WarpPINN-fibers outperformed alternative methodologies in landmark tracking and strain curve prediction for a cine-MRI benchmark in 15 healthy volunteers.
WarpPINN-fibers provides improved cardiac strain estimation from standard cine-MRI by incorporating fiber mechanics into a physics-informed neural network.
The contractile motion of the heart is strongly determined by the distribution of the fibers that constitute cardiac tissue. Strain analysis informed with the orientation of fibers allows to describe several pathologies that are typically associated with impaired mechanics of the myocardium, such as cardiovascular disease. Several methods have been developed to estimate strain-derived metrics from traditional imaging techniques. However, the physical models underlying these methods do not include fiber mechanics, restricting their capacity to accurately explain cardiac function. In this work, we introduce WarpPINN-fibers, a physics-informed neural network framework to accurately obtain cardiac motion and strains enhanced by fiber information. We train our neural network to satisfy a hyper-elastic model and promote fiber contraction with the goal to predict the deformation field of the heart from cine magnetic resonance images. For this purpose, we build a loss function composed of three terms: a data-similarity loss between the reference and the warped template images, a regularizer enforcing near-incompressibility of cardiac tissue and a fiber-stretch penalization that controls strain in the direction of synthetically produced fibers. We show that our neural network improves the former WarpPINN model and effectively controls fiber stretch in a synthetic phantom experiment. Then, we demonstrate that WarpPINN-fibers outperforms alternative methodologies in landmark tracking and strain curve prediction for a cine-MRI benchmark with a cohort of 15 healthy volunteers. We expect that our method will provide more precise cardiac strain quantification through the accurate reconstruction of physiologically consistent deformation fields, releasing the reliance on advanced displacement-mapping techniques such as DENSE or magnetization tagging, as well as fiber-reconstruction modalities like diffusion tensor imaging. A version of WarpPINN-fibers using the accelerated JAX framework can be found at https://github.com/HiddenHeartLab/WarpPINN-fibers-demo.git.
Álvarez-Barrientos et al. (Thu,) conducted a other in Healthy volunteers (n=15). WarpPINN-fibers vs. Alternative methodologies (including former WarpPINN model) was evaluated on Landmark tracking and strain curve prediction. WarpPINN-fibers outperformed alternative methodologies in landmark tracking and strain curve prediction for a cine-MRI benchmark in 15 healthy volunteers.