Advertisement

Towards to Use Image Mining to Classified Skin Problems - A Melanoma Case Study

  • Pamela Coelho
  • Claudio Goncalves
  • Filipe PortelaEmail author
  • Manuel Filipe Santos
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11804)

Abstract

Data mining (DM) is the area where are discovery patterns and the relationship between data. Thus, depending on the type of data, the process will have different names. In this article is used Image Mining (IM), an area that uses DM techniques to find relationship through classification or clustering, using image data. Specifically, in this paper are expressed algorithms that are trying to predict melanomas using skin lesion and melanoma image’s, avoiding the need for a histologic exam. Furthermore, this avoidance is beneficial in terms of the costs and the level of intrusion that the patient usually suffers. In relation to the solutions, are presented two trained Convolutional Neural Networks (CNN), using packages from Keras and TensorFlow. On the other hand, focusing on the results, the best model was one that only used Keras with an accuracy value of 91% and a loss value of 36% using the testing data. As a conclusion, as a last use case for the model, in the long term it could be used in a preventive way, used to detect if a skin lesion is a melanoma. These benefits are major improvements in current Healthcare techniques. Furthermore, the accuracy of the models, considering only that they only serve as a proof of concept, is considered a “success”.

Keywords

Melanoma Data mining Classification Artificial intelligence 

Notes

Acknowledgements

This work has been supported by FCT – Fundação para a Ciência e Tecnologia within the Project Scope: UID/CEC/00319/2019 and Deus ex Machina (DEM): Symbiotic technology for societal efficiency gains - NORTE-01-0145-FEDER-000026.

References

  1. 1.
    Balu, R., Devi, T.: Design and development of automatic appendicitis detection system using sonographic image mining. Int. J. Eng. Innov. Technol. (IJEIT) 1(3), 67–74 (2012)Google Scholar
  2. 2.
    Barata, F.: Automatic detection of melanomas using dermoscopy images. Technical report, Instituto Superior Tecnico Lisboa (2017)Google Scholar
  3. 3.
    Burger, W., Burge, M.J.: Digital Image Processing. Springer, London (2008).  https://doi.org/10.1007/3-540-27563-0. www.imagingbook.comCrossRefzbMATHGoogle Scholar
  4. 4.
    Domingos, P.: The master algorithm: how the quest for the ultimate learning machine will remake our world. Am. Libr. Assoc. (2016).  https://doi.org/10.5860/choice.194685CrossRefGoogle Scholar
  5. 5.
    Gorunescu, F.: Data Mining, Concepts Models and Playlist. Springer, Heidelberg (2011).  https://doi.org/10.1007/978-3-642-19721-5CrossRefzbMATHGoogle Scholar
  6. 6.
    Hand, D.J.D.J., Mannila, H., Smyth, P.: Principles of Data Mining. MIT Press, Cambridge (2001)Google Scholar
  7. 7.
    Messadi, M., Cherifi, H., Bessaid, A.: Segmentation and ABCD rule extraction for skin tumors classification. J. Convergence Inf. Technol. 9(2), 21–34 (2014). https://pdfs.semanticscholar.org/2a7a/bba5a737cde74ebab95e50051cf9488b8987.pdfGoogle Scholar
  8. 8.
    North, M.: Data Mining for the Masses. A Global Text Project Book (2012). https://docs.rapidminer.com/downloads/DataMiningForTheMasses.pdf
  9. 9.
    Peffers, K., Tuunanen, T., Rothenberger, M.A., Chatterjee, S.: A design science research methodology for information systems research. J. Manage. Inf. Syst. 24(8), 45–78 (2007).  https://doi.org/10.2753/MIS0742-1222240302CrossRefGoogle Scholar
  10. 10.
    Phyu, T.N.: Survey of classification techniques in data mining. In: Proceedings of the International MultiConference of Engineers and Computer Scientists (2009)Google Scholar
  11. 11.
    Teixeira, J.W., Annibal, L.P., Felipe, J.C., Ciferri, R.R., Ciferri, C.D.D.A.: A similarity-based data warehousing environment for medical images. Comput. Biol. Med. 66, 190–208 (2015).  https://doi.org/10.1016/J.COMPBIOMED.2015.08.019CrossRefGoogle Scholar
  12. 12.
    Tomar, D., Agarwal, S.: A survey on data mining approaches for healthcare. Int. J. Bio-Sci. Bio-Technol. 5(5), 241–266 (2013).  https://doi.org/10.14257/ijbsbt.2013.5.5.25CrossRefGoogle Scholar
  13. 13.
    Vala, H., Baxi, A.: A review on Otsu image segmentation algorithm. Int. J. Adv. Res. Comput. Eng. Technol. 2(2), 387–389 (2013). https://pdfs.semanticscholar.org/ee8b/aed71d46b4d8747c8f2c73ba73f7c4a06130.pdfGoogle Scholar
  14. 14.
    Wirth, R., Hipp, J.: CRISP-DM: towards a standard process model for data mining. In: Proceedings of the 4th International Conference on the Practical Applications of Knowledge Discovery and Data Mining (2000)Google Scholar
  15. 15.
    Zahradnikova, B., Duchovicova, S., Schreiber, P.: Image mining: review and new challenges. Int. J. Adv. Comput. Sci. Appl. 6(7), 242–246 (2015)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • Pamela Coelho
    • 1
  • Claudio Goncalves
    • 1
  • Filipe Portela
    • 1
    Email author
  • Manuel Filipe Santos
    • 1
  1. 1.Algoritmi Research CentreUniversity of MinhoGuimaraesPortugal

Personalised recommendations