Segmentation of 3d CT volume images using a single 2d atlas

Authors:
Feng Ding;Wee Kheng Leow;Shih-Chang Wang
Affiliations:
Dept. of Computer Science, National University of Singapore, Singapore;Dept. of Computer Science, National University of Singapore, Singapore;Dept. of Diagnostic Radiology, National University of Singapore, Singapore
Venue:
CVBIA'05 Proceedings of the First international conference on Computer Vision for Biomedical Image Applications
Year:
2005

Citing 2
Cited 2

A Method for Registration of 3-D Shapes

IEEE Transactions on Pattern Analysis and Machine Intelligence - Special issue on interpretation of 3-D scenes—part II
Gradient Vector Flow: A New External Force for Snakes

CVPR '97 Proceedings of the 1997 Conference on Computer Vision and Pattern Recognition (CVPR '97)

Automatic segmentation of femur bones in anterior-posterior pelvis x-ray images

CAIP'07 Proceedings of the 12th international conference on Computer analysis of images and patterns
GPU-based active contour segmentation using gradient vector flow

ISVC'06 Proceedings of the Second international conference on Advances in Visual Computing - Volume Part I

Quantified Score

Hi-index	0.00

Visualization

Abstract

Segmentation of medical images is an important first step in the analysis of medical images. A lot of research has been performed on the segmentation of complex CT/MR images using the atlas-based approach. Most existing methods use 3D atlases which are more complex and difficult to control than 2D atlases. They have been applied mostly for the segmentation of brain images. This paper presents a method that can segment multiple slices of an abdominal CT volume using a single 2D atlas. Segmentation of human body images is considerably more difficult and challenging than brain image segmentation. Test results show that our method can handle large variations in shape and intensity between the atlas and the target CT images.