Left ventricle endocardium segmentation for cardiac CT volumes using an optimal smooth surface

Zheng, Yefeng; Georgescu, Bogdan; Vega-Higuera, Fernando; Comanicìu, Dorin

doi:10.1117/12.811033

Cited by 6 publications

(2 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The boundary detector is trained in a leave-one-case-out fashion to ensure the separation of training and test data while still maintaining a high detection quality. As a post-processing step, the surfaces are refined as described in (Zheng et al 2009) by maximizing their smoothness under the constraint that the blood pool be tightly enclosed.…”

Section: Segmentationmentioning

confidence: 99%

Assessing cardiac function from total-variation-regularized 4D C-arm CT in the presence of angular undersampling

et al. 2017

View full text Add to dashboard Cite

Time-resolved tomographic cardiac imaging using an angiographic C-arm device may support clinicians during minimally invasive therapy by enabling a thorough analysis of the heart function directly in the catheter laboratory. However, clinically feasible acquisition protocols entail a highly challenging reconstruction problem which suffers from sparse angular sampling of the trajectory. Compressed sensing theory promises that useful images can be recovered despite massive undersampling by means of sparsity-based regularization. For a multitude of reasons-most notably the desired reduction of scan time, dose and contrast agent required-it is of great interest to know just how little data is actually sufficient for a certain task. In this work, we apply a convex optimization approach based on primal-dual splitting to 4D cardiac C-arm computed tomography. We examine how the quality of spatially and temporally total-variation-regularized reconstruction degrades when using as few as [Formula: see text] projection views per heart phase. First, feasible regularization weights are determined in a numerical phantom study, demonstrating the individual benefits of both regularizers. Secondly, a task-based evaluation is performed in eight clinical patients. Semi-automatic segmentation-based volume measurements of the left ventricular blood pool performed on strongly undersampled images show a correlation of close to 99% with measurements obtained from less sparsely sampled data.

show abstract

Section: Segmentationmentioning

confidence: 99%

Assessing cardiac function from total-variation-regularized 4D C-arm CT in the presence of angular undersampling

et al. 2017

View full text Add to dashboard Cite

show abstract

“…In [10], a convex hull is established around classified LV bloodpool voxels. Similarly, in [11], papillaries and trabeculations at the endocardium are addressed by post-processing of a modelbased segmentation: If contrast suffices to classify the LV bloodpool voxels near the initial segmentation, a convex mesh is established around the classified voxels. [12] presents a model-based segmentation with locally disabled image forces near the papillary muscles without contour post-processing.…”

Section: Introductionmentioning

confidence: 99%

Accurate Segmentation of the Left Ventricle in Computed Tomography Images for Local Wall Thickness Assessment

Peters

Lessick

Kneser

et al. 2010

Medical Image Computing and Computer-Assisted Intervention – MICCAI 2010

View full text Add to dashboard Cite

In recent years, the fully automatic segmentation of the whole heart from three-dimensional (3D) CT or MR images has become feasible with mean surface accuracies in the order of 1mm. The assessment of local myocardial motion and wall thickness for different heart phases requires highly consistent delineation of the involved surfaces. Papillary muscles and misleading pericardial structures lead to challenges that are not easily resolved. This paper presents a framework to train boundary detection functions to explicitly avoid unwanted structures. A two-pass deformable adaptation process allows to reduce false boundary detections in the first pass while detecting most wanted boundaries in a second pass refinement. Cross-validation tests were performed for 67 cardiac datasets from 33 patients. Mean surface accuracies for the left ventricular endoand epicardium are 0.76mm and 0.68mm, respectively. The percentage of local outliers with segmentation errors > 2mm is reduced by a factor of 3 as compared to a previously published approach. Wall thickness measurements in full 3D demonstrate that artifacts due to irregular endoand epicardial contours are drastically reduced.

show abstract

Left atrial size and function as assessed by computed tomography in cardiac resynchronization therapy: Association to echocardiographic and clinical outcome

Hansen

Sommer

Nørgaard

et al. 2017

Int J Cardiovasc Imaging

View full text Add to dashboard Cite

To evaluate whether baseline left atrial (LA) volume and function were associated with clinical or echocardiographic response to cardiac resynchronization therapy (CRT), and to determine LA reverse remodeling as assessed by computed tomography (CT). We prospectively included patients receiving a CRT system who underwent dynamic cardiac CT with measurement of LA size and function before and 6 months after implantation. Patients alive not hospitalized for heart failure, and improving ≥1 NYHA class or ≥10% in 6-min walk test after 6 months follow-up were classified as clinical responders. Echocardiographic response was defined as ≥15% reduction in left ventricular (LV) end-systolic volume. We included 138 patients, of whom 95 (69%) were clinical responders and 114 (83%) were echocardiographic responders. We found no association between baseline measures of LA volume or function and clinical or echocardiographic response. Mean reduction in LA maximum and minimum volumes at 6 months were 3.3 ± 12.7 ml/m (p = 0.004) and 2.6 ± 11.4 ml/m (p = 0.01) corresponding to a relative reduction of 4.1 and 5.0%, respectively. LV end-systolic relative volume reduction was 35.2 ± 22.4% (p < 0.001). No measures of LA function changed significantly. Cardiac CT measures of baseline LA volume and function are not associated with clinical or echocardiographic response to CRT. Change in LA volume and function is marginal after 6 months despite pronounced LV reverse remodeling.

show abstract

Left ventricle endocardium segmentation for cardiac CT volumes using an optimal smooth surface

Cited by 6 publications

References 22 publications

Assessing cardiac function from total-variation-regularized 4D C-arm CT in the presence of angular undersampling

Assessing cardiac function from total-variation-regularized 4D C-arm CT in the presence of angular undersampling

Accurate Segmentation of the Left Ventricle in Computed Tomography Images for Local Wall Thickness Assessment

Left atrial size and function as assessed by computed tomography in cardiac resynchronization therapy: Association to echocardiographic and clinical outcome

Contact Info

Product

Resources

About