Detection of Cutaneous Tumors in Dogs Using Deep Learning Techniques

  • Lorena Zapata
  • Lorena Chalco
  • Lenin Aguilar
  • Esmeralda Pimbosa
  • Iván Ramírez-Morales
  • Jairo Hidalgo
  • Marco Yandún
  • Hugo Arias-Flores
  • Cesar GuevaraEmail author
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 965)


Cytological diagnosis is useful in the practical context compared to the histopathology, since it can classify pathologies among the cutaneous masses, the samples can be collected easily without anesthetizing the patient, at very low cost. However, an experimented veterinarian performs the cytological diagnosis in approximately 25 min. Artificial intelligence is being used for the diagnosis of many pathologies in human medicine, the experience gained by years of work in the area of work allow to issue correct diagnoses, this experience can be trained in an intelligent system. In this work, we collected a total of 1500 original cytologic images, performed some preliminary tests and also propose a deep learning based approach for image analysis and classification using convolutional neural networks (CNN). To adjust the parameters of the classification model, we recommend to perform a random and grid search will be applied, modifying the batch size of images for training, the number of layers, the learning speed and the selection of three optimizers: Adadelta, RMSProp and SGD. The performance of the classifiers will be evaluated by measuring the accuracy and two loss functions: cross-categorical entropy and mean square error. These metrics will be evaluated in a set of images different from those with which the model was trained (test set). By applying this model, an image classifier can be generated that efficiently identifies a cytology diagnostic in a short time and with an optimal detection rate. This is the first approach for the development of a more complex model of skin mass detection in all its types.


Deep learning Cancer Veterinary Cytology Convolutional Neural Networks 


Acknowledgements [1]

The authors wish to thank CEDIA National Research and Education Network. Iván Ramírez-Morales would also like to thank the support provided by NVIDIA. This work is part of DINTA-UTMACH and GIPASA research groups.


  1. 1.
    Graf, R., Pospischil, A., Guscetti, F., Meier, D., Welle, M., Dettwiler, M.: Cutaneous tumors in swiss dogs: retrospective data from the swiss canine cancer registry, 2008–2013. Vet. Pathol. 55, 809–820 (2018)CrossRefGoogle Scholar
  2. 2.
    Vinueza, R.L., Cabrera, F., Donoso, L., Pérez, J., Díaz, R.: Frecuencia de neoplasias en caninos en Quito. Ecuador. Rev Investig Vet Peru 28, 92–100 (2017)CrossRefGoogle Scholar
  3. 3.
    Hamasaki, M., Chang, K.H.F., Nabeshima, K., Tauchi-Nishi, P.S.: Intraoperative squash and touch preparation cytology of brain lesions stained with H + E and diff-QUIKTM: a 20-year retrospective analysis and comparative literature review. Acta Cytol. 62, 44–53 (2018)CrossRefGoogle Scholar
  4. 4.
    Pantanowitz, L., Sinard, J.H., Henricks, W.H., Fatheree, L.A., Carter, A.B., Contis, L., et al.: Validating whole slide imaging for diagnostic purposes in pathology: guideline from the college of American Pathologists Pathology and Laboratory Quality Center. Arch. Pathol. Lab. Med. 137, 1710–1722 (2013)CrossRefGoogle Scholar
  5. 5.
    Esteva, A., Kuprel, B., Novoa, R.A., Ko, J., Swetter, S.M., Blau, H.M., et al.: Dermatologist-level classification of skin cancer with deep neural networks. Nature 542, 115–118 (2017)CrossRefGoogle Scholar
  6. 6.
    Liu, J., Xu, B., Zheng, C., Gong, Y., Garibaldi, J., Soria, D., et al.: An end-to-end deep learning histochemical scoring system for breast cancer TMA. IEEE Trans. Med. Imaging (2018). Scholar
  7. 7.
    Bychkov, D., Linder, N., Turkki, R., Nordling, S., Kovanen, P.E., Verrill, C., et al.: Deep learning based tissue analysis predicts outcome in colorectal cancer. Sci. Rep. 8, 3395 (2018)CrossRefGoogle Scholar
  8. 8.
    Cascardi, A., Micelli, F., Aiello, M.A.: An artificial neural networks model for the prediction of the compressive strength of FRP-confined concrete circular columns. Eng. Struct. 140, 199–208 (2017)CrossRefGoogle Scholar
  9. 9.
    Jiang, J., Trundle, P., Ren, J.: Medical image analysis with artificial neural networks. Comput. Med. Imaging Graph. 34, 617–631 (2010)CrossRefGoogle Scholar
  10. 10.
    Kruse, R., Borgelt, C., Klawonn, F., Moewes, C., Steinbrecher, M., Held, P.: Multi-layer perceptrons. In: Computational Intelligence, pp. 47–81. Springer, London (2013)Google Scholar
  11. 11.
    Ruck, D.W., Rogers, S.K., Kabrisky, M., Oxley, M.E., Suter, B.W.: The multilayer perceptron as an approximation to a Bayes optimal discriminant function. IEEE Trans. Neural. Netw. 1, 296–298 (1990)CrossRefGoogle Scholar
  12. 12.
    Gardner, M.W., Dorling, S.R.: Artificial neural networks (the multilayer perceptron)—a review of applications in the atmospheric sciences. Atmos. Environ. 32, 2627–2636 (1998)CrossRefGoogle Scholar
  13. 13.
    Herrera, F., Hervas, C., Otero, J., Sánchez, L.: Un estudio empırico preliminar sobre los tests estadısticos más habituales en el aprendizaje automático. Tendencias de La Minerıa de Datos En Espana, Red Espanola de Minerıa de Datos Y Aprendizaje (TIC2002-11124-E), pp. 403–412 (2004)Google Scholar
  14. 14.
    Rivero, D., Fernandez-Blanco, E., Dorado, J., Pazos, A.: Using recurrent ANNs for the detection of epileptic seizures in EEG signals. IEEE Congr. Evol. Comput. (CEC) 2011, 587–592 (2011)Google Scholar
  15. 15.
    Wahab, N., Khan, A., Lee, Y.S.: Two-phase deep convolutional neural network for reducing class skewness in histopathological images based breast cancer detection. Comput. Biol. Med. 85, 86–97 (2017)CrossRefGoogle Scholar
  16. 16.
    Soriano, D., Aguilar, C., Ramirez-Morales, I., Tusa, E., Rivas, W., Pinta, M.: Mammogram classification schemes by using convolutional neural networks. In: Technology Trends, pp. 71–85. Springer, Charm (2018)Google Scholar
  17. 17.
    Fawcett, T.: An introduction to ROC analysis. Pattern Recogn. Lett. 27, 861–874 (2006)CrossRefGoogle Scholar
  18. 18.
    Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., Wojna, Z.: Rethinking the inception architecture for computer vision. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2818–2826. (2016)
  19. 19.
    Abadi, M., Barham, P., Chen, J., Chen, Z., Davis, A., Dean, J.: Tensorflow: a system for large-scale machine learning. In: OSDI (2016)Google Scholar
  20. 20.
    Bottou, L.: Large-scale machine learning with stochastic gradient descent. In: Proceedings of COMPSTAT 2010, pp. 177–186. Physica-Verlag HD (2010)Google Scholar
  21. 21.
    Hinton, G., Srivastava, N., Swersky, K.: Neural networks for machine learning lecture 6a overview of mini-batch gradient descent. Cited on 2012:14Google Scholar
  22. 22.
    Zeiler, M.D.: ADADELTA: An Adaptive Learning Rate Method. arXiv [csLG] (2012)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  • Lorena Zapata
    • 1
  • Lorena Chalco
    • 1
  • Lenin Aguilar
    • 1
  • Esmeralda Pimbosa
    • 1
  • Iván Ramírez-Morales
    • 1
  • Jairo Hidalgo
    • 2
  • Marco Yandún
    • 2
  • Hugo Arias-Flores
    • 3
  • Cesar Guevara
    • 3
    Email author
  1. 1.Faculty of Agricultural and Livestock SciencesUniversidad Técnica de MachalaMachalaEcuador
  2. 2.Universidad Politécnica Estatal Del CarchiTulcánEcuador
  3. 3.Institute of Research, Development and Innovation—MISTUniversidad IndoaméricaQuitoEcuador

Personalised recommendations