High Performance Deformable Image Registration Algorithms for Manycore Processors

1st Edition

Authors: James Shackleford Nagarajan Kandasamy Gregory Sharp
Paperback ISBN: 9780124077416
eBook ISBN: 9780124078802
Imprint: Morgan Kaufmann
Published Date: 1st July 2013
Page Count: 122
47.95 + applicable tax
37.99 + applicable tax
58.95 + applicable tax
Unavailable
Compatible Not compatible
VitalSource PC, Mac, iPhone & iPad Amazon Kindle eReader
ePub & PDF Apple & PC desktop. Mobile devices (Apple & Android) Amazon Kindle eReader
Mobi Amazon Kindle eReader Anything else

Institutional Access


Description

High Performance Deformable Image Registration Algorithms for Manycore Processors develops highly data-parallel image registration algorithms suitable for use on modern multi-core architectures, including graphics processing units (GPUs). Focusing on deformable registration, we show how to develop data-parallel versions of the registration algorithm suitable for execution on the GPU. Image registration is the process of aligning two or more images into a common coordinate frame and is a fundamental step to be able to compare or fuse data obtained from different sensor measurements. Extracting useful information from 2D/3D data is essential to realizing key technologies underlying our daily lives. Examples include autonomous vehicles and humanoid robots that can recognize and manipulate objects in cluttered environments using stereo vision and laser sensing and medical imaging to localize and diagnose tumors in internal organs using data captured by CT/MRI scans.

Key Features

  • Demonstrates how to redesign widely used image registration algorithms so as to best expose the underlying parallelism available in these algorithms
  • Shows how to pose and implement the parallel versions of the algorithms within the single instruction, multiple data (SIMD) model supported by GPUs
  • Provides Programming "tricks" that can help readers develop other image processing algorithms, including registration algorithms for the GPU

Readership

Developers of image registration algorithms and software, including graduate students, researchers (post-doctoral researchers, research scientists, professionals working in the areas of computer vision, image processing, and medical imaging

Table of Contents

Biographies

Chapter 1. Introduction

Information in This Chapter:

1.1 Introduction

1.2 Applications of Deformable Image Registration

1.3 Algorithmic Approaches to Deformable Registration

1.4 Organization of Chapters

References

Chapter 2. Unimodal B-Spline Registration

Information in This Chapter:

2.1 Introduction

2.2 Overview of B-Spline Registration

2.3 B-Spline Registration on the GPU

2.4 Performance Evaluation

2.5 Summary

References

Chapter 3. Multimodal B-Spline Registration

Information in This Chapter

3.1 Introduction

3.2 Using B-Splines to Represent the Deformation Field

3.3 MI as A Cost Function

3.4 Efficient Computation of MI

3.5 Performance Evaluation

3.6 Related Work

3.7 Summary

References

Chapter 4. Analytic Vector Field Regularization for B-spline Parameterized Methods

Information in This Chapter:

4.1 Introduction

4.2 Theory and Mathematical Formalism

4.3 Algorithmic Implementation

4.4 Performance Evaluation

4.5 Summary

References

Chapter 5. Deformable Registration Using Optical-Flow Methods

Information in This Chapter:

5.1 Introduction

5.2 Demons Algorithm for Deformable Registration

5.3 SIMD Version of Demons Algorithm

5.4 Performance Evaluation

5.5 Summary

References

Chapter 6. Plastimatch—An Open-Source Software for Radiotherapy Imaging

Information in This Chapter:

6.1 Introduction

6.2 Overview of Plastimatch

6.3 Licensing

References

Details

No. of pages:
122
Language:
English
Copyright:
© Morgan Kaufmann 2014
Published:
Imprint:
Morgan Kaufmann
eBook ISBN:
9780124078802
Paperback ISBN:
9780124077416

About the Author

James Shackleford

Affiliations and Expertise

Assistant Professor, Drexel University ECE Dept.

Nagarajan Kandasamy

Affiliations and Expertise

Drexel University, Philadelphia, PA, USA

Gregory Sharp

Affiliations and Expertise

Massachusetts General Hospital, Boston, MA, USA

Reviews

"…the methods included in this book are explained in great detail. I recommend it to experts in the field of deformable image registration and those with deep knowledge of computing and computer architecture (mainly parallel programming with GPUs)." --ComputingReviews.com, January 2014

"Shackleford, Kandasamy and Sharp develop highly data-parallel deformable image registration algorithms suitable for use on modern multicore processors. Their grid alignment technique and associated data structures reduce the complexity of B-spline registration and can be extended to perform multimodal image registration by utilizing the mutual information similarity metric." --Reference and Research Book News, October 2013