Phase based volume registration using cuda

We present a method for fast phase based registration of volume data for medical applications. As the number of different modalities within medical imaging increases, it becomes more and more important with registration that works for a mixture of modalities. For these applications the phase based registration approach has proven to be superior. Today there seem to be two kinds of groups that work with medical image registration, one that works with refining of the registration algorithms and one that works with implementation of more simple algorithms on graphic cards for speeding up the algorithms. We put the work from these groups together and get the best from both worlds. We achieve a speedup of 10–30 compared to our CPU implementation, which makes fast phase based registration possible for large medical volumes.

[1]  Paul W. Fieguth,et al.  Fast phase-based registration of multimodal image data , 2009, Signal Process..

[2]  John D. Owens,et al.  Fast Deformable Registration on the GPU: A CUDA Implementation of Demons , 2008, 2008 International Conference on Computational Sciences and Its Applications.

[3]  Satoshi Matsuoka,et al.  Bandwidth intensive 3-D FFT kernel for GPUs using CUDA , 2008, 2008 SC - International Conference for High Performance Computing, Networking, Storage and Analysis.

[4]  Richard J. Davidson,et al.  Comparison of fMRI motion correction software tools , 2005, NeuroImage.

[5]  Jay B. Brockman,et al.  Performance analysis of accelerated image registration using GPGPU , 2009, GPGPU-2.

[6]  Hans Knutsson,et al.  Phase-based multidimensional volume registration , 2000, IEEE Transactions on Medical Imaging.

[7]  H. Knutsson,et al.  Advanced Filter Design , 1999 .

[8]  Marc M. Van Hulle,et al.  Realtime phase-based optical flow on the GPU , 2008, 2008 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops.

[9]  Michael Brady,et al.  Non-rigid Multimodal Image Registration Using Local Phase , 2004, MICCAI.