Robust Real-Time Myocardial Border Tracking for Echocardiography: An Information Fusion Approach

Abstract

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.

Treatment of Obstructive Sleep Apnea in Young and Middle‐Aged Adults: Effects of Positive Airway Pressure and Compliance on Arterial Stiffness, Endothelial Function, and Cardiac Hemodynamics

“…Left ventricle (LV) mass was calculated using the two‐dimensional (2D)‐derived ASE corrected cubed formula, at end‐diastole. LV ejection fraction (LVEF) was calculated using the biplane method of disks using a semiautomated border detection algorithm 33. Left atrial (LA) volume was measured using the biplane area‐length method.…”

Automatic Computation of Left Ventricular Volume Changes Over a Cardiac Cycle from Echocardiography Images by Nonlinear Dimensionality Reduction

“…In all these techniques [4][5][6][7][8][9][10][11][12], first inner wall of LV is separated automatically in all images of a cardiac cycle. This is done with different image processing methods such as active contour models [5][6][7], active shape model [8], active appearance motion model [9], a combination of database-guided segmentation and an information fusion framework for robust shape tracking [4,10], a weighted radial edge filtering algorithm [11], and a combination of multiresolution edge detection technique based on the global maximum of wavelet transform and radial search algorithm [12]. It should be noted some of these image processing algorithms are also used in segmentation of LV from cardiac MR images [13][14][15].…”

“…Moreover, because of the opening of the mitral valve during diastole phase, automatic segmentation of the LV in four chamber view is difficult. Furthermore, in some of these methods [4,[8][9][10], a large data set under various diseases is required for training of shape and textural information within LV region.…”

Simultaneous Registration and Modeling of Deformable Shapes

“…On the other hand, the statistical parameterization of the shape models provides global constraints that allow the shapes to vary only in a limited number of styles. Fitting the models to the measurements has achieved robust performance in registering deformable shapes [3,2]. Thus registration and modeling of deformable shapes are coupled as chicken-egg problems.…”

“…The previous methods [3,14,9,2] proposed to solve the coupled problems separately in two consecutive steps. The first step registers the measured shapes, where Generalized Procrustes Analysis [7,8,10,11,15] has been widely used.…”