Standard

Randomly perturbed b-splines for nonrigid image registration. / Niessen, Wiro J.; Sun, W; Klein, S.

In: IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 39, No. 7, 7533440, 01.07.2017, p. 1401-1413.

Research output: Contribution to journalArticleScientificpeer-review

Harvard

Niessen, WJ, Sun, W & Klein, S 2017, 'Randomly perturbed b-splines for nonrigid image registration' IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 39, no. 7, 7533440, pp. 1401-1413. https://doi.org/10.1109/TPAMI.2016.2598344

APA

Niessen, W. J., Sun, W., & Klein, S. (2017). Randomly perturbed b-splines for nonrigid image registration. IEEE Transactions on Pattern Analysis and Machine Intelligence, 39(7), 1401-1413. [7533440]. https://doi.org/10.1109/TPAMI.2016.2598344

Vancouver

Niessen WJ, Sun W, Klein S. Randomly perturbed b-splines for nonrigid image registration. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2017 Jul 1;39(7):1401-1413. 7533440. https://doi.org/10.1109/TPAMI.2016.2598344

Author

Niessen, Wiro J. ; Sun, W ; Klein, S. / Randomly perturbed b-splines for nonrigid image registration. In: IEEE Transactions on Pattern Analysis and Machine Intelligence. 2017 ; Vol. 39, No. 7. pp. 1401-1413.

BibTeX

@article{39e59916f7fd4ab0bf33a6f32fef33ef,
title = "Randomly perturbed b-splines for nonrigid image registration",
abstract = "B-splines are commonly utilized to construct the transformation model in free-form deformation (FFD) based registration. B-splines become smoother with increasing spline order. However, a higher-order B-spline requires a larger support region involving more control points, which means higher computational cost. In general, the third-order B-spline is considered as a good compromise between spline smoothness and computational cost. A lower-order function is seldom used to construct the transformation model for registration since it is less smooth. In this research, we investigated whether lower-order B-spline functions can be utilized for more efficient registration, while preserving smoothness of the deformation by using a novel random perturbation technique. With the proposed perturbation technique, the expected value of the cost function given probability density function (PDF) of the perturbation is minimized by a stochastic gradient descent optimization. Extensive experiments on 2D synthetically deformed brain images, and real 3D lung and brain scans demonstrated that the novel randomly perturbed free-form deformation (RPFFD) approach improves the registration accuracy and transformation smoothness. Meanwhile, lower-order RPFFD methods reduce the computational cost substantially.",
keywords = "B-splines, free-form deformation, Nonrigid registration, perturbation, stochastic optimization, transformation",
author = "Niessen, {Wiro J.} and W Sun and S. Klein",
year = "2017",
month = "7",
day = "1",
doi = "10.1109/TPAMI.2016.2598344",
language = "English",
volume = "39",
pages = "1401--1413",
journal = "IEEE Transactions on Pattern Analysis and Machine Intelligence",
issn = "0162-8828",
publisher = "IEEE Computer Society",
number = "7",

}

RIS

TY - JOUR

T1 - Randomly perturbed b-splines for nonrigid image registration

AU - Niessen, Wiro J.

AU - Sun, W

AU - Klein, S.

PY - 2017/7/1

Y1 - 2017/7/1

N2 - B-splines are commonly utilized to construct the transformation model in free-form deformation (FFD) based registration. B-splines become smoother with increasing spline order. However, a higher-order B-spline requires a larger support region involving more control points, which means higher computational cost. In general, the third-order B-spline is considered as a good compromise between spline smoothness and computational cost. A lower-order function is seldom used to construct the transformation model for registration since it is less smooth. In this research, we investigated whether lower-order B-spline functions can be utilized for more efficient registration, while preserving smoothness of the deformation by using a novel random perturbation technique. With the proposed perturbation technique, the expected value of the cost function given probability density function (PDF) of the perturbation is minimized by a stochastic gradient descent optimization. Extensive experiments on 2D synthetically deformed brain images, and real 3D lung and brain scans demonstrated that the novel randomly perturbed free-form deformation (RPFFD) approach improves the registration accuracy and transformation smoothness. Meanwhile, lower-order RPFFD methods reduce the computational cost substantially.

AB - B-splines are commonly utilized to construct the transformation model in free-form deformation (FFD) based registration. B-splines become smoother with increasing spline order. However, a higher-order B-spline requires a larger support region involving more control points, which means higher computational cost. In general, the third-order B-spline is considered as a good compromise between spline smoothness and computational cost. A lower-order function is seldom used to construct the transformation model for registration since it is less smooth. In this research, we investigated whether lower-order B-spline functions can be utilized for more efficient registration, while preserving smoothness of the deformation by using a novel random perturbation technique. With the proposed perturbation technique, the expected value of the cost function given probability density function (PDF) of the perturbation is minimized by a stochastic gradient descent optimization. Extensive experiments on 2D synthetically deformed brain images, and real 3D lung and brain scans demonstrated that the novel randomly perturbed free-form deformation (RPFFD) approach improves the registration accuracy and transformation smoothness. Meanwhile, lower-order RPFFD methods reduce the computational cost substantially.

KW - B-splines

KW - free-form deformation

KW - Nonrigid registration

KW - perturbation

KW - stochastic optimization

KW - transformation

UR - http://www.scopus.com/inward/record.url?scp=85020297265&partnerID=8YFLogxK

U2 - 10.1109/TPAMI.2016.2598344

DO - 10.1109/TPAMI.2016.2598344

M3 - Article

VL - 39

SP - 1401

EP - 1413

JO - IEEE Transactions on Pattern Analysis and Machine Intelligence

T2 - IEEE Transactions on Pattern Analysis and Machine Intelligence

JF - IEEE Transactions on Pattern Analysis and Machine Intelligence

SN - 0162-8828

IS - 7

M1 - 7533440

ER -

ID: 36286229