Automated contouring error detection based on supervised geometric attribute distribution models for radiation therapy: A general strategy

Hsin Chen Chen, Jun Tan, Steven Dolly, James Kavanaugh, Mark A. Anastasio, Daniel A. Low, H. Harold Li, Michael Altman, Hiram Gay, Wade L. Thorstad, Sasa Mutic, Hua Li

Research output: Contribution to journalArticle

11 Citations (Scopus)

Abstract

Purpose: One of the most critical steps in radiation therapy treatment is accurate tumor and critical organ-at-risk (OAR) contouring. Both manual and automated contouring processes are prone to errors and to a large degree of inter- and intraobserver variability. These are often due to the limitations of imaging techniques in visualizing human anatomy as well as to inherent anatomical variability among individuals. Physicians/physicists have to reverify all the radiation therapy contours of every patient before using them for treatment planning, which is tedious, laborious, and still not an error-free process. In this study, the authors developed a general strategy based on novel geometric attribute distribution (GAD) models to automatically detect radiation therapy OAR contouring errors and facilitate the current clinical workflow. Methods: Considering the radiation therapy structures geometric attributes (centroid, volume, and shape), the spatial relationship of neighboring structures, as well as anatomical similarity of individual contours among patients, the authors established GAD models to characterize the interstructural centroid and volume variations, and the intrastructural shape variations of each individual structure. The GAD models are scalable and deformable, and constrained by their respective principal attribute variations calculated from training sets with verified OAR contours. A new iterative weighted GAD model-fitting algorithm was developed for contouring error detection. Receiver operating characteristic (ROC) analysis was employed in a unique way to optimize the model parameters to satisfy clinical requirements. A total of forty-four head-and-neck patient cases, each of which includes nine critical OAR contours, were utilized to demonstrate the proposed strategy. Twenty-nine out of these forty-four patient cases were utilized to train the inter- and intrastructural GAD models. These training data and the remaining fifteen testing data sets were separately employed to test the effectiveness of the proposed contouring error detection strategy. Results: An evaluation tool was implemented to illustrate how the proposed strategy automatically detects the radiation therapy contouring errors for a given patient and provides 3D graphical visualization of error detection results as well. The contouring error detection results were achieved with an average sensitivity of 0.954/0.906 and an average specificity of 0.901/0.909 on the centroid/volume related contouring errors of all the tested samples. As for the detection results on structural shape related contouring errors, an average sensitivity of 0.816 and an average specificity of 0.94 on all the tested samples were obtained. The promising results indicated the feasibility of the proposed strategy for the detection of contouring errors with low false detection rate. Conclusions: The proposed strategy can reliably identify contouring errors based upon inter- and intrastructural constraints derived from clinically approved contours. It holds great potential for improving the radiation therapy workflow. ROC and box plot analyses allow for analytically tuning of the system parameters to satisfy clinical requirements. Future work will focus on the improvement of strategy reliability by utilizing more training sets and additional geometric attribute constraints.

Original languageEnglish (US)
Pages (from-to)1048-1059
Number of pages12
JournalMedical Physics
Volume42
Issue number2
DOIs
StatePublished - Feb 1 2015

Fingerprint

Organs at Risk
Radiotherapy
Workflow
ROC Curve
Observer Variation
Anatomy
Neck
Head
Physicians
Therapeutics
Neoplasms

Keywords

  • attribute distribution model
  • contouring error detection
  • geometric attribute
  • principal component analysis
  • radiation therapy

ASJC Scopus subject areas

  • Biophysics
  • Radiology Nuclear Medicine and imaging

Cite this

Automated contouring error detection based on supervised geometric attribute distribution models for radiation therapy : A general strategy. / Chen, Hsin Chen; Tan, Jun; Dolly, Steven; Kavanaugh, James; Anastasio, Mark A.; Low, Daniel A.; Harold Li, H.; Altman, Michael; Gay, Hiram; Thorstad, Wade L.; Mutic, Sasa; Li, Hua.

In: Medical Physics, Vol. 42, No. 2, 01.02.2015, p. 1048-1059.

Research output: Contribution to journalArticle

Chen, HC, Tan, J, Dolly, S, Kavanaugh, J, Anastasio, MA, Low, DA, Harold Li, H, Altman, M, Gay, H, Thorstad, WL, Mutic, S & Li, H 2015, 'Automated contouring error detection based on supervised geometric attribute distribution models for radiation therapy: A general strategy', Medical Physics, vol. 42, no. 2, pp. 1048-1059. https://doi.org/10.1118/1.4906197
Chen, Hsin Chen ; Tan, Jun ; Dolly, Steven ; Kavanaugh, James ; Anastasio, Mark A. ; Low, Daniel A. ; Harold Li, H. ; Altman, Michael ; Gay, Hiram ; Thorstad, Wade L. ; Mutic, Sasa ; Li, Hua. / Automated contouring error detection based on supervised geometric attribute distribution models for radiation therapy : A general strategy. In: Medical Physics. 2015 ; Vol. 42, No. 2. pp. 1048-1059.
@article{2d4484a600924ec783e289c6cc0bd80e,
title = "Automated contouring error detection based on supervised geometric attribute distribution models for radiation therapy: A general strategy",
abstract = "Purpose: One of the most critical steps in radiation therapy treatment is accurate tumor and critical organ-at-risk (OAR) contouring. Both manual and automated contouring processes are prone to errors and to a large degree of inter- and intraobserver variability. These are often due to the limitations of imaging techniques in visualizing human anatomy as well as to inherent anatomical variability among individuals. Physicians/physicists have to reverify all the radiation therapy contours of every patient before using them for treatment planning, which is tedious, laborious, and still not an error-free process. In this study, the authors developed a general strategy based on novel geometric attribute distribution (GAD) models to automatically detect radiation therapy OAR contouring errors and facilitate the current clinical workflow. Methods: Considering the radiation therapy structures geometric attributes (centroid, volume, and shape), the spatial relationship of neighboring structures, as well as anatomical similarity of individual contours among patients, the authors established GAD models to characterize the interstructural centroid and volume variations, and the intrastructural shape variations of each individual structure. The GAD models are scalable and deformable, and constrained by their respective principal attribute variations calculated from training sets with verified OAR contours. A new iterative weighted GAD model-fitting algorithm was developed for contouring error detection. Receiver operating characteristic (ROC) analysis was employed in a unique way to optimize the model parameters to satisfy clinical requirements. A total of forty-four head-and-neck patient cases, each of which includes nine critical OAR contours, were utilized to demonstrate the proposed strategy. Twenty-nine out of these forty-four patient cases were utilized to train the inter- and intrastructural GAD models. These training data and the remaining fifteen testing data sets were separately employed to test the effectiveness of the proposed contouring error detection strategy. Results: An evaluation tool was implemented to illustrate how the proposed strategy automatically detects the radiation therapy contouring errors for a given patient and provides 3D graphical visualization of error detection results as well. The contouring error detection results were achieved with an average sensitivity of 0.954/0.906 and an average specificity of 0.901/0.909 on the centroid/volume related contouring errors of all the tested samples. As for the detection results on structural shape related contouring errors, an average sensitivity of 0.816 and an average specificity of 0.94 on all the tested samples were obtained. The promising results indicated the feasibility of the proposed strategy for the detection of contouring errors with low false detection rate. Conclusions: The proposed strategy can reliably identify contouring errors based upon inter- and intrastructural constraints derived from clinically approved contours. It holds great potential for improving the radiation therapy workflow. ROC and box plot analyses allow for analytically tuning of the system parameters to satisfy clinical requirements. Future work will focus on the improvement of strategy reliability by utilizing more training sets and additional geometric attribute constraints.",
keywords = "attribute distribution model, contouring error detection, geometric attribute, principal component analysis, radiation therapy",
author = "Chen, {Hsin Chen} and Jun Tan and Steven Dolly and James Kavanaugh and Anastasio, {Mark A.} and Low, {Daniel A.} and {Harold Li}, H. and Michael Altman and Hiram Gay and Thorstad, {Wade L.} and Sasa Mutic and Hua Li",
year = "2015",
month = "2",
day = "1",
doi = "10.1118/1.4906197",
language = "English (US)",
volume = "42",
pages = "1048--1059",
journal = "Medical Physics",
issn = "0094-2405",
publisher = "AAPM - American Association of Physicists in Medicine",
number = "2",

}

TY - JOUR

T1 - Automated contouring error detection based on supervised geometric attribute distribution models for radiation therapy

T2 - A general strategy

AU - Chen, Hsin Chen

AU - Tan, Jun

AU - Dolly, Steven

AU - Kavanaugh, James

AU - Anastasio, Mark A.

AU - Low, Daniel A.

AU - Harold Li, H.

AU - Altman, Michael

AU - Gay, Hiram

AU - Thorstad, Wade L.

AU - Mutic, Sasa

AU - Li, Hua

PY - 2015/2/1

Y1 - 2015/2/1

N2 - Purpose: One of the most critical steps in radiation therapy treatment is accurate tumor and critical organ-at-risk (OAR) contouring. Both manual and automated contouring processes are prone to errors and to a large degree of inter- and intraobserver variability. These are often due to the limitations of imaging techniques in visualizing human anatomy as well as to inherent anatomical variability among individuals. Physicians/physicists have to reverify all the radiation therapy contours of every patient before using them for treatment planning, which is tedious, laborious, and still not an error-free process. In this study, the authors developed a general strategy based on novel geometric attribute distribution (GAD) models to automatically detect radiation therapy OAR contouring errors and facilitate the current clinical workflow. Methods: Considering the radiation therapy structures geometric attributes (centroid, volume, and shape), the spatial relationship of neighboring structures, as well as anatomical similarity of individual contours among patients, the authors established GAD models to characterize the interstructural centroid and volume variations, and the intrastructural shape variations of each individual structure. The GAD models are scalable and deformable, and constrained by their respective principal attribute variations calculated from training sets with verified OAR contours. A new iterative weighted GAD model-fitting algorithm was developed for contouring error detection. Receiver operating characteristic (ROC) analysis was employed in a unique way to optimize the model parameters to satisfy clinical requirements. A total of forty-four head-and-neck patient cases, each of which includes nine critical OAR contours, were utilized to demonstrate the proposed strategy. Twenty-nine out of these forty-four patient cases were utilized to train the inter- and intrastructural GAD models. These training data and the remaining fifteen testing data sets were separately employed to test the effectiveness of the proposed contouring error detection strategy. Results: An evaluation tool was implemented to illustrate how the proposed strategy automatically detects the radiation therapy contouring errors for a given patient and provides 3D graphical visualization of error detection results as well. The contouring error detection results were achieved with an average sensitivity of 0.954/0.906 and an average specificity of 0.901/0.909 on the centroid/volume related contouring errors of all the tested samples. As for the detection results on structural shape related contouring errors, an average sensitivity of 0.816 and an average specificity of 0.94 on all the tested samples were obtained. The promising results indicated the feasibility of the proposed strategy for the detection of contouring errors with low false detection rate. Conclusions: The proposed strategy can reliably identify contouring errors based upon inter- and intrastructural constraints derived from clinically approved contours. It holds great potential for improving the radiation therapy workflow. ROC and box plot analyses allow for analytically tuning of the system parameters to satisfy clinical requirements. Future work will focus on the improvement of strategy reliability by utilizing more training sets and additional geometric attribute constraints.

AB - Purpose: One of the most critical steps in radiation therapy treatment is accurate tumor and critical organ-at-risk (OAR) contouring. Both manual and automated contouring processes are prone to errors and to a large degree of inter- and intraobserver variability. These are often due to the limitations of imaging techniques in visualizing human anatomy as well as to inherent anatomical variability among individuals. Physicians/physicists have to reverify all the radiation therapy contours of every patient before using them for treatment planning, which is tedious, laborious, and still not an error-free process. In this study, the authors developed a general strategy based on novel geometric attribute distribution (GAD) models to automatically detect radiation therapy OAR contouring errors and facilitate the current clinical workflow. Methods: Considering the radiation therapy structures geometric attributes (centroid, volume, and shape), the spatial relationship of neighboring structures, as well as anatomical similarity of individual contours among patients, the authors established GAD models to characterize the interstructural centroid and volume variations, and the intrastructural shape variations of each individual structure. The GAD models are scalable and deformable, and constrained by their respective principal attribute variations calculated from training sets with verified OAR contours. A new iterative weighted GAD model-fitting algorithm was developed for contouring error detection. Receiver operating characteristic (ROC) analysis was employed in a unique way to optimize the model parameters to satisfy clinical requirements. A total of forty-four head-and-neck patient cases, each of which includes nine critical OAR contours, were utilized to demonstrate the proposed strategy. Twenty-nine out of these forty-four patient cases were utilized to train the inter- and intrastructural GAD models. These training data and the remaining fifteen testing data sets were separately employed to test the effectiveness of the proposed contouring error detection strategy. Results: An evaluation tool was implemented to illustrate how the proposed strategy automatically detects the radiation therapy contouring errors for a given patient and provides 3D graphical visualization of error detection results as well. The contouring error detection results were achieved with an average sensitivity of 0.954/0.906 and an average specificity of 0.901/0.909 on the centroid/volume related contouring errors of all the tested samples. As for the detection results on structural shape related contouring errors, an average sensitivity of 0.816 and an average specificity of 0.94 on all the tested samples were obtained. The promising results indicated the feasibility of the proposed strategy for the detection of contouring errors with low false detection rate. Conclusions: The proposed strategy can reliably identify contouring errors based upon inter- and intrastructural constraints derived from clinically approved contours. It holds great potential for improving the radiation therapy workflow. ROC and box plot analyses allow for analytically tuning of the system parameters to satisfy clinical requirements. Future work will focus on the improvement of strategy reliability by utilizing more training sets and additional geometric attribute constraints.

KW - attribute distribution model

KW - contouring error detection

KW - geometric attribute

KW - principal component analysis

KW - radiation therapy

UR - http://www.scopus.com/inward/record.url?scp=84923348233&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84923348233&partnerID=8YFLogxK

U2 - 10.1118/1.4906197

DO - 10.1118/1.4906197

M3 - Article

C2 - 25652517

AN - SCOPUS:84923348233

VL - 42

SP - 1048

EP - 1059

JO - Medical Physics

JF - Medical Physics

SN - 0094-2405

IS - 2

ER -