WE‐C‐I‐609‐10: A Feasibility Study of Atlas‐Based Image Segmentation in 3D Treatment Planning

T. Zhang, H. Shah, I. Nelson, Wolfgang A. Tome, B. Paliwal

Research output: Contribution to journalArticle

Abstract

Purpose: To develop and evaluate a fully automatic atlas‐based image segmentation method for radiotherapy treatment planning. Method and Materials: A very important part of 3‐dimensional radiotherapy treatment planning is the contouring of normal regions of interests (ROIs). Currently, automatic image segmentation tools provided in treatment planning systems are usually based on edge detection and may not always be satisfactory. Atlas‐based image segmentation is a promising method that uses deformable image registration to register the target images with reference images containing previously contoured ROIs. Atlas‐based image segmentation utilizes all of the information in the images and has the potential to perform better than edge‐detection based algorithms, in which only the edge information is used. The performance of atlas‐based image segmentation relies on the deformable image registration algorithm. We implemented a fast variational deformable image registration algorithm. The algorithm was tested at three common radiotherapy sites: head/neck, chest and pelvis. Physicians manually contoured the ROIs in the reference CT images. The new, randomly selected target images were automatically contoured. The results were evaluated by the physicians. Results: The entire process was completed in less than 15 minutes using a single CPU computer. The ROI masks were transformed into the new images using the displacement maps from deformable image registration. Contours were regenerated from the ROI masks and imported into the Pinnacle™ treatment planning system. In all three clinical sites, the majority of generated ROI's required only minor further modifications. Conclusions: Atlas‐based image segmentation is a powerful automatic contouring tool. Our algorithm provides excellent results in a majority of clinical cases. Implementation of atlas‐based image segmentation may reduce the time required by physicians to contour normal structure ROI's in treatment planning. Additionally, it opens up the possibility of standardizing ROI contours, such as the parotid, in head and neck IMRT.

Original languageEnglish (US)
Pages (from-to)2122
Number of pages1
JournalMedical Physics
Volume32
Issue number6
DOIs
StatePublished - 2005
Externally publishedYes

Fingerprint

Feasibility Studies
Radiotherapy
Masks
Physicians
Neck
Head
Therapeutics
Pelvis
Thorax

ASJC Scopus subject areas

  • Biophysics
  • Radiology Nuclear Medicine and imaging

Cite this

WE‐C‐I‐609‐10 : A Feasibility Study of Atlas‐Based Image Segmentation in 3D Treatment Planning. / Zhang, T.; Shah, H.; Nelson, I.; Tome, Wolfgang A.; Paliwal, B.

In: Medical Physics, Vol. 32, No. 6, 2005, p. 2122.

Research output: Contribution to journalArticle

@article{c414282947ce4fff8babd3f7a766a515,
title = "WE‐C‐I‐609‐10: A Feasibility Study of Atlas‐Based Image Segmentation in 3D Treatment Planning",
abstract = "Purpose: To develop and evaluate a fully automatic atlas‐based image segmentation method for radiotherapy treatment planning. Method and Materials: A very important part of 3‐dimensional radiotherapy treatment planning is the contouring of normal regions of interests (ROIs). Currently, automatic image segmentation tools provided in treatment planning systems are usually based on edge detection and may not always be satisfactory. Atlas‐based image segmentation is a promising method that uses deformable image registration to register the target images with reference images containing previously contoured ROIs. Atlas‐based image segmentation utilizes all of the information in the images and has the potential to perform better than edge‐detection based algorithms, in which only the edge information is used. The performance of atlas‐based image segmentation relies on the deformable image registration algorithm. We implemented a fast variational deformable image registration algorithm. The algorithm was tested at three common radiotherapy sites: head/neck, chest and pelvis. Physicians manually contoured the ROIs in the reference CT images. The new, randomly selected target images were automatically contoured. The results were evaluated by the physicians. Results: The entire process was completed in less than 15 minutes using a single CPU computer. The ROI masks were transformed into the new images using the displacement maps from deformable image registration. Contours were regenerated from the ROI masks and imported into the Pinnacle™ treatment planning system. In all three clinical sites, the majority of generated ROI's required only minor further modifications. Conclusions: Atlas‐based image segmentation is a powerful automatic contouring tool. Our algorithm provides excellent results in a majority of clinical cases. Implementation of atlas‐based image segmentation may reduce the time required by physicians to contour normal structure ROI's in treatment planning. Additionally, it opens up the possibility of standardizing ROI contours, such as the parotid, in head and neck IMRT.",
author = "T. Zhang and H. Shah and I. Nelson and Tome, {Wolfgang A.} and B. Paliwal",
year = "2005",
doi = "10.1118/1.1998501",
language = "English (US)",
volume = "32",
pages = "2122",
journal = "Medical Physics",
issn = "0094-2405",
publisher = "AAPM - American Association of Physicists in Medicine",
number = "6",

}

TY - JOUR

T1 - WE‐C‐I‐609‐10

T2 - A Feasibility Study of Atlas‐Based Image Segmentation in 3D Treatment Planning

AU - Zhang, T.

AU - Shah, H.

AU - Nelson, I.

AU - Tome, Wolfgang A.

AU - Paliwal, B.

PY - 2005

Y1 - 2005

N2 - Purpose: To develop and evaluate a fully automatic atlas‐based image segmentation method for radiotherapy treatment planning. Method and Materials: A very important part of 3‐dimensional radiotherapy treatment planning is the contouring of normal regions of interests (ROIs). Currently, automatic image segmentation tools provided in treatment planning systems are usually based on edge detection and may not always be satisfactory. Atlas‐based image segmentation is a promising method that uses deformable image registration to register the target images with reference images containing previously contoured ROIs. Atlas‐based image segmentation utilizes all of the information in the images and has the potential to perform better than edge‐detection based algorithms, in which only the edge information is used. The performance of atlas‐based image segmentation relies on the deformable image registration algorithm. We implemented a fast variational deformable image registration algorithm. The algorithm was tested at three common radiotherapy sites: head/neck, chest and pelvis. Physicians manually contoured the ROIs in the reference CT images. The new, randomly selected target images were automatically contoured. The results were evaluated by the physicians. Results: The entire process was completed in less than 15 minutes using a single CPU computer. The ROI masks were transformed into the new images using the displacement maps from deformable image registration. Contours were regenerated from the ROI masks and imported into the Pinnacle™ treatment planning system. In all three clinical sites, the majority of generated ROI's required only minor further modifications. Conclusions: Atlas‐based image segmentation is a powerful automatic contouring tool. Our algorithm provides excellent results in a majority of clinical cases. Implementation of atlas‐based image segmentation may reduce the time required by physicians to contour normal structure ROI's in treatment planning. Additionally, it opens up the possibility of standardizing ROI contours, such as the parotid, in head and neck IMRT.

AB - Purpose: To develop and evaluate a fully automatic atlas‐based image segmentation method for radiotherapy treatment planning. Method and Materials: A very important part of 3‐dimensional radiotherapy treatment planning is the contouring of normal regions of interests (ROIs). Currently, automatic image segmentation tools provided in treatment planning systems are usually based on edge detection and may not always be satisfactory. Atlas‐based image segmentation is a promising method that uses deformable image registration to register the target images with reference images containing previously contoured ROIs. Atlas‐based image segmentation utilizes all of the information in the images and has the potential to perform better than edge‐detection based algorithms, in which only the edge information is used. The performance of atlas‐based image segmentation relies on the deformable image registration algorithm. We implemented a fast variational deformable image registration algorithm. The algorithm was tested at three common radiotherapy sites: head/neck, chest and pelvis. Physicians manually contoured the ROIs in the reference CT images. The new, randomly selected target images were automatically contoured. The results were evaluated by the physicians. Results: The entire process was completed in less than 15 minutes using a single CPU computer. The ROI masks were transformed into the new images using the displacement maps from deformable image registration. Contours were regenerated from the ROI masks and imported into the Pinnacle™ treatment planning system. In all three clinical sites, the majority of generated ROI's required only minor further modifications. Conclusions: Atlas‐based image segmentation is a powerful automatic contouring tool. Our algorithm provides excellent results in a majority of clinical cases. Implementation of atlas‐based image segmentation may reduce the time required by physicians to contour normal structure ROI's in treatment planning. Additionally, it opens up the possibility of standardizing ROI contours, such as the parotid, in head and neck IMRT.

UR - http://www.scopus.com/inward/record.url?scp=85024821850&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85024821850&partnerID=8YFLogxK

U2 - 10.1118/1.1998501

DO - 10.1118/1.1998501

M3 - Article

AN - SCOPUS:85024821850

VL - 32

SP - 2122

JO - Medical Physics

JF - Medical Physics

SN - 0094-2405

IS - 6

ER -