New starting point registration method for tagged MRI tongue motion estimation

TL;DR

This paper introduces a novel registration method for tagged MRI tongue motion estimation that effectively prevents tag jumping and improves accuracy over existing techniques.

Contribution

A new initialization approach combining PVIRA stationary velocity fields enhances tongue motion estimation accuracy and robustness against tag jumping in tagged MRI.

Findings

The proposed method successfully avoids tag jumping.

It outperforms existing methods in tongue motion estimation accuracy.

The approach demonstrates robustness in large motion scenarios.

Abstract

Accurate tongue motion estimation is essential for tongue function evaluation. The harmonic phase processing (HARP) method and the phase vector incompressible registration algorithm (PVIRA) based on HARP can generate motion estimates from tagged MRI images, but they suffer from tag jumping due to large motions. This paper proposes a new registration method by combining the stationary velocity fields produced by PVIRA between successive time frames as a new initialization of the final registration stage to avoid tag jumping. The experiment results demonstrate the proposed method can avoid tag jumping and outperform the existing methods on tongue motion estimates.