Semi-automatic delitneation using weighted CT-MRI registered images for radiotherapy of nasopharyngeal cancer

I. Fitton; S. A. P. Cornelissen; J. C. Duppen; R. J. H. M. Steenbakkers; S. T. H. Peeters; F. J. P. Hoebers; J. H. A. M. Kaanders; P. J. C. M. Nowak; C. R. N. Rasch; M. van Herk

doi:10.1118/1.3611045

Semi-automatic delitneation using weighted CT-MRI registered images for radiotherapy of nasopharyngeal cancer

I. Fitton, S. A. P. Cornelissen, J. C. Duppen, R. J. H. M. Steenbakkers, S. T. H. Peeters, F. J. P. Hoebers, J. H. A. M. Kaanders, P. J. C. M. Nowak, C. R. N. Rasch, M. van Herk^*

^*Corresponding author for this work

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

23 Citations (Scopus)

Abstract

Purpose: To develop a delineation tool that refines physician-drawn contours of the gross tumor volume (GTV) in nasopharynx cancer, using combined pixel value information from x-ray computed tomography (CT) and magnetic resonance imaging (MRI) during delineation.

Methods: Operator-guided delineation assisted by a so-called "snake" algorithm was applied on weighted CT-MRI registered images. The physician delineates a rough tumor contour that is continuously adjusted by the snake algorithm using the underlying image characteristics. The algorithm was evaluated on five nasopharyngeal cancer patients. Different linear weightings CT and MRI were tested as input for the snake algorithm and compared according to contrast and tumor to noise ratio (TNR). The semi-automatic delineation was compared with manual contouring by seven experienced radiation oncologists.

Results: A good compromise for TNR and contrast was obtained by weighing CT twice as strong as MRI. The new algorithm did not notably reduce interobserver variability, it did however, reduce the average delineation time by 6 min per case.

Conclusions: The authors developed a user-driven tool for delineation and correction based a snake algorithm and registered weighted CT image and MRI. The algorithm adds morphological information from CT during the delineation on MRI and accelerates the delineation task. (C) 2011 American Association of Physicists in Medicine. [DOI: 10.1118/1.3611045]

Original language	English
Pages (from-to)	4662-4666
Number of pages	5
Journal	Medical Physics
Volume	38
Issue number	8
DOIs	https://doi.org/10.1118/1.3611045
Publication status	Published - Aug-2011

Keywords

CT-MRI registration
nasopharyngeal carcinoma
snake
active contours
tumor delineation
VOLUME DELINEATION
OBSERVER VARIATION
SEGMENTATION
CARCINOMA
RATIOS
NECK
HEAD

Access to Document

10.1118/1.3611045

Handle.net

Persistent link

Cite this

Fitton, I., Cornelissen, S. A. P., Duppen, J. C., Steenbakkers, R. J. H. M., Peeters, S. T. H., Hoebers, F. J. P., Kaanders, J. H. A. M., Nowak, P. J. C. M., Rasch, C. R. N., & van Herk, M. (2011). Semi-automatic delitneation using weighted CT-MRI registered images for radiotherapy of nasopharyngeal cancer. Medical Physics, 38(8), 4662-4666. https://doi.org/10.1118/1.3611045

@article{37df7df1c0734746b9be8c78f9c3c8be,

title = "Semi-automatic delitneation using weighted CT-MRI registered images for radiotherapy of nasopharyngeal cancer",

abstract = "Purpose: To develop a delineation tool that refines physician-drawn contours of the gross tumor volume (GTV) in nasopharynx cancer, using combined pixel value information from x-ray computed tomography (CT) and magnetic resonance imaging (MRI) during delineation.Methods: Operator-guided delineation assisted by a so-called {"}snake{"} algorithm was applied on weighted CT-MRI registered images. The physician delineates a rough tumor contour that is continuously adjusted by the snake algorithm using the underlying image characteristics. The algorithm was evaluated on five nasopharyngeal cancer patients. Different linear weightings CT and MRI were tested as input for the snake algorithm and compared according to contrast and tumor to noise ratio (TNR). The semi-automatic delineation was compared with manual contouring by seven experienced radiation oncologists.Results: A good compromise for TNR and contrast was obtained by weighing CT twice as strong as MRI. The new algorithm did not notably reduce interobserver variability, it did however, reduce the average delineation time by 6 min per case.Conclusions: The authors developed a user-driven tool for delineation and correction based a snake algorithm and registered weighted CT image and MRI. The algorithm adds morphological information from CT during the delineation on MRI and accelerates the delineation task. (C) 2011 American Association of Physicists in Medicine. [DOI: 10.1118/1.3611045]",

keywords = "CT-MRI registration, nasopharyngeal carcinoma, snake, active contours, tumor delineation, VOLUME DELINEATION, OBSERVER VARIATION, SEGMENTATION, CARCINOMA, RATIOS, NECK, HEAD",

author = "I. Fitton and Cornelissen, {S. A. P.} and Duppen, {J. C.} and Steenbakkers, {R. J. H. M.} and Peeters, {S. T. H.} and Hoebers, {F. J. P.} and Kaanders, {J. H. A. M.} and Nowak, {P. J. C. M.} and Rasch, {C. R. N.} and {van Herk}, M.",

year = "2011",

month = aug,

doi = "10.1118/1.3611045",

language = "English",

volume = "38",

pages = "4662--4666",

journal = "Medical Physics",

issn = "0094-2405",

publisher = "Wiley",

number = "8",

}

TY - JOUR

T1 - Semi-automatic delitneation using weighted CT-MRI registered images for radiotherapy of nasopharyngeal cancer

AU - Fitton, I.

AU - Cornelissen, S. A. P.

AU - Duppen, J. C.

AU - Steenbakkers, R. J. H. M.

AU - Peeters, S. T. H.

AU - Hoebers, F. J. P.

AU - Kaanders, J. H. A. M.

AU - Nowak, P. J. C. M.

AU - Rasch, C. R. N.

AU - van Herk, M.

PY - 2011/8

Y1 - 2011/8

N2 - Purpose: To develop a delineation tool that refines physician-drawn contours of the gross tumor volume (GTV) in nasopharynx cancer, using combined pixel value information from x-ray computed tomography (CT) and magnetic resonance imaging (MRI) during delineation.Methods: Operator-guided delineation assisted by a so-called "snake" algorithm was applied on weighted CT-MRI registered images. The physician delineates a rough tumor contour that is continuously adjusted by the snake algorithm using the underlying image characteristics. The algorithm was evaluated on five nasopharyngeal cancer patients. Different linear weightings CT and MRI were tested as input for the snake algorithm and compared according to contrast and tumor to noise ratio (TNR). The semi-automatic delineation was compared with manual contouring by seven experienced radiation oncologists.Results: A good compromise for TNR and contrast was obtained by weighing CT twice as strong as MRI. The new algorithm did not notably reduce interobserver variability, it did however, reduce the average delineation time by 6 min per case.Conclusions: The authors developed a user-driven tool for delineation and correction based a snake algorithm and registered weighted CT image and MRI. The algorithm adds morphological information from CT during the delineation on MRI and accelerates the delineation task. (C) 2011 American Association of Physicists in Medicine. [DOI: 10.1118/1.3611045]

AB - Purpose: To develop a delineation tool that refines physician-drawn contours of the gross tumor volume (GTV) in nasopharynx cancer, using combined pixel value information from x-ray computed tomography (CT) and magnetic resonance imaging (MRI) during delineation.Methods: Operator-guided delineation assisted by a so-called "snake" algorithm was applied on weighted CT-MRI registered images. The physician delineates a rough tumor contour that is continuously adjusted by the snake algorithm using the underlying image characteristics. The algorithm was evaluated on five nasopharyngeal cancer patients. Different linear weightings CT and MRI were tested as input for the snake algorithm and compared according to contrast and tumor to noise ratio (TNR). The semi-automatic delineation was compared with manual contouring by seven experienced radiation oncologists.Results: A good compromise for TNR and contrast was obtained by weighing CT twice as strong as MRI. The new algorithm did not notably reduce interobserver variability, it did however, reduce the average delineation time by 6 min per case.Conclusions: The authors developed a user-driven tool for delineation and correction based a snake algorithm and registered weighted CT image and MRI. The algorithm adds morphological information from CT during the delineation on MRI and accelerates the delineation task. (C) 2011 American Association of Physicists in Medicine. [DOI: 10.1118/1.3611045]

KW - CT-MRI registration

KW - nasopharyngeal carcinoma

KW - snake

KW - active contours

KW - tumor delineation

KW - VOLUME DELINEATION

KW - OBSERVER VARIATION

KW - SEGMENTATION

KW - CARCINOMA

KW - RATIOS

KW - NECK

KW - HEAD

U2 - 10.1118/1.3611045

DO - 10.1118/1.3611045

M3 - Article

SN - 0094-2405

VL - 38

SP - 4662

EP - 4666

JO - Medical Physics

JF - Medical Physics

IS - 8

ER -

Semi-automatic delitneation using weighted CT-MRI registered images for radiotherapy of nasopharyngeal cancer

Abstract

Keywords

Access to Document

Handle.net

Fingerprint

Cite this