An Optimized Convolutional Neural Network for Classification of Melanoma Skin Cancer
International Journal of Research · 25.05.2026 · 279
DOI: 10.26643/ijr/73 ↗Kurz gefasst
Fachartikel in der Zeitschrift International Journal of Research, online erschienen am 25.05.2026. Verfasst von Jibrin Attahiru Abdullahi und 2 weiteren Autor:innen.
Abstract (Originalsprache)
Melanoma is the most lethal form of skin cancer, responsible for approximately 75% of all skin cancer-related deaths despite representing only 4% of all skin cancer cases. Early and accurate detection is critical to improving patient survival rates. This study proposes an optimized deep learning framework for the automated classification of melanoma and other skin lesion types using dermoscopic images from the ISIC 2019 dataset (HAM10000). Three convolutional neural network (CNN) architectures, namely ResNet50, VGG16, and VGG19, were implemented via transfer learning and fine-tuned using two metaheuristic optimization algorithms: the Genetic Algorithm (GA) and the Grey Wolf Optimizer (GWO).
Zitieren
APA
Abdullahi, J. A., Da'u, A., & Adamu, A. (2026). An Optimized Convolutional Neural Network for Classification of Melanoma Skin Cancer. International Journal of Research, 279. https://doi.org/10.26643/ijr/73
Vancouver
Abdullahi JA, Da'u A, Adamu A. An Optimized Convolutional Neural Network for Classification of Melanoma Skin Cancer. International Journal of Research. 2026:279. doi:10.26643/ijr/73
BibTeX
@article{Abdullahi2026,
author = {Abdullahi, Jibrin Attahiru and Da'u, Aminu and Adamu, Aminu},
title = {An Optimized Convolutional Neural Network for Classification of Melanoma Skin Cancer},
journal = {International Journal of Research},
year = {2026},
pages = {279},
doi = {10.26643/ijr/73}
}
EUVIMED