Towards Physics-Driven Neural-Network pTx Design with Hard Constraints
Motivation: Optimization of parallel transmission (pTx) pulse design with hard constraints on SAR will benefit from faster approaches. Goal(s): We seek to incorporate hard quadratic constraints for pTx using a physics-driven deep learning (DL) approach. Approach: We unroll an extension of the log-barrier method to enforce SAR constraints, while learning the optimal gradient step sizes using a neural network. This strategy accelerates optimization with fewer steps, while not sacrificing performance. Results: Preliminary results show that our method is faster than traditional techniques like CVXPY with similar performance. Impact: Our proposed method reduces the time-consuming optimization used in conventional pTx and may lead to improvements especially for real-time UHF applications.
Authors
- Ömer Faruk Demirel (ORCID: https://orcid.org/0000-0003-3012-1252)
- Patrick Alexander Liebig (ORCID: https://orcid.org/0000-0001-7342-3715)
- Toygan Kılıç (ORCID: https://orcid.org/0000-0001-7969-5738)
- Mehmet Akçakaya (ORCID: https://orcid.org/0000-0001-6400-7736)
- Kâmil Uǧurbil (ORCID: https://orcid.org/0000-0002-8475-9334)
- Jürgen Herrler (ORCID: https://orcid.org/0000-0002-4620-8216)
- Armin Michael Nagel (ORCID: https://orcid.org/0000-0003-0948-1421)
- Mingyi Hong (ORCID: https://orcid.org/0000-0003-1263-9365)
Publication Details
- Journal
- Proceedings on CD-ROM - International Society for Magnetic Resonance in Medicine. Scientific Meeting and Exhibition/Proceedings of the International Society for Magnetic Resonance in Medicine, Scientific Meeting and Exhibition
- Published
- 2024-11-26
- DOI
- https://doi.org/10.58530/2024/4091
- Primary Topic
- Neural Networks and Applications
- Type
- article
- Field-Weighted Citation Impact
- 0.00