TY - JOUR
T1 - A general fast registration framework by learning deformation-appearance correlation
AU - Kim, Minjeong
AU - Wu, Guorong
AU - Yap, Pew Thian
AU - Shen, Dinggang
N1 - Funding Information:
Manuscript received December 30, 2010; revised May 19, 2011 and August 14, 2011; accepted September 19, 2011. Date of publication October 06, 2011; date of current version March 21, 2012. This work was supported in part by the National Institutes of Health under Grant EB006733, Grant EB008374, and Grant EB009634, the National Basic Research Program of China (973 Program) under Grant 2010CB832505, and NSFC Grant 61075010. The associate editor coordinating the review of this manuscript and approving it for publication was Prof. Sina Farsiu.
PY - 2012/4
Y1 - 2012/4
N2 - In this paper, we propose a general framework for performance improvement of the current state-of-the-art registration algorithms in terms of both accuracy and computation time. The key concept involves rapid prediction of a deformation field for registration initialization, which is achieved by a statistical correlation model learned between image appearances and deformation fields. This allows us to immediately bring a template image as close as possible to a subject image that we need to register. The task of the registration algorithm is hence reduced to estimating small deformation between the subject image and the initially warped template image, i.e., the intermediate template (IT). Specifically, to obtain a good subject-specific initial deformation, support vector regression is utilized to determine the correlation between image appearances and their respective deformation fields. When registering a new subject onto the template, an initial deformation field is first predicted based on the subject's image appearance for generating an IT. With the IT, only the residual deformation needs to be estimated, presenting much less challenge to the existing registration algorithms. Our learning-based framework affords two important advantages: 1) by requiring only the estimation of the residual deformation between the IT and the subject image, the computation time can be greatly reduced; 2) by leveraging good deformation initialization, local minima giving suboptimal solution could be avoided. Our framework has been extensively evaluated using medical images from different sources, and the results indicate that, on top of accuracy improvement, significant registration speedup can be achieved, as compared with the case where no prediction of initial deformation is performed.
AB - In this paper, we propose a general framework for performance improvement of the current state-of-the-art registration algorithms in terms of both accuracy and computation time. The key concept involves rapid prediction of a deformation field for registration initialization, which is achieved by a statistical correlation model learned between image appearances and deformation fields. This allows us to immediately bring a template image as close as possible to a subject image that we need to register. The task of the registration algorithm is hence reduced to estimating small deformation between the subject image and the initially warped template image, i.e., the intermediate template (IT). Specifically, to obtain a good subject-specific initial deformation, support vector regression is utilized to determine the correlation between image appearances and their respective deformation fields. When registering a new subject onto the template, an initial deformation field is first predicted based on the subject's image appearance for generating an IT. With the IT, only the residual deformation needs to be estimated, presenting much less challenge to the existing registration algorithms. Our learning-based framework affords two important advantages: 1) by requiring only the estimation of the residual deformation between the IT and the subject image, the computation time can be greatly reduced; 2) by leveraging good deformation initialization, local minima giving suboptimal solution could be avoided. Our framework has been extensively evaluated using medical images from different sources, and the results indicate that, on top of accuracy improvement, significant registration speedup can be achieved, as compared with the case where no prediction of initial deformation is performed.
KW - Deformation prediction
KW - fast image registration
KW - principal component analysis (PCA)
KW - support vector regression (SVR)
UR - http://www.scopus.com/inward/record.url?scp=84859010761&partnerID=8YFLogxK
U2 - 10.1109/TIP.2011.2170698
DO - 10.1109/TIP.2011.2170698
M3 - Article
C2 - 21984505
AN - SCOPUS:84859010761
VL - 21
SP - 1823
EP - 1833
JO - IEEE Transactions on Image Processing
JF - IEEE Transactions on Image Processing
SN - 1057-7149
IS - 4
M1 - 6035779
ER -