The role of regularization in deformable image registration for head and neck adaptive radiotherapy

D. Ciardo, M. Peroni, M. Riboldi, D. Alterio, G. Baroni, R. Orecchia

Research output: Contribution to journalArticle

7 Citations (Scopus)

Abstract

Deformable image registration provides a robust mathematical framework to quantify morphological changes that occur along the course of external beam radiotherapy treatments. As clinical reliability of deformable image registration is not always guaranteed, algorithm regularization is commonly introduced to prevent sharp discontinuities in the quantified deformation and achieve anatomically consistent results. In this work we analyzed the influence of regularization on two different registration methods, i.e. B-Splines and Log Domain Diffeomorphic Demons, implemented in an open-source platform. We retrospectively analyzed the simulation computed tomography (CTsim) and the corresponding re-planning computed tomography (CTrepl) scans in 30 head and neck cancer patients. First, we investigated the influence of regularization levels on hounsfield units (HU) information in 10 test patients for each considered method. Then, we compared the registration results of the open-source implementation at selected best performing regularization levels with a clinical commercial software on the remaining 20 patients in terms of mean volume overlap, surface and center of mass distances between manual outlines and propagated structures. The regularized B-Splines method was not statistically different from the commercial software. The tuning of the regularization parameters allowed open-source algorithms to achieve better results in deformable image registration for head and neck patients, with the additional benefit of a framework where regularization can be tuned on a patient specific basis.

Original languageEnglish
Pages (from-to)323-331
Number of pages9
JournalTechnology in Cancer Research and Treatment
Volume12
Issue number4
DOIs
Publication statusPublished - 2013

Fingerprint

Neck
Radiotherapy
Head
Software
Tomography
Head and Neck Neoplasms
Therapeutics

Keywords

  • B-Splines
  • Deformable image registration
  • Demons
  • Head and neck cancer
  • MIMvista
  • Regularization

ASJC Scopus subject areas

  • Cancer Research
  • Oncology
  • Medicine(all)

Cite this

The role of regularization in deformable image registration for head and neck adaptive radiotherapy. / Ciardo, D.; Peroni, M.; Riboldi, M.; Alterio, D.; Baroni, G.; Orecchia, R.

In: Technology in Cancer Research and Treatment, Vol. 12, No. 4, 2013, p. 323-331.

Research output: Contribution to journalArticle

@article{cedd32e14fe841e8a14c6933eceef886,
title = "The role of regularization in deformable image registration for head and neck adaptive radiotherapy",
abstract = "Deformable image registration provides a robust mathematical framework to quantify morphological changes that occur along the course of external beam radiotherapy treatments. As clinical reliability of deformable image registration is not always guaranteed, algorithm regularization is commonly introduced to prevent sharp discontinuities in the quantified deformation and achieve anatomically consistent results. In this work we analyzed the influence of regularization on two different registration methods, i.e. B-Splines and Log Domain Diffeomorphic Demons, implemented in an open-source platform. We retrospectively analyzed the simulation computed tomography (CTsim) and the corresponding re-planning computed tomography (CTrepl) scans in 30 head and neck cancer patients. First, we investigated the influence of regularization levels on hounsfield units (HU) information in 10 test patients for each considered method. Then, we compared the registration results of the open-source implementation at selected best performing regularization levels with a clinical commercial software on the remaining 20 patients in terms of mean volume overlap, surface and center of mass distances between manual outlines and propagated structures. The regularized B-Splines method was not statistically different from the commercial software. The tuning of the regularization parameters allowed open-source algorithms to achieve better results in deformable image registration for head and neck patients, with the additional benefit of a framework where regularization can be tuned on a patient specific basis.",
keywords = "B-Splines, Deformable image registration, Demons, Head and neck cancer, MIMvista, Regularization",
author = "D. Ciardo and M. Peroni and M. Riboldi and D. Alterio and G. Baroni and R. Orecchia",
year = "2013",
doi = "10.7785/tcrt.2012.500327",
language = "English",
volume = "12",
pages = "323--331",
journal = "Technology in Cancer Research and Treatment",
issn = "1533-0346",
publisher = "Adenine Press",
number = "4",

}

TY - JOUR

T1 - The role of regularization in deformable image registration for head and neck adaptive radiotherapy

AU - Ciardo, D.

AU - Peroni, M.

AU - Riboldi, M.

AU - Alterio, D.

AU - Baroni, G.

AU - Orecchia, R.

PY - 2013

Y1 - 2013

N2 - Deformable image registration provides a robust mathematical framework to quantify morphological changes that occur along the course of external beam radiotherapy treatments. As clinical reliability of deformable image registration is not always guaranteed, algorithm regularization is commonly introduced to prevent sharp discontinuities in the quantified deformation and achieve anatomically consistent results. In this work we analyzed the influence of regularization on two different registration methods, i.e. B-Splines and Log Domain Diffeomorphic Demons, implemented in an open-source platform. We retrospectively analyzed the simulation computed tomography (CTsim) and the corresponding re-planning computed tomography (CTrepl) scans in 30 head and neck cancer patients. First, we investigated the influence of regularization levels on hounsfield units (HU) information in 10 test patients for each considered method. Then, we compared the registration results of the open-source implementation at selected best performing regularization levels with a clinical commercial software on the remaining 20 patients in terms of mean volume overlap, surface and center of mass distances between manual outlines and propagated structures. The regularized B-Splines method was not statistically different from the commercial software. The tuning of the regularization parameters allowed open-source algorithms to achieve better results in deformable image registration for head and neck patients, with the additional benefit of a framework where regularization can be tuned on a patient specific basis.

AB - Deformable image registration provides a robust mathematical framework to quantify morphological changes that occur along the course of external beam radiotherapy treatments. As clinical reliability of deformable image registration is not always guaranteed, algorithm regularization is commonly introduced to prevent sharp discontinuities in the quantified deformation and achieve anatomically consistent results. In this work we analyzed the influence of regularization on two different registration methods, i.e. B-Splines and Log Domain Diffeomorphic Demons, implemented in an open-source platform. We retrospectively analyzed the simulation computed tomography (CTsim) and the corresponding re-planning computed tomography (CTrepl) scans in 30 head and neck cancer patients. First, we investigated the influence of regularization levels on hounsfield units (HU) information in 10 test patients for each considered method. Then, we compared the registration results of the open-source implementation at selected best performing regularization levels with a clinical commercial software on the remaining 20 patients in terms of mean volume overlap, surface and center of mass distances between manual outlines and propagated structures. The regularized B-Splines method was not statistically different from the commercial software. The tuning of the regularization parameters allowed open-source algorithms to achieve better results in deformable image registration for head and neck patients, with the additional benefit of a framework where regularization can be tuned on a patient specific basis.

KW - B-Splines

KW - Deformable image registration

KW - Demons

KW - Head and neck cancer

KW - MIMvista

KW - Regularization

UR - http://www.scopus.com/inward/record.url?scp=84880059991&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84880059991&partnerID=8YFLogxK

U2 - 10.7785/tcrt.2012.500327

DO - 10.7785/tcrt.2012.500327

M3 - Article

C2 - 23448576

AN - SCOPUS:84880059991

VL - 12

SP - 323

EP - 331

JO - Technology in Cancer Research and Treatment

JF - Technology in Cancer Research and Treatment

SN - 1533-0346

IS - 4

ER -