Lung Nodule Diagnosis via Deep Learning and Swarm Intelligence

  • Cesar Affonso de Pinho Pinheiro
  • Nadia NedjahEmail author
  • Luiza de Macedo Mourelle
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11537)


In general, it is difficult to perform cancer diagnosis. In particular, pulmonary cancer is one of the most aggressive type of cancer and hard to be detected. When properly identified in its early stages, the chances of survival of the patient increase significantly. However, this detection is a hard problem, since it depends only on visual inspection of tomography images. Computer aided diagnosis methods can improve a great deal the detection and, thus, increasing the surviving rates. In this paper, we exploit computational intelligence techniques, such as deep learning, convolutional neural networks and swarm intelligence, in order to propose an efficient approach that allows identifying carcinogenic nodules in digital tomography scans. We use 7 different swarm intelligence techniques to approach the learning stage of a convolutional deep learning network. We are able to identify and classify cancerous pulmonary nodules successfully in the tomography scans of the Lung Image Database Consortium and Image Database Resource Initiative (LIDC-IDRI). The proposed approach, which consists of training Convolutional Neural Networks using swarm intelligence techniques, proved to be more efficient than the classic training with Back-propagation and Gradient Descent. It improves the average accuracy from 93% to 94%, precision from 92% to 94%, sensitivity from 91% to 93% and specificity from 97% to 98%.


Deep learning Swarm intelligence Lung cancer detection Convolutional neural networks 


  1. 1.
    Kuan, K., et al.: Deep learning for lung cancer detection: tackling the kaggle data science bowl 2017 challenge. arXiv preprint arXiv:1705.09435 (2017)
  2. 2.
    Chon, A., Balachandra, N., Lu, P.: Deep convolutional neural networks for lung cancer detection. Standford University (2017)Google Scholar
  3. 3.
    Jayanthi, S., Preetha, K.: Breast cancer detection and classification using artificial neural network with particle swarm optimization. Int. J. Adv. Res. Basic Eng. Sci. Technol. 2 (2016)Google Scholar
  4. 4.
    Ronneberger, O., Fischer, P., Brox, T.: U-net: convolutional networks for biomedical image segmentation. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds.) MICCAI 2015. LNCS, vol. 9351, pp. 234–241. Springer, Cham (2015). Scholar
  5. 5.
    Kennedy, J., Eberhart, R.: Particle swarm optimization (1995)Google Scholar
  6. 6.
    Karaboga, D., Basturk, B.: A powerful and efficient algorithm for numerical function optimization: artificial bee colony (ABC) algorithm. J. Global Optim. 39(3), 459–471 (2007)MathSciNetCrossRefGoogle Scholar
  7. 7.
    Passino, K.M.: Bacterial foraging optimization. Int. J. Swarm. Intell. Res. 1(1), 1–16 (2010)MathSciNetCrossRefGoogle Scholar
  8. 8.
    Ritthipakdee, T., Premasathian, J.: Firefly mating algorithm for continuous optimization problems, July 2017Google Scholar
  9. 9.
    Tan, Y., Zhu, Y.: Fireworks algorithm for optimization. In: Tan, Y., Shi, Y., Tan, K.C. (eds.) ICSI 2010. LNCS, vol. 6145, pp. 355–364. Springer, Heidelberg (2010). Scholar
  10. 10.
    Geem, Z.W., Kim, J.H., Loganathan, G.: A new heuristic optimization algorithm: harmony search. SIMULATION 76(2), 60–68 (2001)CrossRefGoogle Scholar
  11. 11.
    Khajehzadeh, M., Eslami, M.: Gravitational search algorithm for optimization of retaining structures. Indian J. Sci. Technol. 5(1) (2012)Google Scholar
  12. 12.
    Cancer Imaging Archive: The lung image database consortium image collection (LIDC-IDRI). Accessed 2 Feb 2018
  13. 13.
    Jacobs, C., Setio, A.A.A., Traverso, A., van Ginneken, B.: Lung nodule analysis 2016 (LUNA16). Accessed 2 Feb 2018

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • Cesar Affonso de Pinho Pinheiro
    • 1
  • Nadia Nedjah
    • 1
    Email author
  • Luiza de Macedo Mourelle
    • 2
  1. 1.Department of Electronics Engineering and Telecommunications, Faculty of EngineeringState University of Rio de JaneiroRio de JaneiroBrazil
  2. 2.Department of Systems Engineering and Computation, Faculty of EngineeringState University of Rio de JaneiroRio de JaneiroBrazil

Personalised recommendations