A statistical level set framework for segmentation of left ventricle

Authors:
Gang Yu;Changguo Wang;Peng Li;Yalin Miao;Zhengzhong Bian
Affiliations:
School of Life Science and Technology, Xi'an Jiaotong University, Xi'an, China;Nantong Vocational College, Nantong, China;School of Life Science and Technology, Xi'an Jiaotong University, Xi'an, China;School of Life Science and Technology, Xi'an Jiaotong University, Xi'an, China;School of Life Science and Technology, Xi'an Jiaotong University, Xi'an, China
Venue:
IWICPAS'06 Proceedings of the 2006 Advances in Machine Vision, Image Processing, and Pattern Analysis international conference on Intelligent Computing in Pattern Analysis/Synthesis
Year:
2006

Citing 7
Cited 0

Scale-Space and Edge Detection Using Anisotropic Diffusion

IEEE Transactions on Pattern Analysis and Machine Intelligence
Geodesic Active Contours

International Journal of Computer Vision
On the Incorporation of shape priors into geometric active contours

VLSM '01 Proceedings of the IEEE Workshop on Variational and Level Set Methods (VLSM'01)
Gradient Vector Flow Fast Geometric Active Contours

IEEE Transactions on Pattern Analysis and Machine Intelligence
Influence of the Noise Model on Level Set Active Contour Segmentation

IEEE Transactions on Pattern Analysis and Machine Intelligence
A novel 3d partitioned active shape model for segmentation of brain MR images

MICCAI'05 Proceedings of the 8th international conference on Medical Image Computing and Computer-Assisted Intervention - Volume Part I
Active contours without edges

IEEE Transactions on Image Processing

Quantified Score

Hi-index	0.00

Visualization

Abstract

A novel statistical framework for segmentation of the echocardiographic images is presented. The framework begins with presegmentation at a low resolution image and passes the result to the high resolution image for a fast optimal segmentation. We applied Rayleigh distribution to analyze the echocardiographic image, and introduced a posterior probability-based level set model. The model is applied for the pre-segmentation. The pre-segmentation result at the low resolution is used to initialize the front for the high resolution image with a fast scheme. At the high resolution, an efficient statistical active contour model is used to make the curve smoother and drives it closer to the real boundary. Segmentation results show that the statistical framework can extract the boundary accurately and automatically.