Canny edge-based deformable image registration

Vasant Kearney, Yihui Huang, Weihua Mao, Baohong Yuan, Liping Tang

Research output: Contribution to journalArticle

5 Citations (Scopus)

Abstract

This work focuses on developing a 2D Canny edge-based deformable image registration (Canny DIR) algorithm to register in vivo white light images taken at various time points. This method uses a sparse interpolation deformation algorithm to sparsely register regions of the image with strong edge information. A stability criterion is enforced which removes regions of edges that do not deform in a smooth uniform manner. Using a synthetic mouse surface ground truth model, the accuracy of the Canny DIR algorithm was evaluated under axial rotation in the presence of deformation. The accuracy was also tested using fluorescent dye injections, which were then used for gamma analysis to establish a second ground truth. The results indicate that the Canny DIR algorithm performs better than rigid registration, intensity corrected Demons, and distinctive features for all evaluation matrices and ground truth scenarios. In conclusion Canny DIR performs well in the presence of the unique lighting and shading variations associated with white-light-based image registration.

Original languageEnglish (US)
Pages (from-to)966-985
Number of pages20
JournalPhysics in Medicine and Biology
Volume62
Issue number3
DOIs
StatePublished - Feb 7 2017

Fingerprint

Light
Lighting
Fluorescent Dyes
Injections

Keywords

  • deformable image registration
  • sparse interpolation
  • surface registration

ASJC Scopus subject areas

  • Radiological and Ultrasound Technology
  • Radiology Nuclear Medicine and imaging

Cite this

Kearney, V., Huang, Y., Mao, W., Yuan, B., & Tang, L. (2017). Canny edge-based deformable image registration. Physics in Medicine and Biology, 62(3), 966-985. https://doi.org/10.1088/1361-6560/aa5342

Canny edge-based deformable image registration. / Kearney, Vasant; Huang, Yihui; Mao, Weihua; Yuan, Baohong; Tang, Liping.

In: Physics in Medicine and Biology, Vol. 62, No. 3, 07.02.2017, p. 966-985.

Research output: Contribution to journalArticle

Kearney, V, Huang, Y, Mao, W, Yuan, B & Tang, L 2017, 'Canny edge-based deformable image registration', Physics in Medicine and Biology, vol. 62, no. 3, pp. 966-985. https://doi.org/10.1088/1361-6560/aa5342
Kearney, Vasant ; Huang, Yihui ; Mao, Weihua ; Yuan, Baohong ; Tang, Liping. / Canny edge-based deformable image registration. In: Physics in Medicine and Biology. 2017 ; Vol. 62, No. 3. pp. 966-985.
@article{14edb0cb885845af872c33e29694392a,
title = "Canny edge-based deformable image registration",
abstract = "This work focuses on developing a 2D Canny edge-based deformable image registration (Canny DIR) algorithm to register in vivo white light images taken at various time points. This method uses a sparse interpolation deformation algorithm to sparsely register regions of the image with strong edge information. A stability criterion is enforced which removes regions of edges that do not deform in a smooth uniform manner. Using a synthetic mouse surface ground truth model, the accuracy of the Canny DIR algorithm was evaluated under axial rotation in the presence of deformation. The accuracy was also tested using fluorescent dye injections, which were then used for gamma analysis to establish a second ground truth. The results indicate that the Canny DIR algorithm performs better than rigid registration, intensity corrected Demons, and distinctive features for all evaluation matrices and ground truth scenarios. In conclusion Canny DIR performs well in the presence of the unique lighting and shading variations associated with white-light-based image registration.",
keywords = "deformable image registration, sparse interpolation, surface registration",
author = "Vasant Kearney and Yihui Huang and Weihua Mao and Baohong Yuan and Liping Tang",
year = "2017",
month = "2",
day = "7",
doi = "10.1088/1361-6560/aa5342",
language = "English (US)",
volume = "62",
pages = "966--985",
journal = "Physics in Medicine and Biology",
issn = "0031-9155",
publisher = "IOP Publishing Ltd.",
number = "3",

}

TY - JOUR

T1 - Canny edge-based deformable image registration

AU - Kearney, Vasant

AU - Huang, Yihui

AU - Mao, Weihua

AU - Yuan, Baohong

AU - Tang, Liping

PY - 2017/2/7

Y1 - 2017/2/7

N2 - This work focuses on developing a 2D Canny edge-based deformable image registration (Canny DIR) algorithm to register in vivo white light images taken at various time points. This method uses a sparse interpolation deformation algorithm to sparsely register regions of the image with strong edge information. A stability criterion is enforced which removes regions of edges that do not deform in a smooth uniform manner. Using a synthetic mouse surface ground truth model, the accuracy of the Canny DIR algorithm was evaluated under axial rotation in the presence of deformation. The accuracy was also tested using fluorescent dye injections, which were then used for gamma analysis to establish a second ground truth. The results indicate that the Canny DIR algorithm performs better than rigid registration, intensity corrected Demons, and distinctive features for all evaluation matrices and ground truth scenarios. In conclusion Canny DIR performs well in the presence of the unique lighting and shading variations associated with white-light-based image registration.

AB - This work focuses on developing a 2D Canny edge-based deformable image registration (Canny DIR) algorithm to register in vivo white light images taken at various time points. This method uses a sparse interpolation deformation algorithm to sparsely register regions of the image with strong edge information. A stability criterion is enforced which removes regions of edges that do not deform in a smooth uniform manner. Using a synthetic mouse surface ground truth model, the accuracy of the Canny DIR algorithm was evaluated under axial rotation in the presence of deformation. The accuracy was also tested using fluorescent dye injections, which were then used for gamma analysis to establish a second ground truth. The results indicate that the Canny DIR algorithm performs better than rigid registration, intensity corrected Demons, and distinctive features for all evaluation matrices and ground truth scenarios. In conclusion Canny DIR performs well in the presence of the unique lighting and shading variations associated with white-light-based image registration.

KW - deformable image registration

KW - sparse interpolation

KW - surface registration

UR - http://www.scopus.com/inward/record.url?scp=85010049854&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85010049854&partnerID=8YFLogxK

U2 - 10.1088/1361-6560/aa5342

DO - 10.1088/1361-6560/aa5342

M3 - Article

C2 - 28081014

AN - SCOPUS:85010049854

VL - 62

SP - 966

EP - 985

JO - Physics in Medicine and Biology

JF - Physics in Medicine and Biology

SN - 0031-9155

IS - 3

ER -