Software for the detection of melanoma through the recognition of images and artificial neural networks

Abstract

Ingeniería en Sistemas Computacionales

The objective of this study is to develop a software that detects melanoma in nevus in a way that is automatic, easy, noninvasive, objective and at a low cost using as the basis of the analysis the “ABCDE” of lesions along with the processing of images and artificial neural networks. The software’s evaluation was made with cases previously diagnosed with malignant melanoma and with cases of suspicious moles. The evaluation showed a sensibility of 76.56% and specificity in 87.58%