Cape Town - 2026 ISMRM-ISMRT Annual Meeting and Exhibition
9 May 2026 – 14 May 2026 · Cape Town, South Africa
567-02-013 ISMRM Abstract

Highly-Efficient RF Pulse Design via Compiler-Level Reverse-Mode Automatic Differentiation of GPU-Accelerated MRI Simulations

Primary: Physics & Engineering - RF Pulse Design & Fields
Secondary: Acquisition & Reconstruction - Open source software, sequences, and reconstruction algorithms
567-02-013 · Open-Source Software, Sequences, and Reconstruction Algorithms · Wednesday, 13 May, 9:15 AM–10:10 AM · Digital Posters Row H
Keywords: Open-source software RF Pulse Design Bloch simulations GPU acceleration
Accepted
Kareem Fareed 1, Charles McGrath1,2, Jakub Mitura3, Daniel B Ennis1,2,4, Carlos A Castillo-Passi1,2
1Department of Radiology, Stanford University, Stanford, United States of America
2Cardiovascular Institute, Stanford University, Stanford, United States of America
3University Clinic for Radiology and Nuclear Medicine, Otto von Guericke University Magdeburg, Magdeburg, Germany
4Department of Bioengineering, Stanford University, Stanford, United States of America
Presenting Author: Kareem Fareed

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. Saslow L, Li DKB, Halper J, Banwell B, Barkhof F, Barlow L, Costello K, Damiri P, Dunn J, Giri S, Maes M, Morrow SA, Newsome SD, Oh J, Paul F, Quarterman P, Reich DS, Shewchuk JR, Shinohara RT, Van Hecke W, van de Ven K, Wallin MT, Wolinsky JS, Traboulsee A. An International Standardized Magnetic Resonance Imaging Protocol for Diagnosis and Follow-up of Patients with Multiple Sclerosis: Advocacy, Dissemination, and Implementation Strategies. Int J MS Care. 2020 Sep-Oct;22(5):226-232. doi: 10.7224/1537-2073.2020-094. Epub 2020 Oct 27. PMID: 33177959; PMCID: PMC7643842. [doi] [pmid]
2. Wilm BJ, Svensson J, Henning A, Pruessmann KP, Boesiger P, Kollias SS. Reduced field-of-view MRI using outer volume suppression for spinal cord diffusion imaging. Magn Reson Med. 2007 Mar;57(3):625-30. doi: 10.1002/mrm.21167. PMID: 17326167. [doi] [pmid]
3. Wheeler-Kingshott CA, Hickman SJ, Parker GJ, Ciccarelli O, Symms MR, Miller DH, Barker GJ. Investigating cervical spinal cord structure using axial diffusion tensor imaging. Neuroimage. 2002 May;16(1):93-102. doi: 10.1006/nimg.2001.1022. PMID: 11969321. [doi] [pmid]
4. Saritas, E. U., Cunningham, C. H., Lee, J. H., Han, E. T., & Nishimura, D. G. (2008). DWI of the spinal cord with reduced FOV single-shot EPI. Magnetic Resonance in Medicine, 60(2), 468-473. https://doi.org/10.1002/mrm.21640 [doi]
5. Luo T, Noll DC, Fessler JA, Nielsen JF. Joint Design of RF and Gradient Waveforms via Auto-differentiation for 3D Tailored Excitation in MRI. IEEE Trans Med Imaging. 2021 Dec;40(12):3305-3314. doi: 10.1109/TMI.2021.3083104. Epub 2021 Nov 30. PMID: 34029188; PMCID: PMC8669750. [doi] [pmid]
6. Moses William, Churavy Valentin. Instead of Rewriting Foreign Code for Machine Learning, Automatically Synthesize Fast Gradients. https://doi.org/10.5555/3495724.3496770 [doi]
7. William S. Moses, Valentin Churavy, Ludger Paehler, Jan Hückelheim, Sri Hari Krishna Narayanan, Michel Schanen, and Johannes Doerfert. 2021. Reverse-mode automatic differentiation and optimization of GPU kernels via Enzyme. In Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis (SC '21). Association for Computing Machinery, New York, NY, USA, Article 61, 1–16. https://doi.org/10.1145/3458817.3476165 [doi]
8. Castillo-Passi C, Coronado R, Varela-Mattatall G, Alberola-López C, Botnar R, Irarrazaval P. KomaMRI.jl: An open-source framework for general MRI simulations with GPU acceleration. Magn Reson Med. 2023; 90: 329-342. doi:10.1002/mrm.29635 [doi]
9. Malitsky, Y., & Mishchenko, K. (2019). Adaptive Gradient Descent without Descent. ArXiv. https://arxiv.org/abs/1910.09529
10. Glover GH. Simple analytic spiral K-space algorithm. Magn Reson Med. 1999 Aug;42(2):412-5. doi: 10.1002/(sici)1522-2594(199908)42:2<412::aid-mrm25>3.0.co;2-u. PMID: 10440968. [doi] [pmid]
11. Layton KJ, Kroboth S, Jia F, Littin S, Yu H, Leupold J, Nielsen JF, Stöcker T, Zaitsev M. Pulseq: A rapid and hardware-independent pulse sequence prototyping framework. Magn Reson Med. 2017 Apr;77(4):1544-1552. doi: 10.1002/mrm.26235. Epub 2016 Jun 7. PMID: 27271292. [doi] [pmid]
12. Weine J, McGrath C, Kozerke S. CMRSeq – A Python package for intuitive sequence design. In: Proceedings of the 31st Annual Meeting of the International Society for Magnetic Resonance in Medicine (ISMRM); 3–8 June 2023; Toronto, Canada. Abstract 2398.
13. Churavy, V. (2025). KernelAbstractions.jl (v0.9.38). Zenodo. https://doi.org/10.5281/zenodo.16328263 [doi]
14. Besard, T., Foket, C., & De Sutter, B. (2017). Effective Extensible Programming: Unleashing Julia on GPUs. ArXiv. https://doi.org/10.1109/TPDS.2018.2872064 [doi]
15. Liu H, Versteeg E, Fuderer M, van der Heide O, Schilder MB, van den Berg CAT, Sbrizzi A. Time-efficient, high-resolution 3T whole-brain relaxometry using Cartesian 3D MR Spin Tomography in Time-Domain (MR-STAT) with cerebrospinal fluid suppression. Magn Reson Med. 2025 May;93(5):2008-2019. doi: 10.1002/mrm.30384. Epub 2024 Nov 28. PMID: 39607873; PMCID: PMC11893030. [doi] [pmid]
16. Sbrizzi, A., Van der Heide, O., Cloos, M., Van der Toorn, A., Hoogduin, H., Luijten, P.R. and Van den Berg, C.A., (2018). Fast quantitative MRI as a nonlinear tomography problem. Mag Res Imag 46:56-63. https://doi.org/10.1016/j.mri.2017.10.015; [doi]

Cite this abstract

http://echo.ismrm.org/p/ISMRM2026/567-02-013