Non-dermatoscopic Image Analysis for the Recognition of Malignant Skin Diseases with Convolutional Neural Network and Autoencoders

  • Ricardo CoronadoEmail author
  • Alexander Ocsa
  • Oscar Quispe
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10657)


Every year, people around the world are affected by different skin diseases or cancer. Nowadays, these can only be detected accurately by clinical analysis and skin biopsy. However, the diagnosis of this malignant disease does not ensure the survival of the patient, since many clinical cases are detected in the terminal phases. Only early diagnosis would increase the life expectancy of patients.

In this paper, we propose a method to recognition malignant skin diseases to identify malignant lesions in non-dermatoscopic images. For the method, we use Convolutional Neural Network and propose the use of autoencoders as another classification model that provides more information on the diagnosis. Experiments show that our proposal reaches up to 84.4% of accuracy in the well-known dataset of the ISIC-2016. In addition, we collect non-dermatoscopic images of skin lesions and developed a new dataset to demonstrate the advantage of our method.


Skin cancer Convolutional Neural Networks Autoencoders Image classification 



This work has been partially funded by the Master Scholarship at the Universidad Nacional de San Agustín, which is an initiative of CITEC through a fund FONDECYT (Perú). We would like to thank research department of Instituto Nacional de Enfermedades Neoplásicas from Peru, for gently providing us his advice on the direction of this article.


  1. 1.
    Fornaciali, M., Carvalho, M., Bittencourt, F.V., de Avila, S.E.F., Valle, E.: Towards automated melanoma screening: Proper computer vision & reliable results. CoRR, abs/1604.04024 (2016)Google Scholar
  2. 2.
    Jafari, M.H., Nasr-Esfahani, E., Karimi, N., Reza Soroushmehr, S.M., Samavi, S., Najarian, K.: Extraction of skin lesions from non-dermoscopic images using deep learning. ArXiv e-prints, September 2016Google Scholar
  3. 3.
    Whited, J.D., Grichnik, J.M.: Does this patient have a mole or a melanoma? JAMA 279(9), 696–701 (1998)CrossRefGoogle Scholar
  4. 4.
    Kawahara, J., BenTaieb, A., Hamarneh, G.: Deep features to classify skin lesions. In: 2016 IEEE 13th International Symposium on Biomedical Imaging (ISBI), pp. 1397–1400, April 2016Google Scholar
  5. 5.
    Le, Q.V., Google Brain and Google Inc.: A tutorial on deep learning part 2: Autoencoders, convolutional neural networks and recurrent neural networks (2015)Google Scholar
  6. 6.
    Menegola, A., Fornaciali, M., Pires, R., Bittencourt, F.V., de Avila, S.E.F., Valle, E.: Knowledge transfer for melanoma screening with deep learning. CoRR, abs/1703.07479 (2017)Google Scholar
  7. 7.
    Nachbar, F., Stolz, W., Merkle, T., Cognetta, A.B., Vogt, T., Landthaler, M., Bilek, P., Braun-Falco, O., Plewig, G.: The ABCD rule of dermatoscopy. J. Am. Acad. Dermatol. 30(4), 551–559 (1994)CrossRefGoogle Scholar
  8. 8.
    Othman, E., Bazi, Y., Alajlan, N., Alhichri, H., Melgani, F.: Using convolutional features and a sparse autoencoder for land-use scene classification. Int. J. Remote Sens. 37(10), 2149–2167 (2016)CrossRefGoogle Scholar
  9. 9.
    Premaladha, J., Ravichandran, K.S.: Novel approaches for diagnosing melanoma skin lesions through supervised and deep learning algorithms. J. Med. Syst. 40(4), 1–12 (2016)CrossRefGoogle Scholar
  10. 10.
    Sablayrolles, A., Douze, M., Jégou, H., Usunier, N.: How should we evaluate supervised hashing? CoRR, abs/1609.06753 (2016)Google Scholar
  11. 11.
    Siegel, R., Miller, K., Jemal, A.: Cancer statistics. CA Cancer J. Clin. 66(1), 7–30 (2016)CrossRefGoogle Scholar

Copyright information

© Springer International Publishing AG, part of Springer Nature 2018

Authors and Affiliations

  1. 1.Universidad Nacional de San AgustínArequipaPeru

Personalised recommendations