Deformable image registration for temporal subtraction of chest radiographs

Min Li, Edward Castillo, Hong Yan Luo, Xiao Lin Zheng, Richard Castillo, Dmitriy Meshkov, Thomas Guerrero

Research output: Contribution to journalArticle

4 Citations (Scopus)

Abstract

Purpose: Temporal subtraction images constructed from image registration can facilitate the visualization of pathologic changes. In this study, we propose a deformable image registration (DIR) framework for creating temporal subtraction images of chest radiographs. Methods: We developed a DIR methodology using two different image similarity metrics, varying flow (VF) and compressible flow (CF). The proposed registration method consists of block matching, filtering, and interpolation. Specifically, corresponding point pairs between reference and target images are initially determined by minimizing a nonlinear least squares formulation using grid-searching optimization. A two-step filtering process, including least median of squares filtering and backward matching filtering, is then applied to the estimated point matches in order to remove erroneous matches. Finally, moving least squares is used to generate a full displacement field from the filtered point pairs. Results: We applied the proposed DIR method to 10 pairs of clinical chest radiographs and compared it with the demons and B-spline algorithms using the five-point rating score method. The average quality scores were 2.7 and 3 for the demons and B-spline methods, but 3.5 and 4.1 for the VF and CF methods. In addition, subtraction images improved the visual perception of abnormalities in the lungs by using the proposed method. Conclusion: The VF and CF models achieved a higher accuracy than the demons and the B-splinemethods. Furthermore, the proposed methodology demonstrated the ability to create clinically acceptable temporal subtraction chest radiographs that enhance interval changes and can be used to detect abnormalities such as non-small cell lung cancer.

Original languageEnglish (US)
Pages (from-to)513-522
Number of pages10
JournalInternational journal of computer assisted radiology and surgery
Volume9
Issue number4
DOIs
StatePublished - 2014
Externally publishedYes

Fingerprint

Image registration
Compressible flow
Thorax
Splines
Least-Squares Analysis
Interpolation
Visualization
Cells
Visual Perception
Aptitude
Non-Small Cell Lung Carcinoma
Lung

Keywords

  • Chest radiograph
  • Image registration
  • Intensity variation
  • Temporal subtraction

ASJC Scopus subject areas

  • Radiology Nuclear Medicine and imaging
  • Health Informatics
  • Surgery

Cite this

Deformable image registration for temporal subtraction of chest radiographs. / Li, Min; Castillo, Edward; Luo, Hong Yan; Zheng, Xiao Lin; Castillo, Richard; Meshkov, Dmitriy; Guerrero, Thomas.

In: International journal of computer assisted radiology and surgery, Vol. 9, No. 4, 2014, p. 513-522.

Research output: Contribution to journalArticle

Li, Min ; Castillo, Edward ; Luo, Hong Yan ; Zheng, Xiao Lin ; Castillo, Richard ; Meshkov, Dmitriy ; Guerrero, Thomas. / Deformable image registration for temporal subtraction of chest radiographs. In: International journal of computer assisted radiology and surgery. 2014 ; Vol. 9, No. 4. pp. 513-522.
@article{e4aa7595424e456280412b9edc790a4f,
title = "Deformable image registration for temporal subtraction of chest radiographs",
abstract = "Purpose: Temporal subtraction images constructed from image registration can facilitate the visualization of pathologic changes. In this study, we propose a deformable image registration (DIR) framework for creating temporal subtraction images of chest radiographs. Methods: We developed a DIR methodology using two different image similarity metrics, varying flow (VF) and compressible flow (CF). The proposed registration method consists of block matching, filtering, and interpolation. Specifically, corresponding point pairs between reference and target images are initially determined by minimizing a nonlinear least squares formulation using grid-searching optimization. A two-step filtering process, including least median of squares filtering and backward matching filtering, is then applied to the estimated point matches in order to remove erroneous matches. Finally, moving least squares is used to generate a full displacement field from the filtered point pairs. Results: We applied the proposed DIR method to 10 pairs of clinical chest radiographs and compared it with the demons and B-spline algorithms using the five-point rating score method. The average quality scores were 2.7 and 3 for the demons and B-spline methods, but 3.5 and 4.1 for the VF and CF methods. In addition, subtraction images improved the visual perception of abnormalities in the lungs by using the proposed method. Conclusion: The VF and CF models achieved a higher accuracy than the demons and the B-splinemethods. Furthermore, the proposed methodology demonstrated the ability to create clinically acceptable temporal subtraction chest radiographs that enhance interval changes and can be used to detect abnormalities such as non-small cell lung cancer.",
keywords = "Chest radiograph, Image registration, Intensity variation, Temporal subtraction",
author = "Min Li and Edward Castillo and Luo, {Hong Yan} and Zheng, {Xiao Lin} and Richard Castillo and Dmitriy Meshkov and Thomas Guerrero",
year = "2014",
doi = "10.1007/s11548-013-0947-y",
language = "English (US)",
volume = "9",
pages = "513--522",
journal = "Computer-Assisted Radiology and Surgery",
issn = "1861-6410",
publisher = "Springer Verlag",
number = "4",

}

TY - JOUR

T1 - Deformable image registration for temporal subtraction of chest radiographs

AU - Li, Min

AU - Castillo, Edward

AU - Luo, Hong Yan

AU - Zheng, Xiao Lin

AU - Castillo, Richard

AU - Meshkov, Dmitriy

AU - Guerrero, Thomas

PY - 2014

Y1 - 2014

N2 - Purpose: Temporal subtraction images constructed from image registration can facilitate the visualization of pathologic changes. In this study, we propose a deformable image registration (DIR) framework for creating temporal subtraction images of chest radiographs. Methods: We developed a DIR methodology using two different image similarity metrics, varying flow (VF) and compressible flow (CF). The proposed registration method consists of block matching, filtering, and interpolation. Specifically, corresponding point pairs between reference and target images are initially determined by minimizing a nonlinear least squares formulation using grid-searching optimization. A two-step filtering process, including least median of squares filtering and backward matching filtering, is then applied to the estimated point matches in order to remove erroneous matches. Finally, moving least squares is used to generate a full displacement field from the filtered point pairs. Results: We applied the proposed DIR method to 10 pairs of clinical chest radiographs and compared it with the demons and B-spline algorithms using the five-point rating score method. The average quality scores were 2.7 and 3 for the demons and B-spline methods, but 3.5 and 4.1 for the VF and CF methods. In addition, subtraction images improved the visual perception of abnormalities in the lungs by using the proposed method. Conclusion: The VF and CF models achieved a higher accuracy than the demons and the B-splinemethods. Furthermore, the proposed methodology demonstrated the ability to create clinically acceptable temporal subtraction chest radiographs that enhance interval changes and can be used to detect abnormalities such as non-small cell lung cancer.

AB - Purpose: Temporal subtraction images constructed from image registration can facilitate the visualization of pathologic changes. In this study, we propose a deformable image registration (DIR) framework for creating temporal subtraction images of chest radiographs. Methods: We developed a DIR methodology using two different image similarity metrics, varying flow (VF) and compressible flow (CF). The proposed registration method consists of block matching, filtering, and interpolation. Specifically, corresponding point pairs between reference and target images are initially determined by minimizing a nonlinear least squares formulation using grid-searching optimization. A two-step filtering process, including least median of squares filtering and backward matching filtering, is then applied to the estimated point matches in order to remove erroneous matches. Finally, moving least squares is used to generate a full displacement field from the filtered point pairs. Results: We applied the proposed DIR method to 10 pairs of clinical chest radiographs and compared it with the demons and B-spline algorithms using the five-point rating score method. The average quality scores were 2.7 and 3 for the demons and B-spline methods, but 3.5 and 4.1 for the VF and CF methods. In addition, subtraction images improved the visual perception of abnormalities in the lungs by using the proposed method. Conclusion: The VF and CF models achieved a higher accuracy than the demons and the B-splinemethods. Furthermore, the proposed methodology demonstrated the ability to create clinically acceptable temporal subtraction chest radiographs that enhance interval changes and can be used to detect abnormalities such as non-small cell lung cancer.

KW - Chest radiograph

KW - Image registration

KW - Intensity variation

KW - Temporal subtraction

UR - http://www.scopus.com/inward/record.url?scp=84906858000&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84906858000&partnerID=8YFLogxK

U2 - 10.1007/s11548-013-0947-y

DO - 10.1007/s11548-013-0947-y

M3 - Article

VL - 9

SP - 513

EP - 522

JO - Computer-Assisted Radiology and Surgery

JF - Computer-Assisted Radiology and Surgery

SN - 1861-6410

IS - 4

ER -