Border Detection on Short Axis Echocardiographic Views Using a Region Based Ellipse-Driven Framework

Taron, Maxime; Paragios, Nikos; Jolly, Marie-Pierre

doi:10.1007/978-3-540-30135-6_54

Cited by 10 publications

(5 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In unsupervised segmentation the approaches by Taron et al [38] and Brox and Cremers [6], possibly the most closely related to ours, are alternating schemes of segmentation and color model estimation. While spatial variation of color distributions often degrades the convergence of such unsupervised segmentation methods to suboptimal local minima (the respective color distributions simply adapt to the local context), we show that in interactive segmentation-combined with recent convex relaxation techniques-explicitly modeling the spatial context of color information leads to drastic performance improvements with optimal or near-optimal results.…”

Section: Previous Data Fidelity Termsmentioning

confidence: 69%

Spatially Varying Color Distributions for Interactive Multilabel Segmentation

Nieuwenhuis

Cremers

2013

IEEE Trans. Pattern Anal. Mach. Intell.

View full text Add to dashboard Cite

Abstract-We propose a method for interactive multilabel segmentation which explicitly takes into account the spatial variation of color distributions. To this end, we estimate a joint distribution over color and spatial location using a generalized Parzen density estimator applied to each user scribble. In this way, we obtain a likelihood for observing certain color values at a spatial coordinate. This likelihood is then incorporated in a Bayesian MAP estimation approach to multiregion segmentation which in turn is optimized using recently developed convex relaxation techniques. These guarantee global optimality for the two-region case (foreground/background) and solutions of bounded optimality for the multiregion case. We show results on the GrabCut benchmark, the recently published Graz benchmark, and on the Berkeley segmentation database which exceed previous approaches such as GrabCut [32]

show abstract

Section: Previous Data Fidelity Termsmentioning

confidence: 69%

Spatially Varying Color Distributions for Interactive Multilabel Segmentation

Nieuwenhuis

Cremers

2013

IEEE Trans. Pattern Anal. Mach. Intell.

View full text Add to dashboard Cite

show abstract

“…In the present paper, we complete their work by showing that the Mumford-Shah functional can be interpreted as a firstorder approximation of a specific maximum a-posteriori model, where pixel intensities are not, as usual, identically distributed but where the distribution varies with the position in the image. Such local region statistics have recently been introduced in the scope of medical image segmentation (Taron et al 2004) and silhouette based 3D tracking (Brox et al 2005). The statistical interpretation we derive is considerably different from the one in Tsai et al (2001).…”

Section: T Brox ( ) · D Cremersmentioning

confidence: 99%

On Local Region Models and a Statistical Interpretation of the Piecewise Smooth Mumford-Shah Functional

2008

View full text Add to dashboard Cite

The Mumford-Shah functional is a general and quite popular variational model for image segmentation. In particular, it provides the possibility to represent regions by smooth approximations. In this paper, we derive a statistical interpretation of the full (piecewise smooth) Mumford-Shah functional by relating it to recent works on local region statistics. Moreover, we show that this statistical interpretation comes along with several implications. Firstly, one can derive extended versions of the Mumford-Shah functional including more general distribution models. Secondly, it leads to faster implementations. Finally, thanks to the analytical expression of the smooth approximation via Gaussian convolution, the coordinate descent can be replaced by a true gradient descent.

show abstract

“…Taron et al used an ellipse–shaped model to constrain the short axis LV border detection. It was based on the assumption that the short axis endocardium of LV was similar to an ellipse, and which limited its application to only the LV short axis (Taron et al 2004). Recently, Dienbeck et al proposed a geometrically constrained level set algorithm to detect the whole LV myocardium on 2D echocardiography (Dietenbeck et al 2012).…”

Section: Introductionmentioning

confidence: 99%

Automatic segmentation of right ventricular ultrasound images using sparse matrix transform and a level set

2013

View full text Add to dashboard Cite

An automatic segmentation framework is proposed to segment the right ventricle (RV) in echocardiographic images. The method can automatically segment both epicardial and endocardial boundaries from a continuous echocardiography series by combining sparse matrix transform, a training model, and a localized region-based level set. First, the sparse matrix transform extracts main motion regions of the myocardium as eigen-images by analyzing the statistical information of the images. Second, an RV training model is registered to the eigen-images in order to locate the position of the RV. Third, the training model is adjusted and then serves as an optimized initialization for the segmentation of each image. Finally, based on the initializations, a localized, region-based level set algorithm is applied to segment both epicardial and endocardial boundaries in each echocardiograph. Three evaluation methods were used to validate the performance of the segmentation framework. The Dice coefficient measures the overall agreement between the manual and automatic segmentation. The absolute distance and the Hausdorff distance between the boundaries from manual and automatic segmentation were used to measure the accuracy of the segmentation. Ultrasound images of human subjects were used for validation. For the epicardial and endocardial boundaries, the Dice coefficients were 90.8 ± 1.7% and 87.3 ± 1.9%, the absolute distances were 2.0 ± 0.42 mm and 1.79 ± 0.45 mm, and the Hausdorff distances were 6.86 ± 1.71 mm and 7.02 ± 1.17 mm, respectively. The automatic segmentation method based on a sparse matrix transform and level set can provide a useful tool for quantitative cardiac imaging.

show abstract

Border Detection on Short Axis Echocardiographic Views Using a Region Based Ellipse-Driven Framework

Cited by 10 publications

References 10 publications

Spatially Varying Color Distributions for Interactive Multilabel Segmentation

Spatially Varying Color Distributions for Interactive Multilabel Segmentation

On Local Region Models and a Statistical Interpretation of the Piecewise Smooth Mumford-Shah Functional

Automatic segmentation of right ventricular ultrasound images using sparse matrix transform and a level set

Contact Info

Product

Resources

About