Abstract
We propose PHIMO, a physics-informed learning-based motion correction method tailored to quantitative MRI. PHIMO leverages information from the signal evolution to exclude motion-corrupted k-space lines from a data-consistent reconstruction. We demonstrate the potential of PHIMO for the application of T2* quantification from gradient echo MRI, which is particularly sensitive to motion due to its sensitivity to magnetic field inhomogeneities. A state-of-the-art technique for motion correction requires redundant acquisition of the k-space center, prolonging the acquisition. We show that PHIMO can detect and exclude intra-scan motion events and, thus, correct for severe motion artifacts. PHIMO approaches the performance of the state-of-the-art motion correction method, while substantially reducing the acquisition time by over 40%, facilitating clinical applicability. Our code is available at https://github.com/compai-lab/2024-miccai-eichhorn.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Atkinson, D.: Retrospective correction of motion in MR images. In: van der Kouwe, A.J., Andre, J.B. (eds.) Motion Correction in MR, vol. 6, pp. 259–267. Academic Press (2022). https://doi.org/10.1016/B978-0-12-824460-9.00022-4
Chatterjee, S., Sciarra, A., Dünnwald, M., Oeltze-Jafra, S., Nürnberger, A., Speck, O.: Retrospective motion correction of MR images using prior-assisted deep learning. In: Proceedings of the 34th Conference on NeurIPS (2020). https://doi.org/10.48550/arXiv.2011.14134
Eichhorn, H., et al.: Physics-aware motion simulation for T2*-weighted brain MRI. In: Wolterink, J.M., Svoboda, D., Zhao, C., Fernandez, V. (eds.) SASHIMI 2023. LNCS, vol. 14288, pp. 42–52. Springer, Cham (2023). https://doi.org/10.1007/978-3-031-44689-4_5
Hammernik, K., Küstner, T.: Machine enhanced reconstruction learning and interpretation networks (MERLIN). In: Proceedings of the International Society for Magnetic Resonance in Medicine (ISMRM) (2022)
Haskell, M.W., et al.: Network accelerated motion estimation and reduction (NAMER): convolutional neural network guided retrospective motion correction using a separable motion model. Magn. Reson. Med. 82(4), 1452–1461 (2019). https://doi.org/10.1002/mrm.27771
Hirsch, N.M., Preibisch, C.: T2* mapping with background gradient correction using different excitation pulse shapes. Am. J. Neuroradiol. 34(6), E65–E68 (2013). https://doi.org/10.3174/ajnr.A3021
Hirsch, N.M., Toth, V., Förschler, A., Kooijman, H., Zimmer, C., Preibisch, C.: Technical considerations on the validity of blood oxygenation level-dependent-based MR assessment of vascular deoxygenation. NMR Biomed. 27(7), 853–862 (2014). https://doi.org/10.1002/nbm.3131
Hossbach, J., et al.: Deep learning-based motion quantification from k-space for fast model-based MRI motion correction. Med. Phys. (2022). https://doi.org/10.1002/mp.16119
Johnson, P.M., Drangova, M.: Conditional generative adversarial network for 3D rigid-body motion correction in MRI. Magn. Reson. Med. 82(3), 901–910 (2019). https://doi.org/10.1002/mrm.27772
Kaczmarz, S., Hyder, F., Preibisch, C.: Oxygen extraction fraction mapping with multi-parametric quantitative BOLD MRI: reduced transverse relaxation bias using 3D-GraSE imaging. Neuroimage 220, 117095 (2020). https://doi.org/10.1016/j.neuroimage.2020.117095
Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In: Proceedings of the 3rd ICLR (2015). https://doi.org/10.48550/arXiv.1412.6980
Küstner, T., Armanious, K., Yang, J., Yang, B., Schick, F., Gatidis, S.: Retrospective correction of motion-affected MR images using deep learning frameworks. Magn. Reson. Med. 82(4), 1527–1540 (2019). https://doi.org/10.1002/mrm.27783
Magerkurth, J., et al.: Quantitative T2*-mapping based on multi-slice multiple gradient echo flash imaging: retrospective correction for subject motion effects: movement correction in T2* mapping. Magn. Reson. Med. 66(4), 989–997 (2011). https://doi.org/10.1002/mrm.22878
Nöth, U., Volz, S., Hattingen, E., Deichmann, R.: An improved method for retrospective motion correction in quantitative T2* mapping. NeuroImage 92, 106–119 (2014). https://doi.org/10.1016/j.neuroimage.2014.01.050
Oh, G., Lee, J.E., Ye, J.C.: Unpaired MR motion artifact deep learning using outlier-rejecting bootstrap aggregation. IEEE Trans. Med. Imaging 40(11), 3125–3139 (2021). https://doi.org/10.1109/TMI.2021.3089708
Singh, N.M., et al.: Data consistent deep rigid MRI motion correction. In: Medical Imaging with Deep Learning. Proceedings of Machine Learning Research, vol. 227, pp. 368–381. PMLR (2024). https://proceedings.mlr.press/v227/singh24a.html
Spieker, V., et al.: Deep learning for retrospective motion correction in MRI: a comprehensive review. IEEE Trans. Med. Imaging 43(2), 846–859 (2024). https://doi.org/10.1109/TMI.2023.3323215
Wang, Z., Bovik, A., Sheikh, H., Simoncelli, E.: Image quality assessment: from error visibility to structural similarity. IEEE Trans. Image Process. 13(4), 600–612 (2004). https://doi.org/10.1109/TIP.2003.819861
Xu, X., et al.: Learning-based motion artifact removal networks for quantitative R2\(\ast \) mapping. Magn. Reson. Med. 88(1), 106–119 (2022). https://doi.org/10.1002/mrm.29188
Zhang, L., Zhang, L., Mou, X., Zhang, D.: FSIM: a feature similarity index for image quality assessment. IEEE Trans. Image Process. 20(8), 2378–2386 (2011). https://doi.org/10.1109/TIP.2011.2109730
Acknowledgments
H.E. and V.S. are partially supported by the Helmholtz Association under the joint research school “Munich School for Data Science - MUDS”.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Ethics declarations
Disclosure of Interests
K.W. is an employee of Philips GmbH Market DACH.
1 Electronic supplementary material
Below is the link to the electronic supplementary material.
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Eichhorn, H. et al. (2024). Physics-Informed Deep Learning for Motion-Corrected Reconstruction of Quantitative Brain MRI. 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_54
Download citation
DOI: https://doi.org/10.1007/978-3-031-72104-5_54
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)