Literature DB >> 33542943

Faster dense deformable image registration by utilizing both CPU and GPU.

Simon Ekström1,2, Martino Pilia1, Joel Kullberg1,2, Håkan Ahlström1,2, Robin Strand1,3, Filip Malmberg1,3.   

Abstract

Purpose: Image registration is an important aspect of medical image analysis and a key component in many analysis concepts. Applications include fusion of multimodal images, multi-atlas segmentation, and whole-body analysis. Deformable image registration is often computationally expensive, and the need for efficient registration methods is highlighted by the emergence of large-scale image databases, e.g., the UK Biobank, providing imaging from 100,000 participants. Approach: We present a heterogeneous computing approach, utilizing both the CPU and the graphics processing unit (GPU), to accelerate a previously proposed image registration method. The parallelizable task of computing the matching criterion is offloaded to the GPU, where it can be computed efficiently, while the more complex optimization task is performed on the CPU. To lessen the impact of data synchronization between the CPU and GPU, we propose a pipeline model, effectively overlapping computational tasks with data synchronization. The performance is evaluated on a brain labeling task and compared with a CPU implementation of the same method and the popular advanced normalization tools (ANTs) software.
Results: The proposed method presents a speed-up by factors of 4 and 8 against the CPU implementation and the ANTs software, respectively. A significant improvement in labeling quality was also observed, with measured mean Dice overlaps of 0.712 and 0.701 for our method and ANTs, respectively. Conclusions: We showed that the proposed method compares favorably to the ANTs software yielding both a significant speed-up and an improvement in labeling quality. The registration method together with the proposed parallelization strategy is implemented as an open-source software package, deform.
© 2021 The Authors.

Entities:  

Keywords:  Atlas-based segmentation; brain MRI; deformable image registration; graphics processing unit

Year:  2021        PMID: 33542943      PMCID: PMC7849043          DOI: 10.1117/1.JMI.8.1.014002

Source DB:  PubMed          Journal:  J Med Imaging (Bellingham)        ISSN: 2329-4302


  29 in total

Review 1.  A survey of medical image registration on graphics hardware.

Authors:  O Fluck; C Vetter; W Wein; A Kamen; B Preim; R Westermann
Journal:  Comput Methods Programs Biomed       Date:  2010-11-26       Impact factor: 5.428

2.  Dense image registration through MRFs and efficient linear programming.

Authors:  Ben Glocker; Nikos Komodakis; Georgios Tziritas; Nassir Navab; Nikos Paragios
Journal:  Med Image Anal       Date:  2008-04-07       Impact factor: 8.545

3.  Fast free-form deformation using graphics processing units.

Authors:  Marc Modat; Gerard R Ridgway; Zeike A Taylor; Manja Lehmann; Josephine Barnes; David J Hawkes; Nick C Fox; Sébastien Ourselin
Journal:  Comput Methods Programs Biomed       Date:  2009-10-08       Impact factor: 5.428

4.  Accelerating image registration of MRI by GPU-based parallel computation.

Authors:  Teng-Yi Huang; Yu-Wei Tang; Shiun-Ying Ju
Journal:  Magn Reson Imaging       Date:  2011-04-29       Impact factor: 2.546

Review 5.  Multi-atlas segmentation of biomedical images: A survey.

Authors:  Juan Eugenio Iglesias; Mert R Sabuncu
Journal:  Med Image Anal       Date:  2015-07-06       Impact factor: 8.545

6.  Implementation and evaluation of various demons deformable image registration algorithms on a GPU.

Authors:  Xuejun Gu; Hubert Pan; Yun Liang; Richard Castillo; Deshan Yang; Dongju Choi; Edward Castillo; Amitava Majumdar; Thomas Guerrero; Steve B Jiang
Journal:  Phys Med Biol       Date:  2010-01-07       Impact factor: 3.609

7.  Supervoxels for Graph Cuts-Based Deformable Image Registration Using Guided Image Filtering.

Authors:  Adam Szmul; Bartłomiej W Papież; Andre Hallack; Vicente Grau; Julia A Schnabel
Journal:  J Electron Imaging       Date:  2017-10-04       Impact factor: 0.945

8.  Fast graph-cut based optimization for practical dense deformable registration of volume images.

Authors:  Simon Ekström; Filip Malmberg; Håkan Ahlström; Joel Kullberg; Robin Strand
Journal:  Comput Med Imaging Graph       Date:  2020-06-19       Impact factor: 4.790

9.  Accelerating Neuroimage Registration through Parallel Computation of Similarity Metric.

Authors:  Yun-Gang Luo; Ping Liu; Lin Shi; Yishan Luo; Lei Yi; Ang Li; Jing Qin; Pheng-Ann Heng; Defeng Wang
Journal:  PLoS One       Date:  2015-09-09       Impact factor: 3.240

10.  Three-dimensional maximum probability atlas of the human brain, with particular reference to the temporal lobe.

Authors:  Alexander Hammers; Richard Allom; Matthias J Koepp; Samantha L Free; Ralph Myers; Louis Lemieux; Tejal N Mitchell; David J Brooks; John S Duncan
Journal:  Hum Brain Mapp       Date:  2003-08       Impact factor: 5.038

View more

北京卡尤迪生物科技股份有限公司 © 2022-2023.