NevusCheck: A Dysplastic Nevi Detection Model Using Convolutional Neural Networks †

• Autores: Ingaroca-Torres, Andreluis, Heredia-Moscoso, Lucía, Aures-García, Alvaro
• Formato: artículo
• Fecha de Publicación: 2025
• Institución: Universidad Peruana de Ciencias Aplicadas
• Repositorio: UPC-Institucional
• Lenguaje: inglés
• OAI Identifier: oai:repositorioacademico.upc.edu.pe:10757/684677
• Enlace del recurso: https://doi.org/10.3390/engproc2025083011; http://hdl.handle.net/10757/684677
• Nivel de acceso: acceso abierto
• Materia: convolutional neural networks; deep learning; dysplastic nevus; image classification; melanoma; skin cancer; skin lesion; https://purl.org/pe-repo/ocde/ford#3.00.00

Dysplastic nevi are skin lesions that have distinctive clinical features and are considered risk markers for the development of melanoma, the deadliest type of skin cancer. A specific deep learning technique to identify diseases is convolutional neural networks (CNNs) because of their great capacity to extract features and classify objects. Therefore, the research aims to develop a model to diagnose dysplastic nevi using a deep learning network whose classification is based on the pre-trained architecture EfficientNet-B7, which was selected for its high classification accuracy and low computational complexity. As for the results obtained, an accuracy of 78.33% was achieved in the classification model. Also, the degree of similarity between the detection by a dermatology expert and the proposed model reached an accuracy of 79.69%.