DRIMET: Deep Registration for 3D Incompressible Motion Estimation in Tagged-MRI with Application to the Tongue

TL;DR

This paper introduces an unsupervised deep learning method for 3D motion estimation in tagged MRI, specifically for tongue motion, addressing challenges like tag fading and large deformations with improved accuracy and speed.

Contribution

The paper presents a novel phase-based deep registration technique with a sinusoidal transformation and Jacobian determinant loss to produce accurate, dense, and incompressible 3D motion fields in tagged MRI.

Findings

Outperforms existing methods in accuracy and robustness

Improves speed and handling of large tongue motions

Effectively manages tag fading in MRI data

Abstract

Tagged magnetic resonance imaging~(MRI) has been used for decades to observe and quantify the detailed motion of deforming tissue. However, this technique faces several challenges such as tag fading, large motion, long computation times, and difficulties in obtaining diffeomorphic incompressible flow fields. To address these issues, this paper presents a novel unsupervised phase-based 3D motion estimation technique for tagged MRI. We introduce two key innovations. First, we apply a sinusoidal transformation to the harmonic phase input, which enables end-to-end training and avoids the need for phase interpolation. Second, we propose a Jacobian determinant-based learning objective to encourage incompressible flow fields for deforming biological tissues. Our method efficiently estimates 3D motion fields that are accurate, dense, and approximately diffeomorphic and incompressible. The efficacy of the method is assessed using human tongue motion during speech, and includes both healthy controls and patients that have undergone glossectomy. We show that the method outperforms existing approaches, and also exhibits improvements in speed, robustness to tag fading, and large tongue motion. The code is available: https://github.com/jasonbian97/DRIMET-tagged-MRI