• Corpus ID: 15470382

High performance computing for deformable image registration: towards a new paradigm in adaptive radiotherapy.

@article{Samant2008HighPC,
  title={High performance computing for deformable image registration: towards a new paradigm in adaptive radiotherapy.},
  author={Sanjiv S. Samant and Junyi Xia and Pinar Muyan-Ozcelik and John Douglas Owens},
  journal={Medical physics},
  year={2008},
  volume={35 8},
  pages={
          3546-53
        }
}
The advent of readily available temporal imaging or time series volumetric (4D) imaging has become an indispensable component of treatment planning and adaptive radiotherapy (ART) at many radiotherapy centers. Deformable image registration (DIR) is also used in other areas of medical imaging, including motion corrected image reconstruction. Due to long computation time, clinical applications of DIR in radiation therapy and elsewhere have been limited and consequently relegated to offline… 

Figures and Tables from this paper

Implementation and evaluation of various demons deformable image registration algorithms on a GPU
TLDR
It is interesting to find out that the original passive force demons algorithms outperform subsequently proposed variants based on the combination of accuracy, efficiency and ease of implementation.
A survey of GPU-based medical image computing techniques.
TLDR
The continuous advancement of GPU computing is reviewed and the existing traditional applications in three areas of medical image processing, namely, segmentation, registration and visualization, are surveyed.
GPU-based ultrafast IMRT plan optimization
TLDR
This work presents the implementation of an intensity-modulated radiation therapy (IMRT) optimization algorithm on graphics processing units (GPUs) using a penalty-based quadratic optimization model, which is solved by using a gradient projection method with Armijo's line search rule.
GPU-based ultra-fast direct aperture optimization for online adaptive radiation therapy
TLDR
This work has solved a major problem in developing ultra-fast (re-)planning technologies for online ART by implementing an intensity-modulated radiation therapy (IMRT) direct aperture optimization (DAO) algorithm on the graphics processing unit (GPU) based on previous work on the CPU.
GPU-based high-performance computing for radiation therapy
TLDR
The current applications of GPU in major imaging-related and therapy-related problems encountered in radiotherapy are reviewed and a comparison of GPU with other platforms will also be presented.
On developing B-spline registration algorithms for multi-core processors
TLDR
This paper proposes a grid-alignment scheme and associated data structures that greatly reduce the complexity of the registration algorithm, and develops highly data parallel designs for B-spline registration within the stream-processing model, suitable for implementation on multi-core processors such as graphics processing units (GPUs).
Technical note: DIRART--A software suite for deformable image registration and adaptive radiotherapy research.
TLDR
A set of image processing/registration algorithms and postprocessing functions to facilitate the development and testing of DIR algorithms, and potentially a convenient and flexible platform that may facilitate ART and DIR research.
GPU-based ultra-fast dose calculation using a finite size pencil beam model.
TLDR
The computational time for calculating dose deposition coefficients for a nine-field prostate IMRT plan with this new framework is less than 1 s, indicating that the GPU-based FSPB algorithm is well suited for online re-planning for adaptive radiotherapy.
GPU-based iterative cone-beam CT reconstruction using tight frame regularization.
TLDR
A fast graphic processing unit (GPU)-based algorithm to reconstruct high-quality CBCT images from undersampled and noisy projection data so as to lower the imaging dose and quantitatively analyzed the reconstructed CBCT image quality in terms of the modulation-transfer function and contrast-to-noise ratio.
...
...

References

SHOWING 1-10 OF 39 REFERENCES
GPU-based streaming architectures for fast cone-beam CT image reconstruction and demons deformable registration.
This paper shows how to significantly accelerate cone-beam CT reconstruction and 3D deformable image registration using the stream-processing model. We describe data-parallel designs for the
The Juggler algorithm: a hybrid deformable image registration algorithm for adaptive radiotherapy
TLDR
A hybrid algorithm, the "Juggler", based on a multi-diffusion model to achieve fast convergence, which successfully incorporates the benefits of different diffusion models into a single unified model.
Hardware Implementation of Hierarchical Volume Subdivision-based Elastic Registration
TLDR
This article shows how the existing FPGA-based architecture can be adapted to support hierarchical volume subdivision-based image registration, and achieves speedups of 100 for elastic registration against an optimized software implementation on a 3.2 GHz Pentium III Xeon workstation.
FPGA-based acceleration of mutual information calculation for real-time 3D image registration
TLDR
A custom hardware architecture is developed that, in a single-module PC-based implementation, achieves registration speeds comparable to those of a 64-processor parallel supercomputer.
Image Registration by a Regularized Gradient Flow. A Streaming Implementation in DX9 Graphics Hardware
TLDR
The presented image registration method uses a regularized gradient flow to correlate the intensities in two images to guarantee a sufficient accuracy of the algorithm and eliminate previously present concerns about the use of graphics hardware for medical computing.
Validation of an accelerated ‘demons’ algorithm for deformable image registration in radiation therapy
TLDR
The results suggest that the accelerated demons algorithm has significant potential for delineating and tracking doses in targets and critical structures during CT-guided radiotherapy.
Motion correction for improved target localization with on-board cone-beam computed tomography
TLDR
A motion compensation method for slow-rotating CBCT scans by incorporating into image reconstruction a patient-specific motion model, which is derived from previously obtained four-dimensional treatment planning CT images of the same patient via deformable registration, which may improve the accuracy of target localization and patient positioning when CBCT is used as the treatment guidance.
Automatic re-contouring in 4D radiotherapy
TLDR
An automatic re-contouring algorithm that combines techniques of deformable registration and surface construction to delineate regions of interest on each phase of four-dimensional computed tomography images and changes of tumour and sensitive structures during respiration are quantitatively analysed.
Implementation of a cone-beam backprojection algorithm on the cell broadband engine processor
TLDR
This study investigates the relative performance of a perspective backprojection algorithm when implemented on a standard PC and on the Cell processor and compares these results to the performance achievable with FPGAs based boards and high end GPUs.
Estimation of images and nonrigid deformations in gated emission CT
TLDR
It is shown that a new iterative algorithm to simultaneously estimate the nonrigid motion vector fields and the emission images for a complete cardiac cycle in gated cardiac emission tomography produces images with improved spatial resolution characteristics and noise properties compared with those obtained from postsmoothed 4-D maximum likelihood methods.
...
...