Skin cancer diagnostics: a VGGEnsemble approach

Arzmi, Mohd Hafiz and P.P. Abdul Majeed, Anwar and Musa, Rabiu Muazu and Mohd Razman, Mohd Azraai and Gan, Hong-Seng and Mohd Khairuddin, Ismail and Ab. Nasir, Ahmad Fakhri (2023) Skin cancer diagnostics: a VGGEnsemble approach. In: Deep Learning in Cancer Diagnostics. SpringerBriefs in Applied Sciences and Technology (1). Springer, Singapore, pp. 27-32. ISBN 978-981-19-8936-0

PDF (Book Chapter) - Published Version Restricted to Repository staff only Download (296kB) | Request a copy

Abstract

The human skin is the largest organ of the human body, and it is highly susceptible to lesions. This study attempts to classify two distinct classes of malignant skin cancers, i.e., Actinic Keratosis (AK) and Basal Cell Carcinoma (BCC), as well as Dermatofibroma (DF), which is benign. A total of 330 dermoscopy images were split into the 70:15:15 ratio for training, testing and validation, respectively. Different VGG-Logistic Regression (LR) pipelines, i.e., VGG16-LR and VGG19-LR, were formulated. In addition, the effect of combining the features extracted from both VGG models, dubbed as VGGEnsemble, was also investigated. It was demonstrated from the study that the ensemble model yielded a better classification accuracy than its standalone versions. Therefore, it could be concluded that the performance of the pipeline is improved through this approach and subsequently could aid the diagnostics of different types of skin diseases by dermatologists.

Item Type:	Book Chapter
Uncontrolled Keywords:	Computer-Aided diagnosis; Skin cancer; VGG16; VGG19; Ensemble
Subjects:	R Medicine > R Medicine (General)
Kulliyyahs/Centres/Divisions/Institutes (Can select more than one option. Press CONTROL button):	Kulliyyah of Dentistry > Department of Fundamental Dental and Medical Sciences Kulliyyah of Dentistry
Depositing User:	AP Ts Dr Mohd Hafiz Arzmi
Date Deposited:	09 Mar 2023 14:26
Last Modified:	09 Mar 2023 14:26
URI:	http://irep.iium.edu.my/id/eprint/103899

Actions (login required)

View Item