Distortion correction via non-rigid registration of functional to anatomical magnetic resonance brain images

Ali Gholipour, Nasser Kehtarnavaz, Kaundinya Gopinath, Richard Briggs, Michael Devous, Robert Haley

Research output: Chapter in Book/Report/Conference proceedingConference contribution

10 Citations (Scopus)

Abstract

Functional to anatomical brain image registration is needed for accurate localization of brain activation maps. Due to the presence of nonlinear distortions, it is more effective to consider non-rigid transformations to achieve such a registration. In this paper, a non-rigid registration technique based on the B-spline free-form deformation model and mutual information similarity measure is introduced. An optimization formulation is devised to achieve a fast and robust registration. This formulation differs from the previous formulations by utilizing a limited-memory, second-order optimization algorithm instead of the usual first-order gradient-based algorithms. It also enforces hard parameter constraints instead of constraints based upon physics or Jacobian smoothness. The results obtained indicate that this registration technique provides improvements over rigid and affine techniques when registering functional to anatomical magnetic resonance brain images.

Original languageEnglish (US)
Title of host publicationProceedings - International Conference on Image Processing, ICIP
Pages1181-1184
Number of pages4
DOIs
StatePublished - 2006
Event2006 IEEE International Conference on Image Processing, ICIP 2006 - Atlanta, GA, United States
Duration: Oct 8 2006Oct 11 2006

Other

Other2006 IEEE International Conference on Image Processing, ICIP 2006
CountryUnited States
CityAtlanta, GA
Period10/8/0610/11/06

Fingerprint

Magnetic resonance
Brain
Nonlinear distortion
Image registration
Splines
Physics
Chemical activation
Data storage equipment

Keywords

  • Brain
  • Distortion
  • Image registration
  • Magnetic resonance imaging

ASJC Scopus subject areas

  • Software
  • Computer Vision and Pattern Recognition
  • Signal Processing

Cite this

Gholipour, A., Kehtarnavaz, N., Gopinath, K., Briggs, R., Devous, M., & Haley, R. (2006). Distortion correction via non-rigid registration of functional to anatomical magnetic resonance brain images. In Proceedings - International Conference on Image Processing, ICIP (pp. 1181-1184). [4106746] https://doi.org/10.1109/ICIP.2006.312768

Distortion correction via non-rigid registration of functional to anatomical magnetic resonance brain images. / Gholipour, Ali; Kehtarnavaz, Nasser; Gopinath, Kaundinya; Briggs, Richard; Devous, Michael; Haley, Robert.

Proceedings - International Conference on Image Processing, ICIP. 2006. p. 1181-1184 4106746.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Gholipour, A, Kehtarnavaz, N, Gopinath, K, Briggs, R, Devous, M & Haley, R 2006, Distortion correction via non-rigid registration of functional to anatomical magnetic resonance brain images. in Proceedings - International Conference on Image Processing, ICIP., 4106746, pp. 1181-1184, 2006 IEEE International Conference on Image Processing, ICIP 2006, Atlanta, GA, United States, 10/8/06. https://doi.org/10.1109/ICIP.2006.312768
Gholipour A, Kehtarnavaz N, Gopinath K, Briggs R, Devous M, Haley R. Distortion correction via non-rigid registration of functional to anatomical magnetic resonance brain images. In Proceedings - International Conference on Image Processing, ICIP. 2006. p. 1181-1184. 4106746 https://doi.org/10.1109/ICIP.2006.312768
Gholipour, Ali ; Kehtarnavaz, Nasser ; Gopinath, Kaundinya ; Briggs, Richard ; Devous, Michael ; Haley, Robert. / Distortion correction via non-rigid registration of functional to anatomical magnetic resonance brain images. Proceedings - International Conference on Image Processing, ICIP. 2006. pp. 1181-1184
@inproceedings{c38dcccf46964264bacca41d8a96b983,
title = "Distortion correction via non-rigid registration of functional to anatomical magnetic resonance brain images",
abstract = "Functional to anatomical brain image registration is needed for accurate localization of brain activation maps. Due to the presence of nonlinear distortions, it is more effective to consider non-rigid transformations to achieve such a registration. In this paper, a non-rigid registration technique based on the B-spline free-form deformation model and mutual information similarity measure is introduced. An optimization formulation is devised to achieve a fast and robust registration. This formulation differs from the previous formulations by utilizing a limited-memory, second-order optimization algorithm instead of the usual first-order gradient-based algorithms. It also enforces hard parameter constraints instead of constraints based upon physics or Jacobian smoothness. The results obtained indicate that this registration technique provides improvements over rigid and affine techniques when registering functional to anatomical magnetic resonance brain images.",
keywords = "Brain, Distortion, Image registration, Magnetic resonance imaging",
author = "Ali Gholipour and Nasser Kehtarnavaz and Kaundinya Gopinath and Richard Briggs and Michael Devous and Robert Haley",
year = "2006",
doi = "10.1109/ICIP.2006.312768",
language = "English (US)",
isbn = "1424404819",
pages = "1181--1184",
booktitle = "Proceedings - International Conference on Image Processing, ICIP",

}

TY - GEN

T1 - Distortion correction via non-rigid registration of functional to anatomical magnetic resonance brain images

AU - Gholipour, Ali

AU - Kehtarnavaz, Nasser

AU - Gopinath, Kaundinya

AU - Briggs, Richard

AU - Devous, Michael

AU - Haley, Robert

PY - 2006

Y1 - 2006

N2 - Functional to anatomical brain image registration is needed for accurate localization of brain activation maps. Due to the presence of nonlinear distortions, it is more effective to consider non-rigid transformations to achieve such a registration. In this paper, a non-rigid registration technique based on the B-spline free-form deformation model and mutual information similarity measure is introduced. An optimization formulation is devised to achieve a fast and robust registration. This formulation differs from the previous formulations by utilizing a limited-memory, second-order optimization algorithm instead of the usual first-order gradient-based algorithms. It also enforces hard parameter constraints instead of constraints based upon physics or Jacobian smoothness. The results obtained indicate that this registration technique provides improvements over rigid and affine techniques when registering functional to anatomical magnetic resonance brain images.

AB - Functional to anatomical brain image registration is needed for accurate localization of brain activation maps. Due to the presence of nonlinear distortions, it is more effective to consider non-rigid transformations to achieve such a registration. In this paper, a non-rigid registration technique based on the B-spline free-form deformation model and mutual information similarity measure is introduced. An optimization formulation is devised to achieve a fast and robust registration. This formulation differs from the previous formulations by utilizing a limited-memory, second-order optimization algorithm instead of the usual first-order gradient-based algorithms. It also enforces hard parameter constraints instead of constraints based upon physics or Jacobian smoothness. The results obtained indicate that this registration technique provides improvements over rigid and affine techniques when registering functional to anatomical magnetic resonance brain images.

KW - Brain

KW - Distortion

KW - Image registration

KW - Magnetic resonance imaging

UR - http://www.scopus.com/inward/record.url?scp=34047126292&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=34047126292&partnerID=8YFLogxK

U2 - 10.1109/ICIP.2006.312768

DO - 10.1109/ICIP.2006.312768

M3 - Conference contribution

AN - SCOPUS:34047126292

SN - 1424404819

SN - 9781424404810

SP - 1181

EP - 1184

BT - Proceedings - International Conference on Image Processing, ICIP

ER -