Skin cancer has high incidence and fatality rates, making accurate and rapid detection crucial. This study developed a web-based skin cancer detection system using YOLOv8. The model detects seven types of skin cancer using a dataset of 17.366 annotated images. Methods included data collection, pre-processing, augmentation, model training, and performance evaluation using precision, recall, and mean Average Precision (mAP). Results show that the YOLOv8 model achieved a precision of 0.975 and a recall of 0.969. Evaluation with a confusion matrix demonstrated strong detection capabilities. A web interface was developed to allow users to upload images and view detection results in real-time. The YOLOv8-based skin cancer detection system provides accurate results and can be used as a tool for early diagnosis.
