Cape Town - 2026 ISMRM-ISMRT Annual Meeting and Exhibition
9 May 2026 – 14 May 2026 · Cape Town, South Africa
431-03-004 / 431-03-004 ISMRM Abstract

Towards a Unified Theoretical Framework for Self-Supervised MRI Reconstruction

Primary: Acquisition & Reconstruction - Image Reconstruction: AI
Secondary: Acquisition & Reconstruction - AI methods
431-03-004 · Image Reconstruction · Tuesday, 12 May, 4:00 PM–5:36 PM · Roof Terrace
431-03-004 · Image Reconstruction · Tuesday, 12 May, 4:00 PM–5:36 PM · Roof Terrace
Keywords: AI/ML Image Reconstruction Deep learning reconstruction Undersampling Self-supervised learning Theoretical framework
Accepted
Siying Xu 1, Kerstin Hammernik2, Daniel Rueckert2,3, Sergios Gatidis1,4, Thomas Küstner1,5
1Medical Image and Data Analysis (MIDAS.lab), Department of Diagnostic and Interventional Radiology, University Hospital of Tuebingen, Tuebingen, Germany
2Chair for AI in Healthcare and Medicine, Technical University of Munich and TUM University Hospital, Munich, Germany
3Department of Computing, Imperial College London, London, United Kingdom
4Department of Radiology, Stanford University, Stanford, United States of America
5Institute for Bioinformatics and Medical Informatics, Eberhard-Karls University of Tuebingen, Tuebingen, Germany
Presenting Author: Siying Xu

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. Wang S, Su Z, Ying L, Peng X, Zhu S, Liang F, Feng D, Liang D. Accelerating magnetic resonance imaging via deep learning. In 2016 IEEE 13th international symposium on biomedical imaging (ISBI). 2016 Apr 13 (pp. 514-517). doi:10.1109/ISBI.2016.7493320 [doi]
2. Hammernik K, Klatzer T, Kobler E, Recht MP, Sodickson DK, Pock T, Knoll F. Learning a variational network for reconstruction of accelerated MRI data. Magnetic resonance in medicine. 2018 Jun;79(6):3055-71. doi:10.1002/mrm.26977 [doi]
3. Küstner T, Fuin N, Hammernik K, Bustin A, Qi H, Hajhosseiny R, Masci PG, Neji R, Rueckert D, Botnar RM, Prieto C. CINENet: deep learning-based 3D cardiac CINE MRI reconstruction with multi-coil complex-valued 4D spatio-temporal convolutions. Scientific reports. 2020 Aug 13;10(1):13710. doi:10.1038/s41598-020-70551-8 [doi]
4. Hammernik K, Küstner T, Yaman B, Huang Z, Rueckert D, Knoll F, Akçakaya M. Physics-driven deep learning for computational magnetic resonance imaging: Combining physics and machine learning for improved medical imaging. IEEE signal processing magazine. 2023 Jan 2;40(1):98-114. doi:10.1109/msp.2022.3215288 [doi]
5. Heckel R, Jacob M, Chaudhari A, Perlman O, Shimron E. Deep learning for accelerated and robust MRI reconstruction. Magnetic Resonance Materials in Physics, Biology and Medicine. 2024 Jul;37(3):335-68. doi:10.1007/s10334-024-01173-8 [doi]
6. Xu S, Hammernik K, Lingg A, Kuebler J, Krumm P, Rueckert D, Gatidis S, Kuestner T. Attention incorporated network for sharing low-rank, image and k-space information during MR image reconstruction to achieve single breath-hold cardiac Cine imaging. Computerized Medical Imaging and Graphics. 2025 Mar 1;120:102475. doi: 10.1016/j.compmedimag.2024.102475 [doi]
7. Lehtinen J, Munkberg J, Hasselgren J, Laine S, Karras T, Aittala M, Aila T. Noise2Noise: Learning image restoration without clean data. arXiv preprint arXiv:1803.04189. 2018 Mar 12. doi: 10.48550/arXiv.1803.04189 [doi]
8. Liu J, Sun Y, Eldeniz C, Gan W, An H, Kamilov US. RARE: Image reconstruction using deep priors learned without groundtruth. IEEE Journal of Selected Topics in Signal Processing. 2020 May 28;14(6):1088-99. doi:10.1109/JSTSP.2020.2998402 [doi]
9. Yaman B, Hosseini SA, Moeller S, Ellermann J, Uğurbil K, Akçakaya M. Self‐supervised learning of physics‐guided reconstruction neural networks without fully sampled reference data. Magnetic resonance in medicine. 2020 Dec;84(6):3172-91. doi:10.1002/mrm.28378 [doi]
10. Yaman B, Hosseini SA, Akçakaya M. Zero-shot self-supervised learning for MRI reconstruction. arXiv preprint arXiv:2102.07737. 2021 Feb 15. doi: 10.48550/arXiv.2102.07737 [doi]
11. Aggarwal HK, Pramanik A, John M, Jacob M. ENSURE: A general approach for unsupervised training of deep image reconstruction algorithms. IEEE transactions on medical imaging. 2022 Nov 23;42(4):1133-44. doi:10.1109/TMI.2022.3224359 [doi]
12. Cui ZX, Cao C, Liu S, Zhu Q, Cheng J, Wang H, Zhu Y, Liang D. Self-score: Self-supervised learning on score-based models for mri reconstruction. arXiv preprint arXiv:2209.00835. 2022 Sep 2. doi: 10.48550/arXiv.2209.00835 [doi]
13. Zou J, Li C, Jia S, Wu R, Pei T, Zheng H, Wang S. SelfCoLearn: Self-supervised collaborative learning for accelerating dynamic MR imaging. Bioengineering. 2022 Nov 4;9(11):650. doi:10.3390/bioengineering9110650 [doi]
14. Wang S, Wu R, Li C, Zou J, Zhang Z, Liu Q, Xi Y, Zheng H. PARCEL: Physics-based unsupervised contrastive representation learning for multi-coil MR imaging. IEEE/ACM Transactions on Computational Biology and Bioinformatics. 2022 Oct 11;20(5):2659-70. doi:10.1109/TCBB.2022.3213669 [doi]
15. Zhou B, Schlemper J, Dey N, Salehi SS, Sheth K, Liu C, Duncan JS, Sofka M. Dual-domain self-supervised learning for accelerated non-Cartesian MRI reconstruction. Medical Image Analysis. 2022 Oct 1;81:102538. doi:10.1016/j.media.2022.102538 [doi]
16. Korkmaz Y, Cukur T, Patel VM. Self-supervised MRI reconstruction with unrolled diffusion models. InInternational Conference on Medical Image Computing and Computer-Assisted Intervention 2023 Oct 1 (pp. 491-501). Cham: Springer Nature Switzerland. doi:10.1007/978-3-031-43999-5_47 [doi]
17. Millard C, Chiew M. A theoretical framework for self-supervised MR image reconstruction using sub-sampling via variable density Noisier2Noise. IEEE transactions on computational imaging. 2023 Jul 26;9:707-20. doi:10.1109/TCI.2023.3299212 [doi]
18. Molaei A, Aminimehr A, Tavakoli A, Kazerouni A, Azad B, Azad R, Merhof D. Implicit neural representation in medical imaging: A comparative survey. In Proceedings of the IEEE/CVF International Conference on Computer Vision 2023 (pp. 2381-2391). doi:10.48550/arXiv.2307.16142 [doi]
19. Wang F, Qi H, De Goyeneche A, Heckel R, Lustig M, Shimron E. K-band: self-supervised MRI reconstruction via stochastic gradient descent over k-space subsets. arXiv preprint arXiv:2308.02958. 2023 Aug 5. doi: 10.48550/arXiv.2308.02958 [doi]
20. Zou J, Pei T, Li C, Wu R, Wang S. Self-supervised federated learning for fast MR imaging. IEEE Transactions on Instrumentation and Measurement. 2023 Nov 10;73:1-1. doi:10.1109/TIM.2023.3331413 [doi]
21. Huang W, Spieker V, Xu S, Cruz G, Prieto C, Schnabel JA, Hammernik K, Kuestner T, Rueckert D. Subspace implicit neural representations for real-time cardiac cine MR imaging. In International Conference on Information Processing in Medical Imaging 2025 May 25 (pp. 168-183). doi:10.48550/arXiv.2412.12742 [doi]
22. Xu S, Früh M, Hammernik K, Lingg A, Kübler J, Krumm P, Rueckert D, Gatidis S, Küstner T. Self-supervised feature learning for cardiac Cine MR image reconstruction. IEEE Transactions on Medical Imaging. 2025 May 23. doi:10.1109/TMI.2025.3570226 [doi]
23. Li X, Huang J, Sun G, Yang Z. Self-supervised learning for MRI reconstruction: a review and new perspective. Magnetic Resonance Materials in Physics, Biology and Medicine. 2025 Jun 26:1-22. doi:10.1007/s10334-025-01274-y [doi]
24. Ahmad R, Xue H, Giri S, Ding Y, Craft J, Simonetti OP. Variable density incoherent spatiotemporal acquisition (VISTA) for highly accelerated cardiac MRI. Magnetic resonance in medicine. 2015 Nov;74(5):1266-78. doi:10.1002/mrm.25507 [doi]

Cite this abstract

http://echo.ismrm.org/p/ISMRM2026/431-03-004