Hyperthermia critical tissues automatic segmentation of head and neck CT images using atlas registration and graph cuts

V. Fortunati; R.F. Verhaart; F. van der Lijn; W.J. Niessen; J.F. Veenland; M.M. Paulides; T. van Walsum

doi:10.1109/ISBI.2012.6235902

Hyperthermia critical tissues automatic segmentation of head and neck CT images using atlas registration and graph cuts

V. Fortunati
, R.F. Verhaart
, F. van der Lijn
, W.J. Niessen
, J.F. Veenland
, M.M. Paulides
, T. van Walsum

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

11 Citations (Scopus)

Abstract

Outcome optimization of hyperthermia tumor treatment in the head and neck requires accurate hyperthermia treatment planning. Hyperthermia treatment planning is based on tissue segmentation for 3D patient model generation. We present here an automatic atlas-based segmentation algorithm for the organs at risk from CT images of the head and neck. To overcome the large anatomical variability, atlas registration and intensity-based classification were combined. A cost function composed of an intensity energy term, a spatial prior energy term based on the atlas registration and a regularization term is globally minimized using graph cut. The method was evaluated by measuring Dice similarity coefficient, mean and Hausdorff surface distances with respect to manual delineation. Overall a high correspondence was found with Dice similarity coefficient higher than 0.86 and a mean distance lower than the voxel resolution.

Original language	English
Title of host publication	2012 9th IEEE International Symposium on Biomedical Imaging
Subtitle of host publication	From Nano to Macro, ISBI 2012 - Proceedings
Place of Publication	Piscataway
Publisher	Institute of Electrical and Electronics Engineers
Pages	1683-1686
Number of pages	4
ISBN (Electronic)	978-1-4577-1858-8
ISBN (Print)	978-1-4577-1857-1
DOIs	https://doi.org/10.1109/ISBI.2012.6235902
Publication status	Published - 15 Aug 2012
Externally published	Yes
Event	9th IEEE International Symposium on Biomedical Imaging (ISBI 2012) - Centre de Convencions Internacional de Barcelona, Barcelona, Spain Duration: 2 May 2012 → 5 May 2012 Conference number: 9 https://www.ieee.org/conferences_events/conferences/conferencedetails/index.html?Conf_ID=17944

Conference

Conference	9th IEEE International Symposium on Biomedical Imaging (ISBI 2012)
Abbreviated title	ISBI 2012
Country/Territory	Spain
City	Barcelona
Period	2/05/12 → 5/05/12
Other	"From Nano to Macro"
Internet address	https://www.ieee.org/conferences_events/conferences/conferencedetails/index.html?Conf_ID=17944

Keywords

Atlas-based method
Computed Tomography
Graph-cuts
Hyperthermia
Image segmentation

Access to Document

10.1109/ISBI.2012.6235902

Cite this

Fortunati, V., Verhaart, R. F., van der Lijn, F., Niessen, W. J., Veenland, J. F., Paulides, M. M., & van Walsum, T. (2012). Hyperthermia critical tissues automatic segmentation of head and neck CT images using atlas registration and graph cuts. In 2012 9th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2012 - Proceedings (pp. 1683-1686). Article 6235902 Institute of Electrical and Electronics Engineers. https://doi.org/10.1109/ISBI.2012.6235902

@inproceedings{1288c25b787f4061a9a1f4f4bfae51a6,

title = "Hyperthermia critical tissues automatic segmentation of head and neck CT images using atlas registration and graph cuts",

abstract = "Outcome optimization of hyperthermia tumor treatment in the head and neck requires accurate hyperthermia treatment planning. Hyperthermia treatment planning is based on tissue segmentation for 3D patient model generation. We present here an automatic atlas-based segmentation algorithm for the organs at risk from CT images of the head and neck. To overcome the large anatomical variability, atlas registration and intensity-based classification were combined. A cost function composed of an intensity energy term, a spatial prior energy term based on the atlas registration and a regularization term is globally minimized using graph cut. The method was evaluated by measuring Dice similarity coefficient, mean and Hausdorff surface distances with respect to manual delineation. Overall a high correspondence was found with Dice similarity coefficient higher than 0.86 and a mean distance lower than the voxel resolution.",

keywords = "Atlas-based method, Computed Tomography, Graph-cuts, Hyperthermia, Image segmentation",

author = "V. Fortunati and R.F. Verhaart and \{van der Lijn\}, F. and W.J. Niessen and J.F. Veenland and M.M. Paulides and \{van Walsum\}, T.",

year = "2012",

month = aug,

day = "15",

doi = "10.1109/ISBI.2012.6235902",

language = "English",

isbn = "978-1-4577-1857-1",

pages = "1683--1686",

booktitle = "2012 9th IEEE International Symposium on Biomedical Imaging",

publisher = "Institute of Electrical and Electronics Engineers",

address = "United States",

note = "9th IEEE International Symposium on Biomedical Imaging (ISBI 2012), ISBI 2012 ; Conference date: 02-05-2012 Through 05-05-2012",

url = "https://www.ieee.org/conferences\_events/conferences/conferencedetails/index.html?Conf\_ID=17944",

}

Fortunati, V, Verhaart, RF, van der Lijn, F, Niessen, WJ, Veenland, JF, Paulides, MM & van Walsum, T 2012, Hyperthermia critical tissues automatic segmentation of head and neck CT images using atlas registration and graph cuts. in 2012 9th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2012 - Proceedings., 6235902, Institute of Electrical and Electronics Engineers, Piscataway, pp. 1683-1686, 9th IEEE International Symposium on Biomedical Imaging (ISBI 2012), Barcelona, Spain, 2/05/12. https://doi.org/10.1109/ISBI.2012.6235902

Hyperthermia critical tissues automatic segmentation of head and neck CT images using atlas registration and graph cuts. / Fortunati, V.; Verhaart, R.F.; van der Lijn, F. et al.
2012 9th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2012 - Proceedings. Piscataway: Institute of Electrical and Electronics Engineers, 2012. p. 1683-1686 6235902.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

TY - GEN

T1 - Hyperthermia critical tissues automatic segmentation of head and neck CT images using atlas registration and graph cuts

AU - Fortunati, V.

AU - Verhaart, R.F.

AU - van der Lijn, F.

AU - Niessen, W.J.

AU - Veenland, J.F.

AU - Paulides, M.M.

AU - van Walsum, T.

N1 - Conference code: 9

PY - 2012/8/15

Y1 - 2012/8/15

N2 - Outcome optimization of hyperthermia tumor treatment in the head and neck requires accurate hyperthermia treatment planning. Hyperthermia treatment planning is based on tissue segmentation for 3D patient model generation. We present here an automatic atlas-based segmentation algorithm for the organs at risk from CT images of the head and neck. To overcome the large anatomical variability, atlas registration and intensity-based classification were combined. A cost function composed of an intensity energy term, a spatial prior energy term based on the atlas registration and a regularization term is globally minimized using graph cut. The method was evaluated by measuring Dice similarity coefficient, mean and Hausdorff surface distances with respect to manual delineation. Overall a high correspondence was found with Dice similarity coefficient higher than 0.86 and a mean distance lower than the voxel resolution.

AB - Outcome optimization of hyperthermia tumor treatment in the head and neck requires accurate hyperthermia treatment planning. Hyperthermia treatment planning is based on tissue segmentation for 3D patient model generation. We present here an automatic atlas-based segmentation algorithm for the organs at risk from CT images of the head and neck. To overcome the large anatomical variability, atlas registration and intensity-based classification were combined. A cost function composed of an intensity energy term, a spatial prior energy term based on the atlas registration and a regularization term is globally minimized using graph cut. The method was evaluated by measuring Dice similarity coefficient, mean and Hausdorff surface distances with respect to manual delineation. Overall a high correspondence was found with Dice similarity coefficient higher than 0.86 and a mean distance lower than the voxel resolution.

KW - Atlas-based method

KW - Computed Tomography

KW - Graph-cuts

KW - Hyperthermia

KW - Image segmentation

UR - https://www.scopus.com/pages/publications/84864858828

U2 - 10.1109/ISBI.2012.6235902

DO - 10.1109/ISBI.2012.6235902

M3 - Conference contribution

AN - SCOPUS:84864858828

SN - 978-1-4577-1857-1

SP - 1683

EP - 1686

BT - 2012 9th IEEE International Symposium on Biomedical Imaging

PB - Institute of Electrical and Electronics Engineers

CY - Piscataway

T2 - 9th IEEE International Symposium on Biomedical Imaging (ISBI 2012)

Y2 - 2 May 2012 through 5 May 2012

ER -

Fortunati V, Verhaart RF, van der Lijn F, Niessen WJ, Veenland JF, Paulides MM et al. Hyperthermia critical tissues automatic segmentation of head and neck CT images using atlas registration and graph cuts. In 2012 9th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2012 - Proceedings. Piscataway: Institute of Electrical and Electronics Engineers. 2012. p. 1683-1686. 6235902 doi: 10.1109/ISBI.2012.6235902

Hyperthermia critical tissues automatic segmentation of head and neck CT images using atlas registration and graph cuts

Abstract

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this