Skin cancer classification model based on VGG 19 and transfer learning

Nour Aburaed; Alavikunhu Panthakkan; Mina Al-Saad; Saad Ali Amin; Wathiq Mansoor

doi:10.1109/ICSPIS51252.2020.9340143

Skin cancer classification model based on VGG 19 and transfer learning

Nour Aburaed, Alavikunhu Panthakkan, Mina Al-Saad, Saad Ali Amin, Wathiq Mansoor

Electronic And Electrical Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution book

44 Citations (Scopus)

1089 Downloads (Pure)

Abstract

Skin cancer is a concerning health issue with yearly increasing numbers. Detecting and classifying cancer type is problematic, especially since patients have to undergo several diagnosis over lengthy periods of time, which hinders early treatment and survival chances. With the aid of digital image processing, features can be extracted to identify skin cancer and its different types. Convolutional Neural Networks (CNNs) recently emerged as powerful autonomous feature extractors, and they have high potential to achieve high accuracy with skin cancer diagnosis. In this paper, two cancer types in addition to one non-cancer type taken from Human Against Machine (HAM10000) dataset are classified using CNN model based on VGG 19 and Transfer Learning technique. The training strategy is explained, tested, and evaluated by calculating the network's overall accuracy and loss.

Original language	English
Title of host publication	3rd International Conference on Signal Processing and Information Security (ICSPIS)
Place of Publication	Piscataway, N.J.
Publisher	IEEE
Number of pages	4
ISBN (Electronic)	9781728189987
DOIs	https://doi.org/10.1109/ICSPIS51252.2020.9340143
Publication status	Published - 9 Feb 2021

Keywords

skin cancer
image classification
convolutional neural network
transfer learning
skin cancer diagnosis

UN SDGs

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

Access to Document

10.1109/ICSPIS51252.2020.9340143

Aburaed-etal-ICSPIS-2021-Skin-cancer-classification-model-based-on-VGG19Accepted author manuscript, 1.48 MBLicence: Strath_1

Cite this

@inproceedings{415e03b169a74e5b8384682ca27f544c,

title = "Skin cancer classification model based on VGG 19 and transfer learning",

abstract = "Skin cancer is a concerning health issue with yearly increasing numbers. Detecting and classifying cancer type is problematic, especially since patients have to undergo several diagnosis over lengthy periods of time, which hinders early treatment and survival chances. With the aid of digital image processing, features can be extracted to identify skin cancer and its different types. Convolutional Neural Networks (CNNs) recently emerged as powerful autonomous feature extractors, and they have high potential to achieve high accuracy with skin cancer diagnosis. In this paper, two cancer types in addition to one non-cancer type taken from Human Against Machine (HAM10000) dataset are classified using CNN model based on VGG 19 and Transfer Learning technique. The training strategy is explained, tested, and evaluated by calculating the network's overall accuracy and loss.",

keywords = "skin cancer, image classification, convolutional neural network, transfer learning, skin cancer diagnosis",

author = "Nour Aburaed and Alavikunhu Panthakkan and Mina Al-Saad and Amin, \{Saad Ali\} and Wathiq Mansoor",

year = "2021",

month = feb,

day = "9",

doi = "10.1109/ICSPIS51252.2020.9340143",

language = "English",

booktitle = "3rd International Conference on Signal Processing and Information Security (ICSPIS)",

publisher = "IEEE",

}

TY - GEN

T1 - Skin cancer classification model based on VGG 19 and transfer learning

AU - Aburaed, Nour

AU - Panthakkan, Alavikunhu

AU - Al-Saad, Mina

AU - Amin, Saad Ali

AU - Mansoor, Wathiq

PY - 2021/2/9

Y1 - 2021/2/9

N2 - Skin cancer is a concerning health issue with yearly increasing numbers. Detecting and classifying cancer type is problematic, especially since patients have to undergo several diagnosis over lengthy periods of time, which hinders early treatment and survival chances. With the aid of digital image processing, features can be extracted to identify skin cancer and its different types. Convolutional Neural Networks (CNNs) recently emerged as powerful autonomous feature extractors, and they have high potential to achieve high accuracy with skin cancer diagnosis. In this paper, two cancer types in addition to one non-cancer type taken from Human Against Machine (HAM10000) dataset are classified using CNN model based on VGG 19 and Transfer Learning technique. The training strategy is explained, tested, and evaluated by calculating the network's overall accuracy and loss.

AB - Skin cancer is a concerning health issue with yearly increasing numbers. Detecting and classifying cancer type is problematic, especially since patients have to undergo several diagnosis over lengthy periods of time, which hinders early treatment and survival chances. With the aid of digital image processing, features can be extracted to identify skin cancer and its different types. Convolutional Neural Networks (CNNs) recently emerged as powerful autonomous feature extractors, and they have high potential to achieve high accuracy with skin cancer diagnosis. In this paper, two cancer types in addition to one non-cancer type taken from Human Against Machine (HAM10000) dataset are classified using CNN model based on VGG 19 and Transfer Learning technique. The training strategy is explained, tested, and evaluated by calculating the network's overall accuracy and loss.

KW - skin cancer

KW - image classification

KW - convolutional neural network

KW - transfer learning

KW - skin cancer diagnosis

U2 - 10.1109/ICSPIS51252.2020.9340143

DO - 10.1109/ICSPIS51252.2020.9340143

M3 - Conference contribution book

BT - 3rd International Conference on Signal Processing and Information Security (ICSPIS)

PB - IEEE

CY - Piscataway, N.J.

ER -

Skin cancer classification model based on VGG 19 and transfer learning

Abstract

Keywords

UN SDGs

Access to Document

Fingerprint

Cite this