Automated Detection of Melanoma Through Dermoscopic Image Analysis

Chavez H.; Trujillo C.S.H.; Huaman K.G.; Zapata G.; Raymundo C. · Studies in Systems, Decision and Control (2026) · DOI: 10.1007/978-3-031-85398-2_64

Resumen

Currently, skin diseases are a public health challenge due to their prevalence and the difficulty in detecting and differentiating certain conditions. One of them is melanoma, which is a type of skin cancer, on the other hand, there is nevus and seborrheic keratosis, which are generally benign conditions, however, these can be confused with each other. In this context, this study presents an automated system to detect and classify between these three skin conditions using artificial intelligence techniques applied to dermoscopic images. To evaluate the performance of the model, metrics such as precision and accuracy were used, obtaining an accuracy of 79.1%. These results demonstrate that artificial intelligence has great potential as a support tool for dermatology professionals, allowing a rapid and precise detection of these skin conditions. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2026.

Instituciones: Universidad Peruana de Ciencias Aplicadas