High-speed registration of three- and four-dimensional medical images by using voxel similarity.

@article{Shekhar2003HighspeedRO,
  title={High-speed registration of three- and four-dimensional medical images by using voxel similarity.},
  author={Raj Shekhar and Vladimir Zagrodsky and Carlos R. Castro-Pareja and Vivek Walimbe and Jogikal M. Jagadeesh},
  journal={Radiographics : a review publication of the Radiological Society of North America, Inc},
  year={2003},
  volume={23 6},
  pages={
          1673-81
        }
}
  • R. Shekhar, V. Zagrodsky, J. Jagadeesh
  • Published 1 November 2003
  • Physics, Medicine
  • Radiographics : a review publication of the Radiological Society of North America, Inc
A generalized, accurate, automatic, retrospective method of image registration for three-dimensional images has been developed. The method is based on mutual information, a specific measure of voxel similarity, and is applicable to a wide range of imaging modalities and organs, rigid or deformable. A drawback of mutual information-based image registration is long execution times. To overcome the speed problem, low-cost, customized hardware to accelerate this computationally intensive task was… 

Figures and Tables from this paper

Hardware acceleration of mutual information-based 3D image registration

TLDR
A hardware architecture is presented that can be used to accelerate a number of linear and elastic image registration algorithms that use mutual information as an image similarity measure and achieved speedups of 30 for linear registration and 100 for elastic registration against a 3.2 GHz Pentium III Xeon workstation.

Towards a Heterogeneous Medical Image Registration Acceleration Platform

TLDR
This work believes that a heterogeneous compute platform customized for image registration can provide robust, scalable, cost effective sub-minute medical image registration capabilities.

A taxonomy for medical image registration acceleration techniques

TLDR
This paper samples existing literature on image registration acceleration techniques and proposes a classification of "levels" into which they can be binned and shows experimentally that combining approaches from different levels can lead to over 100x speedup on an eight node heterogeneous cluster.

Towards systematic exploration of tradeoffs for medical image registration on heterogeneous platforms

TLDR
This study examines the differences in accuracy and speed of implementations of the same image registration algorithm on a general purpose uniprocessor, a GPU, and a cluster of GPUs using a novel domain specific framework that allows them to simultaneously exploit parallelism on a heterogeneous platform.

Fast non-rigid registration of medical images: comparing the thin-plate and biharmonic splines

TLDR
This paper presents a novel approach based on fast Radial Basis Function evaluation using the thin-plate and biharmonic spline models, which is evaluated in software and hardware assisted versions and runs on a standard PC.

Automatic segmentation of phase-correlated CT scans through nonrigid image registration using geometrically regularized free-form deformation.

TLDR
The clinical implementation of 4D treatment planning is critically dependent on automatic segmentation, for which a free-form deformation-based nonrigid image registration algorithm is offered one of the most accurate algorithms yet presented.

A Hybrid Similarity Measure Framework for Multimodal Medical Image Registration

TLDR
The thesis findings conclusively confirm the hybrid SM framework offers an accurate and robust 2D registration solution for challenging multimodal medical imaging datasets, while its inherent flexibility means it can also be extended to the 3D registration domain.

References

SHOWING 1-10 OF 18 REFERENCES

FAIR: a hardware architecture for real-time 3-D image registration

TLDR
This paper presents details of a hardware architecture for real-time three-dimensional (3-D) image registration that provides superior per-processor performance at a lower cost compared to a parallel supercomputer.

Mutual information-based rigid and nonrigid registration of ultrasound volumes

TLDR
The registration of ultrasound volumes based on the mutual information measure is investigated, a technique originally applied to multimodality registration of brain images, and should work well for a variety of applications examining serial anatomic and physiologic changes.

Three dimensional image alignment, registration and fusion.

  • S. TrevesK. MitchellI. Habboush
  • Medicine, Physics
    The quarterly journal of nuclear medicine : official publication of the Italian Association of Nuclear Medicine (AIMN) [and] the International Association of Radiopharmacology
  • 1998
TLDR
This review describes a simple, intuitive and robust image registration approach developed in the laboratory that can register images accurately and quickly without the use of elaborate mathematical modeling or optimization techniques.

PET-CT image registration in the chest using free-form deformations

TLDR
An algorithm for three-dimensional positron emission tomography transmission-to-computed tomography registration in the chest is implemented, using mutual information as a similarity criterion, and a rigid body deformation combined with localized cubic B-splines is used to capture this motion.

Semiautomatic 3-D image registration as applied to interventional MRI liver cancer treatment

TLDR
Despite motion and deformation in the liver, mutual information registration is sufficiently accurate and robust for useful applications in I-MRT thermal ablation therapy.

Automated three-dimensional registration of magnetic resonance and positron emission tomography brain images by multiresolution optimization of voxel similarity measures.

TLDR
A method of multiresolution optimization of five measures of voxel intensity similarity is described and the mutual information measure proved the most robust to initial starting estimate, successfully registering 98.8% of 900 trial misregistrations.

Multimodality image registration by maximization of mutual information

TLDR
The results demonstrate that subvoxel accuracy with respect to the stereotactic reference solution can be achieved completely automatically and without any prior segmentation, feature extraction, or other preprocessing steps which makes this method very well suited for clinical applications.

Semiautomatic registration of volumetric ultrasound scans.

Accurate Three‐Dimensional Registration of CT, PET, and/or MR Images of the Brain

TLDR
A surface matching technique has been developed to register multiple imaging scans of the brain in three dimensions, with accuracy on the order of the image pixel sizes, which provides a novel quantitative method to address the fundamental problem of relating structure to function in the brain.