Automatic Extraction of 3D Dynamic Left Ventricle Model from 2D Rotational Angiocardiogram

Chen, Mingqing; Zheng, Yefeng; Mueller, Kerstin; Rohkohl, Christopher; Lauritsch, Guenter; Boese, Jan; Funka-Lea, Gareth; Hornegger, Joachim; Comanicìu, Dorin

doi:10.1007/978-3-642-23626-6_58

Cited by 8 publications

(22 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The bars "Static Mesh" show the initialization error using a static mesh extracted from a 3D volume using non-ECGgated reconstruction, while the bars "Prior Model" show the initialization error using the pre-learned motion model, which is more accurate than the initialization using a static mesh. The performance of the previous approach [4] is shown as the green bar, which is surpassed by the proposed method (the purple bar). The proposed method achieves a mean contour distance of 2.87 ± 1.00 mm.…”

Section: Methodsmentioning

confidence: 92%

“…In order to convert the 2D motion vector estimated from the angiogram to 3D, a previous assumption is that the motion occurs mainly along the surface normal [4]. It is reasonable for most parts of the LV where the motion is dominated by the contraction and relaxation of the LV cavity.…”

Section: Motion Trajectorymentioning

confidence: 99%

“…Most of these methods rely on manual editing of the silhouette of the LV endocardium due to the difficulty in automatic boundary detection. Recently, an automatic method was proposed for 3D motion estimation of the LV from rotational angiocardiography [4]. First, a 3D LV mesh model is segmented from the 3D volume containing motion blur.…”

Section: Introductionmentioning

confidence: 99%

“…First, the initialization with a static LV model [4] (which is close to the shape of the end-diastolic phase) is not accurate enough, especially for the end-systolic phase, which has a much smaller LV volume. To address this issue, a prior LV motion model is learned from a set of dynamic cardiac CT sequences.…”

Section: Introductionmentioning

confidence: 99%

“…In this work, for each mesh point, a 3D motion trajectory is also learned from the dynamic cardiac sequences to replace the assumption of motion along the surface normal. Third, instead of using each individual local image feature [4] for the weak classifiers to train an AdaBoost based boundary detector, principal component analysis (PCA) is applied to a local image patch to create a compact feature representation. The new feature pool is composed of the top principal components (PC) and the combination of a pair of PCs, which are more powerful than the previous local image features.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Automatic 3D Motion Estimation of Left Ventricle from C-arm Rotational Angiocardiography Using a Prior Motion Model and Learning Based Boundary Detector

Chen

Zheng

Wang

et al. 2013

Advanced Information Systems Engineering

Self Cite

View full text Add to dashboard Cite

Abstract. Compared to pre-operative imaging modalities, it is more convenient to estimate the current cardiac physiological status from C-arm angiocardiography since C-arm is a widely used intra-operative imaging modality to guide many cardiac interventions. The 3D shape and motion of the left ventricle (LV) estimated from rotational angiocardiography provide important cardiac function measurements, e.g., ejection fraction and myocardium motion dyssynchrony. However, automatic estimation of the 3D LV motion is difficult since all anatomical structures overlap on the 2D X-ray projections and the nearby confounding strong image boundaries (e.g., pericardium) often cause ambiguities to LV endocardium boundary detection. In this paper, a new framework is proposed to overcome the aforementioned difficulties: (1) A new learning-based boundary detector is developed by training a boosting boundary classifier combined with the principal component analysis of a local image patch; (2) The prior LV motion model is learned from a set of dynamic cardiac computed tomography (CT) sequences to provide a good initial estimate of the 3D LV shape of different cardiac phases; (3) The 3D motion trajectory is learned for each mesh point; 4) All these components are integrated into a multi-surface graph optimization method to extract the globally coherent motion. The method is tested on seven patient scans, showing significant improvement on the ambiguous boundary cases with a detection accuracy of 2.87 ± 1.00 mm on LV endocardium boundary delineation in the 2D projections.

show abstract

Section: Methodsmentioning

confidence: 92%

Section: Motion Trajectorymentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Automatic 3D Motion Estimation of Left Ventricle from C-arm Rotational Angiocardiography Using a Prior Motion Model and Learning Based Boundary Detector

Chen

Zheng

Wang

et al. 2013

Advanced Information Systems Engineering

Self Cite

View full text Add to dashboard Cite

show abstract

3D Lung Tumor Motion Model Extraction from 2D Projection Images of Mega-voltage Cone Beam CT via Optimal Graph Search

Chen

Bai

Zheng

et al. 2012

Medical Image Computing and Computer-Assisted Intervention – MICCAI 2012

Self Cite

View full text Add to dashboard Cite

Abstract. In this paper, we propose a novel method to convert segmentation of objects with quasi-periodic motion in 2D rotational cone beam projection images into an optimal 3D multiple interrelated surface detection problem, which can be solved by a graph search framework. The method is tested on lung tumor segmentation in projection images of mega-voltage cone beam CT (MVCBCT). A 4D directed graph is constructed based on an initialized tumor mesh model, where the cost value for this graph is computed from the point location of a silhouette outline of projected tumor mesh in 2D projection images. The method was first evaluated on four different sized phantom inserts (all above 1.9 cm in diameter) with a predefined motion of 3.0 cm to mimic the imaging of lung tumors. A dice coefficient of 0.87 ± 0.03 and a centroid error of 1.94 ± 1.31mm were obtained. Results based on 12 MVCBCT scans from 3 patients obtained 0.91 ± 0.03 for dice coefficient and 1.83 ± 1.31mm for centroid error, compared with a difference between two sets of independent manual contours of 0.89 ± 0.03 and 1.61 ± 1.19mm, respectively.

show abstract

Image artefact propagation in motion estimation and reconstruction in interventional cardiac C-arm CT

Müller¹,

Maier²,

Schwemmer³

et al. 2014

Phys. Med. Biol.

View full text Add to dashboard Cite

The acquisition of data for cardiac imaging using a C-arm CT system requires several seconds and multiple heartbeats. Hence, incorporation of motion correction in the reconstruction step may improve the resulting image quality. Cardiac motion can be estimated by deformable 3-D/3-D registration performed on initial 3-D images of different heart phases. This motion information can be used for a motion-compensated reconstruction allowing the use of all acquired data for image reconstruction. However, the result of the registration procedure and hence the estimated deformations are influenced by the quality of the initial 3-D images. In this paper, the sensitivity of the 3-D/3-D registration step to the image quality of the initial images is studied. Different reconstruction algorithms are evaluated for a recently proposed cardiac C-arm CT acquisition protocol. The initial 3-D images are all based on retrospective electrocardiogram (ECG)-gated data. ECG-gating of data from a single C-arm rotation provides only a few projections per heart phase for image reconstruction. This view sparsity leads to prominent streak artefacts and a poor signal to noise ratio. Five different initial image reconstructions are evaluated: (1) cone beam filtered-backprojection (FDK), (2) cone beam filtered-backprojection and an additional bilateral filter (FFDK), (3) removal of the shadow of dense objects (catheter, pacing electrode, etc.) before reconstruction with a cone beam filtered-backprojection (cathFDK), (4) removal of the shadow of dense objects before reconstruction with a cone beam filtered-backprojection and a bilateral filter (cathFFDK). The last method (5) is an iterative few-view reconstruction (FV), the prior image constrained compressed sensing (PICCS) combined with the improved total variation (iTV) algorithm. All reconstructions are investigated with respect to the final motion-compensated reconstruction quality. The algorithms were tested on a mathematical phantom data set with and without a catheter and on two porcine models using qualitative and quantitative measures. The quantitative results of the phantom experiments show that if no dense object is present within the scan field of view, the quality of the FDK initial images is sufficient for motion estimation via 3-D/3-D registration. When a catheter or pacing electrode is present, the shadow of these objects needs to be removed before the initial image reconstruction. An additional bilateral filter shows no major improvement with respect to the final motion-compensated reconstruction quality. The results with respect to image quality of the cathFDK, cathFFDK and FV images are comparable. As conclusion, in terms of computational complexity, the algorithm of choice is the cathFDK algorithm.

show abstract

Automatic Extraction of 3D Dynamic Left Ventricle Model from 2D Rotational Angiocardiogram

Cited by 8 publications

References 11 publications

Automatic 3D Motion Estimation of Left Ventricle from C-arm Rotational Angiocardiography Using a Prior Motion Model and Learning Based Boundary Detector

Automatic 3D Motion Estimation of Left Ventricle from C-arm Rotational Angiocardiography Using a Prior Motion Model and Learning Based Boundary Detector

3D Lung Tumor Motion Model Extraction from 2D Projection Images of Mega-voltage Cone Beam CT via Optimal Graph Search

Image artefact propagation in motion estimation and reconstruction in interventional cardiac C-arm CT

Contact Info

Product

Resources

About