Cardiovascular magnetic resonance: deeper insights through bioengineering

Fully Automated Myocardial Strain Estimation from Cardiovascular MRI-tagged Images Using a Deep Learning Framework in the UK Biobank

PURPOSE

To demonstrate the feasibility and performance of a fully automated deep learning framework to estimate myocardial strain from short-axis cardiac MRI-tagged images.

MATERIALS AND METHODS

In this retrospective cross-sectional study, 4508 cases from the U.K. Biobank were split randomly into 3244 training cases, 812 validation cases, and 452 test cases. Ground truth myocardial landmarks were defined and tracked by manual initialization and correction of deformable image registration using previously validated software with five readers. The fully automatic framework consisted of (a) a convolutional neural network (CNN) for localization and (b) a combination of a recurrent neural network (RNN) and a CNN to detect and track the myocardial landmarks through the image sequence for each slice. Radial and circumferential strain were then calculated from the motion of the landmarks and averaged on a slice basis.

RESULTS

Within the test set, myocardial end-systolic circumferential Green strain errors were -0.001 ± 0.025, -0.001 ± 0.021, and 0.004 ± 0.035 in the basal, mid-, and apical slices, respectively (mean ± standard deviation of differences between predicted and manual strain). The framework reproduced significant reductions in circumferential strain in participants with diabetes, hypertensive participants, and participants with a previous heart attack. Typical processing time was approximately 260 frames (approximately 13 slices) per second on a GPU with 12 GB RAM compared with 6-8 minutes per slice for the manual analysis.

CONCLUSION

The fully automated combined RNN and CNN framework for analysis of myocardial strain enabled unbiased strain evaluation in a high-throughput workflow, with similar ability to distinguish impairment due to diabetes, hypertension, and previous heart attack.Published under a CC BY 4.0 license. Supplemental material is available for this article.

A Meshfree Representation for Cardiac Medical Image Computing

The prominent advantage of meshfree method, is the way to build the representation of computational domain, based on the nodal points without any explicit meshing connectivity. Therefore, meshfree method can conveniently process the numerical computation inside interested domains with large deformation or inhomogeneity. In this paper, we adopt the idea of meshfree representation into cardiac medical image analysis in order to overcome the difficulties caused by large deformation and inhomogeneous materials of the heart. In our implementation, as element-free Galerkin method can efficiently build a meshfree representation using its shape function with moving least square fitting, we apply this meshfree method to handle large deformation or inhomogeneity for solving cardiac segmentation and motion tracking problems. We evaluate the performance of meshfree representation on a synthetic heart data and an in-vivo cardiac MRI image sequence. Results showed that the error of our framework against the ground truth was 0.1189 ± 0.0672 while the error of the traditional FEM was 0.1793 ± 0.1166. The proposed framework has minimal consistency constraints, handling large deformation and material discontinuities are simple and efficient, and it provides a way to avoid the complicated meshing procedures while preserving the accuracy with a relatively small number of nodes.

Multimodality Imaging for Left Ventricular Hypertrophy Severity Grading: A Methodological Review

Left ventricular hypertrophy (LVH), defined by an increase in left ventricular mass (LVM), is a common cardiac finding generally caused by an increase in pressure or volume load. Assessing severity of LVH is of great clinical value in terms of prognosis and treatment choices, as LVH severity grades correlate with the risk for presenting cardiovascular events. The three main cardiac parameters for the assessment of LVH are wall thickness, LVM, and LV geometry. Echocardiography, with large availability and low cost, is the technique of choice for their assessment. Consequently, reference values for LVH severity in clinical guidelines are based on this technique. However, cardiac magnetic resonance (CMR) and computed tomography (CT) are increasingly used in clinical practice, providing excellent image quality. Nevertheless, there is no extensive data to support reference values based on these techniques, while comparative studies between the three techniques show different results in wall thickness and LVM measurements. In this paper, we provide an overview of the different methodologies used to assess LVH severity with echocardiography, CMR and CT. We argue that establishing reference values per imaging modality, and possibly indexed to body surface area and classified per gender, ethnicity and age-group, might be essential for the correct classification of LVH severity.

Challenges of cardiac image analysis in large-scale population-based studies

Large-scale population-based imaging studies of preclinical and clinical heart disease are becoming possible due to the advent of standardized robust non-invasive imaging methods and infrastructure for big data analysis. This gives an exciting opportunity to gain new information about the development and progression of heart disease across population groups. However, the large amount of image data and prohibitive time required for image analysis present challenges for obtaining useful derived data from the images. Automated analysis tools for cardiac image analysis are only now becoming available. This paper reviews the challenges and possible solutions to the analysis of big imaging data in population studies. We also highlight the potential of recent large epidemiological studies using cardiac imaging to discover new knowledge on heart health and well-being.

Atlas-based quantification of cardiac remodeling due to myocardial infarction

Myocardial infarction leads to changes in the geometry (remodeling) of the left ventricle (LV) of the heart. The degree and type of remodeling provides important diagnostic information for the therapeutic management of ischemic heart disease. In this paper, we present a novel analysis framework for characterizing remodeling after myocardial infarction, using LV shape descriptors derived from atlas-based shape models. Cardiac magnetic resonance images from 300 patients with myocardial infarction and 1991 asymptomatic volunteers were obtained from the Cardiac Atlas Project. Finite element models were customized to the spatio-temporal shape and function of each case using guide-point modeling. Principal component analysis was applied to the shape models to derive modes of shape variation across all cases. A logistic regression analysis was performed to determine the modes of shape variation most associated with myocardial infarction. Goodness of fit results obtained from end-diastolic and end-systolic shapes were compared against the traditional clinical indices of remodeling: end-diastolic volume, end-systolic volume and LV mass. The combination of end-diastolic and end-systolic shape parameter analysis achieved the lowest deviance, Akaike information criterion and Bayesian information criterion, and the highest area under the receiver operating characteristic curve. Therefore, our framework quantitatively characterized remodeling features associated with myocardial infarction, better than current measures. These features enable quantification of the amount of remodeling, the progression of disease over time, and the effect of treatments designed to reverse remodeling effects.

Lagrangian postprocessing of computational hemodynamics

Recent advances in imaging, modeling, and computing have rapidly expanded our capabilities to model hemodynamics in the large vessels (heart, arteries, and veins). This data encodes a wealth of information that is often under-utilized. Modeling (and measuring) blood flow in the large vessels typically amounts to solving for the time-varying velocity field in a region of interest. Flow in the heart and larger arteries is often complex, and velocity field data provides a starting point for investigating the hemodynamics. This data can be used to perform Lagrangian particle tracking, and other Lagrangian-based postprocessing. As described herein, Lagrangian methods are necessary to understand inherently transient hemodynamic conditions from the fluid mechanics perspective, and to properly understand the biomechanical factors that lead to acute and gradual changes of vascular function and health. The goal of the present paper is to review Lagrangian methods that have been used in post-processing velocity data of cardiovascular flows.

Accurate high-resolution measurements of 3-D tissue dynamics with registration-enhanced displacement encoded MRI

Displacement fields are important to analyze deformation, which is associated with functional and material tissue properties often used as indicators of health. Magnetic resonance imaging (MRI) techniques like DENSE and image registration methods like Hyperelastic Warping have been used to produce pixel-level deformation fields that are desirable in high-resolution analysis. However, DENSE can be complicated by challenges associated with image phase unwrapping, in particular offset determination. On the other hand, Hyperelastic Warping can be hampered by low local image contrast. The current work proposes a novel approach for measuring tissue displacement with both DENSE and Hyperelastic Warping, incorporating physically accurate displacements obtained by the latter to improve phase characterization in DENSE. The validity of the proposed technique is demonstrated using numerical and physical phantoms, and in vivo small animal cardiac MRI.