Title:
40e87b3a-0df7-43ec-8729-916b7c6ea92fR Download
Description: In this paper, we propose a GPU-based acceleration method to speed up volume image registration using Compute
Unified Device Architecture(CUDA). An novel CUDA-based method for joint histogram computation is introduced
in this paper, which is also valuable for 2D image registration and other general graphics applications. Additionally,
an algorithm refinement is proposed to improve the widely used FMRIB’s Linear Image Registration Tool
(FLIRT). Although extra time is taken by applying that algorithm refinements, our implementation showed the
ability to perform a full 12 DOF (Degrees of Freedom) registration of two brain volume image in nearly 35 seconds,
which is about 10 time faster than the native FLIRT implementation. Experimental results showed that our
implementation with algorithm refinement can avoid some mis-registration.
File list (Check if you may need any files):
paper\cvir-pg09-fin.pdf
results-jpg\65-ref-ADC.jpg
...........\75-reg-T2.jpg
...........\75-ref-ADC.jpg
...........\65-reg-T2.jpg
readme.txt
glirt-src\bbsort.linkinfo
.........\costFunctionsGPU.cu
.........\costFunctionsGPU.linkinfo
.........\glirt.sln
.........\glirt.suo
.........\glirt.vcproj
.........\glirt.vcproj.20090507-1624.Administrator.user
.........\shcommend.sh
.........\vc80.pdb
.........\ve-640E.tmp
.........\data\MRT2_153359_LXZ_512x512x23_0.46875x0.468746x6_2_8bit.raw
.........\....\MR_153359_LXZ_128x128x19_1.79688x1.79688x6.5_3ep_b0_1000_8bit.raw
.........\glirt.ncb
.........\bbsort.cuh
.........\bbsort_kernel.cu
.........\common.h
.........\costFunctions.cpp
.........\costFunctions.h
.........\costFunctionsGPU.cuh
.........\costFunctionsGPU_kernel.cu
.........\flirt.cpp
.........\matrix44.cpp
.........\matrix44.h
.........\options.h
.........\search.cpp
.........\search.h
.........\volume.cpp
.........\volume.h
.........\bbsort.cu
intro.doc
result.jpg
glirt-src\results
.........\data
paper
results-jpg
glirt-src