Fast parallel image registration on CPU and GPU for diagnostic classification of Alzheimer's disease
Leiden University Medical Center
Indexed incrossrefdoajpubmed
Abstract
Nonrigid image registration is an important, but time-consuming task in medical image analysis. In typical neuroimaging studies, multiple image registrations are performed, i.e., for atlas-based segmentation or template construction. Faster image registration routines would therefore be beneficial. In this paper we explore acceleration of the image registration package elastix by a combination of several techniques: (i) parallelization on the CPU, to speed up the cost function derivative calculation; (ii) parallelization on the GPU building on and extending the OpenCL framework from ITKv4, to speed up the Gaussian pyramid computation and the image resampling step; (iii) exploitation of certain properties of…
Citation impact
602
total citations
- FWCI
- 16.02
- Percentile
- 100%
- References
- 48
Citations per year
Authors
1Topics & keywords
Topics
Keywords
- Computer science
- Speedup
- Artificial intelligence
- Voxel
- Image registration
- Resampling
- Pattern recognition (psychology)
- Contextual image classification
No related works found for this paper.
Funding
- AAAlzheimer's AssociationAward: U01 AG024904
- BSBristol-Myers SquibbAwards: U01 AG024904, AG024904
- ELEli Lilly and CompanyAwards: U01 AG024904, AG024904
- BBiogenAwards: U01 AG024904, AG024904
- FHF. Hoffmann-La RocheAwards: AG024904, U01 AG024904
- MMedpaceAward: U01 AG024904
- MSMeso Scale DiagnosticsAwards: U01 AG024904, AG024904
- ADAlzheimer's Disease Neuroimaging InitiativeAwards: AG024904, U01 AG024904
- BBioClinicaAwards: U01 AG024904, AG024904
- NONederlandse Organisatie voor Wetenschappelijk OnderzoekAward: 639.021.919
- EEisaiAwards: U01 AG024904, AG024904
- IIXICOAwards: AG024904, U01 AG024904
- NINational Institutes of HealthAwards: AG024904, U01 AG024904
- GGenentechAwards: AG024904, U01 AG024904