GPU-based stochastic-gradient optimization for non-rigid medical image registration in time-critical applications

Conference paper (2018)

Authors

P.S. Bhosale Leiden University Medical Center
M. Staring Pattern Recognition and Bioinformatics - EEMCS , Leiden University Medical Center
Z. Al-Ars Computer Engineering - EEMCS
Floris Berendsen Leiden University Medical Center
Research Group
Pattern Recognition and Bioinformatics (EEMCS) (TU Delft)
Copyright: © 2018 P.S. Bhosale, M. Staring, Z. Al-Ars, Floris F. Berendsen
DOI
help_outline
https://doi.org/10.1117/12.2293098
GPGPU Memory access optimization Stochastic gradient descent Non-rigid image registration Random chunk sampling
More Info
expand_more

Published Date

2018

Language

English

Reuse Rights

Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.

Faculty

Electrical Engineering, Mathematics and Computer Science

Department

Intelligent Systems

Research Group

Pattern Recognition and Bioinformatics

Abstract

Currently, non-rigid image registration algorithms are too computationally intensive to use in time-critical applications. Existing implementations that focus on speed typically address this by either parallelization on GPU-hardware, or by introducing methodically novel techniques into CPU-oriented algorithms. Stochastic gradient descent (SGD) optimization and variations thereof have proven to drastically reduce the computational burden for CPU-based image registration, but have not been successfully applied in GPU hardware due to its stochastic nature. This paper proposes 1) NiftyRegSGD, a SGD optimization for the GPU-based image registration tool NiftyReg, 2) random chunk sampler, a new random sampling strategy that better utilizes the memory bandwidth of GPU hardware. Experiments have been performed on 3D lung CT data of 19 patients, which compared NiftyRegSGD (with and without random chunk sampler) with CPU-based elastix Fast Adaptive SGD (FASGD) and NiftyReg. The registration runtime was 21.5s, 4.4s and 2.8s for elastix-FASGD, NiftyRegSGD without, and NiftyRegSGD with random chunk sampling, respectively, while similar accuracy was obtained. Our method is publicly available at https://github.com/SuperElastix/NiftyRegSGD.