Solving a Nonlinear Blind Inverse Problem for Tagged MRI with Physics and Deep Generative Priors

TL;DR

This work introduces a blind and nonlinear inverse framework for tagged MRI that unifies these tasks: anatomical image recovery, high-resolution cine image synthesis, and motion estimation, and demonstrates that the approach yields high-resolution anatomy images, cine images, and more accurate motion than specialized methods.

Abstract

Tagged MRI enables tracking internal tissue motion non-invasively. It encodes motion by modulating anatomy with periodic tags, which deform along with tissue. However, the entanglement between anatomy, tags and motion poses significant challenges for post-processing. The existence of tags and imaging blur hinders downstream tasks such as segmenting anatomy. Tag fading, due to T1-relaxation, disrupts the brightness constancy assumption for motion tracking. For decades, these challenges have been handled in isolation and sub-optimally. In contrast, we introduce a blind and nonlinear inverse framework for tagged MRI that, for the first time, unifies these tasks: anatomical image recovery, high-resolution cine image synthesis, and motion estimation. At its core, the synergy of MR physics and generative priors enables us to blindly estimate the unknown forward imaging models and high-resolution underlying anatomy, while simultaneously tracking 3D diffeomorphic Lagrangian motion over time. Experiments on tagged brain MRI demonstrate that our approach yields high-resolution anatomy images, cine images, and more accurate motion than specialized methods.

Figures (7)

• Figure 1: We address a nonlinear blind inverse problem: given a time series of 3D tagged MRI volumes, we jointly estimate the imaging point spread functions responsible for image blurring, a sequence of high-resolution cine images, and the underlying motion fields. No additional training data are required.
• Figure 2: Qualitative comparison of tag-to-cine synthesis. For two subjects, we show early ($t{=}1$) and late ($t{=}6$) frames. Left-most column shows input tagged MRI (other views and orientations are omitted) while right-most shows ground-truth cine. Fourier spectrum of input and ours are shown. Orange arrows indicate the faded and smeared harmonic peaks. Red arrows indicate the aliasing artifact.
• Figure 3: Results of estimated point spread functions (PSFs) under different blurring settings and noise levels.
• Figure 4: Motion magnitude comparison across methods. Cols. 1-2: input tagged MRI at two time points. Last column: ground-truth motion magnitude. Both sagittal and coronal views are shown.
• Figure 5: Real tagged MRI: gel cylinder.