Learning-based Regularization for Cardiac Strain Analysis with Ability for Domain Adaptation

TL;DR

This paper introduces a semi-supervised neural network regularization method with domain adaptation for more accurate and physiologically plausible cardiac motion and strain analysis from 4D echocardiography, improving infarct detection.

Contribution

It proposes a novel semi-supervised autoencoder framework with biomechanical constraints for domain adaptation in cardiac strain analysis from 4DE data.

Findings

The method produces physiologically plausible displacements.

It accurately identifies infarcted regions in vivo.

The approach outperforms traditional methods in strain estimation.

Abstract

Reliable motion estimation and strain analysis using 3D+time echocardiography (4DE) for localization and characterization of myocardial injury is valuable for early detection and targeted interventions. However, motion estimation is difficult due to the low-SNR that stems from the inherent image properties of 4DE, and intelligent regularization is critical for producing reliable motion estimates. In this work, we incorporated the notion of domain adaptation into a supervised neural network regularization framework. We first propose an unsupervised autoencoder network with biomechanical constraints for learning a latent representation that is shown to have more physiologically plausible displacements. We extended this framework to include a supervised loss term on synthetic data and showed the effects of biomechanical constraints on the network's ability for domain adaptation. We validated both the autoencoder and semi-supervised regularization method on in vivo data with implanted sonomicrometers. Finally, we showed the ability of our semi-supervised learning regularization approach to identify infarcted regions using estimated regional strain maps with good agreement to manually traced infarct regions from postmortem excised hearts.