Cape Town - 2026 ISMRM-ISMRT Annual Meeting and Exhibition
9 May 2026 – 14 May 2026 · Cape Town, South Africa
351-03-010 / 351-03-010 ISMRM Abstract

K-space parallel imaging reconstruction using complex-valued deep Koopman autoencoders

Primary: Acquisition & Reconstruction - AI methods
Secondary: Acquisition & Reconstruction - Image Reconstruction: AI
351-03-010 · AI Methods · Monday, 11 May, 4:10 PM–5:46 PM · Power Pitch Theatre 1
351-03-010 · AI Methods · Monday, 11 May, 4:10 PM–5:46 PM · Power Pitch Theatre 1
Keywords: Parallel Imaging AI/ML Image Reconstruction Koopman Autoencoder K-space interpolation Accelerated imaging
Accepted
Wassim Ben Salah 1,2, Jon O Cleary3,4, Sarah McElroy5, Antoine Naegel6, Kasim Ali Mohamed3, Saranya BALESWARAN3, Sebastien Ourselin2, Jonathan Shapey2,7, Christos Bergeles2, Radhouene Neji1,2
1Imaging Physics and Engineering Department, School of Biomedical Engineering & Imaging Sciences, King's College London, London, United Kingdom
2Surgical & Interventional Engineering Research Department, School of Biomedical Engineering and Imaging Sciences, King's College London, London, United Kingdom
3Department of Radiology, Guy's and St. Thomas' NHS Foundation Trust, London, United Kingdom
4Research Department of Cancer Imaging, School of Biomedical Engineering and Imaging Sciences, King's College London, London, United Kingdom
5MR Research Collaborations, Siemens Healthcare Limited, Montreal, Canada
6Siemens Healthcare SAS, Courbevoie, France
7Department of Neurosurgery, King's College Hospital NHS Foundation Trust London, London, United Kingdom
Presenting Author: Wassim Ben Salah

Synopsis

Motivation:
Goals:
Approach:
Results:
Full abstract & presentation

The full text, figures, and any recorded presentation for this abstract are not shown here. Log in if you are a member or registered attendee with access.

Full abstracts, figures, and presentations for Cape Town - 2026 ISMRM-ISMRT Annual Meeting and Exhibition are available to registered attendees. This content becomes freely available to the public roughly two years after the meeting.

To request or purchase access, contact the ISMRM Central Office at info@ismrm.org.

Log in

References

1. Griswold, Mark A et al. “Generalized autocalibrating partially parallel acquisitions (GRAPPA).” Magnetic resonance in medicine vol. 47,6 (2002):1202-10. doi:10.1002/mrm.10171 [doi]
2. Chang, Yuchou et al. “Nonlinear GRAPPA: a kernel approach to parallel MRI reconstruction.” Magnetic resonance in medicine vol. 68,3 (2012):730-40. doi:10.1002/mrm.23279 [doi]
3. Akçakaya, Mehmet et al. “Scan-specific robust artificial-neural-networks for k-space interpolation (RAKI) reconstruction: Database-free deeplearning for fast imaging.” Magnetic resonance in medicine vol. 81,1 (2019): 439-453. doi:10.1002/mrm.27420 [doi]
4. Ben Salah, Wassim et al. "K-space Interpolation using Deep Koopman Autoencoders", 5150, In ISMRM & ISMRT 2025 Annual Meeting & Exhibition. ISMRM, 2025. https://doi.org/10.58530/2025/5150 [doi]
5. Huang, F. and Duensing, G.R., 2006, May. A theoretical analysis of errors in GRAPPA. In Proceedings of the 14th Annual Meeting of ISMRM, Seattle (Vol. 2468).
6. Nana, R., Zhao, T., Heberlein, K., LaConte, S.M. and Hu, X., 2008. Cross‐validation‐based kernel support selection for improved GRAPPA reconstruction. Magnetic Resonance in Medicine: An Official Journal of the International Society for Magnetic Resonance in Medicine, 59(4), pp.819-825.
7. Nana, R. and Hu, X., 2010. Data consistency criterion for selecting parameters for k-space-based reconstruction in parallel imaging. Magnetic resonance imaging, 28(1), pp.119-128.
8. Dawood P, Breuer F, Gram M, et al. Image space formalism of convolutional neural networks for k-space interpolation. Magn Reson Med. 2025; 94(6): 2680-2701. doi: 10.1002/mrm.70002 [doi]
9. Lusch, B., Kutz, J.N. & Brunton, S.L. Deep learning for universal linear embeddings of nonlinear dynamics. Nat Commun 9, 4950 (2018). https://doi.org/10.1038/s41467-018-07210-0 [doi]
10. Brunton, S.L., Budišić, M., Kaiser, E. and Kutz, J.N., 2021. Modern Koopman theory for dynamical systems. arXiv preprint arXiv:2102.12086.
11. Poole, Ben, Jascha Sohl-Dickstein, and Surya Ganguli. "Analyzing noise in autoencoders and deep networks." arXiv preprint arXiv:1406.1831(2014).
12. Arjovsky, M., Shah, A. and Bengio, Y., 2016, June. Unitary evolution recurrent neural networks. In International conference on machine learning (pp. 1120-1128). PMLR.
13. Zbontar, Jure, et al. "fastMRI: An open dataset and benchmarks for accelerated MRI." arXiv preprint arXiv:1811.08839 (2018).
14. He, K., Zhang, X., Ren, S. and Sun, J., 2015. Delving deep into rectifiers: Surpassing human-level performance on imagenet classification. In Proceedings of the IEEE international conference on computer vision (pp. 1026-1034).
15. Sutskever, I., Martens, J., Dahl, G. and Hinton, G., 2013, May. On the importance of initialization and momentum in deep learning. In International conference on machine learning (pp. 1139-1147). pmlr.
16. Kingma, D.P., 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980.

Cite this abstract

http://echo.ismrm.org/p/ISMRM2026/351-03-010