Regional myocardial strain analysis via 2D speckle tracking echocardiography: validation with sonomicrometry and correlation with regional blood flow in the presence of graded coronary stenoses and dobutamine stress

Multi-Task Learning for Motion Analysis and Segmentation in 3D Echocardiography

Characterizing left ventricular deformation and strain using 3D+time echocardiography provides useful insights into cardiac function and can be used to detect and localize myocardial injury. To achieve this, it is imperative to obtain accurate motion estimates of the left ventricle. In many strain analysis pipelines, this step is often accompanied by a separate segmentation step; however, recent works have shown both tasks to be highly related and can be complementary when optimized jointly. In this work, we present a multi-task learning network that can simultaneously segment the left ventricle and track its motion between multiple time frames. Two task-specific networks are trained using a composite loss function. Cross-stitch units combine the activations of these networks by learning shared representations between the tasks at different levels. We also propose a novel shape-consistency unit that encourages motion propagated segmentations to match directly predicted segmentations. Using a combined synthetic and in-vivo 3D echocardiography dataset, we demonstrate that our proposed model can achieve excellent estimates of left ventricular motion displacement and myocardial segmentation. Additionally, we observe strong correlation of our image-based strain measurements with crystal-based strain measurements as well as good correspondence with SPECT perfusion mappings. Finally, we demonstrate the clinical utility of the segmentation masks in estimating ejection fraction and sphericity indices that correspond well with benchmark measurements.

Multiaxial pressure-strain analysis of regional myocardial work in the setting of graded coronary stenoses and dobutamine stress

We present a detailed analysis of regional myocardial blood flow and work to better understand the effects of coronary stenoses and low-dose dobutamine stress. Our analysis is based on a unique open-chest model in anesthetized canines that features invasive hemodynamic monitoring, microsphere-based blood flow analysis, and an extensive three-dimensional (3-D) sonomicrometer array that provides multiaxial deformational assessments in the ischemic, border, and remote vascular territories. We use this model to construct regional pressure-strain loops for each territory and quantify the loop subcomponent areas that reflect myocardial work contributing to the ejection of blood and wasted work that does not. We demonstrate that reductions in coronary blood flow markedly alter the shapes and temporal relationships of pressure-strain loops, as well as the magnitudes of their total and subcomponent areas. Specifically, we show that moderate stenoses in the mid-left anterior descending coronary artery decrease regional midventricle myocardial work indices and substantially increase indices of wasted work. In the midventricle, these effects are most pronounced along the radial and longitudinal axes, with more modest effects along the circumferential axis. We further demonstrate that low-dose dobutamine can help to restore or even improve function, but often at the cost of increased wasted work. This detailed, multiaxial analysis provides unique insight into the physiology and mechanics of the heart in the presence of ischemia and low-dose dobutamine, with potential implications in many areas, including the detection and characterization of ischemic heart disease and the use of inotropic support for low cardiac output.NEW & NOTEWORTHY Our unique experimental model assesses cardiac pressure-strain relationships along multiple axes in multiple regions. We demonstrate that moderate coronary stenoses decrease regional myocardial work and increase wasted work and that low-dose dobutamine can help to restore myocardial function, but often with further increases in wasted work. Our findings highlight the significant directional variation of cardiac mechanics and demonstrate potential advantages of pressure-strain analyses over traditional, purely deformational measures, especially in characterizing physiological changes related to dobutamine.

Preliminary Feasibility of Stress Myocardial Elastography for the Detection of Coronary Artery Disease

Myocardial elastography (ME) is a cardiac strain imaging technique that has been found capable of detecting a decrease in radial strain caused by ischemia or infarction in patients with coronary artery disease (CAD) as well as in a canine model. Prior studies have focused on rest imaging, but stress testing can reveal functional deficits caused by stenoses that are asymptomatic at rest. Therefore, it has been proposed that stress ME (S-ME) improves the detection of CAD. A novel strain difference (Δε) metric is presented and investigated in a canine model of induced ischemia, as well as in a study in human patients with CAD validated by myocardial perfusion imaging. In the canine model study, flow-limiting stenosis was induced by partial ligation in n = 2 canines, and stenosis was found to consistently reduce Δε in the affected myocardial regions compared with baseline, as well as compared to myocardial regions that are remote to the induced stenosis. In the clinical study, the median Δε was significantly lower (p < 0.05) in infarcted myocardial regions (-6.29%) than in those with normal perfusion (4.62%), with Δε in ischemic regions falling in between (-2.91%). The same trend was observed when considering radial strain during stress and, to a lesser degree, at rest alone. The results indicate that S-ME may be more sensitive to mild cases of CAD that are functionally asymptomatic at rest.

Simultaneous Segmentation and Motion Estimation of Left Ventricular Myocardium in 3D Echocardiography Using Multi-task Learning

Motion estimation and segmentation are both critical steps in identifying and assessing myocardial dysfunction, but are traditionally treated as unique tasks and solved as separate steps. However, many motion estimation techniques rely on accurate segmentations. It has been demonstrated in the computer vision and medical image analysis literature that both these tasks may be mutually beneficial when solved simultaneously. In this work, we propose a multi-task learning network that can concurrently predict volumetric segmentations of the left ventricle and estimate motion between 3D echocardiographic image pairs. The model exploits complementary latent features between the two tasks using a shared feature encoder with task-specific decoding branches. Anatomically inspired constraints are incorporated to enforce realistic motion patterns. We evaluate our proposed model on an in vivo 3D echocardiographic canine dataset. Results suggest that coupling these two tasks in a learning framework performs favorably when compared against single task learning and other alternative methods.

Learning-Based Regularization for Cardiac Strain Analysis via Domain Adaptation

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 a semi-supervised Multi-Layered Perceptron (MLP) 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 the 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 infarct regions using estimated regional strain maps with good agreement to manually traced infarct regions from postmortem excised hearts.

Role of Two-Dimensional Speckle-Tracking Echocardiography in Early Detection of Left Ventricular Dysfunction in Dogs

Simple Summary

Two-dimensional speckle-tracking echocardiography represents an advanced imaging technique that allows the analysis of global and regional myocardial function, cardiac rotation and synchronicity using deformation imaging. It has gained growing importance over the last decade, especially in human medicine as a method of evaluating myocardial function. This review aims to give an overview of the current understanding of this technique and its clinical applicability in the field of veterinary medicine with a focus on early detection of left ventricular dysfunction in dogs.

Abstract

Two-dimensional speckle-tracking echocardiography (2D–STE) is an advanced echocardiographic technique based on deformation imaging that allows comprehensive evaluation of the myocardial function. Clinical application of 2D–STE holds great potential for its ability to provide valuable information on both global and regional myocardial function and to quantify cardiac rotation and synchronicity, which are not readily possible with the conventional echocardiography. It has gained growing importance over the past decade, especially in human medicine, and its application includes assessment of myocardial function, detection of subclinical myocardial dysfunction and serving as a prognostic indicator. This review illustrates the fundamental concepts of deformation analysis and gives an overview of the current understanding and its clinical application of this technique in veterinary medicine, with a focus on early detection of left ventricular (LV) dysfunction in dogs.

SHAPE-REGULARIZED UNSUPERVISED LEFT VENTRICULAR MOTION NETWORK WITH SEGMENTATION CAPABILITY IN 3D+TIME ECHOCARDIOGRAPHY

Accurate motion estimation and segmentation of the left ventricle from medical images are important tasks for quantitative evaluation of cardiovascular health. Echocardiography offers a cost-efficient and non-invasive modality for examining the heart, but provides additional challenges for automated analyses due to the low signal-to-noise ratio inherent in ultrasound imaging. In this work, we propose a shape regularized convolutional neural network for estimating dense displacement fields between sequential 3D B-mode echocardiography images with the capability of also predicting left ventricular segmentation masks. Manually traced segmentations are used as a guide to assist in the unsupervised estimation of displacement between a source and a target image while also serving as labels to train the network to additionally predict segmentations. To enforce realistic cardiac motion patterns, a flow incompressibility term is also incorporated to penalize divergence. Our proposed network is evaluated on an in vivo canine 3D+t B-mode echocardiographic dataset. It is shown that the shape regularizer improves the motion estimation performance of the network and our overall model performs favorably against competing methods.

Multi-frame Attention Network for Left Ventricle Segmentation in 3D Echocardiography

Echocardiography is one of the main imaging modalities used to assess the cardiovascular health of patients. Among the many analyses performed on echocardiography, segmentation of left ventricle is crucial to quantify the clinical measurements like ejection fraction. However, segmentation of left ventricle in 3D echocardiography remains a challenging and tedious task. In this paper, we propose a multi-frame attention network to improve the performance of segmentation of left ventricle in 3D echocardiography. The multi-frame attention mechanism allows highly correlated spatiotemporal features in a sequence of images that come after a target image to be used to augment the performance of segmentation. Experimental results shown on 51 in vivo porcine 3D+time echocardiography images show that utilizing correlated spatiotemporal features significantly improves the performance of left ventricle segmentation when compared to other standard deep learning-based medical image segmentation models.

A Semi-supervised Joint Network for Simultaneous Left Ventricular Motion Tracking and Segmentation in 4D Echocardiography

This work presents a novel deep learning method to combine segmentation and motion tracking in 4D echocardiography. The network iteratively trains a motion branch and a segmentation branch. The motion branch is initially trained entirely unsupervised and learns to roughly map the displacements between a source and a target frame. The estimated displacement maps are then used to generate pseudo-ground truth labels to train the segmentation branch. The labels predicted by the trained segmentation branch are fed back into the motion branch and act as landmarks to help retrain the branch to produce smoother displacement estimations. These smoothed out displacements are then used to obtain smoother pseudo-labels to retrain the segmentation branch. Additionally, a biomechanically-inspired incompressibility constraint is implemented in order to encourage more realistic cardiac motion. The proposed method is evaluated against other approaches using synthetic and in-vivo canine studies. Both the segmentation and motion tracking results of our model perform favorably against competing methods.

Computed Tomographic Angiography Assessment of Epicardial Coronary Vasoreactivity for Early Detection of Doxorubicin-Induced Cardiotoxicity

Background

The vascular endothelium is a novel target for the detection, management, and prevention of doxorubicin (DOX)-induced cardiotoxicity.

Objectives

The study aimed to: 1) develop a methodology by computed tomography angiography (CTA) to evaluate stress-induced changes in epicardial coronary diameter; and 2) apply this to a chronic canine model of DOX-induced cardiotoxicity to assess vascular toxicity.

Methods

To develop and validate quantitative methods, sequential retrospectively gated coronary CTAs were performed in 16 canines. Coronary diameters were measured at prespecified distances during rest, adenosine (ADE) (280 μg/kg/min), rest 30 min post-ADE, and dobutamine (DOB) (5 μg/kg/min). A subgroup of 8 canines received weekly intravenous DOX (1 mg/kg) for 12 to 15 weeks, followed by rest-stress CTA at cumulative doses of ∼4-mg/kg (3 to 5 mg/kg), ∼8-mg/kg (7 to 9 mg/kg), and ∼12-mg/kg (12 to 15 mg/kg) of DOX. Echocardiograms were performed at these timepoints to assess left ventricular ejection fraction and global longitudinal strain.

Results

Under normal conditions, epicardial coronary arteries reproducibly dilated in response to ADE (left anterior descending coronary artery [LAD]: 12 ± 2%, left circumflex coronary artery [LCx]: 13 ± 2%, right coronary artery [RCA]: 14 ± 2%) and DOB (LAD: 17 ± 3%, LCx: 18 ± 2%, RCA: 15 ± 3%). With DOX, ADE vasodilator responses were impaired after ∼4-mg/kg (LAD: –3 ± 1%, LCx: 0 ± 2%, RCA: –5 ± 2%) and ∼8-mg/kg (LAD: –3 ± 1%, LCx: 0 ± 1%, RCA: –2 ± 2%). The DOB dilation response was preserved at ∼4-mg/kg of DOX (LAD: 18 ± 4%, LCx: 11 ± 3%, RCA: 11 ± 2%) but tended to decrease at ∼8-mg/kg of DOX (LAD: 4 ± 2%, LCx: 8 ± 3%, RCA: 3 ± 2%). A significant left ventricular ejection fraction reduction was observed only at 12 to 15 mg/kg DOX (baseline: 63 ± 2%, 12-mg/kg: 45 ± 3%). Global longitudinal strain was abnormal at ∼4-mg/kg of DOX (p = 0.011).

Conclusions

CTA can reliably assess epicardial coronary diameter in response to pharmacological stressors, providing a noninvasive functional index of coronary vasoreactivity. Impaired epicardial vasodilation occurs early in DOX-induced cardiotoxicity.