Groupwise Deformable Registration of Diffusion Tensor Cardiovascular Magnetic Resonance: Disentangling Diffusion Contrast, Respiratory and Cardiac Motions

TL;DR

This paper presents a novel groupwise registration framework for diffusion tensor cardiovascular magnetic resonance that effectively disentangles respiratory and cardiac motions while preserving diffusion contrast, improving analysis accuracy.

Contribution

It introduces a new registration method with an implicit template and tensor-embedded branch, tailored loss refinement, and novel evaluation metrics for DT-CMR motion correction.

Findings

Successfully isolates respiratory and cardiac motions in DT-CMR images

Preserves diffusion contrast textures during registration

Improves motion correction accuracy in low SNR conditions

Abstract

Diffusion tensor based cardiovascular magnetic resonance (DT-CMR) offers a non-invasive method to visualize the myocardial microstructure. With the assumption that the heart is stationary, frames are acquired with multiple repetitions for different diffusion encoding directions. However, motion from poor breath-holding and imprecise cardiac triggering complicates DT-CMR analysis, further challenged by its inherently low SNR, varied contrasts, and diffusion induced textures. Our solution is a novel framework employing groupwise registration with an implicit template to isolate respiratory and cardiac motions, while a tensor-embedded branch preserves diffusion contrast textures. We have devised a loss refinement tailored for non-linear least squares fitting and low SNR conditions. Additionally, we introduce new physics-based and clinical metrics for performance evaluation. Access code and supplementary materials at: https://github.com/ayanglab/DTCMR-Reg