Examining the Capability of GANs to Replace Real Biomedical Images in Classification Models Training

  • Vassili Kovalev
  • Siarhei KazlouskiEmail author
Conference paper
Part of the Communications in Computer and Information Science book series (CCIS, volume 1055)


In this paper, we explore the possibility of generating artificial biomedical images that can be used as a substitute for real image datasets in applied machine learning tasks. We are focusing on generation of realistic chest X-ray images as well as on the lymph node histology images using the two recent GAN architectures including DCGAN and PGGAN. The possibility of the use of artificial images instead of real ones for training machine learning models was examined by benchmark classification tasks being solved using conventional and deep learning methods. In particular, a comparison was made by replacing real images with synthetic ones at the model training stage and comparing the prediction results with the ones obtained while training on the real image data. It was found that the drop of classification accuracy caused by such training data substitution ranged between 2.2% and 3.5% for deep learning models and between 5.5% and 13.25% for conventional methods such as LBP + Random Forests.


Generative Adversarial Networks X-ray images Histology images 


  1. 1.
    Litjens, G., et al.: A survey on deep learning in medical image analysis. Med. Image Anal. 42, 60–88 (2017)CrossRefGoogle Scholar
  2. 2.
    Kovalev, V., Liauchuk, V., Kalinovsky, A., Shukelovich, A.A.: Comparison of conventional and deep learning methods of image classification on a database of chest radiographs. Int. J. Comput. Assist. Radiol. Surg. 12, 139–140 (2017)Google Scholar
  3. 3.
    Ching, T., et al.: Opportunities and obstacles for deep learning in biology and medicine. bioRxiv preprint bioRxiv:142760 (2018)Google Scholar
  4. 4.
    Cunniff, C., et al.: Informed consent for medical photographs. Genet. Med. 2(6), 353–355 (2000)CrossRefGoogle Scholar
  5. 5.
    Goodfellow, I., et al.: Generative adversarial nets. In: Ghahramani, Z., et al. (eds.) Neural Information Processing Systems (NIPS), vol. 2, pp. 2672–2680. MIT Press, Montreal (2014)Google Scholar
  6. 6.
    Kazeminiaa, S., et al.: GANs for medical image analysis. arXiv preprint arXiv:1809.06222 (2018)
  7. 7.
    Yia, X., Waliaa, E., Babyna, P.: Generative adversarial network in medical imaging: a review. arXiv preprint arXiv:1809.07294 (2019)
  8. 8.
    Radford, A., Metz, L., Chintala, S.: Unsupervised representation learning with deep convolutional generative adversarial networks. arXiv preprint arXiv:1511.06434 (2016)
  9. 9.
    Karras, T., Aila, T., Laine, S., Lehtinen, J.: Progressive growing of GANs for improved quality, stability, and variation. arXiv preprint arXiv:1710.10196 (2017)
  10. 10.
    Veta, M., et al.: Predicting breast tumor proliferation from whole-slide images. Med. Image Anal. 54, 111–121 (2019)CrossRefGoogle Scholar
  11. 11.
    DCGAN implementation (2019). Accessed 1 Apr 2019
  12. 12.
    PGGAN implementation (2019). Accessed 1 Apr 2019

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  1. 1.United Institute of Informatics ProblemsMinskBelarus

Personalised recommendations