DocumentCode
2807655
Title
A new consistent image registration formulation with a B-spline deformation model
Author
Feng, Wei ; Reeves, Stanley J. ; Denney, Thomas S., Jr. ; Lloyd, Steven ; Dell´Italia, L. ; Gupta, Himanshu
Author_Institution
ECE Dept., Auburn Univ., Auburn, AL, USA
fYear
2009
fDate
June 28 2009-July 1 2009
Firstpage
979
Lastpage
982
Abstract
A consistent image registration formulation with B-spline deformation model is proposed. This formulation avoids the computation of the inverse of a deformation in the iterative optimization and allows the analytical computation of both gradient and Hessian of the cost function. Because of the formulation, the algorithm is computationally efficient and could potentially produce more accurate registration results. Experiments show that the proposed algorithm produces promising results while keeping the estimated deformations consistent.
Keywords
Hessian matrices; biomedical MRI; gradient methods; image registration; medical image processing; splines (mathematics); B-spline deformation model; Hessian matrix; brain MR images; consistent image registration formulation; gradient algorithm; iterative optimization; magnetic resonance imaging; B-spline; MRI; consistent image registration; myocardial strain;
fLanguage
English
Publisher
ieee
Conference_Titel
Biomedical Imaging: From Nano to Macro, 2009. ISBI '09. IEEE International Symposium on
Conference_Location
Boston, MA
ISSN
1945-7928
Print_ISBN
978-1-4244-3931-7
Electronic_ISBN
1945-7928
Type
conf
DOI
10.1109/ISBI.2009.5193218
Filename
5193218
Link To Document