Citation

Al Huda, Md Sadi and Ali, Md. Asraf and Hossain, Ajran and Tuz Johora, Fatama and Liew, Tze Hui and Sadib, Ridwan Jamal and Hossen, Md. Jakir and Ahmed, Nasim (2024) Enhancing Early Detection of Melanoma: A Deep Learning Approach for Skin Cancer Prediction. JOIV : International Journal on Informatics Visualization, 8 (3-2). pp. 1772-1778. ISSN 2549-9610

Text 3081-9087-1-PB.pdf - Published Version Restricted to Repository staff only Download (3MB)

Abstract

Melanoma, a form of skin cancer, is a substantial global public health threat due to its rising prevalence and the potential for severe outcomes if not promptly identified and managed. Detecting skin cancer lesions in their first stages enhances patient outcomes and decreases mortality rates. The core issue investigated in this research paper is the enduring problem of early skin cancer prediction. In the past, individuals often lacked awareness of their skin cancer condition until it had reached late stages. Consequently, this resulted in delayed diagnoses, which restricted the available treatment options and perhaps led to worse outcomes. This research focuses on finding key attributes and methods in a specialized dataset to effectively differentiate between benign and potentially malignant skin lesions, particularly the implementation of an early-stage skin cancer prediction model. It aims to accurately categorize skin mole pictures as benign or malignant using a Convolutional Neural Network (CNN) model built within the PyTorch framework. The primary aim of this study was to enhance the accuracy and effectiveness of diagnosing skin problems by implementing deep learning algorithms to automate the process of showing such conditions. The model underwent training using 3600 skin mole images sourced from the ISIC-Archive on a GPU RTX 3080. Its outstanding performance is shown by an F1 score of 0.8496 and an accuracy rate of 85%. This research aims to create a predictive model and offer a practical solution that healthcare professionals can readily use for early skin cancer prediction.

Item Type:	Article
Uncontrolled Keywords:	Deep learning; CNN, PyTorch; early detection; malignancy prediction; skin cancer; automated diagnosis.
Subjects:	R Medicine > RC Internal medicine > RC71-78.7 Examination. Diagnosis
Divisions:	Faculty of Information Science and Technology (FIST)
Depositing User:	Ms Nurul Iqtiani Ahmad
Date Deposited:	03 Jan 2025 04:12
Last Modified:	03 Jan 2025 04:12
URII:	http://shdl.mmu.edu.my/id/eprint/13283

Downloads

Edit (login required)