A data distributed parallel algorithm for nonrigid image registration

Image registration is a technique for defining a geometric relationship between each point in images. This paper presents a data distributed parallel algorithm that is capable of aligning large-scale three-dimensional (3-D) images of deformable objects. The novelty of our algorithm is to overcome th...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Parallel computing Ročník 31; číslo 1; s. 19 - 43
Hlavní autoři: Ino, Fumihiko, Ooyama, Kanrou, Hagihara, Kenichi
Médium: Journal Article
Jazyk:angličtina
Vydáno: Elsevier B.V 2005
Témata:
Adaptive mesh refinement
Data distribution
Free-form deformation
Load balancing
Nonrigid image registration
Free-form deformation
Data distribution
Nonrigid image registration
Adaptive mesh refinement
Load balancing
ISSN:0167-8191, 1872-7336
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:Image registration is a technique for defining a geometric relationship between each point in images. This paper presents a data distributed parallel algorithm that is capable of aligning large-scale three-dimensional (3-D) images of deformable objects. The novelty of our algorithm is to overcome the limitations on the memory space as well as the execution time. In order to enable this, our algorithm incorporates data distribution, data-parallel processing, and load balancing techniques into Schnabel’s registration algorithm that realizes robust and efficient alignment based on information theory and adaptive mesh refinement. We also present some experimental results obtained on a 128-CPU cluster of PCs interconnected by Myrinet and Fast Ethernet switches. The results show that our algorithm requires less amount of memory resources, so that aligns datasets up to 1024 × 1024 × 590 voxel images with reducing the execution time from hours to minutes, a clinically compatible time.
ISSN:0167-8191
1872-7336
DOI:10.1016/j.parco.2004.12.001