Quantitative analysis of left ventricular function as a tool in clinical research. Theoretical basis and methodology

DeepStrain: A Deep Learning Workflow for the Automated Characterization of Cardiac Mechanics

Myocardial strain analysis from cinematic magnetic resonance imaging (cine-MRI) data provides a more thorough characterization of cardiac mechanics than volumetric parameters such as left-ventricular ejection fraction, but sources of variation including segmentation and motion estimation have limited its wider clinical use. We designed and validated a fast, fully-automatic deep learning (DL) workflow to generate both volumetric parameters and strain measures from cine-MRI data consisting of segmentation and motion estimation convolutional neural networks. The final motion network design, loss function, and associated hyperparameters are the result of a thorough ad hoc implementation that we carefully planned specific for strain quantification, tested, and compared to other potential alternatives. The optimal configuration was trained using healthy and cardiovascular disease (CVD) subjects (n = 150). DL-based volumetric parameters were correlated (>0.98) and without significant bias relative to parameters derived from manual segmentations in 50 healthy and CVD test subjects. Compared to landmarks manually-tracked on tagging-MRI images from 15 healthy subjects, landmark deformation using DL-based motion estimates from paired cine-MRI data resulted in an end-point-error of 2.9 ± 1.5 mm. Measures of end-systolic global strain from these cine-MRI data showed no significant biases relative to a tagging-MRI reference method. On 10 healthy subjects, intraclass correlation coefficient for intra-scanner repeatability was good to excellent (>0.75) for all global measures and most polar map segments. In conclusion, we developed and evaluated the first end-to-end learning-based workflow for automated strain analysis from cine-MRI data to quantitatively characterize cardiac mechanics of healthy and CVD subjects.

Accuracy of Left Ventricular Cavity Volume and Ejection Fraction for Conventional Estimation Methods and 3D Surface Fitting

Background

While left ventricular cavity volume (LVV) and ejection fraction (LVEF) are used routinely for clinical decision‐making, the errors in LVV and LVEF estimates in the clinic have yet to be rigorously quantified and are perhaps underappreciated.

Methods and Results

The goal of this study was to quantify the accuracy and precision of several common geometric‐model‐based methods for estimating LVV and LVEF using a highly sampled, high‐resolution magnetic resonance imaging data set and an independent ground truth. The effect on LVV and LVEF accuracy of slice number and orientation was also studied. When using the common geometric assumptions and limited short‐ and/or long‐axis views, the expected LVEF measurement uncertainty can be as high as 49%. The composite midpoint rule applied to a stack of short‐axis slices can achieve LVEF error <3% and LVV error of ≈10%, but in the clinic an additional ≈8% uncertainty is expected. An analogous approach applied to a series of radially prescribed long‐axis slices can achieve higher LVEF accuracy, up to 3.9% with 12 slices, and more reliable LVV measurements than methods based solely on short‐axis images. Using a mathematical 3‐dimensional surface model that incorporates anatomic information from multiple views achieves superior accuracy, with LVEF error <4% and LVV error <2.5% when using 6 slices in each short‐ and long‐axis view.

Conclusions

Combining anatomical information from multiple views into a conformal 3‐dimensional surface model greatly reduces errors in LVV and LVEF estimates, with potential clinical benefit via improved early detection of cardiac disease.

Early Detection of Cardiovascular Changes After Radiotherapy for Breast Cancer: Protocol for a European Multicenter Prospective Cohort Study (MEDIRAD EARLY HEART Study)

Background

Breast cancer is the most common cancer among women, and radiotherapy plays a major role in its treatment. However, breast cancer radiotherapy can lead to incidental irradiation of the heart, resulting in an increased risk for a variety of heart diseases arising many years after radiotherapy. Therefore, identifying breast cancer patients at the highest risk for radiation-induced cardiac complications is crucial for developing strategies for primary and secondary prevention, which may contribute to healthy aging. There is still a need for precise knowledge on the relationship between radiation dose to specific cardiac structures and early subclinical cardiac changes and their occurrence over time that could finally lead to cardiac complications.

Objective

The MEDIRAD EARLY HEART study aims to identify and validate new cardiac imaging and circulating biomarkers of radiation-induced cardiovascular changes arising within first 2 years of breast cancer radiotherapy and to develop risk models integrating these biomarkers combined with precise dose metrics of cardiac structures based on three-dimensional dosimetry.

Methods

The EARLY HEART study is a multicenter, prospective cohort study in which 250 women treated for breast cancer and followed for 2 years after radiotherapy will be included. Women treated with radiotherapy without chemotherapy for a unilateral breast cancer and aged 40-75 years meet the inclusion criteria. Baseline and follow-up data include cardiac measurements based on two-dimensional speckle-tracking echocardiography, computed tomography coronary angiography, cardiac magnetic resonance imaging, and a wide panel of circulating biomarkers of cardiac injury. The absorbed dose will be evaluated globally for the heart and different substructures. Furthermore, the dose-response relationship will allow modeling the radiation-induced occurrence and evolution of subclinical cardiac lesions and biomarkers to develop prediction models.

Results

This study details the protocol of the MEDIRAD EARLY HEART study and presents the main limits and advantages of this international project. The inclusion of patients began in 2017. Preliminary results are expected to be published in 2019, and complete analysis should be published in 2021.

Conclusions

The MEDIRAD EARLY HEART study will allow identifying the main cardiac imaging and blood-based determinants of radiation-induced cardiac injuries to better propose primary and secondary preventive measures in order to contribute to enhanced patient care and quality of life.

Trial Registration

ClinicalTrials.gov NCT03297346; https://clinicaltrials.gov/ct2/show/NCT03297346 (Archived by WebCite at http://www.webcitation.org/72KS7MIUU)

Registered Report Identifier

RR1-10.2196/9906

Comparison of left ventricular ejection fraction values obtained using invasive contrast left ventriculography, two-dimensional echocardiography, and gated single-photon emission computed tomography

Objectives:

Left ventricular ejection fraction can be measured by a variety of invasive and non-invasive cardiac techniques. This study assesses the relation of three diagnostic modalities to each other in the measurement of left ventricular ejection fraction: invasive contrast left ventriculography, two-dimensional echocardiography, and quantitative gated single-photon emission computed tomography.

Methods:

Retrospective chart review was conducted on 58 patients hospitalized with chest pain, who underwent left ventricular ejection fraction evaluation using each of the aforementioned modalities within a 3-month period not interrupted by myocardial infarction or revascularization.

Results:

The mean left ventricular ejection fraction values were as follows: invasive contrast left ventriculography (0.44±0.15), two-dimensional echocardiography (0.46±0.13), and gated single-photon emission computed tomography (0.37±0.10). Correlations coefficients and associated p values were as follows: invasive contrast left ventriculography versus two-dimensional echocardiography (r=0.69, p<0.001), invasive contrast left ventriculography versus gated single-photon emission computed tomography (r=0.80, p<0.0001), and gated single-photon emission computed tomography versus two-dimensional echocardiography (r=0.69, p<0.001).

Conclusion:

Our results indicate that strong positive correlations exist among the three techniques studied.

Phases I-III Clinical Trials Using Adult Stem Cells

First randomized clinical trials have demonstrated that stem cell therapy can improve cardiac recovery after the acute phase of myocardial ischemia and in patients with chronic ischemic heart disease. Nevertheless, some trials have shown that conflicting results and uncertainties remain in the case of mechanisms of action and possible ways to improve clinical impact of stem cells in cardiac repair. In this paper we will examine the evidence available, analyze the main phase I and II randomized clinical trials and their limitations, discuss the key points in the design of future trials, and depict new directions of research in this fascinating field.