Cape Town - 2026 ISMRM-ISMRT Annual Meeting and Exhibition
9 May 2026 – 14 May 2026 · Cape Town, South Africa
561-04-004 ISMRM Abstract

Mitigating Divergence in PINN(Physics-Informed Neural Network)-MREPT using Stepwise Training and Collocation Enhancement

Primary: Acquisition & Reconstruction - AI methods
Secondary: Acquisition & Reconstruction - Image Reconstruction: AI
561-04-004 · Deep Learning Meets k-Space: New Frontiers in Reconstruction · Wednesday, 13 May, 2:35 PM–3:30 PM · Digital Posters Row B
Keywords: Dielectric properties Electric properties tomography Physics-informed Neural Networks Stepwised learning Collocation points
Accepted
Ruian Qin1, Junqi YANG 1, shaoying huang2, Wenwei Yu1,3
1Department of Medical Engineering, Chiba University, Chiba, Japan
2Engineering Product Development, Singapore University of Technology and Design, Singapore, Singapore
3Center for Frontier Medical Engineering, Chiba University, Chiba, Japan
Presenting Author: Junqi YANG

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. Zhang, Liu, and He. Magnetic-resonance-based electrical properties tomography: a review. IEEE reviews in biomedical engineering. 2014;7:87–96.
2. Leijsen, Brink, Berg, van den, Webb, and Remis. Electrical properties tomography: a methodological review. Diagnostics. 2021;11(2):176.
3. Wen. Noninvasive quantitative mapping of conductivity and dielectric distributions using rf wave propagation effects in high-field mri. In Medical Imaging 2003: Physics of Medical Imaging. SPIE. 2003. pp. 471–7.
4. Hafalir, Oran, Gurler, and Ider. Convection-reaction equation based magnetic resonance electrical properties tomography (cr-mrept). IEEE transactions on medical imaging. 2014;33(3):777–93.
5. Li, Yu, and Huang. An mr-based viscosity-type regularization method for electrical property tomography. Tomography. 2017;3(1):50.
6. Inda, Huang, İmamoğlu, Qin, Yang, Chen, Yuan, and Yu. Physics informed neural networks (pinn) for low snr magnetic resonance electrical properties tomography (mrept). Diagnostics. 2022;12(11):2627.
7. Ruan, Wang, Liu, Xia, Wang, Qi, and Chen. Magnetic resonance electrical properties tomography based on modified physics-informed neural network and multiconstraints. IEEE Transactions on Medical Imaging. 2024;43(9):3263–78.
8. Gazoulis, Gkanis, and Makridakis. On the stability and convergence of physics informed neural networks. arXiv preprint arXiv:2308.05423. 2023.
9. Doumèche, Biau, and Boyer. On the convergence of pinns. Bernoulli. 2025;31(3):2127–51.
10. Wong, Ooi, Gupta, and Ong. Learning in sinusoidal spaces with physics-informed neural networks. IEEE Transactions on Artificial Intelligence. 2022;5(3):985–1000.
11. Rohrhofer, Posch, Gößnitzer, and Geiger. On the role of fixed points of dynamical systems in training physics-informed neural networks. arXiv preprint arXiv:2203.13648. 2022.

Cite this abstract

http://echo.ismrm.org/p/ISMRM2026/561-04-004