Paper Info
Title
Automatic inter-subject registration of whole body images
Abstract
3D inter-subject registration of image volumes is important for tasks such as atlas-based segmentation, deriving population averages, or voxel and tensor-based morphometry. A number of methods have been proposed to tackle this problem but few of them have focused on the problem of registering whole body image volumes acquired either from humans or small animals. These image volumes typically contain a large number of articulated structures, which makes registration more difficult than the registration of head images, to which the vast majority of registration algorithms have been applied. This paper pre-sents a new method for the automatic registration of whole body CT volumes, which consists of two steps. Skeletons and external surfaces are first brought into approximate correspondence with a robust point-based method. Trans-formations so obtained are refined with an intensity-based algorithm that includes spatial adaptation of the transformation's stiffness. The approach has been applied to whole body CT images of mice and to CT images of the human upper torso. We demonstrate that the approach we propose can successfully register image volumes even when these volumes are very different in size and shape or if they have been acquired with the subjects in different positions.
Year
DOI
Venue
2006
10.1007/11784012_3
WBIR
Keywords
Field
DocType
image volume,head image,whole body image volume,automatic inter-subject registration,whole body ct image,registration algorithm,inter-subject registration,automatic registration,ct image,whole body ct volume,different position
Voxel,Torso,Computer vision,Population,Segmentation,Computer science,Body images,Artificial intelligence,Image registration
Conference
Volume
ISSN
ISBN
4057
0302-9743
3-540-35648-7
Citations 
PageRank 
References 
4
0.48
13
Authors
4
Name
Order
Citations
PageRank
Xia Li1163.19
Todd E. Peterson23610.02
John C Gore361641.36
Benoit M. Dawant41388223.11