Skip to main content
Top

2021 | OriginalPaper | Chapter

Adversarially Learned Iterative Reconstruction for Imaging Inverse Problems

Authors : Subhadip Mukherjee, Ozan Öktem, Carola-Bibiane Schönlieb

Published in: Scale Space and Variational Methods in Computer Vision

Publisher: Springer International Publishing

Activate our intelligent search to find suitable subject content or patents.

search-config
loading …

Abstract

In numerous practical applications, especially in medical image reconstruction, it is often infeasible to obtain a large ensemble of ground-truth/measurement pairs for supervised learning. Therefore, it is imperative to develop unsupervised learning protocols that are competitive with supervised approaches in performance. Motivated by the maximum-likelihood principle, we propose an unsupervised learning framework for solving ill-posed inverse problems. Instead of seeking pixel-wise proximity between the reconstructed and the ground-truth images, the proposed approach learns an iterative reconstruction network whose output matches the ground-truth in distribution. Considering tomographic reconstruction as an application, we demonstrate that the proposed unsupervised approach not only performs on par with its supervised variant in terms of objective quality measures, but also successfully circumvents the issue of over-smoothing that supervised approaches tend to suffer from. The improvement in reconstruction quality comes at the expense of higher training complexity, but, once trained, the reconstruction time remains the same as its supervised counterpart.

Dont have a licence yet? Then find out more about our products and how to get one now:

Springer Professional "Wirtschaft+Technik"

Online-Abonnement

Mit Springer Professional "Wirtschaft+Technik" erhalten Sie Zugriff auf:

  • über 102.000 Bücher
  • über 537 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Maschinenbau + Werkstoffe
  • Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

Springer Professional "Technik"

Online-Abonnement

Mit Springer Professional "Technik" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 390 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Maschinenbau + Werkstoffe




 

Jetzt Wissensvorsprung sichern!

Springer Professional "Wirtschaft"

Online-Abonnement

Mit Springer Professional "Wirtschaft" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 340 Zeitschriften

aus folgenden Fachgebieten:

  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Versicherung + Risiko




Jetzt Wissensvorsprung sichern!

Literature
2.
go back to reference Adler, J., Öktem, O.: Solving ill-posed inverse problems using iterative deep neural networks. Inverse Probl. 33(12), 1–24 (2017) Adler, J., Öktem, O.: Solving ill-posed inverse problems using iterative deep neural networks. Inverse Probl. 33(12), 1–24 (2017)
3.
go back to reference Adler, J., Öktem, O.: Learned primal-dual reconstruction. IEEE Trans. Med. Imaging 37(6), 1322–1332 (2018)CrossRef Adler, J., Öktem, O.: Learned primal-dual reconstruction. IEEE Trans. Med. Imaging 37(6), 1322–1332 (2018)CrossRef
5.
go back to reference Arridge, S., Maass, P., Öktem, O., Schönlieb, C.B.: Solving inverse problems using data-driven models. Acta Numerica 28, 1–174 (2019)MathSciNetCrossRef Arridge, S., Maass, P., Öktem, O., Schönlieb, C.B.: Solving inverse problems using data-driven models. Acta Numerica 28, 1–174 (2019)MathSciNetCrossRef
6.
go back to reference Byeongsu, S., Gyutaek, O., Jeongsol, K., Chanyong, J., Ye, J.C.: Optimal transport driven CycleGAN for unsupervised learning in inverse problems. arXiv:1909.12116v4, August 2020 Byeongsu, S., Gyutaek, O., Jeongsol, K., Chanyong, J., Ye, J.C.: Optimal transport driven CycleGAN for unsupervised learning in inverse problems. arXiv:​1909.​12116v4, August 2020
7.
go back to reference Chambolle, A., Pock, T.: A first-order primal-dual algorithm for convex problems with applications to imaging. J. Math. Imaging Vis. 40(1), 120–145 (2010)MathSciNetCrossRef Chambolle, A., Pock, T.: A first-order primal-dual algorithm for convex problems with applications to imaging. J. Math. Imaging Vis. 40(1), 120–145 (2010)MathSciNetCrossRef
8.
go back to reference Gregor, K., LeCun, Y.: Learning fast approximations of sparse coding. In: International Conference on Machine Learning (2010) Gregor, K., LeCun, Y.: Learning fast approximations of sparse coding. In: International Conference on Machine Learning (2010)
9.
10.
go back to reference Jin, K.H., McCann, M.T., Froustey, E., Unser, M.: Deep convolutional neural network for inverse problems in imaging. IEEE Trans. Image Process. 26(9), 4509–4522 (2017)MathSciNetCrossRef Jin, K.H., McCann, M.T., Froustey, E., Unser, M.: Deep convolutional neural network for inverse problems in imaging. IEEE Trans. Image Process. 26(9), 4509–4522 (2017)MathSciNetCrossRef
11.
go back to reference Kobler, E., Effland, A., Kunisch, K., Pock, T.: Total deep variation for linear inverse problems. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7549–7558 (2020) Kobler, E., Effland, A., Kunisch, K., Pock, T.: Total deep variation for linear inverse problems. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7549–7558 (2020)
12.
13.
go back to reference Lin, J., Xia, Y., Qin, T., Chen, Z., Liu, T.: Conditional image-to-image translation. In: IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 5524–5532 (2018) Lin, J., Xia, Y., Qin, T., Chen, Z., Liu, T.: Conditional image-to-image translation. In: IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 5524–5532 (2018)
14.
go back to reference Lunz, S., Öktem, O., Schönlieb, C.B.: Adversarial regularizers in inverse problems. In: Advances in Neural Information Processing Systems, pp. 8507–8516 (2018) Lunz, S., Öktem, O., Schönlieb, C.B.: Adversarial regularizers in inverse problems. In: Advances in Neural Information Processing Systems, pp. 8507–8516 (2018)
15.
go back to reference McCollough, C.: TFG-207a-04: overview of the low dose CT grand challenge. Med. Phys. 43(6), 3759–3760 (2014) McCollough, C.: TFG-207a-04: overview of the low dose CT grand challenge. Med. Phys. 43(6), 3759–3760 (2014)
16.
go back to reference Meinhardt, T., Moller, M., Hazirbas, C., Cremers, D.: Learning proximal operators: using denoising networks for regularizing inverse imaging problems. In: Proceedings of the IEEE International Conference on Computer Vision pp. 1781–1790 (2017) Meinhardt, T., Moller, M., Hazirbas, C., Cremers, D.: Learning proximal operators: using denoising networks for regularizing inverse imaging problems. In: Proceedings of the IEEE International Conference on Computer Vision pp. 1781–1790 (2017)
18.
go back to reference Zhu, B., Liu, J.Z., Cauley, S.F., Rosen, B.R., Rosen, M.S.: Image reconstruction by domain-transform manifold learning. Nature 555, 487–492 (2018)CrossRef Zhu, B., Liu, J.Z., Cauley, S.F., Rosen, B.R., Rosen, M.S.: Image reconstruction by domain-transform manifold learning. Nature 555, 487–492 (2018)CrossRef
19.
go back to reference Zhu, J.Y., Park, T., Isola, P., Efros, A.A.: Unpaired image-to-image translation using cycle-consistent adversarial networks. arXiv:1703.10593v7, August 2020 Zhu, J.Y., Park, T., Isola, P., Efros, A.A.: Unpaired image-to-image translation using cycle-consistent adversarial networks. arXiv:​1703.​10593v7, August 2020
Metadata
Title
Adversarially Learned Iterative Reconstruction for Imaging Inverse Problems
Authors
Subhadip Mukherjee
Ozan Öktem
Carola-Bibiane Schönlieb
Copyright Year
2021
DOI
https://doi.org/10.1007/978-3-030-75549-2_43

Premium Partner