Machine Learning Model for Early-stage Melanoma Diagnosis

• Autores: Pardo Valdivia, Flavia, Valeria Villanueva Zárate, Natalia, Aliaga Cerna, Esther
• Formato: artículo
• Fecha de Publicación: 2024
• Institución: Universidad Peruana de Ciencias Aplicadas
• Repositorio: UPC-Institucional
• Lenguaje: español
• OAI Identifier: oai:repositorioacademico.upc.edu.pe:10757/676332
• Enlace del recurso: http://hdl.handle.net/10757/676332
• Nivel de acceso: acceso embargado
• Materia: Machine Learning; Melanoma; Skin Melanoma; Support Vector Machine

There are Machine Learning (ML) algorithms for the development of recognition and classification models for medical images, aiming to facilitate access to the healthcare sector.Therefore, this paper seeks to demonstrate the effectiveness of the Support Vector Machine (SVM) algorithm for classifying skin lesion images into Melanoma and Non-Melanoma categories.With this aim, an ML model was developed and trained using the Python programming language, SVM, and images from the ISIC 2019 and ISIC 2020 repositories.For model development, training, and testing, Amazon Web Services cloud services were employed, yielding results of 0.77 precision, 0.82 recall or sensitivity, 0.80 F1-Score, and 0.76 accuracy.These effectiveness metric results exceeding 0.75 or 75% endorse the suitability of the model for medical applications in the field of image recognition and classification.