Dynamic imaging using Motion-Compensated SmooThness Regularization on Manifolds (MoCo-SToRM)

TL;DR

This paper presents an unsupervised MRI reconstruction method that models respiratory and bulk motion as smooth deformations on a manifold, using a CNN generator and latent vectors to improve high-resolution free-breathing pulmonary MRI.

Contribution

It introduces a novel unsupervised framework modeling motion as a manifold of deformation maps driven by a CNN generator with shared weights and low-dimensional latent vectors.

Findings

Improved image reconstruction quality over existing methods.

Effective handling of bulk motion during scans.

Unsupervised learning of motion and image volume from k-t space data.

Abstract

We introduce an unsupervised motion-compensated reconstruction scheme for high-resolution free-breathing pulmonary MRI. We model the image frames in the time series as the deformed version of the 3D template image volume. We assume the deformation maps to be points on a smooth manifold in high-dimensional space. Specifically, we model the deformation map at each time instant as the output of a CNN-based generator that has the same weight for all time-frames, driven by a low-dimensional latent vector. The time series of latent vectors account for the dynamics in the dataset, including respiratory motion and bulk motion. The template image volume, the parameters of the generator, and the latent vectors are learned directly from the k-t space data in an unsupervised fashion. Our experimental results show improved reconstructions compared to state-of-the-art methods, especially in the context of bulk motion during the scans.