This paper demonstrates that it is possible to approach the skin lesion classification problem as
a detection problem, a much more complex and interesting problem, by training a deep neural
network based detection architecture and applying image processing techniques to a dermatology
dataset as part of the data augmentation strategy with satisfactory and promising results. The
image dataset used in the experiments comes from the ISIC Dermoscopic Archive, an openaccess dermatology repository. In particular, the ISIC 2017 dataset, a subset of the ISIC archive,
released for the annual ISIC challenge was used. We show that it is possible to adapt a high
quality imaging dataset to the requirements demanded by a deep learning detection architecture
such as YOLOv3. In conjunction with image processing techniques as a previous step, the deep
neural network was successfully trained to identify and locate three different types of skin lesions
in real-time.