Bayesian Segmentation of Atrium Wall Using Globally-Optimal Graph Cuts on 3D Meshes

Veni, Gopalkrishna; Fu, Zhisong; Awate, Suyash P.; Whitaker, Ross T.

doi:10.1007/978-3-642-38868-2_55

Cited by 11 publications

(26 citation statements)

References 12 publications

(19 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Thus, the graph becomes, essentially, a discrete approximation to an underlying continuous parameterization of a subset of the 3D volume. The work in this paper builds on the previous work of the authors (Veni et al, 2013, 2015). The paper also discusses further improvements in the generative intensity model by embedding the covariance structure that exists between intensity profiles.…”

Section: Related Workmentioning

confidence: 90%

“…Veni et al (2013) defined the image intensity model by means of a set of training images with an isotropic Gaussian distribution around a learned mean. Here we model the intensity profiles for a surface at a column location with a column-dependent mean, μ i and covariance Σ i .…”

Section: Methodsmentioning

confidence: 99%

“…Song et al (2013) extended this idea by introducing shape priors into such surface estimation schemes, but the priors were strictly local, implemented as modifications to smoothness parameters in the optimal cut formulation. Veni et al (2013) used an another form of the surface-net approach, namely, a VCE-weight net surface problem by enforcing soft constraints on surface smoothness and interrelations between coupled surfaces. However, they do not incorporate parameterized shape priors in their Bayesian formulation, which is essential for the LA wall segmentation.…”

Section: Related Workmentioning

confidence: 99%

“…Lower-level deformable shape methods, such as level sets (Malladi et al, 1995; Whitaker, 1994), which typically rely on gradient descent optimizations, have been shown to be unable to handle such large variations in the boundary contrast. Moreover, statistical and deformable methods rely on some sort of incremental fitting algorithm that is prone to get trapped in local minima during optimization, which has been demonstrated in (Veni et al, 2013). The difficulty in optimizing shape models in the presence of such a challenging environment motivates us to consider an optimization strategy that seeks a globally optimal solution.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

ShapeCut: Bayesian surface estimation using shape-driven graph

Veni

Elhabian

Whitaker

2017

Medical Image Analysis

Self Cite

View full text Add to dashboard Cite

A variety of medical image segmentation problems present significant technical challenges, including heterogeneous pixel intensities, noisy/ill-defined boundaries and irregular shapes with high variability. The strategy of estimating optimal segmentations within a statistical framework that combines image data with priors on anatomical structures promises to address some of these technical challenges. However, methods that rely on local optimization techniques and/or local shape penalties (e.g., smoothness) have been proven to be inadequate for many difficult segmentation problems. These challenging segmentation problems can benefit from the inclusion of global shape priors within a maximum-a-posteriori estimation framework, which biases solutions toward an object class of interest. In this paper, we propose a maximum-a-posteriori formulation that relies on a generative image model by incorporating both local and global shape priors. The proposed method relies on graph cuts as well as a new shape parameters estimation that provides a global updates-based optimization strategy. We demonstrate our approach on synthetic datasets as well as on the left atrial wall segmentation from late-gadolinium enhancement MRI, which has been shown to be effective for identifying myocardial fibrosis in the diagnosis of atrial fibrillation. Experimental results prove the effectiveness of the proposed approach in terms of the average surface distance between extracted surfaces and the corresponding ground-truth, as well as the clinical efficacy of the method in the identification of fibrosis and scars in the atrial wall.

show abstract

Section: Related Workmentioning

confidence: 90%

Section: Methodsmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

ShapeCut: Bayesian surface estimation using shape-driven graph

Veni

Elhabian

Whitaker

2017

Medical Image Analysis

Self Cite

View full text Add to dashboard Cite

show abstract

“…In practice, the ELF computation can be limited to a local neighborhood, which works well for surfaces of limited curvature but no longer offers the theoretical nonself-intersection guarantee that is present in the general case. A recent approach [30] uses dynamic particle systems to compute layers of sample points around the base graph. While this approach was shown to work well for simple shapes, it does not guarantee nonself-intersection in the complex setting of the cortical surface.…”

Section: Discussionmentioning

confidence: 99%

LOGISMOS-B: Layered Optimal Graph Image Segmentation of Multiple Objects and Surfaces for the Brain

Oguz

Sonka

2014

IEEE Trans. Med. Imaging

View full text Add to dashboard Cite

Automated reconstruction of the cortical surface is one of the most challenging problems in the analysis of human brain magnetic resonance imaging (MRI). A desirable segmentation must be both spatially and topologically accurate, as well as robust and computationally efficient. We propose a novel algorithm, LOGISMOS-B, based on probabilistic tissue classification, generalized gradient vector flows and the LOGISMOS graph segmentation framework. Quantitative results on MRI datasets from both healthy subjects and multiple sclerosis patients using a total of 16 800 manually placed landmarks illustrate the excellent performance of our algorithm with respect to spatial accuracy. Remarkably, the average signed error was only 0.084 mm for the white matter and 0.008 mm for the gray matter, even in the presence of multiple sclerosis lesions. Statistical comparison shows that LO-GISMOS-B produces a significantly more accurate cortical reconstruction than FreeSurfer, the current state-of-the-art approach (p ≪ 0.001. Furthermore, LOGISMOS-B enjoys a run time that is less than a third of that of FreeSurfer, which is both substantial, considering the latter takes 10 h/subject on average, and a statistically significant speedup.

show abstract