Journal article
Efficient methods for implementation of multi-level nonrigid mass-preserving image registration on GPUs and multi-threaded CPUs
Computer methods and programs in biomedicine, Vol.127, pp.290-300
04/2016
DOI: 10.1016/j.cmpb.2015.12.018
PMCID: PMC4803628
PMID: 26776541
Abstract
•A Multilevel Transform Composite method for GPU accelerated registration is proposed.•Method focused on mass-preserving registration of lung images with large deformation.•Diffeomorphic MTC achieves computation and memory efficiencies, preserves accuracy.•GPU speedup factor ranging from 6 to 112 achieved compared to CPU counterparts.•Improved computational speed essential to analyze data for population-based studies.
Faster and more accurate methods for registration of images are important for research involved in conducting population-based studies that utilize medical imaging, as well as improvements for use in clinical applications. We present a novel computation- and memory-efficient multi-level method on graphics processing units (GPU) for performing registration of two computed tomography (CT) volumetric lung images.
We developed a computation- and memory-efficient Diffeomorphic Multi-level B-Spline Transform Composite (DMTC) method to implement nonrigid mass-preserving registration of two CT lung images on GPU. The framework consists of a hierarchy of B-Spline control grids of increasing resolution. A similarity criterion known as the sum of squared tissue volume difference (SSTVD) was adopted to preserve lung tissue mass. The use of SSTVD consists of the calculation of the tissue volume, the Jacobian, and their derivatives, which makes its implementation on GPU challenging due to memory constraints. The use of the DMTC method enabled reduced computation and memory storage of variables with minimal communication between GPU and Central Processing Unit (CPU) due to ability to pre-compute values. The method was assessed on six healthy human subjects.
Resultant GPU-generated displacement fields were compared against the previously validated CPU counterpart fields, showing good agreement with an average normalized root mean square error (nRMS) of 0.044±0.015. Runtime and performance speedup are compared between single-threaded CPU, multi-threaded CPU, and GPU algorithms. Best performance speedup occurs at the highest resolution in the GPU implementation for the SSTVD cost and cost gradient computations, with a speedup of 112 times that of the single-threaded CPU version and 11 times over the twelve-threaded version when considering average time per iteration using a Nvidia Tesla K20X GPU.
The proposed GPU-based DMTC method outperforms its multi-threaded CPU version in terms of runtime. Total registration time reduced runtime to 2.9min on the GPU version, compared to 12.8min on twelve-threaded CPU version and 112.5min on a single-threaded CPU. Furthermore, the GPU implementation discussed in this work can be adapted for use of other cost functions that require calculation of the first derivatives.
Details
- Title: Subtitle
- Efficient methods for implementation of multi-level nonrigid mass-preserving image registration on GPUs and multi-threaded CPUs
- Creators
- Nathan D Ellingwood - University of IowaYoubing Yin - University of IowaMatthew Smith - National Cheng Kung UniversityChing-Long Lin - University of Iowa
- Resource Type
- Journal article
- Publication Details
- Computer methods and programs in biomedicine, Vol.127, pp.290-300
- DOI
- 10.1016/j.cmpb.2015.12.018
- PMID
- 26776541
- PMCID
- PMC4803628
- NLM abbreviation
- Comput Methods Programs Biomed
- ISSN
- 0169-2607
- eISSN
- 1872-7565
- Publisher
- Elsevier Ireland Ltd
- Grant note
- DOI: 10.13039/100000002, name: NIH, award: R01 HL094315, U01 HL114494, S10 RR022421
- Language
- English
- Date published
- 04/2016
- Academic Unit
- Roy J. Carver Department of Biomedical Engineering; Radiology; Mechanical Engineering
- Record Identifier
- 9984195169402771
Metrics
14 Record Views