TY - JOUR
T1 - TIMER
T2 - Tensor Image Morphing for Elastic Registration
AU - Yap, Pew Thian
AU - Wu, Guorong
AU - Zhu, Hongtu
AU - Lin, Weili
AU - Shen, Dinggang
N1 - Funding Information:
The authors would like to express their gratitude to Gary Zhang of Penn Image Computing and Science Lab (PISCL) for helping them understand his algorithm better and for his graciousness in optimizing the code for the comparisons conducted in this paper. This work was supported in part by grants 1R01EB006733, 1R03EB008760 and R01EB008374, as well as the UNC RRC grant.
Copyright:
Copyright 2009 Elsevier B.V., All rights reserved.
PY - 2009/8/15
Y1 - 2009/8/15
N2 - We propose a novel diffusion tensor imaging (DTI) registration algorithm, called Tensor Image Morphing for Elastic Registration (TIMER), which leverages the hierarchical guidance of regional distributions and local boundaries, both extracted directly from the tensors. Currently available DTI registration methods generally extract tensor scalar features from each tensor to construct scalar maps. Subsequently, regional integration and other operations such as edge detection are performed to extract more features to guide the registration. However, there are two major limitations with these approaches. First, the computed regional features might not reflect the actual regional tensor distributions. Second, by the same token, gradient maps calculated from the tensor-derived scalar feature maps might not represent the actual tissue tensor boundaries. To overcome these limitations, we propose a new approach which extracts regional and edge information directly from a tensor neighborhood. Regional tensor distribution information, such as mean and variance, is computed in a multiscale fashion directly from the tensors by taking into account the voxel neighborhood of different sizes, and hence capturing tensor information at different scales, which in turn can be employed to hierarchically guide the registration. Such multiscale scheme can help alleviate the problem of local minimum and is also more robust to noise since one can better determine the statistical properties of each voxel by taking into account the properties of its surrounding. Also incorporated in our method is edge information extracted directly from the tensors, which is crucial to facilitate registration of tissue boundaries. Experiments involving real subjects, simulated subjects, fiber tracking, and atrophy detection indicate that TIMER performs better than the other methods (Yang et al., 2008; Zhang et al., 2006).
AB - We propose a novel diffusion tensor imaging (DTI) registration algorithm, called Tensor Image Morphing for Elastic Registration (TIMER), which leverages the hierarchical guidance of regional distributions and local boundaries, both extracted directly from the tensors. Currently available DTI registration methods generally extract tensor scalar features from each tensor to construct scalar maps. Subsequently, regional integration and other operations such as edge detection are performed to extract more features to guide the registration. However, there are two major limitations with these approaches. First, the computed regional features might not reflect the actual regional tensor distributions. Second, by the same token, gradient maps calculated from the tensor-derived scalar feature maps might not represent the actual tissue tensor boundaries. To overcome these limitations, we propose a new approach which extracts regional and edge information directly from a tensor neighborhood. Regional tensor distribution information, such as mean and variance, is computed in a multiscale fashion directly from the tensors by taking into account the voxel neighborhood of different sizes, and hence capturing tensor information at different scales, which in turn can be employed to hierarchically guide the registration. Such multiscale scheme can help alleviate the problem of local minimum and is also more robust to noise since one can better determine the statistical properties of each voxel by taking into account the properties of its surrounding. Also incorporated in our method is edge information extracted directly from the tensors, which is crucial to facilitate registration of tissue boundaries. Experiments involving real subjects, simulated subjects, fiber tracking, and atrophy detection indicate that TIMER performs better than the other methods (Yang et al., 2008; Zhang et al., 2006).
KW - Diffusion tensor imaging
KW - Elastic registration
KW - Log-Euclidean manifold
KW - Tensor boundaries
KW - Tensor regional distributions
UR - http://www.scopus.com/inward/record.url?scp=67349227431&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=67349227431&partnerID=8YFLogxK
U2 - 10.1016/j.neuroimage.2009.04.055
DO - 10.1016/j.neuroimage.2009.04.055
M3 - Article
C2 - 19398022
AN - SCOPUS:67349227431
SN - 1053-8119
VL - 47
SP - 549
EP - 563
JO - NeuroImage
JF - NeuroImage
IS - 2
ER -