<![CDATA[Skin cancer is one of the most prevalent types of cancer worldwide, requiring early detection for effective treatment and improved patient outcomes. Traditional diagnostic methods, such as biopsies, are time-consuming, costly, and uncomfortable for patients. In response to these challenges, this study systematically reviews the application of Convolutional Neural Networks (CNNs) in automated skin cancer diagnosis using dermatoscopic images. CNNs have demonstrated remarkable performance in image processing tasks due to their ability to extract complex features and ensure high classification accuracy. This review analyzes various CNN architectures, such as GoogLeNet, ResNet, and YOLOv8, in terms of their effectiveness in distinguishing between benign and malignant skin lesions. Results from existing literature indicate that CNN-based systems achieve an accuracy of up to 97.73%, making them a promising solution for automated diagnostic tools. The findings emphasize the importance of data augmentation, parameter optimization, and diverse datasets to improve model generalizability. This study concludes that integrating CNN-based diagnostic systems with clinical workflows has significant potential to enhance early detection, optimize medical resources, and raise public awareness of skin cancer prevention]]>
Copyrights © 2024
