Manuscript received November 27, 2024; accepted February 12, 2025; published April 24, 2025
Abstract—Melanoma, a severe kind of skin cancer, requires early identification to enhance patient outcomes. This paper describes a unique approach to melanoma diagnosis that combines image processing techniques with deep learning methodologies. This paper provides a method for analyzing skin lesion photos that uses a mix of color, texture, and form factors, followed by classification using a convolutional neural network. Using a publicly accessible collection of skin lesion photos, this method obtained a 93% accuracy in differentiating between malignant and benign lesions. These positive findings suggest that this study approach has the potential to considerably benefit dermatologists in the early detection of melanoma, improving treatment outcomes and patient survival.
Keywords—dermatology, melanoma, skin cancer, machine learning, Gaussian mixture model, backpropagation neural network, integrated development environment
Cite: Pooja Illangarathne, Nethari Jayasinghe, Sharith Rodrigo, Kanishka Hewageegana, and Prasad Wimalaratne, "Melanoma Detection Using Convolutional Neural Network," International Journal of Machine Learning vol. 15, no. 2, pp. 34-39, 2025.
Copyright © 2025 by the authors. This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited (CC BY 4.0).