<![CDATA[Skin cancer is a severe condition characterized by the abnormal growth of skin cells, often triggered by ultraviolet exposure and genetic factors. Early detection of skin cancer is essential for improving patient recovery rates, given the high incidence and significant impact of the disease. This study aims to develop a skin cancer classification system using the Convolutional Neural Network (CNN) method with the VGG-16 architecture, known for its effectiveness in medical image analysis. The CNN method was chosen because it can extract complex features from images. At the same time, the VGG-16 architecture was selected for its depth and ability to capture fine details in images—critical for distinguishing between types of skin cancer. The dataset was sourced from the ISIC platform and optimized through data augmentation techniques to address data imbalance issues. The research results indicate that while a basic CNN can provide good accuracy, implementing the VGG-16 architecture significantly increases accuracy. The basic CNN model achieved a training accuracy of 95.68% and a validation accuracy of 89.83%, whereas the CNN with VGG-16 reached a training accuracy of 96.21% and a validation accuracy of 90.89%. These findings suggest that combining CNN with VGG-16 effectively detects skin cancer, with VGG-16 providing a slight accuracy improvement, highlighting this architecture's potential as a more accurate tool to support skin cancer diagnosis.]]>
Copyrights © 2024
