Noise as Domain Shift: Denoising Medical Images by Unpaired Image Translation

  • Ilja ManakovEmail author
  • Markus Rohm
  • Christoph Kern
  • Benedikt Schworm
  • Karsten Kortuem
  • Volker Tresp
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11795)


We cast the problem of image denoising as a domain translation problem between high and low noise domains. By modifying the cycleGAN model, we are able to learn a mapping between these domains on unpaired retinal optical coherence tomography images. In quantitative measurements and a qualitative evaluation by ophthalmologists, we show how this approach outperforms other established methods. The results indicate that the network differentiates subtle changes in the level of noise in the image. Further investigation of the model’s feature maps reveals that it has learned to distinguish retinal layers and other distinct regions of the images.


Optical coherence tomography Generative Adversarial Networks Image denoising 

Supplementary material

490967_1_En_1_MOESM1_ESM.pdf (13.1 mb)
Supplementary material 1 (pdf 13394 KB)


  1. 1.
    Chang, S.G., Vetterli, M.: Adaptive wavelet thresholding for image denoising and compression. IEEE Trans. Image Process. 9(9), 1532–1546 (2000)MathSciNetCrossRefGoogle Scholar
  2. 2.
    Dabov, K., Foi, A., Katkovnik, V., Egiazarian, K.: Image denoising with block-matching and 3D filtering, vol. 6064 (2006)Google Scholar
  3. 3.
    Darbon, J., Cunha, A., Chan, T.F., Osher, S., Jensen, G.J.: Fast nonlocal filtering applied to electron cryomicroscopy. In: 2008 5th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, pp. 1331–1334 (2008)Google Scholar
  4. 4.
    Goodfellow, I., et al.: Generative adversarial nets. Adv. Neural Inf. Process. Syst. 27, 2672–2680 (2014)Google Scholar
  5. 5.
    Halupka, K.J., et al.: Retinal optical coherence tomography image enhancement via deep learning. Biomed. Opt. Express 9(12), 6205–6221 (2018)CrossRefGoogle Scholar
  6. 6.
    He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2016Google Scholar
  7. 7.
    Huang, Y., et al.: Simultaneous denoising and super-resolution of optical coherence tomography images based on generative adversarial network. Opt. Express 27(9), 12289–12307 (2019)CrossRefGoogle Scholar
  8. 8.
    Joseph, M., Schmitt, S.H., Xiang, K.M.Y.: Speckle in optical coherence tomography. J. Biomed. Opt. 4(1), 95–105 (1999)CrossRefGoogle Scholar
  9. 9.
    Lorensen, W.E., Cline, H.E.: Marching cubes: a high resolution 3D surface construction algorithm. In: Proceedings of the 14th Annual Conference on Computer Graphics and Interactive Techniques, pp. 163–169 (1987)Google Scholar
  10. 10.
    Odena, A., Dumoulin, V., Olah, C.: Deconvolution and checkerboard artifacts. Distill 1(10), e3 (2016). Scholar
  11. 11.
    Podoleanu, A.G.: Optical coherence tomography. J. Microsc. 247(3), 209–219 (2012)CrossRefGoogle Scholar
  12. 12.
    Reddy, B.S., Chatterji, B.N.: An FFT-based technique for translation, rotation, and scale-invariant image registration. IEEE Trans. Image Process. 5(8), 1266–1271 (1996)CrossRefGoogle Scholar
  13. 13.
    Tomasi, C., Manduchi, R.: Bilateral filtering for gray and color images. In: Sixth International Conference on Computer Vision, pp. 839–846 (1998)Google Scholar
  14. 14.
    Zhu, J.Y., Park, T., Isola, P., Efros, A.A.: Unpaired image-to-image translation using cycle-consistent adversarial networks. In: The IEEE International Conference on Computer Vision (ICCV) (2017)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • Ilja Manakov
    • 1
    • 2
    Email author
  • Markus Rohm
    • 1
    • 2
  • Christoph Kern
    • 2
  • Benedikt Schworm
    • 2
  • Karsten Kortuem
    • 2
  • Volker Tresp
    • 1
    • 3
  1. 1.Chair for Database Systems and Data MiningLMU MunichMunichGermany
  2. 2.Department of OphthalmologyLMU MunichMunichGermany
  3. 3.Siemens AG, Corporate TechnologyMunichGermany

Personalised recommendations