Documents

DOI

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.

Original languageEnglish
Title of host publicationMedical Imaging 2018
Subtitle of host publicationImage Processing
EditorsElsa D. Angelini, Bennett A. Landman
Place of PublicationBellingham, WA
PublisherSPIE
Pages1-8
ISBN (Electronic)9781510616370
DOIs
Publication statusPublished - 2018
EventMedical Imaging 2018: Ultrasonic Imaging and Tomography - Houston, United States
Duration: 10 Feb 201815 Feb 2018

Publication series

NameProceedings of SPIE
Volume10574
ISSN (Electronic)0277-786X

Conference

ConferenceMedical Imaging 2018: Ultrasonic Imaging and Tomography
CountryUnited States
CityHouston
Period10/02/1815/02/18

    Research areas

  • GPGPU, memory access optimization, Non-rigid image registration, random chunk sampling, stochastic gradient descent

ID: 45239393