High-Resolution Quantitative MRI Using Contrast-Domain Multiscale Energy (MuSE) Regularization
eess.IV
Submitted: 2026-11-03
Updated: 2026-11-03
Comments: 5 pages, 3 figures
License: http://creativecommons.org/licenses/by/4.0/
The gist: Quantitative MRI methods can offer tissue parameter maps (e.g.
Terminology
Abstract
Quantitative MRI methods can offer tissue parameter maps (e.g. T1) that are comparable across scanners, sessions and subjects, together with multiple contrast-weighted images from a single scan. However, most data are acquired at 1 mm, which limits their use in neurodegenerative diseases that affect fine brain structures. We introduce, to our knowledge, the first diffusion-model-based reconstruction for quantitative MRI at 0.5 mm isotropic resolution from scans of less than 5 minutes, which has eightfold smaller voxel volume than clinical protocols. The key idea is to apply the prior to the synthesized contrast images rather than to the subspace coefficients. The prior is then independent of the temporal basis and the sequence, which improves generalization and allows a 2-D multiscale energy (MuSE) model trained on grayscale CelebA face images to be used without any MRI training data. The explicit energy makes reconstruction MAP estimation by a step-size-free majorize-minimize algorithm that regularizes a rotating subset of contrasts along different axes, which makes 3-D multi-contrast reconstruction tractable. For 3-D radial MPnRAGE at 7 T in 4.3 min, MuSE reduced the phantom NRMSE from 0.133 (CG-SENSE) and 0.091 (L1-wavelet) to 0.074 and the WM T1 interquartile range from 117 and 47 ms to 38 ms, and it was demonstrated in vivo at 7 T.
Sources
- Annealed Langevin Posterior Sampling (ALPS): A Rapid Algorithm for Image Restoration with Multiscale Energy Models
- Bigger Isn't Always Better: Towards a General Prior for Medical Image Reconstruction
- On the Posterior Distribution in Denoising: Application to Uncertainty Quantification
Related papers
- HDNet: High-resolution Dual-domain Learning for Spectral Compressive Imaging
- Mask-guided Spectral-wise Transformer for Efficient Hyperspectral Image Reconstruction
- FDIR: Fidelity-Anchored Decompressed Image Restoration for Human and Machine Perception
- A Disease-Centric Vision-Language Foundation Model for Precision Oncology in Kidney Cancer
- CADS: A Comprehensive Anatomical Dataset and Segmentation for Whole-Body Anatomy in Computed Tomography
- Task-Aware Bitrate Thresholds for Codec-Robust Ultrasound Segmentation