Semiautomated segmentation of myocardial contours for fast strain analysis in cine displacement-encoded MRI

The purposes of this study were to develop a semiautomated cardiac contour segmentation method for use with cine displacement-encoded MRI and evaluate its accuracy against manual segmentation. This segmentation model was designed with two distinct phases: preparation and evolution. During the model preparation phase, after manual image cropping and then image intensity standardization, the myocardium is separated from the background based on the difference in their intensity distributions, and the endo- and epi-cardial contours are initialized automatically as zeros of an underlying level set function. During the model evolution phase, the model deformation is driven by the minimization of an energy function consisting of five terms: model intensity, edge attraction, shape prior, contours interaction, and contour smoothness. The energy function is minimized iteratively by adaptively weighting the five terms in the energy function using an annealing algorithm. The validation experiments were performed on a pool of cine data sets of five volunteers. The difference between the semiautomated segmentation and manual segmentation was sufficiently small as to be considered clinically irrelevant. This relatively accurate semiautomated segmentation method can be used to significantly increase the throughput of strain analysis of cine displacement-encoded MR images for clinical applications.      

Watershed-presegmented snake for boundary detection and tracking of left ventricle in echocardiographic images.

In this paper, an automated method of boundary detection of the left ventricle (LV) is proposed. The method uses a watershed transform and morphological operation to locate the region containing the LV, then performs snake deformation with a multiscale directional edge map for the detection of the endocardial boundary of the LV.     

Accurate automatic analysis of cardiac cine images

Acquisition of noncontrast agent cine cardiac magnetic resonance (CMR) gated images through the cardiac cycle is, at present, a well-established part of examining cardiac global function. However, regional quantification is less well established. We propose a new automated framework for analyzing the wall thickness and thickening function on these images that consists of three main steps. First, inner and outer wall borders are segmented from their surrounding tissues with a geometric deformable model guided by a special stochastic speed relationship. The latter accounts for Markov-Gibbs shape and appearance models of the object-of-interest and its background. In the second step, point-to-point correspondences between the inner and outer borders are found by solving the Laplace equation and provide initial estimates of the local wall thickness and the thickening function index. Finally, the effects of the segmentation error is reduced and a continuity analysis of the LV wall thickening is performed through iterative energy minimization using a generalized Gauss-Markov random field (GGMRF) image model. The framework was evaluated on 26 datasets from clinical cine CMR images that have been collected from patients with eleven independent studies, with chronic ischemic heart disease and heart damage. The performance evaluation of the proposed segmentation approach, based on the receiver operating characteristic (ROC) and Dice similarity coefficients (DSC) between manually drawn and automatically segmented contours, confirmed a high robustness and accuracy of the proposed segmentation approach. Furthermore, the Bland-Altman plot is used to assess the limit of agreement of our measurements of the global function parameters compared to the ground truth. Importantly, comparative results on the publicly available database (MICCAI 2009 Cardiac MR Left Ventricle Segmentation) demonstrated a superior performance of the proposed segmentation approach over published methods.     

Automatic contour propagation in cine cardiac magnetic resonance images

We have developed a method for automatic contour propagation in cine cardiac magnetic resonance images. The method consists of a new active contour model that tries to maintain a constant contour environment by matching gray values in profiles perpendicular to the contour. Consequently, the contours should maintain a constant position with respect to neighboring anatomical structures, such that the resulting contours reflect the preferences of the user. This is particularly important in cine cardiac magnetic resonance images because local image features do not describe the desired contours near the papillary muscle. The accuracy of the propagation result is influenced by several parameters. Because the optimal setting of these parameters is application dependent, we describe how to use full factorial experiments to optimize the parameter setting. We have applied our method to cine cardiac magnetic resonance image sequences from the long axis two-chamber view, the long axis four-chamber view, and the short axis view. We performed our optimization procedure for each contour in each view. Next, we performed an extensive clinical validation of our method on 69 short axis data sets and 38 long axis data sets. In the optimal parameter setting, our propagation method proved to be fast, robust, and accurate. The resulting cardiac contours are positioned within the interobserver ranges of manual segmentation. Consequently, the resulting contours can be used to accurately determine physiological parameters such as stroke volume and ejection fraction.     

Segmentation of echocardiographic images using mathematical morphology

A semiautomatic technique for isolating the ventricular endocardial border in echocardiograms from a commercially available two-dimensional phased array ultrasound system is presented. This method processes echo images using mathematical morphology to reduce the effects of range and azimuth variation inherent in echo. After morphological filtering, the endocardial border is extracted with traditional segmentation methods. Further processing of the resulting border using binary morphology produces a region of interest suitable for derivation of motion parameters of the endocardium. The area and the shape of semiautomatically-derived regions correlate well (r>0.93) with those defined by expert observers in a study of induced ischemia in seven canines.<>     

Automatic identification of papillary muscles in left-ventricularshort-axis echocardiographic images

An automatic method for identifying the location of the papillary muscles in two-dimensional (2-D) short-axis echocardiographic images is described. The technique uses both spatial and temporal information to identify the presence and track the location of the muscles in the left ventricle from end-diastole to end-systole. The three main steps of the method are spatial preprocessing, spatial processing, and temporal processing. The spatial preprocessing step includes a region of search estimation. The spatial processing step includes a papillary muscle existence test and an initial approximation of the papillary muscle points. The temporal processing includes motion-pattern evaluation and final papillary muscle location, The estimates of existence and position for the automatic method were compared with estimates made by an independent expert observer. Two hundred and ten frames, three taken from each of 70 image sequences, were evaluated. Since two regions of search were processed for each frame (one for the posterior-inferior and one for the anterior-lateral papillary muscle), a total of 420 approximations were made. Of this total, 340 automatic estimates were judged to be in close agreement with estimates made by the expert. Of the remaining 80 approximations, 54 estimates were made by the expert when the computer determined that no papillary muscle was present, 17 estimates provided poor results, and nine estimates were made by the computer when the observer concluded that no papillary muscle was present     

基于图像运动区域的红外多行人跟踪

针对红外视频监控中的多行人跟踪问题,提出了一种基于图像运动区域的跟踪算法。首先应用三维中值滤波方法建立背景模型,然后使用背景差分法得到运动区域;基于运动区域之间特定的匹配准则,建立帧间运动区域匹配矩阵,从而实现目标的跟踪。使用实际红外图像序列进行测试,该算法鲁棒性好,能够快速有效地实现多行人的跟踪。     

Constrained detection of left ventricular boundaries from cine CT images of human hearts

Detection of the left ventricular (LV) endocardial (inner) and epicardial (outer) boundaries in cardiac images, provided by fast computer tomography (cine CT), magnetic resonance (MR), or ultrasound (echocardiography), is addressed. The automatic detection of the LV boundaries is difficult due to background noise, poor contrast, and often unclear differentiation of the tissue characteristics of the ventricles, papillary muscles, and surrounding tissues. An approach to the automatic ventricular boundary detection that employs set-theoretic techniques, and is based on incorporating a priori knowledge of the heart geometry, its brightness, spatial structure, and temporal dynamics into the boundaries detection algorithm is presented. Available knowledge is interpreted as constraint sets in the functional space, and the consistent boundaries are considered to belong to the intersection of all the introduced sets, thus satisfying the a priori information. An algorithm is also suggested for the simultaneous detection of the endocardial and epicardial boundaries of the LV. The procedure is demonstrated using cine CT images of the human heart.     

Wall position and thickness estimation from sequences of echocardiographic images

Presents a new method for endocardial (inner) and epicardial (outer) contour estimation from sequences of echocardiographic images. The framework herein introduced is fine-tuned for parasternal short axis views at the papillary muscle level. The underlying model is probabilistic; it captures the relevant features of the image generation physical mechanisms and of the heart morphology. Contour sequences are assumed to be two-dimensional noncausal first-order Markov random processes; each variable has a spatial index and a temporal index. The image pixels are modeled as Rayleigh distributed random variables with means depending on their positions (inside endocardium, between endocardium and pericardium, or outside pericardium). The complete probabilistic model is built under the Bayesian framework. As estimation criterion the maximum a posteriori (MAP) is adopted. To solve the optimization problem, one is led to (joint estimation of contours and distributions' parameters), the authors introduce an algorithm herein named iterative multigrid dynamic programming (IMDP). It is a fully data-driven scheme with no ad-hoc parameters. The method is implemented on an ordinary workstation, leading to computation times compatible with operational use. Experiments with simulated and real images are presented.     

Local maximum likelihood segmentation of echocardiographic images with Rayleigh distribution

In order to interpret ultrasound images, it is important to understand their formation and the properties that affect them, especially speckle noise. This image texture, or speckle, is a correlated and multiplicative noise that inherently occurs in all types of coherent imaging systems. Indeed, its statistics depend on the density and on the type of scatterers in the tissues. This paper presents a new method for echocardiographic images segmentation in a variational level set framework. A partial differential equation-based flow is designed locally in order to achieve a maximum likelihood segmentation of the region of interest. A Rayleigh probability distribution is considered to model the local B-mode ultrasound images intensities. In order to confront more the speckle noise and local changes of intensity, the proposed local region term is combined with a local phase-based geodesic active contours term. Comparison results on natural and simulated images show that the proposed model is robust to attenuations and captures well the low-contrast boundaries.     

Segmentation of cardiac cine MR images for extraction of right and left ventricular chambers

A two-stage algorithm for extraction of the ventricular chambers (endocardial surfaces) in flow-enhanced magnetic resonance images is described. In the first stage, the approximate locations and sizes of the endocardial surfaces are determined by intensity thresholding. In the second stage, points on each approximated surface are repositioned to nearest locally maximum gradient magnitude points and a generalized cylinder is fitted to them. Examples of ventricular chambers in cine MR images determined by this algorithm are presented.     

车载红外图像的行人检测与跟踪技术

针对车载红外图像的特点,采用基于区域估计的帧差法实现车载红外图像中的行人检测,再通过行人的几何特征和运动速率特征进行行人的识别,最后运用轮廓矩匹配算法进行行人的跟踪。实验结果表明所采用的方法具有较好的行人检测及跟踪效果。     

Tracking the left ventricle in echocardiographic images by learningheart dynamics

In this paper a temporal learning-filtering procedure is applied to refine the left ventricle (LV) boundary detected by an active-contour model. Instead of making prior assumptions about the LV shape or its motion, this information is incrementally gathered directly from the images and is exploited to achieve more coherent segmentation. A Hough transform technique is used to find an initial approximation of the object boundary at the first frame of the sequence. Then, an active-contour model is used in a coarse-to-fine framework, for the estimation of a noisy LV boundary. The PCA transform is applied to form a reduced ordered orthonormal basis of the LV deformations based on a sequence of noisy boundary observations. Then this basis is used to constrain the motion of the active contour in subsequent frames, and thus provide more coherent identification. Results of epicardial boundary identification in B-mode images are presented.     

Cardiovascular modeling of congenital heart disease based on neonatal echocardiographic images

This paper proposes a 3-D cardiovascular modeling system based on neonatal echocardiographic images. With the system, medical doctors can interactively construct patient-specific cardiovascular models, and share the complex topology and the shape information. For the construction of cardiovascular models with a variety of congenital heart diseases, we propose a set of algorithms and interface that enable editing of the topology and shape of the 3-D models. In order to facilitate interactivity, the centerline and radius of the vessels are used to edit the surface of the heart vessels. This forms a skeleton where the centerlines of blood vessel serve as the nodes and edges, while the radius of the blood vessel is given as an attribute value to each node. Moreover, parent-child relationships are given to each skeleton. They are expressed as the directed acyclic graph, where the skeletons are viewed as graph nodes and the connecting points are graph edges. The cardiovascular models generated from some patient data confirmed that the developed technique is capable of constructing cardiovascular disease models in a tolerable timeframe. It is successful in representing the important structures of the patient-specific heart vessels for better understanding in preoperative planning and electric medical recording of the congenital heart disease.     

Tracking myocardial motion from cine DENSE images using spatiotemporal phase unwrapping and temporal fitting

Displacement encoding with stimulated echoes (DENSE) encodes myocardial tissue displacement into the phase of the MR image. Cine DENSE allows for rapid quantification of myocardial displacement at multiple cardiac phases through the majority of the cardiac cycle. For practical sensitivities to motion, relatively high displacement encoding frequencies are used and phase wrapping typically occurs. In order to obtain absolute measures of displacement, a two-dimensional (2-D) quality-guided phase unwrapping algorithm was adapted to unwrap both spatially and temporally. Both a fully automated algorithm and a faster semi-automated algorithm are proposed. A method for computing the 2-D trajectories of discrete points in the myocardium as they move through the cardiac cycle is introduced. The error in individual displacement measurements is reduced by fitting a time series to sequential displacement measurements along each trajectory. This improvement is in turn reflected in strain maps, which are derived directly from the trajectories. These methods were validated both in vivo and on a rotating phantom. Further measurements were made to optimize the displacement encoding frequency and to estimate the baseline strain noise both on the phantom and in vivo. The fully automated phase unwrapping algorithm was successful for 767 out of 800 images (95.9%), and the semi-automated algorithm was successful for 786 out of 800 images (98.3%). The accuracy of the tracking algorithm for typical cardiac displacements on a rotating phantom is 0.24 +/- 0.15 mm. The optimal displacement encoding frequency is in the region of 0.1 cycles/mm, and, for 2 scans of 17-s duration, the strain noise after temporal fitting was estimated to be 2.5 +/- 3.0% at end-diastole, 3.1 +/- 3.1% at end-systole, and 5.3 +/- 5.0% in mid-diastole. The improvement in intra-myocardial strain measurements due to temporal fitting is apparent in strain histograms, and also in identifying regions of dysfunctional myocardium in studies of patients with infarcts.     

Semi-automatic tracking of myocardial motion in MR tagged images

Tissue tagging using magnetic resonance (MR) imaging has enabled quantitative noninvasive analysis of motion and deformation in vivo. One method for MR tissue tagging is Spatial Modulation of Magnetization (SPAMM). Manual detection and tracking of tissue tags by visual inspection remains a time-consuming and tedious process. The authors have developed an interactively guided semi-automated method of detecting and tracking tag intersections in cardiac MR images. A template matching approach combined with a novel adaptation of active contour modeling permits rapid analysis of MR images. The authors have validated their technique using MR SPAMM images of a silicone gel phantom with controlled deformations. Average discrepancy between theoretically predicted and semi-automatically selected tag intersections was 0.30 mm+/-0.17 [mean+/-SD, NS (P<0.05)]. Cardiac SPAMM images of normal volunteers and diseased patients also have been evaluated using the authors' technique.     

Computation of 3-D velocity fields from 3-D cine CT images of a human heart

A method of computing the three-dimensional (3-D) velocity field from 3-D cine computer tomographs (CTs) of a beating heart is proposed. Using continuum theory, the authors develop two constraints on the 3-D velocity field generated by a beating heart. With these constraints, the computation of the 3-D velocity field is formulated as an optimization problem and a solution to the optimization problem is developed using the Euler-Lagrange method. The solution is then discretized for computer implementation. The authors present the results for both simulated images and clinical cine CT images of a beating heart.     

Knowledge-based image analysis for automated boundary extraction of transesophageal echocardiographic left-ventricular images

A system for automatically determining the contour of the left ventricle (LV) and its bounded area, from transesophageal echocardiographic (TEE) images is presented. It uses knowledge of both heart anatomy and echocardiographic imaging to guide the selection of image processing methodologies for thresholding, edge detection, and contour following and the center-based boundary-finding technique to extract the contour of the LV region. To speed up the processing a rectangular region of interest from a TEE picture is first isolated and then reduced to a coarse version, one-ninth original size. All processing steps, except the final contour edge extraction, are performed on this reduced image. New methods developed for automatic threshold selection, region segmentation, noise removal, and region center determination are described.     

Robust real-time myocardial border tracking for echocardiography: an information fusion approach

Ultrasound is a main noninvasive modality for the assessment of the heart function. Wall tracking from ultrasound data is, however, inherently difficult due to weak echoes, clutter, poor signal-to-noise ratio, and signal dropouts. To cope with these artifacts, pretrained shape models can be applied to constrain the tracking. However, existing methods for incorporating subspace shape constraints in myocardial border tracking use only partial information from the model distribution, and do not exploit spatially varying uncertainties from feature tracking. In this paper, we propose a complete fusion formulation in the information space for robust shape tracking, optimally resolving uncertainties from the system dynamics, heteroscedastic measurement noise, and subspace shape model. We also exploit information from the ground truth initialization where this is available. The new framework is applied for tracking of myocardial borders in very noisy echocardiography sequences. Numerous myocardium tracking experiments validate the theory and show the potential of very accurate wall motion measurements. The proposed framework outperforms the traditional shape-space-constrained tracking algorithm by a significant margin. Due to the optimal fusion of different sources of uncertainties, robust performance is observed even for the most challenging cases.     

Robust shape tracking with multiple models in ultrasound images

This paper addresses object tracking in ultrasound images using a robust multiple model tracker. The proposed tracker has the following features: 1) it uses multiple dynamic models to track the evolution of the object boundary, and 2) it models invalid observations (outliers), reducing their influence on the shape estimates. The problem considered in this paper is the tracking of the left ventricle which is known to be a challenging problem. The heart motion presents two phases (diastole and systole) with different dynamics, the multiple models used in this tracker try to solve this difficulty. In addition, ultrasound images are corrupted by strong multiplicative noise which prevents the use of standard deformable models. Robust estimation techniques are used to address this difficulty. The multiple model data association (MMDA) tracker proposed in this paper is based on a bank of nonlinear filters, organized in a tree structure. The algorithm determines which model is active at each instant of time and updates its state by propagating the probability distribution, using robust estimation techniques.