Automated segmentation of 3D CT images based on statistical atlas and graph cuts

Authors:
Akinobu Shimizu;Keita Nakagomi;Takuya Narihira;Hidefumi Kobatake;Shigeru Nawano;Kenji Shinozaki;Koich Ishizu;Kaori Togashi
Affiliations:
Tokyo University of Agriculture and Technology, Tokyo, Japan;Tokyo University of Agriculture and Technology, Tokyo, Japan;Tokyo University of Agriculture and Technology, Tokyo, Japan;Tokyo University of Agriculture and Technology, Tokyo, Japan;International University of Health and Welfare, Tokyo, Japan;National Kyusyu Cancer Center, Fukuoka, Japan;Kyoto University, Kyoto, Japan;Kyoto University, Kyoto, Japan
Venue:
MCV'10 Proceedings of the 2010 international MICCAI conference on Medical computer vision: recognition techniques and applications in medical imaging
Year:
2010

Citing 7
Cited 1

Active shape models—their training and application

Computer Vision and Image Understanding
Interactive Graph Cut Based Segmentation with Shape Priors

CVPR '05 Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Volume 1 - Volume 01
Graph Cuts and Efficient N-D Image Segmentation

International Journal of Computer Vision
A Review of Statistical Approaches to Level Set Segmentation: Integrating Color, Texture, Motion and Shape

International Journal of Computer Vision
Star Shape Prior for Graph-Cut Image Segmentation

ECCV '08 Proceedings of the 10th European Conference on Computer Vision: Part III
Graph cuts framework for kidney segmentation with prior shape constraints

MICCAI'07 Proceedings of the 10th international conference on Medical image computing and computer-assisted intervention - Volume Part I
Active shape models for a fully automated 3d segmentation of the liver – an evaluation on clinical data

MICCAI'06 Proceedings of the 9th international conference on Medical Image Computing and Computer-Assisted Intervention - Volume Part II

Relaxed conditional statistical shape models and their application to non-contrast liver segmentation

MICCAI'12 Proceedings of the 4th international conference on Abdominal Imaging: computational and clinical applications

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper presents an effective combination of a statistical atlasbased approach and a graph cuts algorithm for fully automated robust and accurate segmentation. Major contribution of this paper is proposal of two new submodular energies for graph cuts. One is shape constrained energy derived from a statistical atlas based segmentation and the other is for constraint from a neighbouring structure. The effectiveness of the proposed energies was demonstrated using a synthesis image with different errors in shape estimation and clinical CT volumes of liver and lung.