TU‐C‐141‐12: A Novel Edge Gradient Distance Metric for Automated Evaluation of Deformable Image Registration Quality

John Ford, A. Gautam, J. Williamson

Research output: Contribution to journalArticle

Abstract

Purpose: To develop and test a new registration quality metric, based on the distance between image edges, for evaluation of deformable image registration algorithms without the need for manually placed landmarks. Methods: A 2D Canny filter is used to create binary gradient images from registered grayscale input images that are to be compared. In each slice, a small subregion (10×10 pixels) of one image is translated relative to the other. The translational distance that maximizes overlap of edges in the subregion is the local edge gradient distance to agreement (EGDTA); repeating over all subregions on every slice provides an EGDTA map. The method was applied to pelvic CT images in 3 patients. For each patient, one CT (the planning CT) was registered to each of three daily CTs using three deformable image registration algorithms: Grayscale‐driven (G), Contour‐driven (C), and Grayscale+Contour‐driven (G+C). C and G+C use manually drawn bladder, prostate and rectum contours on both planning and treatment images to drive the registration. EGDTA maps were created for each of the 27 registrations. Mean EGDTA values in concentric ring ROIs close to and far away from the pelvic organs were compared. Results: Both C and G+C had lower EGDTA values (better registration quality) close to the pelvic organs. Both G and G+C showed much better performance in the regions distant from the pelvic organs compared to contour‐only driven (C). G+C registration exhibited lowest EGDTA values (highest registration quality) throughout the image. Conclusion: The edge distance registration quality metric provides the expected dependence on registration type and ROI location, and shows potential as an automated means of comparing deformable image registration algorithms. Supported by NCI Grant P01 CA 116602.

Original languageEnglish (US)
Number of pages1
JournalMedical Physics
Volume40
Issue number6
DOIs
StatePublished - 2013
Externally publishedYes

Fingerprint

Pelvis
Rectum
Prostate
Urinary Bladder
Therapeutics

ASJC Scopus subject areas

  • Biophysics
  • Radiology Nuclear Medicine and imaging

Cite this

TU‐C‐141‐12 : A Novel Edge Gradient Distance Metric for Automated Evaluation of Deformable Image Registration Quality. / Ford, John; Gautam, A.; Williamson, J.

In: Medical Physics, Vol. 40, No. 6, 2013.

Research output: Contribution to journalArticle

@article{f782317d4847435abe1e7ac334de0621,
title = "TU‐C‐141‐12: A Novel Edge Gradient Distance Metric for Automated Evaluation of Deformable Image Registration Quality",
abstract = "Purpose: To develop and test a new registration quality metric, based on the distance between image edges, for evaluation of deformable image registration algorithms without the need for manually placed landmarks. Methods: A 2D Canny filter is used to create binary gradient images from registered grayscale input images that are to be compared. In each slice, a small subregion (10×10 pixels) of one image is translated relative to the other. The translational distance that maximizes overlap of edges in the subregion is the local edge gradient distance to agreement (EGDTA); repeating over all subregions on every slice provides an EGDTA map. The method was applied to pelvic CT images in 3 patients. For each patient, one CT (the planning CT) was registered to each of three daily CTs using three deformable image registration algorithms: Grayscale‐driven (G), Contour‐driven (C), and Grayscale+Contour‐driven (G+C). C and G+C use manually drawn bladder, prostate and rectum contours on both planning and treatment images to drive the registration. EGDTA maps were created for each of the 27 registrations. Mean EGDTA values in concentric ring ROIs close to and far away from the pelvic organs were compared. Results: Both C and G+C had lower EGDTA values (better registration quality) close to the pelvic organs. Both G and G+C showed much better performance in the regions distant from the pelvic organs compared to contour‐only driven (C). G+C registration exhibited lowest EGDTA values (highest registration quality) throughout the image. Conclusion: The edge distance registration quality metric provides the expected dependence on registration type and ROI location, and shows potential as an automated means of comparing deformable image registration algorithms. Supported by NCI Grant P01 CA 116602.",
author = "John Ford and A. Gautam and J. Williamson",
year = "2013",
doi = "10.1118/1.4815389",
language = "English (US)",
volume = "40",
journal = "Medical Physics",
issn = "0094-2405",
publisher = "AAPM - American Association of Physicists in Medicine",
number = "6",

}

TY - JOUR

T1 - TU‐C‐141‐12

T2 - A Novel Edge Gradient Distance Metric for Automated Evaluation of Deformable Image Registration Quality

AU - Ford, John

AU - Gautam, A.

AU - Williamson, J.

PY - 2013

Y1 - 2013

N2 - Purpose: To develop and test a new registration quality metric, based on the distance between image edges, for evaluation of deformable image registration algorithms without the need for manually placed landmarks. Methods: A 2D Canny filter is used to create binary gradient images from registered grayscale input images that are to be compared. In each slice, a small subregion (10×10 pixels) of one image is translated relative to the other. The translational distance that maximizes overlap of edges in the subregion is the local edge gradient distance to agreement (EGDTA); repeating over all subregions on every slice provides an EGDTA map. The method was applied to pelvic CT images in 3 patients. For each patient, one CT (the planning CT) was registered to each of three daily CTs using three deformable image registration algorithms: Grayscale‐driven (G), Contour‐driven (C), and Grayscale+Contour‐driven (G+C). C and G+C use manually drawn bladder, prostate and rectum contours on both planning and treatment images to drive the registration. EGDTA maps were created for each of the 27 registrations. Mean EGDTA values in concentric ring ROIs close to and far away from the pelvic organs were compared. Results: Both C and G+C had lower EGDTA values (better registration quality) close to the pelvic organs. Both G and G+C showed much better performance in the regions distant from the pelvic organs compared to contour‐only driven (C). G+C registration exhibited lowest EGDTA values (highest registration quality) throughout the image. Conclusion: The edge distance registration quality metric provides the expected dependence on registration type and ROI location, and shows potential as an automated means of comparing deformable image registration algorithms. Supported by NCI Grant P01 CA 116602.

AB - Purpose: To develop and test a new registration quality metric, based on the distance between image edges, for evaluation of deformable image registration algorithms without the need for manually placed landmarks. Methods: A 2D Canny filter is used to create binary gradient images from registered grayscale input images that are to be compared. In each slice, a small subregion (10×10 pixels) of one image is translated relative to the other. The translational distance that maximizes overlap of edges in the subregion is the local edge gradient distance to agreement (EGDTA); repeating over all subregions on every slice provides an EGDTA map. The method was applied to pelvic CT images in 3 patients. For each patient, one CT (the planning CT) was registered to each of three daily CTs using three deformable image registration algorithms: Grayscale‐driven (G), Contour‐driven (C), and Grayscale+Contour‐driven (G+C). C and G+C use manually drawn bladder, prostate and rectum contours on both planning and treatment images to drive the registration. EGDTA maps were created for each of the 27 registrations. Mean EGDTA values in concentric ring ROIs close to and far away from the pelvic organs were compared. Results: Both C and G+C had lower EGDTA values (better registration quality) close to the pelvic organs. Both G and G+C showed much better performance in the regions distant from the pelvic organs compared to contour‐only driven (C). G+C registration exhibited lowest EGDTA values (highest registration quality) throughout the image. Conclusion: The edge distance registration quality metric provides the expected dependence on registration type and ROI location, and shows potential as an automated means of comparing deformable image registration algorithms. Supported by NCI Grant P01 CA 116602.

UR - http://www.scopus.com/inward/record.url?scp=85024813104&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85024813104&partnerID=8YFLogxK

U2 - 10.1118/1.4815389

DO - 10.1118/1.4815389

M3 - Article

AN - SCOPUS:85024813104

VL - 40

JO - Medical Physics

JF - Medical Physics

SN - 0094-2405

IS - 6

ER -