd International Conference on Computer and Information Technology, Proceedings. Institute of Electrical and Electronics Engineers Inc. 2020. 9392716. (ICCIT 2020 - 23rd International Conference on Computer and Information Technology, Proceedings). doi: 10.1109/ICCIT51783.2020.9392716

SkNet: A Convolutional Neural Networks Based Classification Approach for Skin Cancer Classes

Abstract

Publication series

Conference

Keywords

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this