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

TL;DR

This paper introduces a unified nonlinear inverse framework for tagged MRI that combines physics-based modeling and deep generative priors to simultaneously recover anatomy, synthesize cine images, and estimate motion, addressing longstanding challenges.

Contribution

It is the first to unify anatomy recovery, high-resolution image synthesis, and motion estimation in tagged MRI using a physics-informed deep generative approach.

Findings

Achieves high-resolution anatomy images from tagged MRI.

Produces more accurate motion estimation than existing methods.

Demonstrates effectiveness on brain MRI datasets.

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.