New AI Speeds Up MRI Scans for Stiffness Mapping
This could mean faster, more comfortable scans and earlier detection of liver disease.
Magnetic Resonance Elastography (MRE) is a non-invasive imaging technique for mapping biomechanical properties of in vivo tissue, including shear wave speed (SWS), but it involves slow data acquisition and an ill-posed wave inversion. Researchers propose a data-driven approach that jointly combines image reconstruction and MRE inversion for robust SWS estimation from undersampled k-space data.
Their physics-informed framework has two blocks: a model-based neural-network-regularized reconstruction module and a phase-gradient inversion (k-MDEV) that calculates SWS from reconstructed images; concatenating both blocks yields an end-to-end trainable method to estimate SWS directly from measured k-space data. Evaluated on retrospectively highly undersampled brain MRE data against a total variation minimization-based approach, the method reduced NRMSE by 30% compared with TV, and end-to-end training improved SWS estimation over separate image reconstruction and SWS calculation.
The authors report accurate SWS quantification at acceleration factors up to 19, say the method significantly outperforms TV and generalizes to in vivo data, and describe it as the first end-to-end trainable MRE reconstruction method for estimating SWS maps directly from k-space. They suggest NN-based reconstruction can enable rapid stiffness mapping for dynamic studies, functional imaging, and real-time clinical feedback.
- AI makes a special MRI technique 19 times faster by using less data.
- It improves accuracy by 30% compared to traditional methods.
- This could lead to quicker, more comfortable scans and earlier disease detection.
Why It Matters
Faster, more accurate scans could mean earlier diagnosis and less time in the MRI machine.