Shape Modeling with Front Propagation: A Level Set Approach
IEEE Transactions on Pattern Analysis and Machine Intelligence
International Journal of Computer Vision
Using Prior Shapes in Geometric Active Contours in a Variational Framework
International Journal of Computer Vision
Tissue Classification Based on 3D Local Intensity Structures for Volume Rendering
IEEE Transactions on Visualization and Computer Graphics
Level Set Evolution without Re-Initialization: A New Variational Formulation
CVPR '05 Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Volume 1 - Volume 01
IEEE Transactions on Visualization and Computer Graphics
FIMH '09 Proceedings of the 5th International Conference on Functional Imaging and Modeling of the Heart
Left Ventricle Segmentation via Graph Cut Distribution Matching
MICCAI '09 Proceedings of the 12th International Conference on Medical Image Computing and Computer-Assisted Intervention: Part II
Real-time segmentation by Active Geometric Functions
Computer Methods and Programs in Biomedicine
Segmentation of 4D cardiac MRI: Automated method based on spatio-temporal watershed cuts
Image and Vision Computing
Patient-specific modeling and analysis of the mitral valve using 3D-TEE
IPCAI'10 Proceedings of the First international conference on Information processing in computer-assisted interventions
Hi-index | 0.00 |
We describe a method for recovering the left intracardiac cavities from 3D Transesophageal Echocardiography (3D TEE). 3D TEE is an important modality for cardiac applications because of its ability to do fast and non-ionizing 3D imaging of the left heart complex. Segmentation based on 3D TEE can be used to characterize pathophysiologies of the valve and myocardium, and as input to patient-specific biomechanical models and preoperative planning tools. The segmentation employed here is based on a dynamic surface evolution. This is performed under a growth inhibition function that incorporates information from several sources including k-means clustering, 3D gradient magnitude, and a morphological structure tensor intended to locate the mitral valve leaflets. We report experiments using intraoperative 3D TEE data, showing good agreement between the segmented structures and ground truth.