Physics-Informed Deep Learning for Shear Wave Speed Estimation in MR Elastography
Organizations: Physikalisch-Technische Bundesanstalt (PTB), Braunschweig and Berlin, Germany · Charité - Universitätsmedizin Berlin, Germany
Abstract
Objective: Magnetic Resonance Elastography (MRE) is a non-invasive imaging technique for mapping biomechanical properties of in vivo tissue, including shear wave speed (SWS), but involves intrinsically slow data acquisition and an ill-posed wave inversion. Instead of relying on handcrafted image priors, we propose a data-driven approach jointly combining image reconstruction and MRE inversion for robust SWS estimation from undersampled k-space data. Methods: Our physics-informed reconstruction framework comprises two blocks: a model-based neural network (NN)-regularized reconstruction module and a phase-gradient inversion (k-MDEV) calculating SWS from the reconstructed images. Concatenating both blocks yields an end-to-end trainable method to estimate SWS directly from measured k-space data. We evaluated the method on retrospectively highly undersampled brain MRE data and compared it to a total variation (TV) minimization-based approach. We assessed the impact of end-to-end training (qualitative images and SWS maps as targets) versus pre-training (qualitative images as targets) and applied the method also to in vivo data. Results: Our approach significantly reduces NRMSE by 30% compared to TV. End-to-end training improves SWS estimation over separate image reconstruction and SWS calculation. Conclusion: Accurate SWS quantification is possible at acceleration factors up to 19. Our method significantly outperforms TV, highlighting the need for data-driven regularization in this challenging MR problem. Further, our approach successfully generalizes to in vivo data. Significance: We present the first end-to-end trainable MRE reconstruction method for estimating SWS maps directly from k-space. NN-based reconstruction can enable rapid stiffness mapping for dynamic studies, functional imaging, and real-time clinical feedback.
Figures & tables
| Spirals | Method | SSIM | NRMSE | PSNR (dB) |
| 1 | Adjoint | 0.75 0.072 | 0.43 0.054 | 21.10 2.96 |
| it. SENSE | 0.83 0.051 | 0.23 0.040 | 26.79 2.69 | |
| TV | 0.87 0.049 | 0.20 0.041 | 27.81 2.58 | |
| Proposed | 0.93 0.030 | 0.14 0.033 | 30.92 2.34 | |
| 2 | Adjoint | 0.83 0.055 | 0.26 0.030 | 25.37 2.88 |
| it. SENSE | 0.92 0.035 | 0.16 0.036 | 30.10 2.65 |
| T | SSIM | NRMSE | PSNR (dB) | ||
| Image | 1 | 0.00 | 0.90 0.041 | 0.16 0.031 | 31.45 2.64 |
| 1 | 0.10 | 0.91 0.042 | 0.14 0.033 | 31.69 2.74 | |
| 1 | 0.15 | 0.91 0.041 | 0.14 0.032 | 31.75 2.75 | |
| 1 | 0.50 | 0.91 0.041 | 0.14 0.033 | 31.90 2.75 | |
| 6 | 0.00 | 0.95 0.030 | 0.10 0.029 | 34.97 3.07 | |
| 6 | 0.10 | 0.95 0.029 | 0.09 0.028 | 35.34 3.09 |
Magnetic Resonance Imaging
Magnetic resonance imaging uses magnetic fields and radio waves to create images of anatomy and tissue function for research and clinical care.
See all 273 papers