Melanoma Skin Cancer Detection: A Self-Supervised Deep Learning Approach

Syed Ismail A., Atif Alam Ansari, Amaan Hussain, Riyan Acharya

2025

Abstract

Early identification is essential for successful treatment outcomes because skin cancer remains one of the most prevalent and potentially deadly cancers. Using deep learning methods and the ISIC dataset, this study develops a model for automated skin lesion categorization with a focus on precisely identifying malignant types. While pre-processing techniques like data augmentation are employed to address class imbalances in the dataset, convolutional neural networks (CNNs) serve as the foundation for the model architecture. The system’s performance was assessed using metrics such as F1-score, recall, accuracy, and precision; the results demonstrated that the system was successful in comparison to alternative approaches. According to the findings, deep learning may prove to be a helpful tool in dermatology, enhancing early intervention strategies in clinical settings and increasing diagnostic accuracy.

Paper Citation

in Harvard Style

A. S., Ansari A., Hussain A. and Acharya R. (2025). Melanoma Skin Cancer Detection: A Self-Supervised Deep Learning Approach. In Proceedings of the 1st International Conference on Research and Development in Information, Communication, and Computing Technologies - ICRDICCT`25; ISBN 978-989-758-777-1, SciTePress, pages 409-416. DOI: 10.5220/0013883900004919

in Bibtex Style

@conference{icrdicct`2525,
author={Syed A. and Atif Ansari and Amaan Hussain and Riyan Acharya},
title={Melanoma Skin Cancer Detection: A Self-Supervised Deep Learning Approach},
booktitle={Proceedings of the 1st International Conference on Research and Development in Information, Communication, and Computing Technologies - ICRDICCT`25},
year={2025},
pages={409-416},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013883900004919},
isbn={978-989-758-777-1},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 1st International Conference on Research and Development in Information, Communication, and Computing Technologies - ICRDICCT`25
TI - Melanoma Skin Cancer Detection: A Self-Supervised Deep Learning Approach
SN - 978-989-758-777-1
AU - A. S.
AU - Ansari A.
AU - Hussain A.
AU - Acharya R.
PY - 2025
SP - 409
EP - 416
DO - 10.5220/0013883900004919
PB - SciTePress