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

Authors:
Antonio Ruiz;Manuel Ujaldon;Lee Cooper;Kun Huang
Affiliations:
Computer Architecture Department, Campus Teatinos, University of Malaga, Malaga, Spain 29071;Computer Architecture Department, Campus Teatinos, University of Malaga, Malaga, Spain 29071;Biomedical Informatics Department, Ohio State University, Columbus, USA 43210;Biomedical Informatics Department, Ohio State University, Columbus, USA 43210
Venue:
Journal of Signal Processing Systems
Year:
2009

Citing 13
Cited 3

A high performance computing approach to the registration of medical imaging data

Parallel Computing - Special double issue on biomedical applications
The FFT on a GPU

Proceedings of the ACM SIGGRAPH/EUROGRAPHICS conference on Graphics hardware
Insight into Images: Principles and Practice for Segmentation, Registration, and Image Analysis

Insight into Images: Principles and Practice for Segmentation, Registration, and Image Analysis
GPU Cluster for High Performance Computing

Proceedings of the 2004 ACM/IEEE conference on Supercomputing
2-D and 3-D Image Registration: for Medical, Remote Sensing, and Industrial Applications

2-D and 3-D Image Registration: for Medical, Remote Sensing, and Industrial Applications
Understanding the efficiency of GPU algorithms for matrix-matrix multiplication

Proceedings of the ACM SIGGRAPH/EUROGRAPHICS conference on Graphics hardware
A hybrid condensed finite element model with GPU acceleration for interactive 3D soft tissue cutting: Research Articles

Computer Animation and Virtual Worlds - Special Issue: The Very Best Papers from CASA 2004
A data distributed parallel algorithm for nonrigid image registration

Parallel Computing
Visual Simulation of Heat Shimmering and Mirage

IEEE Transactions on Visualization and Computer Graphics
Image Registration of Sectioned Brains

International Journal of Computer Vision
Volume Rendering Phenotype Differences in Mouse Placenta Microscopy Data

Computing in Science and Engineering
A GPGPU approach for accelerating 2-d/3-d rigid registration of medical images

ISPA'06 Proceedings of the 4th international conference on Parallel and Distributed Processing and Applications
Nonrigid image registration in shared-memory multiprocessor environments with application to brains, breasts, and bees

IEEE Transactions on Information Technology in Biomedicine

MEDICS: ultra-portable processing for medical image reconstruction

Proceedings of the 19th international conference on Parallel architectures and compilation techniques
Orders-of-magnitude performance increases in GPU-accelerated correlation of images from the International Space Station

Journal of Real-Time Image Processing
A survey of medical image registration on graphics hardware

Computer Methods and Programs in Biomedicine

Quantified Score

Hi-index	0.00

Visualization

Abstract

Microscopic imaging is an important tool for characterizing tissue morphology and pathology. 3D reconstruction and visualization of large sample tissue structure requires registration of large sets of high-resolution images. However, the scale of this problem presents a challenge for automatic registration methods. In this paper we present a novel method for efficient automatic registration using graphics processing units (GPUs) and parallel programming. Comparing a C++ CPU implementation with Compute Unified Device Architecture (CUDA) libraries and pthreads running on GPU we achieve a speed-up factor of up to 4.11脳 with a single GPU and 6.68脳 with a GPU pair. We present execution times for a benchmark composed of two sets of large-scale images: mouse placenta (16K 脳16K pixels) and breast cancer tumors (23K 脳62K pixels). It takes more than 12聽hours for the genetic case in C++ to register a typical sample composed of 500 consecutive slides, which was reduced to less than 2聽hours using two GPUs, in addition to a very promising scalability for extending those gains easily on a large number of GPUs in a distributed system.