TY - JOUR
T1 - An Efficient Preconditioner for Stochastic Gradient Descent Optimization of Image Registration
AU - Qiao, Yuchuan
AU - Lelieveldt, Boudewijn P.F.
AU - Staring, Marius
PY - 2019
Y1 - 2019
N2 - Stochastic gradient descent (SGD) is commonly used to solve (parametric) image registration problems. In the case of badly scaled problems, SGD, however, only exhibits sublinear convergence properties. In this paper, we propose an efficient preconditioner estimation method to improve the convergence rate of SGD. Based on the observed distribution of voxel displacements in the registration, we estimate the diagonal entries of a preconditioning matrix, thus rescaling the optimization cost function. The preconditioner is efficient to compute and employ and can be used for mono-modal as well as multi-modal cost functions, in combination with different transformation models, such as the rigid, the affine, and the B-spline model. Experiments on different clinical datasets show that the proposed method, indeed, improves the convergence rate compared with SGD with speedups around 25 in all tested settings while retaining the same level of registration accuracy.
AB - Stochastic gradient descent (SGD) is commonly used to solve (parametric) image registration problems. In the case of badly scaled problems, SGD, however, only exhibits sublinear convergence properties. In this paper, we propose an efficient preconditioner estimation method to improve the convergence rate of SGD. Based on the observed distribution of voxel displacements in the registration, we estimate the diagonal entries of a preconditioning matrix, thus rescaling the optimization cost function. The preconditioner is efficient to compute and employ and can be used for mono-modal as well as multi-modal cost functions, in combination with different transformation models, such as the rigid, the affine, and the B-spline model. Experiments on different clinical datasets show that the proposed method, indeed, improves the convergence rate compared with SGD with speedups around 25 in all tested settings while retaining the same level of registration accuracy.
KW - image registration
KW - Optimization
KW - preconditioning
KW - stochastic gradient descent
UR - http://www.scopus.com/inward/record.url?scp=85072925179&partnerID=8YFLogxK
U2 - 10.1109/TMI.2019.2897943
DO - 10.1109/TMI.2019.2897943
M3 - Article
C2 - 30762536
AN - SCOPUS:85072925179
SN - 0278-0062
VL - 38
SP - 2314
EP - 2325
JO - IEEE Transactions on Medical Imaging
JF - IEEE Transactions on Medical Imaging
IS - 10
M1 - 8638803
ER -