<![CDATA[Skin cancer, particularly melanoma, is a serious global health issue due to its aggressive nature and rising incidence. Early and accurate detection is essential to improve patient outcomes, and recent advances in machine learning (ML) and deep learning (DL) offer promising solutions through automated analysis of dermoscopic images. This systematic literature review evaluates the performance of ML-based models, the impact of data augmentation techniques, and the effectiveness of various algorithms using public datasets. The findings show that convolutional neural networks (CNNs) dominate current approaches, with many models achieving high accuracy—especially when enhanced with hybrid or ensemble methods. Data augmentation techniques such as rotation, flipping, and brightness adjustment were found to improve model robustness and generalizability.]]>
Copyrights © 2025
