GPU Applications

Medical Imaging

Medical imaging is one of the earliest applications to take advantage of GPU computing to get acceleration. The use of GPUs in this field has matured to the point that there are several medical modalities shipping with NVIDIA's Tesla GPUs now.

MRI Chart CT-recon
Accelerating Advanced MRI Reconstructions on GPUs
Stone, et al
Computed Tomography Reconstruction
Batenburg, Sijbers, et al

For information on key ISVs and applications, please visit the GPU Applications page.

Technical Reports on Medical Imaging using CUDA
> University of Tokyo Stereoscopic medical imaging system
> Papers on Computed Tomography
       > University of Antwerp, Belgium digital tomography group
       > GE Healthcare CT imaging papers: Cone-Beam back-projection and Fluoro-CT reconstruction
       > Siemens Medical CT reconstruction
       > A Fast And High-Quality Cone Beam Reconstruction Pipeline Using The GPU, Siemens
       > High Performance Tomosynthesis Enabled via a GPU-based Iterative Reconstruction Framework, Siemens
       > Klaus Mueller's Work on Medical Imaging on GPUs
       > 3D Image Registration
       > Fast Deformable Registration
       > Cone Beam CT Toshiba Stroke Research Center and SUNY Buffalo
       > High Speed 3D Tomography on CPU, GPU, and FPGA
       > Accelerated GRAPPA Autocalibration in MRI
       > MR Image Reconstruction Using the GPU, Siemens
       > Fast MRI Gridding
       > Advanced MRI reconstruction
       > Stochastic DT-MRI Connectivity Mapping on the GPU
> Segmentation
       > Random Walks for Interactive Organ Segmentation in Two and Three Dimensions
> Registration
       > Automatic CT-ultrasound Registration for Diagnostic Imaging and Image-Guided Intervention
       > Interactive Model-based Image Registration
> Rendering
       > Importance-driven Rendering in Interventional Imaging
       > Real-time Volume Rendering for High Quality Visualization in Augmented Reality
> Medical Imaging
       > Scene Graph-based Construction of CUDA Kernel Pipelines for XIP

Other Medical Imaging Software/Equipment on CUDA-enabled GPUs
> CUDA Insight Toolkit: CUDA Accelerated extension of Insight Segmentation and Registration Toolkit (ITK)
> GPULib: IDL Acceleration
> ArrayFire GPU function library for C, C++, FORTRAN
> NPP: NVIDIA Performance Primitives: Focuses on image and video processing
> Techniscan Whole Breast Ultrasound Imaging System: Success Story

See Also
> Imaging and Computer Vision using GPUs: Key Functions and Libraries
> ArrayFire GPU function library for C, C++, FORTRAN
> Tesla/CUDA Success stories
> Other Tesla Vertical Solutions
> CUDA Software development tools & libraries
> Buy Tesla

MATLAB is a registered trademark of The MathWorks, Inc.
ArrayFire is a trademark of AccelerEyes