WarpPINN: Cine-MR image registration with physics-informed neural networks

TL;DR

WarpPINN is a physics-informed neural network designed for cine-MRI image registration that accurately estimates cardiac deformation and strain, improving diagnosis of heart failure by capturing local tissue mechanics.

Contribution

This work introduces WarpPINN, a novel neural network architecture that incorporates physical tissue properties and Fourier features for improved cardiac image registration and strain estimation.

Findings

Outperforms existing landmark tracking methods

Accurately estimates cardiac strain from cine-MRI

Demonstrates effectiveness on synthetic and real data

Abstract

Heart failure is typically diagnosed with a global function assessment, such as ejection fraction. However, these metrics have low discriminate power, failing to distinguish different types of this disease. Quantifying local deformations in the form of cardiac strain can provide helpful information, but it remains a challenge. In this work, we introduce WarpPINN, a physics-informed neural network to perform image registration to obtain local metrics of the heart deformation. We apply this method to cine magnetic resonance images to estimate the motion during the cardiac cycle. We inform our neural network of near-incompressibility of cardiac tissue by penalizing the jacobian of the deformation field. The loss function has two components: an intensity-based similarity term between the reference and the warped template images, and a regularizer that represents the hyperelastic behavior of the tissue. The architecture of the neural network allows us to easily compute the strain via automatic differentiation to assess cardiac activity. We use Fourier feature mappings to overcome the spectral bias of neural networks, allowing us to capture discontinuities in the strain field. We test our algorithm on a synthetic example and on a cine-MRI benchmark of 15 healthy volunteers. We outperform current methodologies both landmark tracking and strain estimation. We expect that WarpPINN will enable more precise diagnostics of heart failure based on local deformation information. Source code is available at https://github.com/fsahli/WarpPINN.