A multi-institution evaluation of deformable image registration algorithms for automatic organ delineation in adaptive head and neck radiotherapy

Nicholas Hardcastle; Wolfgang A. Tome; Donald M. Cannon; Charlotte L. Brouwer; Paul W. H. Wittendorp; Nesrin Dogan; Matthias Guckenberger; Stephane Allaire; Yogish Mallya; Prashant Kumar; Markus Oechsner; Anne Richter; Shiyu Song; Michael Myers; Buelent Polat; Karl Bzdusek

doi:10.1186/1748-717X-7-90

A multi-institution evaluation of deformable image registration algorithms for automatic organ delineation in adaptive head and neck radiotherapy

Nicholas Hardcastle^*, Wolfgang A. Tome, Donald M. Cannon, Charlotte L. Brouwer, Paul W. H. Wittendorp, Nesrin Dogan, Matthias Guckenberger, Stephane Allaire, Yogish Mallya, Prashant Kumar, Markus Oechsner, Anne Richter, Shiyu Song, Michael Myers, Buelent Polat, Karl Bzdusek

^*Corresponding author for this work

Research output: Contribution to journal › Article › Academic › peer-review

83 Citations (Scopus)

110 Downloads (Pure)

Abstract

Background: Adaptive Radiotherapy aims to identify anatomical deviations during a radiotherapy course and modify the treatment plan to maintain treatment objectives. This requires regions of interest (ROIs) to be defined using the most recent imaging data. This study investigates the clinical utility of using deformable image registration (DIR) to automatically propagate ROIs.

Methods: Target (GTV) and organ-at-risk (OAR) ROIs were non-rigidly propagated from a planning CT scan to a per-treatment CT scan for 22 patients. Propagated ROIs were quantitatively compared with expert physician-drawn ROIs on the per-treatment scan using Dice scores and mean slicewise Hausdorff distances, and center of mass distances for GTVs. The propagated ROIs were qualitatively examined by experts and scored based on their clinical utility.

Results: Good agreement between the DIR-propagated ROIs and expert-drawn ROIs was observed based on the metrics used. 94% of all ROIs generated using DIR were scored as being clinically useful, requiring minimal or no edits. However, 27% (12/44) of the GTVs required major edits.

Conclusion: DIR was successfully used on 22 patients to propagate target and OAR structures for ART with good anatomical agreement for OARs. It is recommended that propagated target structures be thoroughly reviewed by the treating physician.

Original language	English
Article number	90
Number of pages	7
Journal	Radiation oncology
Volume	7
DOIs	https://doi.org/10.1186/1748-717X-7-90
Publication status	Published - 15-Jun-2012

Keywords

Deformable image registration
Adaptive radiotherapy
Head and neck cancer
INTENSITY-MODULATED RADIOTHERAPY
MEGAVOLTAGE COMPUTED-TOMOGRAPHY
CANCER
VARIABILITY
STRATEGIES
RISK

Access to Document

10.1186/1748-717X-7-90Licence: CC BY

A multi-institution evaluationFinal publisher's version, 675 KBLicence: CC BY

Handle.net

Persistent link

Cite this

Hardcastle, N., Tome, W. A., Cannon, D. M., Brouwer, C. L., Wittendorp, P. W. H., Dogan, N., Guckenberger, M., Allaire, S., Mallya, Y., Kumar, P., Oechsner, M., Richter, A., Song, S., Myers, M., Polat, B., & Bzdusek, K. (2012). A multi-institution evaluation of deformable image registration algorithms for automatic organ delineation in adaptive head and neck radiotherapy. Radiation oncology, 7, Article 90. https://doi.org/10.1186/1748-717X-7-90

@article{4c13104b9b7d481e8ef8496ea47f3081,

title = "A multi-institution evaluation of deformable image registration algorithms for automatic organ delineation in adaptive head and neck radiotherapy",

abstract = "Background: Adaptive Radiotherapy aims to identify anatomical deviations during a radiotherapy course and modify the treatment plan to maintain treatment objectives. This requires regions of interest (ROIs) to be defined using the most recent imaging data. This study investigates the clinical utility of using deformable image registration (DIR) to automatically propagate ROIs.Methods: Target (GTV) and organ-at-risk (OAR) ROIs were non-rigidly propagated from a planning CT scan to a per-treatment CT scan for 22 patients. Propagated ROIs were quantitatively compared with expert physician-drawn ROIs on the per-treatment scan using Dice scores and mean slicewise Hausdorff distances, and center of mass distances for GTVs. The propagated ROIs were qualitatively examined by experts and scored based on their clinical utility.Results: Good agreement between the DIR-propagated ROIs and expert-drawn ROIs was observed based on the metrics used. 94% of all ROIs generated using DIR were scored as being clinically useful, requiring minimal or no edits. However, 27% (12/44) of the GTVs required major edits.Conclusion: DIR was successfully used on 22 patients to propagate target and OAR structures for ART with good anatomical agreement for OARs. It is recommended that propagated target structures be thoroughly reviewed by the treating physician.",

keywords = "Deformable image registration, Adaptive radiotherapy, Head and neck cancer, INTENSITY-MODULATED RADIOTHERAPY, MEGAVOLTAGE COMPUTED-TOMOGRAPHY, CANCER, VARIABILITY, STRATEGIES, RISK",

author = "Nicholas Hardcastle and Tome, {Wolfgang A.} and Cannon, {Donald M.} and Brouwer, {Charlotte L.} and Wittendorp, {Paul W. H.} and Nesrin Dogan and Matthias Guckenberger and Stephane Allaire and Yogish Mallya and Prashant Kumar and Markus Oechsner and Anne Richter and Shiyu Song and Michael Myers and Buelent Polat and Karl Bzdusek",

year = "2012",

month = jun,

day = "15",

doi = "10.1186/1748-717X-7-90",

language = "English",

volume = "7",

journal = "Radiation oncology",

issn = "1748-717X",

publisher = "BMC",

}

Hardcastle, N, Tome, WA, Cannon, DM, Brouwer, CL, Wittendorp, PWH, Dogan, N, Guckenberger, M, Allaire, S, Mallya, Y, Kumar, P, Oechsner, M, Richter, A, Song, S, Myers, M, Polat, B & Bzdusek, K 2012, 'A multi-institution evaluation of deformable image registration algorithms for automatic organ delineation in adaptive head and neck radiotherapy', Radiation oncology, vol. 7, 90. https://doi.org/10.1186/1748-717X-7-90

TY - JOUR

T1 - A multi-institution evaluation of deformable image registration algorithms for automatic organ delineation in adaptive head and neck radiotherapy

AU - Hardcastle, Nicholas

AU - Tome, Wolfgang A.

AU - Cannon, Donald M.

AU - Brouwer, Charlotte L.

AU - Wittendorp, Paul W. H.

AU - Dogan, Nesrin

AU - Guckenberger, Matthias

AU - Allaire, Stephane

AU - Mallya, Yogish

AU - Kumar, Prashant

AU - Oechsner, Markus

AU - Richter, Anne

AU - Song, Shiyu

AU - Myers, Michael

AU - Polat, Buelent

AU - Bzdusek, Karl

PY - 2012/6/15

Y1 - 2012/6/15

N2 - Background: Adaptive Radiotherapy aims to identify anatomical deviations during a radiotherapy course and modify the treatment plan to maintain treatment objectives. This requires regions of interest (ROIs) to be defined using the most recent imaging data. This study investigates the clinical utility of using deformable image registration (DIR) to automatically propagate ROIs.Methods: Target (GTV) and organ-at-risk (OAR) ROIs were non-rigidly propagated from a planning CT scan to a per-treatment CT scan for 22 patients. Propagated ROIs were quantitatively compared with expert physician-drawn ROIs on the per-treatment scan using Dice scores and mean slicewise Hausdorff distances, and center of mass distances for GTVs. The propagated ROIs were qualitatively examined by experts and scored based on their clinical utility.Results: Good agreement between the DIR-propagated ROIs and expert-drawn ROIs was observed based on the metrics used. 94% of all ROIs generated using DIR were scored as being clinically useful, requiring minimal or no edits. However, 27% (12/44) of the GTVs required major edits.Conclusion: DIR was successfully used on 22 patients to propagate target and OAR structures for ART with good anatomical agreement for OARs. It is recommended that propagated target structures be thoroughly reviewed by the treating physician.

AB - Background: Adaptive Radiotherapy aims to identify anatomical deviations during a radiotherapy course and modify the treatment plan to maintain treatment objectives. This requires regions of interest (ROIs) to be defined using the most recent imaging data. This study investigates the clinical utility of using deformable image registration (DIR) to automatically propagate ROIs.Methods: Target (GTV) and organ-at-risk (OAR) ROIs were non-rigidly propagated from a planning CT scan to a per-treatment CT scan for 22 patients. Propagated ROIs were quantitatively compared with expert physician-drawn ROIs on the per-treatment scan using Dice scores and mean slicewise Hausdorff distances, and center of mass distances for GTVs. The propagated ROIs were qualitatively examined by experts and scored based on their clinical utility.Results: Good agreement between the DIR-propagated ROIs and expert-drawn ROIs was observed based on the metrics used. 94% of all ROIs generated using DIR were scored as being clinically useful, requiring minimal or no edits. However, 27% (12/44) of the GTVs required major edits.Conclusion: DIR was successfully used on 22 patients to propagate target and OAR structures for ART with good anatomical agreement for OARs. It is recommended that propagated target structures be thoroughly reviewed by the treating physician.

KW - Deformable image registration

KW - Adaptive radiotherapy

KW - Head and neck cancer

KW - INTENSITY-MODULATED RADIOTHERAPY

KW - MEGAVOLTAGE COMPUTED-TOMOGRAPHY

KW - CANCER

KW - VARIABILITY

KW - STRATEGIES

KW - RISK

U2 - 10.1186/1748-717X-7-90

DO - 10.1186/1748-717X-7-90

M3 - Article

SN - 1748-717X

VL - 7

JO - Radiation oncology

JF - Radiation oncology

M1 - 90

ER -

A multi-institution evaluation of deformable image registration algorithms for automatic organ delineation in adaptive head and neck radiotherapy

Abstract

Keywords

Access to Document

Handle.net

Fingerprint

Cite this