Data-driven shape parameterization for segmentation of the right ventricle from 3D+t echocardiography

Stebbing, Richard V.; Namburete, Ana I. L.; Upton, Ross; Leeson, Paul; Noble, J. Alison

doi:10.1016/j.media.2014.12.002

Cited by 22 publications

(21 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Recently, Stebbing et al [15] presented a RV segmentation method that, instead of using statistical shape information directly, performs segmentation simultaneously in either multiple images from different views of the same patient, or in images of multiple patients. The method achieved median signed trace-surface distances of about 1.5 mm (median over 4 cases) for multiple images of a single patient and 1.7 mm (median over 12 cases) for multiple patients.…”

Section: Discussionmentioning

confidence: 99%

“…Stebbing et. al [15] has described a segmentation method using an explicit Loop subdivision surface model of the RV and solving the fitting problem with energy minimization. Missing edges and information of RV shape in the target population is implicitly handled by solving the energy minimization simultaneously in either multiple views of the same patient, or across multiple patients.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Automated Segmentation of the Right Ventricle in 3D Echocardiography: A Kalman Filter State Estimation Approach

Bersvendsen

Orderud²,

Massey

et al. 2016

IEEE Trans. Med. Imaging

View full text Add to dashboard Cite

As the right ventricle's (RV) role in cardiovascular diseases is being more widely recognized, interest in RV imaging, function and quantification is growing. However, there are currently few RV quantification methods for 3D echocardiography presented in the literature or commercially available. In this paper we propose an automated RV segmentation method for 3D echocardiographic images. We represent the RV geometry by a Doo-Sabin subdivision surface with deformation modes derived from a training set of manual segmentations. The segmentation is then represented as a state estimation problem and solved with an extended Kalman filter by combining the RV geometry with a motion model and edge detection. Validation was performed by comparing surface-surface distances, volumes and ejection fractions in 17 patients with aortic insufficiency between the proposed method, magnetic resonance imaging (MRI), and a manual echocardiographic reference. The algorithm was efficient with a mean computation time of 2.0 s. The mean absolute distances between the proposed and manual segmentations were 3.6 ± 0.7 mm. Good agreements of end diastolic volume, end systolic volume and ejection fraction with respect to MRI ( -26±24 mL , -16±26 mL and 0 ± 10%, respectively) and a manual echocardiographic reference (7 ± 30 mL, 13 ± 17 mL and -5±7% , respectively) were observed.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Automated Segmentation of the Right Ventricle in 3D Echocardiography: A Kalman Filter State Estimation Approach

Bersvendsen

Orderud²,

Massey

et al. 2016

IEEE Trans. Med. Imaging

View full text Add to dashboard Cite

show abstract

“…Additionally, fractal dimension analysis does not require manual contours to be drawn to define the LV endocardium and epicardium, which can be susceptible to inter and intra-observer variability 25 . With current advances in automatic cardiac segmentation [26][27][28][29] , it is reasonable to expect fractal dimension analysis to become fully automated. Since the method is also independent of motion tracking, it can be used to characterize topography even on a single static image of the heart.…”

Section: Discussionmentioning

confidence: 99%

“…While this is not ideal, we note that the aim of this work was to evaluate the feasibility of using topography variation as a surrogate measure of cardiac function, rather than to develop an optimized segmentation algorithm. Given the current advances in machine assisted segmentation techniques, such as convolutional neural networks [26][27][28][29] , we expect that the choice of threshold will very shortly not be subject to inter-user variability. While we have demonstrated the applicability of the method to images acquired with standard clinical protocols, the variability in CT image acquisition (different scanner models) and CT image reconstruction (different fields of view, slice thicknesses, and reconstruction kernels) of these images may introduce biases in the fractal dimension estimates.…”

Section: Limitationsmentioning

confidence: 99%

Regional dynamics of fractal dimension of the left ventricular endocardium from cine computed tomography images

Manohar

Rossini

Colvert

et al. 2019

Preprint

View full text Add to dashboard Cite

We present a method to leverage the high fidelity of CT to quantify regional left ventricular function using topography variation of the endocardium as a surrogate measure of strain. 4DCT images of 10 normal and 10 abnormal subjects, acquired with standard clinical protocols, were used. The topography of the endocardium was characterized by its regional values of fractal dimension (FD), computed using a box-counting algorithm developed in-house. The average FD in each of the 16 American Heart Association segments was calculated for each subject as a function of time over the cardiac cycle. The normal subjects showed a peak systolic percentage change in FD of 5.9% ± 2% in all free-wall segments, while the abnormal cohort experienced a change of 2% ± 1.2% (p < 0.00001). Septal segments, being smooth, did not undergo large changes in FD. Additionally, a principal component analysis was performed on the temporal profiles of FD to highlight the possibility for unsupervised classification of normal and abnormal function. The method developed is free from manual contouring and does not require any feature tracking or registration algorithms. The FD values in the free wall segments correlated well with radial strain and with endocardial regional shortening measurements. advanced disease stages, and GLS is not a local measurement. Additionally, regional dysfunction often precedes global dysfunction and global metrics fail to identify specific regions of abnormally functioning cardiac tissue.Recent advances in x-ray computed tomography (CT) technology have led to very short scan times (~140 ms for a full high resolution 3D volume of the heart), permitting measurement of three-dimensional (3D) motion of the whole heart for a full cardiac cycle within a single heartbeat acquisition 8-12 . Additionally, the superior spatial resolution of CT has made it possible to visualize and track fine endocardial features such as trabeculae carneae 13 . Viewing a simple surface rendered LV blood volume as a 3D movie shows directly that the trabeculae undergo significant deformation during systolic contraction. The aim of this work was to exploit the high fidelity of x-ray CT to derive a simple metric of regional cardiac function with minimal operator involvement and fast post-processing of the images. We hypothesized that the variation of LV endocardial topography across the cardiac cycle, characterized by regional values of its surface fractal dimension (FD), could be obtained from simple threshold data and can serve as a surrogate measure of regional strain in those regions that have trabeculation. Other shape-based measures for cardiac motion analysis have been proposed and established. McEachen & Duncan, 1997 14 established a technique to quantify the non-rigid and non-uniform motion of the LV by matching local segments of the endocardial contour across time using a shape-based optimization function. Duncan et al., 1988 15 proposed a shape-based model using the bending energy required to deform LV endocardial contours from an unde...

show abstract

“…However, the application of these snake models was limited by two facts: (1) Segmentation results were sensitive to the contour initialization; (2) it was not easy to define an excellent a priori constraint to meet the vast variations of CMR images. So researchers developed the active shape and appearance models in which the training data were used to produce a prior knowledge such as the statistical shape and intensity statistics [16][17][18]. These approaches achieved competitive results, but their application was still limited by the size and richness of the training data heavily.…”

Section: Introductionmentioning

confidence: 99%

An SPCNN-GVF-based approach for the automatic segmentation of left ventricle in cardiac cine MR images

Wang

et al. 2016

Int J CARS

View full text Add to dashboard Cite

show abstract

Data-driven shape parameterization for segmentation of the right ventricle from 3D+t echocardiography

Cited by 22 publications

References 22 publications

Automated Segmentation of the Right Ventricle in 3D Echocardiography: A Kalman Filter State Estimation Approach

Automated Segmentation of the Right Ventricle in 3D Echocardiography: A Kalman Filter State Estimation Approach

Regional dynamics of fractal dimension of the left ventricular endocardium from cine computed tomography images

An SPCNN-GVF-based approach for the automatic segmentation of left ventricle in cardiac cine MR images

Contact Info

Product

Resources

About