Analysis of Left Ventricular Motion Using a General Robust Point Matching Algorithm

Lin, Ning; Papademetris, Xenophon; Sinusas, Albert J.; Duncan, James S.

doi:10.1007/978-3-540-39899-8_69

Cited by 18 publications

(12 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The third category of methods uses energy-based warping or optical flow techniques to compute the displacement of the myocardium [10][11][12]. There also exists a method taking advantages of both the second and the third categories, i.e., tracking the cardiac boundaries by image curvatures [13]. Recently, 4D models are also proposed for cardiac registration and segmentation [14,15,16].…”

Section: Introductionmentioning

confidence: 99%

Consistent Estimation of Cardiac Motions by 4D Image Registration

Shen

Sundar

Xue

et al. 2005

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. A 4D image registration method is proposed for consistent estimation of cardiac motion from MR image sequences. Under this 4D registration framework, all 3D cardiac images taken at different time-points are registered simultaneously, and motion estimated is enforced to be spatiotemporally smooth, thereby overcoming potential limitations of some methods that typically estimate cardiac deformation sequentially from one frame to another, instead of treating the entire set of images as a 4D volume. To facilitate our image matching process, an attribute vector is designed for each point in the image to include intensity, boundary and geometric moment invariants (GMIs). Hierarchical registration of two image sequences is achieved by using the most distinctive points for initial registration of two sequences and gradually adding less-distinctive points for refinement of registration. Experimental results on real data demonstrate good performance of the proposed method in registering cardiac images and estimating motions from cardiac image sequences.

show abstract

Section: Introductionmentioning

confidence: 99%

Consistent Estimation of Cardiac Motions by 4D Image Registration

Shen

Sundar

Xue

et al. 2005

Lecture Notes in Computer Science

View full text Add to dashboard Cite

show abstract

“…While curvature can be computed from segmented surfaces, the curvature operator is a second-order differential operator which amplifies the segmentation errors, and hence requiring very accurate segmentation of the ENDO-and EPI surfaces. An alternative is to compute scaled isophote curvature from intensity images in order to reduce the dependency on the accuracy of segmentation [2]. However, isophote curvature could be unreliable at weak boundaries.…”

Section: Feature Extractionmentioning

confidence: 99%

“…There have been a number of efforts in LV deformation analysis [1,2,3,4], of which one important category is to use shape-based tracking algorithm to find the correspondence of the endocardial (ENDO) and epicardial (EPI) borders in two adjacent frames, followed by the dense correspondence interpolation within the myocardium using a biomechanical model. To find the ENDO-and EPI boundaries, Shi used the manual segmentation of the endocardium and epicardium by experts [1].…”

Section: Introductionmentioning

confidence: 99%

“…To find the ENDO-and EPI boundaries, Shi used the manual segmentation of the endocardium and epicardium by experts [1]. Lin eliminated the need for manual segmentation by using a Canny edge detector for rough segmentation, followed by the Generalized Robust Point Matching (GRPM) algorithm to find feature point correspondence [2]. Yan extended their work by introducing the Boundary Element Method (BEM) that greatly improves the computational efficiency of the biomechanical model [3].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Integrated segmentation and deformation analysis of 4-D cardiac MR images

Zhu

Yan

Papademetris

et al. 2008

2008 5th IEEE International Symposium on Biomedical Imaging: From Nano to Macro

Self Cite

View full text Add to dashboard Cite

Segmentation and motion estimation from cardiac images are usually considered separately, yet they can obviously benefit from each other. In this paper, we propose a joint segmentation and motion estimation algorithm for the purposes of myocardial deformation analysis and strain estimation. We use segmentation as a guide for selecting feature points with significant shape characteristics, and invoke a Generalized Robust Point Matching (GRPM) strategy with Boundary Element Method (BEM)-based regularization model to estimate the dense displacement field and strain map from 3-D cardiac sequences. Quantitative analysis of the results is performed in comparison with the displacements found using implanted markers, taken to be gold standards.

show abstract

“…Among all computer vision-based techniques, one important category is to use shape-based tracking algorithm in order to find the correspondence of the myocardial 1 This work is supported by the grant 5R01HL082640-02. boundaries in two adjacent frames, followed by the dense correspondence interpolation within the myocardium using a biomechanical model [11,6,14]. To find the endocardial (ENDO)-and epicardial (EPI) boundaries, Shi used the manual segmentation by experts [11].…”

Section: Introductionmentioning

confidence: 99%

Integrated segmentation and motion analysis of cardiac MR images using a subject-specific dynamical model

Zhu

Papademetris

Sinusas

et al. 2008

2008 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops

Self Cite

View full text Add to dashboard Cite

In this paper we propose an integrated cardiac segmentation and motion tracking algorithm. First, we present a subject-specific dynamical model (SSDM) that simultaneously handles inter-subject variability and temporal dynamics (intra-subject variability), such that it can progressively identify the subject vector associated with a new cardiac sequence, and use this subject vector to predict the subject-specific segmentation of the future frames based on the shapes observed in earlier frames. Second, we use the segmentation as a guide in selecting feature points with significant shape characteristics, and invoke the Generalized Robust Point Matching (G-RPM) strategy with Boundary Element Method (BEM)-based regularization model to estimate physically realistic displacement field in a computationally efficient way. The integrated algorithm is formulated in a recursive Bayesian framework that sequentially segments cardiac images and estimates myocardial displacements. "Leave-one-out" validation on 32 sequences demonstrates that the segmentation results are improved when the SSDM is used, and the tracking results are much more accurate when the segmentation module is added.

show abstract

Analysis of Left Ventricular Motion Using a General Robust Point Matching Algorithm

Cited by 18 publications

References 22 publications

Consistent Estimation of Cardiac Motions by 4D Image Registration

Consistent Estimation of Cardiac Motions by 4D Image Registration

Integrated segmentation and deformation analysis of 4-D cardiac MR images

Integrated segmentation and motion analysis of cardiac MR images using a subject-specific dynamical model

Contact Info

Product

Resources

About