Knowledge-based Registration & Segmentation of the Left Ventricle: A Level Set Approach

Authors:
Nikos Paragios;Mikael Rousson;Visvanathan Ramesh
Affiliations:
-;-;-
Venue:
WACV '02 Proceedings of the Sixth IEEE Workshop on Applications of Computer Vision
Year:
2002

Citing 0
Cited 3

Estimation of Vector Fields in Unconstrained and Inequality Constrained Variational Problems for Segmentation and Registration

Journal of Mathematical Imaging and Vision
Simultaneous registration and segmentation of anatomical structures from brain MRI

MICCAI'05 Proceedings of the 8th international conference on Medical Image Computing and Computer-Assisted Intervention - Volume Part I
Levelset and b-spline deformable model techniques for image segmentation: a pragmatic comparative study

SCIA'05 Proceedings of the 14th Scandinavian conference on Image Analysis

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper, we propose a level set formulation to dealwith the segmentation and registration of the left ventriclein Magnetic Resonance (MR) images. Our approach isbased on the integration of visual information, anatomicalconstraints and a flexible shape-driven cardiac model. Thevisual information is expressed through an intensity-basedgrouping module. The anatomical constraint accounts forthe relative positions of the structures of interest. Globalshape consistency is introduced by seeking for the lowestpotential of the distance between the solution and the priormodel. Registration is obtained using the same criterionwhere the transformation that aligns the latest segmentationmap to either the shape model or to the previous segmentationresult (temporal domain) is to be recovered.