Learn More
This paper presents a dynamical appearance model based on sparse representation and dictionary learning for tracking both endocardial and epicardial contours of the left ventricle in echocardiographic sequences. Instead of learning offline spatiotemporal priors from databases, we exploit the inherent spatiotemporal coherence of individual data to constraint(More)
BACKGROUND Color Doppler jet area (CDJA) is an important measure used to classify mitral regurgitation (MR) severity. The investigators hypothesized that the presence and configuration of multiple regurgitant jets can alter CDJA quantification for fixed regurgitant volumes. This has relevance to MR assessment prior to the treatment of valves with multiple(More)
Quantitative analysis of left ventricular deformation can provide valuable information about the extent of disease as well as the efficacy of treatment. In this work, we develop an adaptive multi-level compactly supported radial basis approach for deformation analysis in 3D+time echocardiography. Our method combines displacement information from shape(More)
BACKGROUND A standard quantitative imaging approach to evaluate peripheral arterial disease does not exist. Quantitative tools for evaluating arteriogenesis in vivo are not readily available, and the feasibility of monitoring serial regional changes in lower extremity perfusion has not been examined. METHODS AND RESULTS Serial changes in lower extremity(More)
Echocardiography is one of the most valuable diagnostic tools in cardiology. Technological advances in ultrasound, computer and electronics enables three-dimensional (3-D) imaging to be a clinically viable modality which has significant impact on diagnosis, management and interventional procedures. Since the inception of 3D fully-sampled matrix(More)
A high-temporal resolution 2D flow pathline analysis method to study early diastolic filling is presented. Filling patterns in normal volunteers (n = 8) and canine animals [baseline (n = 1) and infarcted (n = 6)] are studied. Data are acquired using spatial modulation of magnetization with polarity alternating velocity encoding, which permits simultaneous(More)
BACKGROUND Exercise testing should be symptom-limited. Nevertheless, 40% of clinical laboratories applying for ICANL accreditation use 85% of maximal age-predicted heart rate (MPHR) as the primary exercise endpoint. We hypothesized that this approach importantly may underestimate exercise capacity and inducible ischemia. METHODS Two patient cohorts were(More)
The spatio-temporal coherence in data plays an important role in echocardiographic segmentation. While learning offline dynamical priors from databases has received considerable attention, these priors may not be suitable for post-infarct patients and children with congenital heart disease. This paper presents a dynamical appearance model (DAM) driven by(More)
This paper presents an algorithm for segmenting left ventricular endocardial boundaries from RF ultrasound. Our method incorporates a computationally efficient linear predictor that exploits short-term spatio-temporal coherence in the RF data. Segmentation is achieved jointly using an independent identically distributed (i.i.d.) spatial model for RF(More)
Dictionary learning has been shown to be effective in exploiting spatiotemporal coherence for echocardiographic segmentation. To overcome the limitations of previous methods, we present a stochastic online dictionary learning approach for segmenting left ventricular borders from 4D echocardiography. It is based on stochastic approximations and processes a(More)