Efficient GPU-accelerated elastic image registration

D. Ruijters; B.M. Haar Romenij, ter; P. Suetens

Efficient GPU-accelerated elastic image registration

D. Ruijters, B.M. Haar Romenij, ter, P. Suetens

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

Abstract

Elastic intra-patient registration can be used to correct for local motion within biomedical images. The application of elastic registration during interventional treatment is seri ously hampered by its considerable computation time. The Graphics Processing Units (GPU) can be used to accelerate the calculation of such elastic registrations, without chang ing the basic registration algorithm. This article discusses how elastic image registration, using cubic B-spline based deformation ¿elds, ef¿ciently can be approached to make use of the vast processing power of the GPU. Our approach employs an ef¿cient GPU-based cubic B-spline deforma tion ¿eld, and also calculates the similarity measure and its derivative on the GPU.

Original language	English
Title of host publication	Proceedings of the Sixth IASTED International Conference on Biomedical Engineering (BioMED 2008) : February 13 - 15, 2008, Innsbruck, Austria
Editors	A. Hierlemann
Place of Publication	Calgary
Publisher	ACTA Press
Pages	419-424
ISBN (Print)	978-0-88986-721-5
Publication status	Published - 2009
Event	BioMED 2008 : Sixth IASTED International Conference on Biomedical Engineering - Innsbruck, Austria Duration: 13 Feb 2008 → 15 Feb 2008

Conference

Conference	BioMED 2008 : Sixth IASTED International Conference on Biomedical Engineering
Country/Territory	Austria
City	Innsbruck
Period	13/02/08 → 15/02/08

Cite this

@inproceedings{f4ff0bf747b14b59982a8949f8115230,

title = "Efficient GPU-accelerated elastic image registration",

abstract = "Elastic intra-patient registration can be used to correct for local motion within biomedical images. The application of elastic registration during interventional treatment is seri ously hampered by its considerable computation time. The Graphics Processing Units (GPU) can be used to accelerate the calculation of such elastic registrations, without chang ing the basic registration algorithm. This article discusses how elastic image registration, using cubic B-spline based deformation ¿elds, ef¿ciently can be approached to make use of the vast processing power of the GPU. Our approach employs an ef¿cient GPU-based cubic B-spline deforma tion ¿eld, and also calculates the similarity measure and its derivative on the GPU.",

author = "D. Ruijters and {Haar Romenij, ter}, B.M. and P. Suetens",

year = "2009",

language = "English",

isbn = "978-0-88986-721-5",

pages = "419--424",

editor = "A. Hierlemann",

booktitle = "Proceedings of the Sixth IASTED International Conference on Biomedical Engineering (BioMED 2008) : February 13 - 15, 2008, Innsbruck, Austria",

publisher = "ACTA Press",

address = "Canada",

note = "BioMED 2008 : Sixth IASTED International Conference on Biomedical Engineering ; Conference date: 13-02-2008 Through 15-02-2008",

}

Ruijters, D , Haar Romenij, ter, BM & Suetens, P 2009, Efficient GPU-accelerated elastic image registration. in A Hierlemann (ed.), Proceedings of the Sixth IASTED International Conference on Biomedical Engineering (BioMED 2008) : February 13 - 15, 2008, Innsbruck, Austria. ACTA Press, Calgary, pp. 419-424, BioMED 2008 : Sixth IASTED International Conference on Biomedical Engineering, Innsbruck, Austria, 13/02/08.

Efficient GPU-accelerated elastic image registration. / Ruijters, D.; Haar Romenij, ter, B.M.; Suetens, P.
Proceedings of the Sixth IASTED International Conference on Biomedical Engineering (BioMED 2008) : February 13 - 15, 2008, Innsbruck, Austria. ed. / A. Hierlemann. Calgary: ACTA Press, 2009. p. 419-424.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

TY - GEN

T1 - Efficient GPU-accelerated elastic image registration

AU - Ruijters, D.

AU - Haar Romenij, ter, B.M.

AU - Suetens, P.

PY - 2009

Y1 - 2009

N2 - Elastic intra-patient registration can be used to correct for local motion within biomedical images. The application of elastic registration during interventional treatment is seri ously hampered by its considerable computation time. The Graphics Processing Units (GPU) can be used to accelerate the calculation of such elastic registrations, without chang ing the basic registration algorithm. This article discusses how elastic image registration, using cubic B-spline based deformation ¿elds, ef¿ciently can be approached to make use of the vast processing power of the GPU. Our approach employs an ef¿cient GPU-based cubic B-spline deforma tion ¿eld, and also calculates the similarity measure and its derivative on the GPU.

AB - Elastic intra-patient registration can be used to correct for local motion within biomedical images. The application of elastic registration during interventional treatment is seri ously hampered by its considerable computation time. The Graphics Processing Units (GPU) can be used to accelerate the calculation of such elastic registrations, without chang ing the basic registration algorithm. This article discusses how elastic image registration, using cubic B-spline based deformation ¿elds, ef¿ciently can be approached to make use of the vast processing power of the GPU. Our approach employs an ef¿cient GPU-based cubic B-spline deforma tion ¿eld, and also calculates the similarity measure and its derivative on the GPU.

M3 - Conference contribution

SN - 978-0-88986-721-5

SP - 419

EP - 424

BT - Proceedings of the Sixth IASTED International Conference on Biomedical Engineering (BioMED 2008) : February 13 - 15, 2008, Innsbruck, Austria

A2 - Hierlemann, A.

PB - ACTA Press

CY - Calgary

T2 - BioMED 2008 : Sixth IASTED International Conference on Biomedical Engineering

Y2 - 13 February 2008 through 15 February 2008

ER -

Efficient GPU-accelerated elastic image registration

Abstract

Conference

Fingerprint

Cite this