Skin Cancer Classification Implementing Convolutional Neural Networks
PDF

Cómo citar

Florez Fuentes, A. S. ., Guzman Cabrera, R. ., & Vargas Rodriguez, E. . (2022). Skin Cancer Classification Implementing Convolutional Neural Networks. JÓVENES EN LA CIENCIA, 18, 1–3. Recuperado a partir de https://www.jovenesenlaciencia.ugto.mx/index.php/jovenesenlaciencia/article/view/3850

Resumen

The use of image processing to strengthen medical diagnostics in the medical field is becoming more and more common. In the dermatology area it is used to carry out the identification and monitoring of lesions caused by skin cancer. One of the most used machine learning methods in the state of the art for this problem is the convolutional neural networks. In this work we propose a methodology to perform the automatic classification of images with skin cancer corresponding to the HAM10000 database, where we work with the types of cancer Benign Keratosis, Melanoma, Melanomic Neves, the implementation of a neural network was performed, complemented with several filters to preprocess the images, obtaining results higher than 92% accuracy. The results obtained compete with those reported by several authors in the state of the art and allow us to see the feasibility of the proposed methodology.

PDF
Creative Commons License

Esta obra está bajo una licencia internacional Creative Commons Atribución-NoComercial-SinDerivadas 4.0.