Semi-automatic segmentation of tongue tumors from magnetic resonance imaging

Trushali Doshi; John Soraghan; Lykourgos Petropoulakis; Derek Gross; Kenneth MacKenzie

doi:10.1109/IWSSIP.2013.6623474

Semi-automatic segmentation of tongue tumors from magnetic resonance imaging

Trushali Doshi, John Soraghan, Lykourgos Petropoulakis, Derek Gross, Kenneth MacKenzie

Electronic And Electrical Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution book

5 Citations (Scopus)

Abstract

Radiation therapy is one of the most effective modalities for treatment of tongue cancer. In order to optimize radiation dose to the tumor region, it is necessary to segment the tumor from normal region. This paper presents a new semiautomatic algorithm that is demonstrated to be able to segment tongue tumor from gadolinium-enhanced T1-weighted magnetic resonance imaging (MRI) to support radiation planning. This algorithm takes sequential MRI slices with visible tongue tumor. The Tumor's region from each slice is segmented using three steps (i) preprocessing, (ii) initialization and (iii) localized region-based level set segmentation. The segmentation results obtained from proposed algorithm are compared with manual segmentation from clinical expert. Results from 9 MRI slices show that there is a good overlap between semi-automatic and manual segmentation results with dice similarity coefficient (DSC) of 0.87±0.05.

Original language	English
Title of host publication	2013 20th International Conference on Systems, Signals and Image Processing (IWSSIP)
Publisher	IEEE
Pages	143-146
Number of pages	4
ISBN (Print)	9781479909414
DOIs	https://doi.org/10.1109/IWSSIP.2013.6623474
Publication status	Published - 9 Nov 2013
Event	2013 20th International Conference on Systems, Signals and Image Processing (IWSSIP) - Bucharest, Romania Duration: 7 Jul 2013 → 9 Jul 2013

Conference

Conference	2013 20th International Conference on Systems, Signals and Image Processing (IWSSIP)
Country/Territory	Romania
City	Bucharest
Period	7/07/13 → 9/07/13

Keywords

biomedical MRI
cancer
image segmentation
image sequences
medical image processing
radiation therapy
set theory
tumours
head
tongue
magnetic resonance imaging

UN SDGs

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

Access to Document

10.1109/IWSSIP.2013.6623474

Cite this

@inproceedings{e976061b33fe41969b66fc848620e75b,

title = "Semi-automatic segmentation of tongue tumors from magnetic resonance imaging",

abstract = "Radiation therapy is one of the most effective modalities for treatment of tongue cancer. In order to optimize radiation dose to the tumor region, it is necessary to segment the tumor from normal region. This paper presents a new semiautomatic algorithm that is demonstrated to be able to segment tongue tumor from gadolinium-enhanced T1-weighted magnetic resonance imaging (MRI) to support radiation planning. This algorithm takes sequential MRI slices with visible tongue tumor. The Tumor's region from each slice is segmented using three steps (i) preprocessing, (ii) initialization and (iii) localized region-based level set segmentation. The segmentation results obtained from proposed algorithm are compared with manual segmentation from clinical expert. Results from 9 MRI slices show that there is a good overlap between semi-automatic and manual segmentation results with dice similarity coefficient (DSC) of 0.87±0.05.",

keywords = "biomedical MRI, cancer, image segmentation, image sequences, medical image processing, radiation therapy, set theory, tumours, head, tongue, magnetic resonance imaging",

author = "Trushali Doshi and John Soraghan and Lykourgos Petropoulakis and Derek Gross and Kenneth MacKenzie",

year = "2013",

month = nov,

day = "9",

doi = "10.1109/IWSSIP.2013.6623474",

language = "English",

isbn = "9781479909414",

pages = "143--146",

booktitle = "2013 20th International Conference on Systems, Signals and Image Processing (IWSSIP)",

publisher = "IEEE",

note = "2013 20th International Conference on Systems, Signals and Image Processing (IWSSIP) ; Conference date: 07-07-2013 Through 09-07-2013",

}

Doshi, T, Soraghan, J, Petropoulakis, L, Gross, D & MacKenzie, K 2013, Semi-automatic segmentation of tongue tumors from magnetic resonance imaging. in 2013 20th International Conference on Systems, Signals and Image Processing (IWSSIP). IEEE, pp. 143-146, 2013 20th International Conference on Systems, Signals and Image Processing (IWSSIP), Bucharest, Romania, 7/07/13. https://doi.org/10.1109/IWSSIP.2013.6623474

TY - GEN

T1 - Semi-automatic segmentation of tongue tumors from magnetic resonance imaging

AU - Doshi, Trushali

AU - Soraghan, John

AU - Petropoulakis, Lykourgos

AU - Gross, Derek

AU - MacKenzie, Kenneth

PY - 2013/11/9

Y1 - 2013/11/9

N2 - Radiation therapy is one of the most effective modalities for treatment of tongue cancer. In order to optimize radiation dose to the tumor region, it is necessary to segment the tumor from normal region. This paper presents a new semiautomatic algorithm that is demonstrated to be able to segment tongue tumor from gadolinium-enhanced T1-weighted magnetic resonance imaging (MRI) to support radiation planning. This algorithm takes sequential MRI slices with visible tongue tumor. The Tumor's region from each slice is segmented using three steps (i) preprocessing, (ii) initialization and (iii) localized region-based level set segmentation. The segmentation results obtained from proposed algorithm are compared with manual segmentation from clinical expert. Results from 9 MRI slices show that there is a good overlap between semi-automatic and manual segmentation results with dice similarity coefficient (DSC) of 0.87±0.05.

AB - Radiation therapy is one of the most effective modalities for treatment of tongue cancer. In order to optimize radiation dose to the tumor region, it is necessary to segment the tumor from normal region. This paper presents a new semiautomatic algorithm that is demonstrated to be able to segment tongue tumor from gadolinium-enhanced T1-weighted magnetic resonance imaging (MRI) to support radiation planning. This algorithm takes sequential MRI slices with visible tongue tumor. The Tumor's region from each slice is segmented using three steps (i) preprocessing, (ii) initialization and (iii) localized region-based level set segmentation. The segmentation results obtained from proposed algorithm are compared with manual segmentation from clinical expert. Results from 9 MRI slices show that there is a good overlap between semi-automatic and manual segmentation results with dice similarity coefficient (DSC) of 0.87±0.05.

KW - biomedical MRI

KW - cancer

KW - image segmentation

KW - image sequences

KW - medical image processing

KW - radiation therapy

KW - set theory

KW - tumours

KW - head

KW - tongue

KW - magnetic resonance imaging

UR - http://ieeexplore.ieee.org/xpl/login.jsp?tp=&arnumber=6623474&url=http%3A%2F%2Fieeexplore.ieee.org%2Fxpls%2Fabs_all.jsp%3Farnumber%3D6623474

U2 - 10.1109/IWSSIP.2013.6623474

DO - 10.1109/IWSSIP.2013.6623474

M3 - Conference contribution book

SN - 9781479909414

SP - 143

EP - 146

BT - 2013 20th International Conference on Systems, Signals and Image Processing (IWSSIP)

PB - IEEE

T2 - 2013 20th International Conference on Systems, Signals and Image Processing (IWSSIP)

Y2 - 7 July 2013 through 9 July 2013

ER -

Semi-automatic segmentation of tongue tumors from magnetic resonance imaging

Abstract

Conference

Keywords

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this