Automatic Skin Lesions Classification from Dermoscopic Images Employing Deep Learning

  • Pablo David Minango Negrete UNICAMP
  • Ana Carolina Borges Monteiro
  • einaldo Padilha França
  • Gabriel Gomes de Oliveira


Skin cancers are the most incidental in Brazil. Thousands of Brazilians are diagnosed annually with the disease, which occurs due to the abnormal growth of the cells that make up the skin and therefore can give rise to several types of skin cancer, being divided into two types melanoma and non-melanoma. Skin cancer which are in Brazil, represents 25% of the malignant tumors diagnosed and about 30% of the cases of cancer in Brazil, being the majority due to the excessive exposure to the sun's ultraviolet rays. Skin tumors are usually perceived more easily and when diagnosed early, they are more likely to heal. The present study is based on the development of an algorithm based on Deep Learning for the recognition of tumor in skin images. The AlexNet, which is a Deep Learning architecture is modified to attending our classification problem. The experiments are conducted through 1400 and 2400 images, after twice training with different optimizer, SGD is the better optimizer with 99.79% of accuracy and 0.0120% of loss in training, for the scenary of 2400 images.

Jan 23, 2020
How to Cite
MINANGO NEGRETE, Pablo David et al. Automatic Skin Lesions Classification from Dermoscopic Images Employing Deep Learning. SET INTERNATIONAL JOURNAL OF BROADCAST ENGINEERING, [S.l.], v. 5, p. 7, jan. 2020. ISSN 2446-9432. Available at: <>. Date accessed: 24 jan. 2021.
General Topics for Engineers (Math, Science & Engineering)