Comprehensive evaluation of ten deformable image registration algorithms for contour propagation between CT and cone-beam CT images in adaptive head & neck radiotherapy

Xin Li, Yuyu Zhang, Yinghua Shi, Shuyu Wu, Yang Xiao, Xuejun Gu, Xin Zhen, Linghong Zhou

Research output: Contribution to journalArticle

13 Citations (Scopus)

Abstract

Deformable image registration (DIR) is a critical technic in adaptive radiotherapy (ART) for propagating contours between planning computerized tomography (CT) images and treatment CT/cone-beam CT (CBCT) images to account for organ deformation for treatment re-planning. To validate the ability and accuracy of DIR algorithms in organ at risk (OAR) contour mapping, ten intensity-based DIR strategies, which were classified into four categories -optical flow-based, demons-based, level-set-based and spline-based-were tested on planning CT and fractional CBCT images acquired from twenty-one head & neck (H&N) cancer patients who underwent 6∼7-week intensity-modulated radiation therapy (IMRT). Three similarity metrics, i.e., the Dice similarity coefficient (DSC), the percentage error (PE) and the Hausdorff distance (HD), were employed to measure the agreement between the propagated contours and the physician-delineated ground truths of four OARs, including the vertebra (VTB), the vertebral foramen (VF), the parotid gland (PG) and the submandibular gland (SMG). It was found that the evaluated DIRs in this work did not necessarily outperform rigid registration. DIR performed better for bony structures than soft-tissue organs, and the DIR performance tended to vary for different ROIs with different degrees of deformation as the treatment proceeded. Generally, the optical flow-based DIR performed best, while the demons-based DIR usually ranked last except for a modified demons-based DISC used for CT-CBCT DIR. These experimental results suggest that the choice of a specific DIR algorithm depends on the image modality, anatomic site, magnitude of deformation and application. Therefore, careful examinations and modifications are required before accepting the auto-propagated contours, especially for automatic re-planning ART systems.

Original languageEnglish (US)
Article numbere0175906
JournalPLoS One
Volume12
Issue number4
DOIs
StatePublished - Apr 1 2017

Fingerprint

Cone-Beam Computed Tomography
Computerized tomography
Image registration
tomography
Radiotherapy
radiotherapy
neck
Cones
Neck
planning
Head
Tomography
parotid gland
Organs at Risk
Planning
Submandibular Gland
Parotid Gland
Optical flows
vertebrae
physicians

ASJC Scopus subject areas

  • Medicine(all)
  • Biochemistry, Genetics and Molecular Biology(all)
  • Agricultural and Biological Sciences(all)

Cite this

Comprehensive evaluation of ten deformable image registration algorithms for contour propagation between CT and cone-beam CT images in adaptive head & neck radiotherapy. / Li, Xin; Zhang, Yuyu; Shi, Yinghua; Wu, Shuyu; Xiao, Yang; Gu, Xuejun; Zhen, Xin; Zhou, Linghong.

In: PLoS One, Vol. 12, No. 4, e0175906, 01.04.2017.

Research output: Contribution to journalArticle

@article{6494c2d266d8427f9c51f28f4338b9bc,
title = "Comprehensive evaluation of ten deformable image registration algorithms for contour propagation between CT and cone-beam CT images in adaptive head & neck radiotherapy",
abstract = "Deformable image registration (DIR) is a critical technic in adaptive radiotherapy (ART) for propagating contours between planning computerized tomography (CT) images and treatment CT/cone-beam CT (CBCT) images to account for organ deformation for treatment re-planning. To validate the ability and accuracy of DIR algorithms in organ at risk (OAR) contour mapping, ten intensity-based DIR strategies, which were classified into four categories -optical flow-based, demons-based, level-set-based and spline-based-were tested on planning CT and fractional CBCT images acquired from twenty-one head & neck (H&N) cancer patients who underwent 6∼7-week intensity-modulated radiation therapy (IMRT). Three similarity metrics, i.e., the Dice similarity coefficient (DSC), the percentage error (PE) and the Hausdorff distance (HD), were employed to measure the agreement between the propagated contours and the physician-delineated ground truths of four OARs, including the vertebra (VTB), the vertebral foramen (VF), the parotid gland (PG) and the submandibular gland (SMG). It was found that the evaluated DIRs in this work did not necessarily outperform rigid registration. DIR performed better for bony structures than soft-tissue organs, and the DIR performance tended to vary for different ROIs with different degrees of deformation as the treatment proceeded. Generally, the optical flow-based DIR performed best, while the demons-based DIR usually ranked last except for a modified demons-based DISC used for CT-CBCT DIR. These experimental results suggest that the choice of a specific DIR algorithm depends on the image modality, anatomic site, magnitude of deformation and application. Therefore, careful examinations and modifications are required before accepting the auto-propagated contours, especially for automatic re-planning ART systems.",
author = "Xin Li and Yuyu Zhang and Yinghua Shi and Shuyu Wu and Yang Xiao and Xuejun Gu and Xin Zhen and Linghong Zhou",
year = "2017",
month = "4",
day = "1",
doi = "10.1371/journal.pone.0175906",
language = "English (US)",
volume = "12",
journal = "PLoS One",
issn = "1932-6203",
publisher = "Public Library of Science",
number = "4",

}

TY - JOUR

T1 - Comprehensive evaluation of ten deformable image registration algorithms for contour propagation between CT and cone-beam CT images in adaptive head & neck radiotherapy

AU - Li, Xin

AU - Zhang, Yuyu

AU - Shi, Yinghua

AU - Wu, Shuyu

AU - Xiao, Yang

AU - Gu, Xuejun

AU - Zhen, Xin

AU - Zhou, Linghong

PY - 2017/4/1

Y1 - 2017/4/1

N2 - Deformable image registration (DIR) is a critical technic in adaptive radiotherapy (ART) for propagating contours between planning computerized tomography (CT) images and treatment CT/cone-beam CT (CBCT) images to account for organ deformation for treatment re-planning. To validate the ability and accuracy of DIR algorithms in organ at risk (OAR) contour mapping, ten intensity-based DIR strategies, which were classified into four categories -optical flow-based, demons-based, level-set-based and spline-based-were tested on planning CT and fractional CBCT images acquired from twenty-one head & neck (H&N) cancer patients who underwent 6∼7-week intensity-modulated radiation therapy (IMRT). Three similarity metrics, i.e., the Dice similarity coefficient (DSC), the percentage error (PE) and the Hausdorff distance (HD), were employed to measure the agreement between the propagated contours and the physician-delineated ground truths of four OARs, including the vertebra (VTB), the vertebral foramen (VF), the parotid gland (PG) and the submandibular gland (SMG). It was found that the evaluated DIRs in this work did not necessarily outperform rigid registration. DIR performed better for bony structures than soft-tissue organs, and the DIR performance tended to vary for different ROIs with different degrees of deformation as the treatment proceeded. Generally, the optical flow-based DIR performed best, while the demons-based DIR usually ranked last except for a modified demons-based DISC used for CT-CBCT DIR. These experimental results suggest that the choice of a specific DIR algorithm depends on the image modality, anatomic site, magnitude of deformation and application. Therefore, careful examinations and modifications are required before accepting the auto-propagated contours, especially for automatic re-planning ART systems.

AB - Deformable image registration (DIR) is a critical technic in adaptive radiotherapy (ART) for propagating contours between planning computerized tomography (CT) images and treatment CT/cone-beam CT (CBCT) images to account for organ deformation for treatment re-planning. To validate the ability and accuracy of DIR algorithms in organ at risk (OAR) contour mapping, ten intensity-based DIR strategies, which were classified into four categories -optical flow-based, demons-based, level-set-based and spline-based-were tested on planning CT and fractional CBCT images acquired from twenty-one head & neck (H&N) cancer patients who underwent 6∼7-week intensity-modulated radiation therapy (IMRT). Three similarity metrics, i.e., the Dice similarity coefficient (DSC), the percentage error (PE) and the Hausdorff distance (HD), were employed to measure the agreement between the propagated contours and the physician-delineated ground truths of four OARs, including the vertebra (VTB), the vertebral foramen (VF), the parotid gland (PG) and the submandibular gland (SMG). It was found that the evaluated DIRs in this work did not necessarily outperform rigid registration. DIR performed better for bony structures than soft-tissue organs, and the DIR performance tended to vary for different ROIs with different degrees of deformation as the treatment proceeded. Generally, the optical flow-based DIR performed best, while the demons-based DIR usually ranked last except for a modified demons-based DISC used for CT-CBCT DIR. These experimental results suggest that the choice of a specific DIR algorithm depends on the image modality, anatomic site, magnitude of deformation and application. Therefore, careful examinations and modifications are required before accepting the auto-propagated contours, especially for automatic re-planning ART systems.

UR - http://www.scopus.com/inward/record.url?scp=85017591348&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85017591348&partnerID=8YFLogxK

U2 - 10.1371/journal.pone.0175906

DO - 10.1371/journal.pone.0175906

M3 - Article

VL - 12

JO - PLoS One

JF - PLoS One

SN - 1932-6203

IS - 4

M1 - e0175906

ER -