Beta
ManageSearchChatDiscover
353884

Skin Cancer Classification and Segmentation Using Deep Learning

Article

Last updated: 29 Dec 2024

OverviewSimilar Items

Subjects

-

Tags

-

Abstract

This paper integrates medical science and artificial intelligence, focusing on using convolutional neural networks (CNNs) to improve skin cancer diagnosis accuracy. Given the rising global incidence of skin cancers such as melanoma and basal cell carcinoma, this research is becoming increasingly important. This study uses the HAM10000 and PH2 datasets, which are known for their diverse skin cancer images, and employs a CNN-based approach informed by previous research findings.

The proposed methodology includes extensive preprocessing and augmentation to increase the dataset's variability, allowing for thorough training and evaluation. The CNN model, which was developed using advanced training methods and includes convolutional and pooling layers, is the result of previous research demonstrating the efficacy of CNNs in skin lesion detection. Furthermore, the U-NET-based segmentation model contributes to the comprehensive analysis by precisely delineating lesion boundaries, which improves the understanding of skin cancer. The CNN model's performance is evaluated using a variety of metrics, including accuracy, classification reports, confusion matrices, and segmentation-specific metrics like the Dice coefficient and IOU. These metrics provide valuable insights into the changing landscape of skin cancer diagnosis, allowing for the development of effective, precise, and accessible healthcare solutions in the dynamic field of dermatology.

DOI

10.21608/ijt.2024.280957.1045

Keywords

Deep learning, Computer Vision, skin cancer, Multi-class classification, segmentation

Authors

First Name

Mohamed

Last Name

Badawi

MiddleName

-

Affiliation

Department of Artificial Intelligence, College of Information Technology, Misr University for Science and Technology (MUST), 6th of October City 12566, Egyp

Email

mohammed.badawi@must.edu.eg

City

Cairo

Orcid

0000-0001-6218-160X

First Name

Rania

Last Name

Elgohary

MiddleName

-

Affiliation

Head of Information Technology College, MUST University.

Email

rania.elgohary@must.edu.eg

City

-

Orcid

-

First Name

Mostafa

Last Name

Tarek

MiddleName

-

Affiliation

Department of Artificial Intelligence, College of Information Technology, Misr University for Science and Technology (MUST).

Email

mostafat4438@gmail.com

City

-

Orcid

-

First Name

Mohamed

Last Name

EzzAlRegal

MiddleName

-

Affiliation

epartment of Artificial Intelligence, College of Information Technology, Misr University for Science and Technology (MUST).

Email

mezz7409@gmail.com

City

-

Orcid

-

First Name

Abdulrahman

Last Name

Ahmed

MiddleName

-

Affiliation

Department of Artificial Intelligence, College of Information Technology, Misr University for Science and Technology (MUST).

Email

abdulrahmn477@gmail.com

City

-

Orcid

-

First Name

Ahmed

Last Name

Samir

MiddleName

-

Affiliation

Department of Artificial Intelligence, College of Information Technology, Misr University for Science and Technology (MUST).

Email

amrsalatif@gmail.com

City

-

Orcid

-

First Name

Nour

Last Name

Ehab

MiddleName

-

Affiliation

Department of Artificial Intelligence, College of Information Technology, Misr University for Science and Technology (MUST).

Email

nourehaab21@gmail.com

City

-

Orcid

-

Volume

04

Article Issue

01

Related Issue

46031

Issue Date

2024-02-01

Receive Date

2024-04-03

Publish Date

2024-02-01

Page Start

1

Page End

23

Online ISSN

2805-3044

Article File

IJT_Volume 04_Issue 01_Pages 1-23.pdf

PDF . 2.1MB

Link

https://ijt.journals.ekb.eg/article_353884.html

Detail API

https://ijt.journals.ekb.eg/service?article_code=353884

Order

353,884

Type

Original Article

Type Code

2,522

Publication Type

Journal

Publication Title

International Journal of Telecommunications

Publication Link

https://ijt.journals.ekb.eg/

MainTitle

Skin Cancer Classification and Segmentation Using Deep Learning

Details

Type

Article

Created At

29 Dec 2024