Literature DB >> 31448216

A robust deformable image registration enhancement method based on radial basis function.

Xiao Liang1, Fang-Fang Yin1,2, Chunhao Wang2, Jing Cai2,3.   

Abstract

BACKGROUND: To develop and evaluate a robust deformable image registration (DIR) enhancement method based on radial basis function (RBF) expansion.
METHODS: To improve DIR accuracy using sparsely available measured displacements, it is crucial to estimate the motion correlation between the voxels. In the proposed method, we chose to derive this correlation from the initial displacement vector fields (DVFs), and represent it in the form of RBF expansion coefficients of the voxels. The method consists of three steps: (I) convert an initial DVF to a coefficient matrix comprising expansion coefficients of the Wendland's RBF; (II) modify the coefficient matrix under the guidance of sparely distributed landmarks to generate the post-enhancement coefficient matrix; and (III) convert the post-enhancement coefficient matrix to the post-enhancement DVF. The method was tested on five DIR algorithms using a digital phantom. 3D registration errors were calculated for comparisons between the pre-/post-enhancement DVFs and the ground-truth DVFs. Effects of the number and locations of landmarks on DIR enhancement were evaluated.
RESULTS: After applying the DIR enhancement method, the 3D registration errors per voxel (unit: mm) were reduced from pre-enhancement to post-enhancement by 1.3 (2.4 to 1.1, 54.2%), 0.0 (0.9 to 0.9, 0.0%), 6.1 (8.2 to 2.1, 74.4%), 3.2 (4.7 to 1.5, 68.1%), and 1.7 (2.9 to 1.2, 58.6%) for the five tested DIR algorithms respectively. The average DIR error reduction was 2.5±2.3 mm (percentage error reduction: 51.1%±29.1%). 3D registration errors decreased inverse-exponentially as the number of landmarks increased, and were insensitive to the landmarks' locations in relation to the down-sampling DVF grids.
CONCLUSIONS: We demonstrated the feasibility of a robust RBF-based method for enhancing DIR accuracy using sparsely distributed landmarks. This method has been shown robust and effective in reducing DVF errors using different numbers and distributions of landmarks for various DIR algorithms.

Entities:  

Keywords:  4D; Deformable image registration (DIR); digital phantom; lung motion

Year:  2019        PMID: 31448216      PMCID: PMC6685815          DOI: 10.21037/qims.2019.07.05

Source DB:  PubMed          Journal:  Quant Imaging Med Surg        ISSN: 2223-4306


  24 in total

1.  Consistent landmark and intensity-based image registration.

Authors:  H J Johnson; G E Christensen
Journal:  IEEE Trans Med Imaging       Date:  2002-05       Impact factor: 10.048

2.  Model-based image reconstruction for four-dimensional PET.

Authors:  Tianfang Li; Brian Thorndyke; Eduard Schreibmann; Yong Yang; Lei Xing
Journal:  Med Phys       Date:  2006-05       Impact factor: 4.071

3.  Direct measurement of lung motion using hyperpolarized helium-3 MR tagging.

Authors:  Jing Cai; G Wilson Miller; Talissa A Altes; Paul W Read; Stanley H Benedict; Eduard E de Lange; Gordon D Cates; James R Brookeman; John P Mugler; Ke Sheng
Journal:  Int J Radiat Oncol Biol Phys       Date:  2007-04-18       Impact factor: 7.038

4.  MR grid-tagging using hyperpolarized helium-3 for regional quantitative assessment of pulmonary biomechanics and ventilation.

Authors:  J Cai; T A Altes; G W Miller; K Sheng; P W Read; J F Mata; X Zhong; G D Cates; E E de Lange; J P Mugler; J R Brookeman
Journal:  Magn Reson Med       Date:  2007-08       Impact factor: 4.668

5.  A framework for evaluation of deformable image registration spatial accuracy using large landmark point sets.

Authors:  Richard Castillo; Edward Castillo; Rudy Guerra; Valen E Johnson; Travis McPhail; Amit K Garg; Thomas Guerrero
Journal:  Phys Med Biol       Date:  2009-03-05       Impact factor: 3.609

6.  Results of a multi-institution deformable registration accuracy study (MIDRAS).

Authors:  Kristy K Brock
Journal:  Int J Radiat Oncol Biol Phys       Date:  2009-11-10       Impact factor: 7.038

7.  Reproducibility of interfraction lung motion probability distribution function using dynamic MRI: statistical analysis.

Authors:  Jing Cai; Paul W Read; James M Larner; David R Jones; Stanley H Benedict; Ke Sheng
Journal:  Int J Radiat Oncol Biol Phys       Date:  2008-11-15       Impact factor: 7.038

8.  Retrospective analysis of artifacts in four-dimensional CT images of 50 abdominal and thoracic radiotherapy patients.

Authors:  Tokihiro Yamamoto; Ulrich Langner; Billy W Loo; John Shen; Paul J Keall
Journal:  Int J Radiat Oncol Biol Phys       Date:  2008-09-25       Impact factor: 7.038

9.  Planning lung radiotherapy using 4D CT data and a motion model.

Authors:  R Colgan; J McClelland; D McQuaid; P M Evans; D Hawkes; J Brock; D Landau; S Webb
Journal:  Phys Med Biol       Date:  2008-09-30       Impact factor: 3.609

10.  Dynamic MRI of grid-tagged hyperpolarized helium-3 for the assessment of lung motion during breathing.

Authors:  Jing Cai; Ke Sheng; Stanley H Benedict; Paul W Read; James M Larner; John P Mugler; Eduard E de Lange; Gordon D Cates; G Wilson Miller
Journal:  Int J Radiat Oncol Biol Phys       Date:  2009-06-18       Impact factor: 7.038

View more
  1 in total

1.  Improving deformable image registration with point metric and masking technique for postoperative breast cancer radiotherapy.

Authors:  Xin Xie; Yuchun Song; Feng Ye; Hui Yan; Shulian Wang; Xinming Zhao; Jianrong Dai
Journal:  Quant Imaging Med Surg       Date:  2021-04
  1 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.