RESUMO
Left ventricle (LV) segmentation of 2D echocardiography images is an essential step in the analysis of cardiac morphology and function and - more generally - diagnosis of cardiovascular diseases. Several deep learning (DL) algorithms have recently been proposed for the automatic segmentation of the LV, showing significant performance improvement over the traditional segmentation algorithms. However, unlike the traditional methods, prior information about the segmentation problem, e.g. anatomical shape information, is not usually incorporated for training the DL algorithms. This can degrade the generalization performance of the DL models on unseen images if their characteristics are somewhat different from those of the training images, e.g. low-quality testing images. In this study, a new shape-constrained deep convolutional neural network (CNN) - called BEAS-Net - is introduced for automatic LV segmentation. The BEAS-Net learns how to associate the image features, encoded by its convolutional layers, with anatomical shape-prior information derived by the B-spline explicit active surface (BEAS) algorithm to generate physiologically meaningful segmentation contours when dealing with artifactual or low-quality images. The performance of the proposed network was evaluated using three different in-vivo datasets and was compared a deep segmentation algorithm based on the U-Net model. Both networks yielded comparable results when tested on images of acceptable quality, but the BEAS-Net outperformed the benchmark DL model on artifactual and low-quality images.
RESUMO
The advent of high-frame rate imaging in ultrasound allowed the development of shear wave elastography as a noninvasive alternative for myocardial stiffness assessment. It measures mechanical waves propagating along the cardiac wall with speeds that are related to stiffness. The use of cardiac shear wave elastography in clinical studies is increasing, but a proper understanding of the different factors that affect wave propagation is required to correctly interpret results because of the heart's thin-walled geometry and intricate material properties. The aims of this review are to give an overview of the general concepts in cardiac shear wave elastography and to discuss in depth the effects of age, hemodynamic loading, cardiac morphology, fiber architecture, contractility, viscoelasticity, and system-dependent factors on the measurements, with a focus on clinical application. It also describes how these factors should be considered during acquisition, analysis, and reporting to ensure an accurate, robust, and reproducible measurement of the shear wave.
Assuntos
Cardiologia , Técnicas de Imagem por Elasticidade , Humanos , Valor Preditivo dos Testes , Ultrassonografia , MiocárdioRESUMO
Cardiovascular medical devices undergo a large number of pre- and post-market tests before their approval for clinical practice use. Sophisticated cardiovascular simulators can significantly expedite the evaluation process by providing a safe and controlled environment and representing clinically relevant case scenarios. The complex nature of the cardiovascular system affected by severe pathologies and the inherently intricate patient-device interaction creates a need for high-fidelity test benches able to reproduce intra- and inter-patient variability of disease states. Therefore, we propose an innovative cardiovascular simulator that combines in silico and in vitro modeling techniques with a soft robotic left ventricle. The simulator leverages patient-specific and echogenic soft robotic phantoms used to recreate the intracardiac pressure and volume waveforms, combined with an in silico lumped parameter model of the remaining cardiovascular system. Three different patient-specific profiles were recreated, to assess the capability of the simulator to represent a variety of working conditions and mechanical properties of the left ventricle. The simulator is shown to provide a realistic physiological and anatomical representation thanks to the use of soft robotics combined with in silico modeling. This tool proves valuable for optimizing and validating medical devices and delineating specific indications and boundary conditions.
RESUMO
Radiotherapy treatment plans have become highly conformal, posing additional constraints on the accuracy of treatment delivery. Here, we explore the use of radiation-sensitive ultrasound contrast agents (superheated phase-change nanodroplets) as dosimetric radiation sensors. In a series of experiments, we irradiated perfluorobutane nanodroplets dispersed in gel phantoms at various temperatures and assessed the radiation-induced nanodroplet vaporization events using offline or online ultrasound imaging. At 25 °C and 37 °C, the nanodroplet response was only present at higher photon energies (≥10 MV) and limited to <2 vaporization events per cm2 per Gy. A strong response (~2000 vaporizations per cm2 per Gy) was observed at 65 °C, suggesting radiation-induced nucleation of the droplet core at a sufficiently high degree of superheat. These results emphasize the need for alternative nanodroplet formulations, with a more volatile perfluorocarbon core, to enable in vivo photon dosimetry. The current nanodroplet formulation carries potential as an innovative gel dosimeter if an appropriate gel matrix can be found to ensure reproducibility. Eventually, the proposed technology might unlock unprecedented temporal and spatial resolution in image-based dosimetry, thanks to the combination of high-frame-rate ultrasound imaging and the detection of individual vaporization events, thereby addressing some of the burning challenges of new radiotherapy innovations.
RESUMO
BACKGROUND: Myocardial diastolic function assessment in children by conventional echocardiography is challenging. High-frame rate echocardiography facilitates the assessment of myocardial stiffness, a key factor in diastolic function, by measuring the propagation velocities of myocardial shear waves (SWs). However, normal values of natural SWs in children are currently lacking. The aim of this study was to explore the behavior of natural SWs among children and adolescents, their reproducibility, and the factors affecting SW velocities from childhood into adulthood. METHODS: One hundred six healthy children (2-18 years of age) and 62 adults (19-80 years of age) were recruited. High-frame rate images were acquired using a modified commercial scanner. An anatomic M-mode line was drawn along the ventricular septum, and propagation velocities of natural SWs after mitral valve closure were measured in the tissue acceleration-coded M-mode display. RESULTS: Throughout life, SW velocities after mitral valve closure exhibited pronounced age dependency (r = 0.73; P < .001). Among the pediatric population, SW velocities correlated significantly with measures of cardiac geometry (septal thickness and left ventricular end-diastolic dimension), local hemodynamics (systolic blood pressure), and echocardiographic parameters of systolic and diastolic function (global longitudinal strain, mitral E/e' ratio, isovolumic relaxation time, and mitral deceleration time) (P < .001). In a multivariate analysis including all these factors, the predictors of SW velocities were age, mitral E/e', and global longitudinal strain (r = 0.81). CONCLUSIONS: Natural myocardial SW velocities in children can be detected and measured. SW velocities showed significant dependence on age and diastolic function. Natural SWs could be a promising additive tool for the assessment of diastolic function among children.