Abstract
Numerous deep neural network (DNN)-based methods have been proposed in recent years to tackle the challenging ill-posed inverse problem of MRI reconstruction from undersampled ‘k-space’ (Fourier domain) data. However, these methods have shown instability when faced with variations in the acquisition process and anatomical distribution. This instability indicates that DNN architectures have poorer generalization compared to their classical counterparts in capturing the relevant physical models. Consequently, the limited generalization hinders the applicability of DNNs for undersampled MRI reconstruction in the clinical setting, which is especially critical in detecting subtle pathological regions that play a crucial role in clinical diagnosis. We enhance the generalization capacity of deep neural network (DNN) methods for undersampled MRI reconstruction by introducing a physically-primed DNN architecture and training approach. Our architecture incorporates the undersampling mask into the model and utilizes a specialized training method that leverages data generated with various undersampling masks to encourage the model to generalize the undersampled MRI reconstruction problem. Through extensive experimentation on the publicly available Fast-MRI dataset, we demonstrate the added value of our approach. Our physically-primed approach exhibits significantly improved robustness against variations in the acquisition process and anatomical distribution, particularly in pathological regions, compared to both vanilla DNN methods and DNNs trained with undersampling mask augmentation.
Trained models and code for experiment replication are available at: https://github.com/nitzanavidan/PD_Recon.
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
References
Aja-Fernández, S., Vegas-Sánchez-Ferrero, G.: Statistical Analysis of Noise in MRI. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-39934-8
Antun, V., Renna, F., Poon, C., Adcock, B., Hansen, A.C.: On instabilities of deep learning in image reconstruction and the potential costs of AI. Proc. Natl. Acad. Sci. 117(48), 30088–30095 (2020)
Chen, Y., et al.: AI-based reconstruction for fast MRI-a systematic review and meta-analysis. Proc. IEEE 110(2), 224–245 (2022)
Eo, T., Jun, Y., Kim, T., Jang, J., Lee, H.J., Hwang, D.: Kiki-net: cross-domain convolutional neural networks for reconstructing undersampled magnetic resonance images. Magn. Reson. Med. 80(5), 2188–2201 (2018)
Feinberg, D.A., Hale, J.D., Watts, J.C., Kaufman, L., Mark, A.: Halving MR imaging time by conjugation: demonstration at 3.5 kg. Radiology 161(2), 527–531 (1986)
Griswold, M.A., et al.: Generalized autocalibrating partially parallel acquisitions (GRAPPA). Magn. Reson. Med. Off. J. Int. Soc. Magn. Reson. Med. 47(6), 1202–1210 (2002)
Hammernik, K., et al.: Physics-driven deep learning for computational magnetic resonance imaging. arXiv preprint arXiv:2203.12215 (2022)
Hyun, C.M., Kim, H.P., Lee, S.M., Lee, S., Seo, J.K.: Deep learning for undersampled MRI reconstruction. Phys. Med. Biol. 63(13), 135007 (2018)
Jalal, A., Arvinte, M., Daras, G., Price, E., Dimakis, A.G., Tamir, J.: Robust compressed sensing MRI with deep generative priors. Adv. Neural. Inf. Process. Syst. 34, 14938–14954 (2021)
Liang, Z.P., Lauterbur, P.C.: Principles of Magnetic Resonance Imaging. SPIE Optical Engineering Press, Bellingham (2000)
Liu, F., Samsonov, A., Chen, L., Kijowski, R., Feng, L.: SANTIS: sampling-augmented neural network with incoherent structure for MR image reconstruction. Magn. Reson. Med. 82(5), 1890–1904 (2019)
Lustig, M., Donoho, D., Pauly, J.M.: Sparse MRI: the application of compressed sensing for rapid MR imaging. Magn. Reson. Med. Off. J. Int. Soc. Magn. Reson. Med. 58(6), 1182–1195 (2007)
Pruessmann, K.P., Weiger, M., Scheidegger, M.B., Boesiger, P.: Sense: sensitivity encoding for fast MRI. Magn. Reson. Med. Off. J. Int. Soc. Magn. Reson. Med. 42(5), 952–962 (1999)
Ronneberger, O., Fischer, P., Brox, T.: U-Net: convolutional networks for biomedical image segmentation. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds.) MICCAI 2015. LNCS, vol. 9351, pp. 234–241. Springer, Cham (2015). https://doi.org/10.1007/978-3-319-24574-4_28
Sriram, A., et al.: End-to-end variational networks for accelerated MRI reconstruction. In: Martel, A.L., et al. (eds.) MICCAI 2020. LNCS, vol. 12262, pp. 64–73. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-59713-9_7
Yang, G., et al.: DAGAN: deep de-aliasing generative adversarial networks for fast compressed sensing MRI reconstruction. IEEE Trans. Med. Imaging 37(6), 1310–1321 (2017)
Zbontar, J., et al.: fastMRI: an open dataset and benchmarks for accelerated MRI. arXiv preprint arXiv:1811.08839 (2018)
Zhao, R., et al.: fastMRI+: clinical pathology annotations for knee and brain fully sampled multi-coil MRI data. arXiv preprint arXiv:2109.03812 (2021)
Acknowledgements
This research was supported in part by a research grant from Microsoft Education and the Israel Inter-university computation center (IUCC).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Avidan, N., Freiman, M. (2023). Deep Learning-Based Fast MRI Reconstruction: Improving Generalization for Clinical Translation. In: Wesarg, S., et al. Clinical Image-Based Procedures, Fairness of AI in Medical Imaging, and Ethical and Philosophical Issues in Medical Imaging. CLIP EPIMI FAIMI 2023 2023 2023. Lecture Notes in Computer Science, vol 14242. Springer, Cham. https://doi.org/10.1007/978-3-031-45249-9_6
Download citation
DOI: https://doi.org/10.1007/978-3-031-45249-9_6
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-45248-2
Online ISBN: 978-3-031-45249-9
eBook Packages: Computer ScienceComputer Science (R0)
