Skip to main content
Springer Nature Link
Log in

Self-supervised k-Space Regularization for Motion-Resolved Abdominal MRI Using Neural Implicit k-Space Representations

  • Conference paper
  • First Online:
Medical Image Computing and Computer Assisted Intervention – MICCAI 2024 (MICCAI 2024)

Part of the book series: Lecture Notes in Computer Science ((LNCS,volume 15007))

  • 1946 Accesses

Abstract

Neural implicit k-space representations have shown promising results for dynamic MRI at high temporal resolutions. Yet, their exclusive training in k-space limits the application of common image regularization methods to improve the final reconstruction. In this work, we introduce the concept of parallel imaging-inspired self-consistency (PISCO), which we incorporate as novel self-supervised k-space regularization enforcing a consistent neighborhood relationship. At no additional data cost, the proposed regularization significantly improves neural implicit k-space reconstructions on simulated data. Abdominal in-vivo reconstructions using PISCO result in enhanced spatio-temporal image quality compared to state-of-the-art methods. Code is available at https://github.com/compai-lab/2024-miccai-spieker.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Similar content being viewed by others

References

  1. Ahmad, R., et al.: Plug-and-play methods for magnetic resonance imaging: using denoisers for image recovery. IEEE Signal Process. Mag. 37(1), 105–116 (2020). https://doi.org/10.1109/msp.2019.2949470

  2. Akçakaya, M., Moeller, S., Weingärtner, S., Uğurbil, K.: Scan-specific robust artificial-neural-networks for k-space interpolation (RAKI) reconstruction: Database-free deep learning for fast imaging. Magn. Reson. Med. 81(1), 439–453 (2019). https://doi.org/10.1002/mrm.27420

    Article  Google Scholar 

  3. Breuer, F.A., Kellman, P., Griswold, M.A., Jakob, P.M.: Dynamic autocalibrated parallel imaging using temporal GRAPPA (TGRAPPA). Magn. Reson. Med. 53(4), 981–985 (2005). https://doi.org/10.1002/mrm.20430

    Article  Google Scholar 

  4. Catalán, T., Courdurier, M., Osses, A., Botnar, R., Costabal, F.S., Prieto, C.: Unsupervised reconstruction of accelerated cardiac cine MRI using Neural Fields (25072023). http://arxiv.org/pdf/2307.14363v1

  5. Collins, C.M., Yang, B., Yang, Q.X., Smith, M.B.: Numerical calculations of the static magnetic field in three-dimensional multi-tissue models of the human head. Magn. Reson. Imaging 20(5), 413–424 (2002). https://doi.org/10.1016/s0730-725x(02)00507-6

    Article  Google Scholar 

  6. Feng, L., Axel, L., Chandarana, H., Block, K.T., Sodickson, D.K., Otazo, R.: XD-GRASP: Golden-angle radial MRI with reconstruction of extra motion-state dimensions using compressed sensing. Magn. Reson. Med. 75(2), 775–788 (2016). https://doi.org/10.1002/mrm.25665

    Article  Google Scholar 

  7. Griswold, M.A., et al.: Generalized autocalibrating partially parallel acquisitions (GRAPPA). Magn. Reson. Med. 47(6), 1202–1210 (2002). https://doi.org/10.1002/mrm.10171

  8. Hammernik, K., et al.: Physics-driven deep learning for computational magnetic resonance imaging: combining physics and machine learning for improved medical imaging. IEEE Signal Process. Mag. 40(1), 98–114 (2023). https://doi.org/10.1109/msp.2022.3215288

  9. Huang, W., Li, H.B., Pan, J., Cruz, G., Rueckert, D., Hammernik, K.: Neural implicit k-space for binning-free non-Cartesian cardiac MR imaging. In: Frangi, A., de Bruijne, M., Wassermann, D., Navab, N. (eds.) IPMI 2023, pp. 548–560. Springer, Cham (2023). https://doi.org/10.1007/978-3-031-34048-2_42

  10. Jafari, R., et al.: GRASPNET: Fast spatiotemporal deep learning reconstruction of golden-angle radial data for free-breathing dynamic contrast-enhanced magnetic resonance imaging. NMR Biomed. 36(3), e4861 (2023). https://doi.org/10.1002/nbm.4861

  11. Maril, N., Collins, C.M., Greenman, R.L., Lenkinski, R.E.: Strategies for shimming the breast. Magn. Reson. Med. 54(5), 1139–1145 (2005). https://doi.org/10.1002/mrm.20679

    Article  Google Scholar 

  12. Ryu, K., Alkan, C., Choi, C., Jang, I., Vasanawala, S.: K-space refinement in deep learning MR reconstruction via regularizing scan specific SPIRiT-based self consistency. In: 2021 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW). IEEE (2021). https://doi.org/10.1109/iccvw54120.2021.00446

  13. Segars, W.P., Sturgeon, G., Mendonca, S., Grimes, J., Tsui, B.M.W.: 4D XCAT phantom for multimodality imaging research. Med. Phys. 37(9), 4902–4915 (2010). https://doi.org/10.1118/1.3480985

    Article  Google Scholar 

  14. Seiberlich, N., Ehses, P., Duerk, J., Gilkeson, R., Griswold, M.: Improved radial GRAPPA calibration for real-time free-breathing cardiac imaging. Magn. Reson. Med. 65(2), 492–505 (2011). https://doi.org/10.1002/mrm.22618

    Article  Google Scholar 

  15. Sitzmann, V., Martel, J., Bergman, A., Lindell, D., Wetzstein, G.: Implicit Neural Representations with Periodic Activation Functions. Adv. Neural. Inf. Process. Syst. 33, 7462–7473 (2020)

    Google Scholar 

  16. Spieker, V., et al.: Deep learning for retrospective motion correction in MRI: a comprehensive review. IEEE Trans. Med. Imaging (2023). https://doi.org/10.1109/TMI.2023.3323215

  17. Spieker, V., et al.: ICoNIK: Generating respiratory-resolved abdominal MR reconstructions using neural implicit representations in k-space. In: Mukhopadhyay, A., Oksuz, I., Engelhardt, S., Zhu, D., Yuan, Y. (eds.) Deep Generative Models. MICCAI 2023. LNCS, vol. 14533, pp. 183–192. Springer, Cham (2023). https://doi.org/10.1007/978-3-031-53767-7_18

  18. Stemkens, B., Paulson, E.S., Tijssen, R.H.N.: Nuts and bolts of 4D-MRI for radiotherapy. Phys. Med. Biol. 63(21), 21TR01 (2018). https://doi.org/10.1088/1361-6560/aae56d

  19. Terpstra, M.L., Maspero, M., Verhoeff, J.J.C., van den Berg, C.A.T.: Accelerated respiratory-resolved 4D-MRI with separable spatio-temporal neural networks. Med. Phys. 50(9), 5331–5342 (2023). https://doi.org/10.1002/mp.16643

    Article  Google Scholar 

  20. Uecker, M., et al.: ESPIRiT-an eigenvalue approach to autocalibrating parallel MRI: where SENSE meets GRAPPA. Magn. Reson. Med. 71(3), 990–1001 (2014). https://doi.org/10.1002/mrm.24751

  21. Yu, H., Shimakawa, A., McKenzie, C.A., Brodsky, E., Brittain, J.H., Reeder, S.B.: Multiecho water-fat separation and simultaneous R2* estimation with multifrequency fat spectrum modeling. Magn. Reson. Med. 60(5), 1122–1134 (2008). https://doi.org/10.1002/mrm.21737

    Article  Google Scholar 

  22. Zaitsev, M., Maclaren, J., Herbst, M.: Motion artifacts in MRI: a complex problem with many partial solutions. J. Magn. Reson. Imaging 42(4), 887–901 (2015). https://doi.org/10.1002/jmri.24850

    Article  Google Scholar 

Download references

Acknowledgments

V.S. and H.E. are partially supported by the Helmholtz Association under the joint research school “Munich School for Data Science - MUDS”.

Author information

Authors and Affiliations

  1. Institute of Machine Learning in Biomedical Imaging, Helmholtz Munich, Munich, Germany

    Veronika Spieker, Hannah Eichhorn & Julia A. Schnabel

  2. School of Computation, Information and Technology, Technical University of Munich, Munich, Germany

    Veronika Spieker, Hannah Eichhorn, Daniel Rueckert, Kerstin Hammernik & Julia A. Schnabel

  3. Millenium Institute for Intelligent Healthcare Engineering, Santiago, Chile

    Veronika Spieker, Francisco Sahli Costabal & Claudia Prieto

  4. School of Medicine and Health, Klinikum rechts der Isar, Technical University of Munich, Munich, Germany

    Jonathan K. Stelter, Wenqi Huang, Rickmer F. Braren, Daniel Rueckert & Dimitrios C. Karampinos

  5. German Cancer Consortium (DKTK, Partner Site Munich) and German Cancer Research Center (DKFZ) Heidelberg, Heidelberg, Germany

    Rickmer F. Braren

  6. Department of Computing, Imperial College London, London, UK

    Daniel Rueckert

  7. School of Engineering, Pontificia Universidad Católica de Chile, Santiago, Chile

    Francisco Sahli Costabal & Claudia Prieto

  8. School of Biomedical Engineering and Imaging Sciences, King’s College London, London, UK

    Claudia Prieto & Julia A. Schnabel

Authors
  1. Veronika Spieker
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Hannah Eichhorn
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Jonathan K. Stelter
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Wenqi Huang
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Rickmer F. Braren
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Daniel Rueckert
    View author publications

    You can also search for this author in PubMed Google Scholar

  7. Francisco Sahli Costabal
    View author publications

    You can also search for this author in PubMed Google Scholar

  8. Kerstin Hammernik
    View author publications

    You can also search for this author in PubMed Google Scholar

  9. Claudia Prieto
    View author publications

    You can also search for this author in PubMed Google Scholar

  10. Dimitrios C. Karampinos
    View author publications

    You can also search for this author in PubMed Google Scholar

  11. Julia A. Schnabel
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Veronika Spieker .

Editor information

Editors and Affiliations

  1. Children’s National Hospital/George Washington University, Washington, DC, USA

    Marius George Linguraru

  2. The Chinese University of Hong Kong, Hong Kong, China

    Qi Dou

  3. Technical University of Denmark, Kgs Lyngby, Denmark

    Aasa Feragen

  4. Imperial College London, London, UK

    Stamatia Giannarou

  5. Imperial College London, London, UK

    Ben Glocker

  6. Universitat de Barcelona, Barcelona, Spain

    Karim Lekadir

  7. Helmholtz Munich, Technical University of Munich and King’s College London, Munich, Germany

    Julia A. Schnabel

Ethics declarations

Disclosure of Interests

V.S. received the Bayer Foundation Fellowship during part of this work.

1 Electronic supplementary material

Below is the link to the electronic supplementary material.

Supplementary material 1 (mp4 12867 KB)

Rights and permissions

Reprints and permissions

Copyright information

© 2024 The Author(s), under exclusive license to Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Spieker, V. et al. (2024). Self-supervised k-Space Regularization for Motion-Resolved Abdominal MRI Using Neural Implicit k-Space Representations. In: Linguraru, M.G., et al. Medical Image Computing and Computer Assisted Intervention – MICCAI 2024. MICCAI 2024. Lecture Notes in Computer Science, vol 15007. Springer, Cham. https://doi.org/10.1007/978-3-031-72104-5_59

Download citation

  • DOI: https://doi.org/10.1007/978-3-031-72104-5_59

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-031-72103-8

  • Online ISBN: 978-3-031-72104-5

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics