Fast Deformable Image Registration with Non-smooth Dual Optimization

Martin Rajchl; John S.H. Baxter; Wu Qiu; Ali R. Khan; Aaron Fenster; Terry M. Peters; Daniel Rueckert; Jing Yuan

doi:10.1109/CVPRW.2016.65

Fast Deformable Image Registration with Non-smooth Dual Optimization

Martin Rajchl, John S.H. Baxter, Wu Qiu, Ali R. Khan, Aaron Fenster, Terry M. Peters, Daniel Rueckert, Jing Yuan

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

2 Scopus citations

Abstract

Optimization techniques have been widely used in deformable registration, allowing for the incorporation of similarity metrics with regularization mechanisms. These regularization mechanisms are designed to mitigate the effects of trivial solutions to ill-posed registration problems and to otherwise ensure the resulting deformation fields are well-behaved. This paper introduces a novel deformable registration (DR) algorithm, RANCOR, which uses iterative convexification to address DR problems under nonsmooth total-variation regularization. Initial comparative results against four state-of-the-art registration algorithms and under smooth regularization, respectively, are presented using the Internet Brain Segmentation Repository (IBSR) database.

Original language	English
Title of host publication	Proceedings - 29th IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2016
Publisher	IEEE Computer Society
Pages	465-472
Number of pages	8
ISBN (Electronic)	9781467388504
DOIs	https://doi.org/10.1109/CVPRW.2016.65
State	Published - 16 Dec 2016
Externally published	Yes
Event	29th IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2016 - Las Vegas, United States Duration: 26 Jun 2016 → 1 Jul 2016

Publication series

Name	IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops
ISSN (Print)	2160-7508
ISSN (Electronic)	2160-7516

Conference

Conference	29th IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2016
Country/Territory	United States
City	Las Vegas
Period	26/06/16 → 1/07/16

Access to Document

10.1109/CVPRW.2016.65

Cite this

Rajchl, M., Baxter, J. S. H., Qiu, W., Khan, A. R., Fenster, A., Peters, T. M., Rueckert, D., & Yuan, J. (2016). Fast Deformable Image Registration with Non-smooth Dual Optimization. In Proceedings - 29th IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2016 (pp. 465-472). Article 7789555 (IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops). IEEE Computer Society. https://doi.org/10.1109/CVPRW.2016.65

@inproceedings{4c324b2f02d049a2b73a53f59dabeca6,

title = "Fast Deformable Image Registration with Non-smooth Dual Optimization",

abstract = "Optimization techniques have been widely used in deformable registration, allowing for the incorporation of similarity metrics with regularization mechanisms. These regularization mechanisms are designed to mitigate the effects of trivial solutions to ill-posed registration problems and to otherwise ensure the resulting deformation fields are well-behaved. This paper introduces a novel deformable registration (DR) algorithm, RANCOR, which uses iterative convexification to address DR problems under nonsmooth total-variation regularization. Initial comparative results against four state-of-the-art registration algorithms and under smooth regularization, respectively, are presented using the Internet Brain Segmentation Repository (IBSR) database.",

author = "Martin Rajchl and Baxter, {John S.H.} and Wu Qiu and Khan, {Ali R.} and Aaron Fenster and Peters, {Terry M.} and Daniel Rueckert and Jing Yuan",

note = "Publisher Copyright: {\textcopyright} 2016 IEEE.; 29th IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2016 ; Conference date: 26-06-2016 Through 01-07-2016",

year = "2016",

month = dec,

day = "16",

doi = "10.1109/CVPRW.2016.65",

language = "English",

series = "IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops",

publisher = "IEEE Computer Society",

pages = "465--472",

booktitle = "Proceedings - 29th IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2016",

}

Rajchl, M, Baxter, JSH, Qiu, W, Khan, AR, Fenster, A, Peters, TM, Rueckert, D & Yuan, J 2016, Fast Deformable Image Registration with Non-smooth Dual Optimization. in Proceedings - 29th IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2016., 7789555, IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, IEEE Computer Society, pp. 465-472, 29th IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2016, Las Vegas, United States, 26/06/16. https://doi.org/10.1109/CVPRW.2016.65

Fast Deformable Image Registration with Non-smooth Dual Optimization. / Rajchl, Martin; Baxter, John S.H.; Qiu, Wu et al.
Proceedings - 29th IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2016. IEEE Computer Society, 2016. p. 465-472 7789555 (IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Fast Deformable Image Registration with Non-smooth Dual Optimization

AU - Rajchl, Martin

AU - Baxter, John S.H.

AU - Qiu, Wu

AU - Khan, Ali R.

AU - Fenster, Aaron

AU - Peters, Terry M.

AU - Rueckert, Daniel

AU - Yuan, Jing

PY - 2016/12/16

Y1 - 2016/12/16

N2 - Optimization techniques have been widely used in deformable registration, allowing for the incorporation of similarity metrics with regularization mechanisms. These regularization mechanisms are designed to mitigate the effects of trivial solutions to ill-posed registration problems and to otherwise ensure the resulting deformation fields are well-behaved. This paper introduces a novel deformable registration (DR) algorithm, RANCOR, which uses iterative convexification to address DR problems under nonsmooth total-variation regularization. Initial comparative results against four state-of-the-art registration algorithms and under smooth regularization, respectively, are presented using the Internet Brain Segmentation Repository (IBSR) database.

AB - Optimization techniques have been widely used in deformable registration, allowing for the incorporation of similarity metrics with regularization mechanisms. These regularization mechanisms are designed to mitigate the effects of trivial solutions to ill-posed registration problems and to otherwise ensure the resulting deformation fields are well-behaved. This paper introduces a novel deformable registration (DR) algorithm, RANCOR, which uses iterative convexification to address DR problems under nonsmooth total-variation regularization. Initial comparative results against four state-of-the-art registration algorithms and under smooth regularization, respectively, are presented using the Internet Brain Segmentation Repository (IBSR) database.

UR - http://www.scopus.com/inward/record.url?scp=85010214370&partnerID=8YFLogxK

U2 - 10.1109/CVPRW.2016.65

DO - 10.1109/CVPRW.2016.65

M3 - Conference contribution

AN - SCOPUS:85010214370

T3 - IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops

SP - 465

EP - 472

BT - Proceedings - 29th IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2016

PB - IEEE Computer Society

T2 - 29th IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2016

Y2 - 26 June 2016 through 1 July 2016

ER -

Rajchl M, Baxter JSH, Qiu W, Khan AR, Fenster A, Peters TM et al. Fast Deformable Image Registration with Non-smooth Dual Optimization. In Proceedings - 29th IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2016. IEEE Computer Society. 2016. p. 465-472. 7789555. (IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops). doi: 10.1109/CVPRW.2016.65

Fast Deformable Image Registration with Non-smooth Dual Optimization

Abstract

Publication series

Conference

Access to Document

Other files and links

Fingerprint

Cite this