Learning correspondences of cardiac motion from images using biomechanics-informed modeling

TL;DR

This paper introduces a biomechanics-informed regularization method for modeling cardiac motion from images, improving the physical plausibility and segmentation accuracy of the predicted transformations without added training complexity.

Contribution

It proposes a novel biomechanics-informed prior as regularization on the displacement field, enhancing the physical realism of cardiac motion models across all structures.

Findings

Better preservation of biomechanical properties visually

Improved segmentation performance quantitatively

Robustness demonstrated across datasets

Abstract

Learning spatial-temporal correspondences in cardiac motion from images is important for understanding the underlying dynamics of cardiac anatomical structures. Many methods explicitly impose smoothness constraints such as the $\mathcal{L}_2$ norm on the displacement vector field (DVF), while usually ignoring biomechanical feasibility in the transformation. Other geometric constraints either regularize specific regions of interest such as imposing incompressibility on the myocardium or introduce additional steps such as training a separate network-based regularizer on physically simulated datasets. In this work, we propose an explicit biomechanics-informed prior as regularization on the predicted DVF in modeling a more generic biomechanically plausible transformation within all cardiac structures without introducing additional training complexity. We validate our methods on two publicly available datasets in the context of 2D MRI data and perform extensive experiments to illustrate the effectiveness and robustness of our proposed methods compared to other competing regularization schemes. Our proposed methods better preserve biomechanical properties by visual assessment and show advantages in segmentation performance using quantitative evaluation metrics. The code is publicly available at \url{https://github.com/Voldemort108X/bioinformed_reg}.