A data distributed parallel algorithm for nonrigid image registration

Authors:
Fumihiko Ino;Kanrou Ooyama;Kenichi Hagihara
Affiliations:
Graduate School of Information Science and Technology, Osaka University, 1-3 Machikaneyama, Toyonaka, Osaka 560-8531, Japan;Matsushita Electric Industrial Co., Ltd., 1006 Kadoma, Kadoma, Osaka 571-8501, Japan;Graduate School of Information Science and Technology, Osaka University, 1-3 Machikaneyama, Toyonaka, Osaka 560-8531, Japan
Venue:
Parallel Computing
Year:
2005

Citing 24
Cited 13

Principal Warps: Thin-Plate Splines and the Decomposition of Deformations

IEEE Transactions on Pattern Analysis and Machine Intelligence
Programming with threads

Programming with threads
The design and implementation of zero copy MPI using commodity hardware with a high performance network

ICS '98 Proceedings of the 12th international conference on Supercomputing
The grid: blueprint for a new computing infrastructure

The grid: blueprint for a new computing infrastructure
A high performance computing approach to the registration of medical imaging data

Parallel Computing - Special double issue on biomedical applications
MIMD vs. SIMD parallel processing: a case study in 3D medical image registration

Parallel Computing - Special double issue on biomedical applications
Parallel programming in OpenMP

Parallel programming in OpenMP
Real-time biomechanical simulation of volumetric brain deformation for image guided neurosurgery

Proceedings of the 2000 ACM/IEEE conference on Supercomputing
Scattered Data Interpolation with Multilevel B-Splines

IEEE Transactions on Visualization and Computer Graphics
Parallel Volume Rendering Using Binary-Swap Compositing

IEEE Computer Graphics and Applications
Myrinet: A Gigabit-per-Second Local Area Network

IEEE Micro
A Case for NOW (Networks of Workstations)

IEEE Micro
Robust Registration of Multi-modal Images: Towards Real-Time Clinical Applications

MICCAI '02 Proceedings of the 5th International Conference on Medical Image Computing and Computer-Assisted Intervention-Part II
Intensity-Based Non-rigid Registration Using Adaptive Multilevel Free-Form Deformation with an Incompressibility Constraint

MICCAI '01 Proceedings of the 4th International Conference on Medical Image Computing and Computer-Assisted Intervention
A Generic Framework for Non-rigid Registration Based on Non-uniform Multi-level Free-Form Deformations

MICCAI '01 Proceedings of the 4th International Conference on Medical Image Computing and Computer-Assisted Intervention
Affine Registration with Feature Space Mutual Information

MICCAI '01 Proceedings of the 4th International Conference on Medical Image Computing and Computer-Assisted Intervention
Image Processing or the Grid: A Toolkit or Building Grid-enabled Image Processing Applications.

CCGRID '03 Proceedings of the 3st International Symposium on Cluster Computing and the Grid
A Performance Study of Monitoring and Information Services for Distributed Systems

HPDC '03 Proceedings of the 12th IEEE International Symposium on High Performance Distributed Computing
A Divided-Screenwise Hierarchical Compositing for Sort-Last Parallel Volume Rendering

IPDPS '03 Proceedings of the 17th International Symposium on Parallel and Distributed Processing
Grid Information Services for Distributed Resource Sharing

HPDC '01 Proceedings of the 10th IEEE International Symposium on High Performance Distributed Computing
An improved binary-swap compositing for sort-last parallel rendering on distributed memory multiprocessors

Parallel Computing - Special issue: Parallel and distributed scientific and engineering computing
Differential coding scheme for efficient parallel image composition on a PC cluster system

Parallel Computing
SLIC: Scheduled Linear Image Compositing for Parallel Volume Rendering

PVG '03 Proceedings of the 2003 IEEE Symposium on Parallel and Large-Data Visualization and Graphics
Nonrigid image registration in shared-memory multiprocessor environments with application to brains, breasts, and bees

IEEE Transactions on Information Technology in Biomedicine

Two-stage compression for fast volume rendering of time-varying scalar data

Proceedings of the 4th international conference on Computer graphics and interactive techniques in Australasia and Southeast Asia
A parallel implementation of 2-D/3-D image registration for computer-assisted surgery

International Journal of Bioinformatics Research and Applications
Technical Section: A decompression pipeline for accelerating out-of-core volume rendering of time-varying data

Computers and Graphics
Non-rigid Registration for Large Sets of Microscopic Images on Graphics Processors

Journal of Signal Processing Systems
High-performance cone beam reconstruction using CUDA compatible GPUs

Parallel Computing
B-LUT: Fast and low memory B-spline image interpolation

Computer Methods and Programs in Biomedicine
Automatic Detection and Lesion Description in Cerebral Blood Flow and Cerebral Blood Volume Perfusion Maps

Journal of Signal Processing Systems
A system for detecting and describing pathological changes using dynamic perfusion computer tomography brain maps

Computers in Biology and Medicine
Patient specific dosimetry phantoms using multichannel LDDMM of the whole body

Journal of Biomedical Imaging - Special issue on Parallel Computation in Medical Imaging Applications
Minimizing data size for efficient data reuse in grid-enabled medical applications

ISBMDA'06 Proceedings of the 7th international conference on Biological and Medical Data Analysis
Novel Applications of VR: Visualization of perfusion abnormalities with GPU-based volume rendering

Computers and Graphics
Brain cine-MRI sequences registration using b-spline free-form deformations and MLSDO dynamic optimization algorithm

LION'12 Proceedings of the 6th international conference on Learning and Intelligent Optimization
Real time cardiac image registration during respiration: a time series prediction approach

Journal of Real-Time Image Processing

Quantified Score

Hi-index	0.01

Visualization

Abstract

Image registration is a technique for defining a geometric relationship between each point in images. This paper presents a data distributed parallel algorithm that is capable of aligning large-scale three-dimensional (3-D) images of deformable objects. The novelty of our algorithm is to overcome the limitations on the memory space as well as the execution time. In order to enable this, our algorithm incorporates data distribution, data-parallel processing, and load balancing techniques into Schnabel's registration algorithm that realizes robust and efficient alignment based on information theory and adaptive mesh refinement. We also present some experimental results obtained on a 128-CPU cluster of PCs interconnected by Myrinet and Fast Ethernet switches. The results show that our algorithm requires less amount of memory resources, so that aligns datasets up to 1024x1024x590 voxel images with reducing the execution time from hours to minutes, a clinically compatible time.