Automatic segmentation of nasopharyngeal carcinoma from CT images: Region growing based technique

Chanon Tatanun; Panrasee Ritthipravat; Thongchai Bhongmakapat; Lojana Tuntiyatorn

doi:10.1109/ICSPS.2010.5555663

Automatic segmentation of nasopharyngeal carcinoma from CT images: Region growing based technique

Chanon Tatanun
, Panrasee Ritthipravat
, Thongchai Bhongmakapat
, Lojana Tuntiyatorn

Mahidol University
Ramathibodi Hospital

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

29 Citations (Scopus)

Abstract

This paper describes a framework for automatic nasopharyngeal carcinoma segmentation from CT images. The proposed technique is based on the Region Growing Method. It is automatic segmentation in which an initial seed is generated without human intervention. The seed is generated from a probabilistic map representing the chances of it being tumor. This map is created from three probabilistic functions based on location of the tumor, intensities, and non-tumor region respectively. The pixel in which the probability is the highest will be selected as potential seeds. Only one representative of these seeds will be selected as an initial seed. Then the seed will be used for region growing subsequently. The experimental results showed that the potential seeds and initial seed were correctly determined with a percentage accuracy of 81.60% and 95.10%. The seed was grown in preprocessed CT images for identifying the nasopharyngeal carcinoma region. The results showed that, perfect match and corresponding ratio were 71.31% and 53.00% respectively

Original language	English
Title of host publication	ICSPS 2010 - Proceedings of the 2010 2nd International Conference on Signal Processing Systems
Pages	V2537-V2541
DOIs	https://doi.org/10.1109/ICSPS.2010.5555663
Publication status	Published - 2010
Event	2010 2nd International Conference on Signal Processing Systems, ICSPS 2010 - Dalian, China Duration: 5 Jul 2010 → 7 Jul 2010

Publication series

Name	ICSPS 2010 - Proceedings of the 2010 2nd International Conference on Signal Processing Systems
Volume	2

Conference

Conference	2010 2nd International Conference on Signal Processing Systems, ICSPS 2010
Country/Territory	China
City	Dalian
Period	5/07/10 → 7/07/10

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 3 Good Health and Well-being

Keywords

Automatic segmentation
Nasopharyngeal carcinoma
Region growing technique

Access to Document

10.1109/ICSPS.2010.5555663

Cite this

Tatanun, C., Ritthipravat, P., Bhongmakapat, T., & Tuntiyatorn, L. (2010). Automatic segmentation of nasopharyngeal carcinoma from CT images: Region growing based technique. In ICSPS 2010 - Proceedings of the 2010 2nd International Conference on Signal Processing Systems (pp. V2537-V2541). Article 5555663 (ICSPS 2010 - Proceedings of the 2010 2nd International Conference on Signal Processing Systems; Vol. 2). https://doi.org/10.1109/ICSPS.2010.5555663

Tatanun, Chanon ; Ritthipravat, Panrasee ; Bhongmakapat, Thongchai et al. / Automatic segmentation of nasopharyngeal carcinoma from CT images : Region growing based technique. ICSPS 2010 - Proceedings of the 2010 2nd International Conference on Signal Processing Systems. 2010. pp. V2537-V2541 (ICSPS 2010 - Proceedings of the 2010 2nd International Conference on Signal Processing Systems).

@inproceedings{431e8a68c5ec4cf7b685720fbdd5e9a8,

title = "Automatic segmentation of nasopharyngeal carcinoma from CT images: Region growing based technique",

abstract = "This paper describes a framework for automatic nasopharyngeal carcinoma segmentation from CT images. The proposed technique is based on the Region Growing Method. It is automatic segmentation in which an initial seed is generated without human intervention. The seed is generated from a probabilistic map representing the chances of it being tumor. This map is created from three probabilistic functions based on location of the tumor, intensities, and non-tumor region respectively. The pixel in which the probability is the highest will be selected as potential seeds. Only one representative of these seeds will be selected as an initial seed. Then the seed will be used for region growing subsequently. The experimental results showed that the potential seeds and initial seed were correctly determined with a percentage accuracy of 81.60\% and 95.10\%. The seed was grown in preprocessed CT images for identifying the nasopharyngeal carcinoma region. The results showed that, perfect match and corresponding ratio were 71.31\% and 53.00\% respectively",

keywords = "Automatic segmentation, Nasopharyngeal carcinoma, Region growing technique",

author = "Chanon Tatanun and Panrasee Ritthipravat and Thongchai Bhongmakapat and Lojana Tuntiyatorn",

year = "2010",

doi = "10.1109/ICSPS.2010.5555663",

language = "English",

isbn = "9781424468911",

series = "ICSPS 2010 - Proceedings of the 2010 2nd International Conference on Signal Processing Systems",

pages = "V2537--V2541",

booktitle = "ICSPS 2010 - Proceedings of the 2010 2nd International Conference on Signal Processing Systems",

note = "2010 2nd International Conference on Signal Processing Systems, ICSPS 2010 ; Conference date: 05-07-2010 Through 07-07-2010",

}

Tatanun, C, Ritthipravat, P , Bhongmakapat, T & Tuntiyatorn, L 2010, Automatic segmentation of nasopharyngeal carcinoma from CT images: Region growing based technique. in ICSPS 2010 - Proceedings of the 2010 2nd International Conference on Signal Processing Systems., 5555663, ICSPS 2010 - Proceedings of the 2010 2nd International Conference on Signal Processing Systems, vol. 2, pp. V2537-V2541, 2010 2nd International Conference on Signal Processing Systems, ICSPS 2010, Dalian, China, 5/07/10. https://doi.org/10.1109/ICSPS.2010.5555663

Automatic segmentation of nasopharyngeal carcinoma from CT images: Region growing based technique. / Tatanun, Chanon; Ritthipravat, Panrasee ; Bhongmakapat, Thongchai et al.
ICSPS 2010 - Proceedings of the 2010 2nd International Conference on Signal Processing Systems. 2010. p. V2537-V2541 5555663 (ICSPS 2010 - Proceedings of the 2010 2nd International Conference on Signal Processing Systems; Vol. 2).

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

TY - GEN

T1 - Automatic segmentation of nasopharyngeal carcinoma from CT images

T2 - 2010 2nd International Conference on Signal Processing Systems, ICSPS 2010

AU - Tatanun, Chanon

AU - Ritthipravat, Panrasee

AU - Bhongmakapat, Thongchai

AU - Tuntiyatorn, Lojana

PY - 2010

Y1 - 2010

N2 - This paper describes a framework for automatic nasopharyngeal carcinoma segmentation from CT images. The proposed technique is based on the Region Growing Method. It is automatic segmentation in which an initial seed is generated without human intervention. The seed is generated from a probabilistic map representing the chances of it being tumor. This map is created from three probabilistic functions based on location of the tumor, intensities, and non-tumor region respectively. The pixel in which the probability is the highest will be selected as potential seeds. Only one representative of these seeds will be selected as an initial seed. Then the seed will be used for region growing subsequently. The experimental results showed that the potential seeds and initial seed were correctly determined with a percentage accuracy of 81.60% and 95.10%. The seed was grown in preprocessed CT images for identifying the nasopharyngeal carcinoma region. The results showed that, perfect match and corresponding ratio were 71.31% and 53.00% respectively

AB - This paper describes a framework for automatic nasopharyngeal carcinoma segmentation from CT images. The proposed technique is based on the Region Growing Method. It is automatic segmentation in which an initial seed is generated without human intervention. The seed is generated from a probabilistic map representing the chances of it being tumor. This map is created from three probabilistic functions based on location of the tumor, intensities, and non-tumor region respectively. The pixel in which the probability is the highest will be selected as potential seeds. Only one representative of these seeds will be selected as an initial seed. Then the seed will be used for region growing subsequently. The experimental results showed that the potential seeds and initial seed were correctly determined with a percentage accuracy of 81.60% and 95.10%. The seed was grown in preprocessed CT images for identifying the nasopharyngeal carcinoma region. The results showed that, perfect match and corresponding ratio were 71.31% and 53.00% respectively

KW - Automatic segmentation

KW - Nasopharyngeal carcinoma

KW - Region growing technique

UR - https://www.scopus.com/pages/publications/77957268388

U2 - 10.1109/ICSPS.2010.5555663

DO - 10.1109/ICSPS.2010.5555663

M3 - Conference contribution

AN - SCOPUS:77957268388

SN - 9781424468911

T3 - ICSPS 2010 - Proceedings of the 2010 2nd International Conference on Signal Processing Systems

SP - V2537-V2541

BT - ICSPS 2010 - Proceedings of the 2010 2nd International Conference on Signal Processing Systems

Y2 - 5 July 2010 through 7 July 2010

ER -

Tatanun C, Ritthipravat P , Bhongmakapat T, Tuntiyatorn L. Automatic segmentation of nasopharyngeal carcinoma from CT images: Region growing based technique. In ICSPS 2010 - Proceedings of the 2010 2nd International Conference on Signal Processing Systems. 2010. p. V2537-V2541. 5555663. (ICSPS 2010 - Proceedings of the 2010 2nd International Conference on Signal Processing Systems). doi: 10.1109/ICSPS.2010.5555663

Automatic segmentation of nasopharyngeal carcinoma from CT images: Region growing based technique

Abstract

Publication series

Conference

UN SDGs

Keywords

Access to Document

Other files and links

Fingerprint

Cite this