Modified fuzzy c-means clustering for automatic tongue base tumour extraction from MRI data

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

Research output: Chapter in Book/Report/Conference proceedingConference contribution book

7 Citations (Scopus)

Abstract

Magnetic resonance imaging (MRI) is a widely used imaging modality to extract tumour regions to assist in radiotherapy and surgery planning. Extraction of a tongue base tumour from MRI is challenging due to variability in its shape, size, intensities and fuzzy boundaries. This paper presents a new automatic algorithm that is shown to be able to extract tongue base tumour from gadolinium-enhanced T1-weighted (T1+Gd) MRI slices. In this algorithm, knowledge of tumour location is added to the objective function of standard fuzzy c-means (FCM) to extract the tumour region. Experimental results on 9 real MRI slices demonstrate that there is good agreement between manual and automatic extraction results with dice similarity coefficient (DSC) of 0.77±0.08.
LanguageEnglish
Title of host publication2014 Proceedings of the 22nd European Signal Processing Conference (EUSIPCO)
PublisherIEEE
Pages2460 - 2464
Number of pages5
ISBN (Print)9780992862619
Publication statusPublished - 5 Sep 2014
Event22nd European Signal Processing Conference - Lisbon Congress Centre, Lisbon, Portugal
Duration: 1 Sep 20145 Sep 2014
Conference number: 2014

Conference

Conference22nd European Signal Processing Conference
Abbreviated titleEUSIPCO
CountryPortugal
CityLisbon
Period1/09/145/09/14

Fingerprint

Magnetic resonance imaging
Tumors
Gadolinium
Radiotherapy
Surgery
Imaging techniques
Planning

Keywords

  • Hessian analysis
  • MRI
  • automatic tumour extraction
  • fuzzy c-means
  • throat detection
  • magnetic resonance imaging
  • image segmentation
  • clustering algorithms

Cite this

Doshi, T., Soraghan, J., Grose, D., MacKenzie, K., & Petropoulakis, L. (2014). Modified fuzzy c-means clustering for automatic tongue base tumour extraction from MRI data. In 2014 Proceedings of the 22nd European Signal Processing Conference (EUSIPCO) (pp. 2460 - 2464). IEEE.
Doshi, Trushali ; Soraghan, John ; Grose, Derek ; MacKenzie, Kenneth ; Petropoulakis, Lykourgos. / Modified fuzzy c-means clustering for automatic tongue base tumour extraction from MRI data. 2014 Proceedings of the 22nd European Signal Processing Conference (EUSIPCO). IEEE, 2014. pp. 2460 - 2464
@inproceedings{5218f443540e490db5aab0857b8ffbbd,
title = "Modified fuzzy c-means clustering for automatic tongue base tumour extraction from MRI data",
abstract = "Magnetic resonance imaging (MRI) is a widely used imaging modality to extract tumour regions to assist in radiotherapy and surgery planning. Extraction of a tongue base tumour from MRI is challenging due to variability in its shape, size, intensities and fuzzy boundaries. This paper presents a new automatic algorithm that is shown to be able to extract tongue base tumour from gadolinium-enhanced T1-weighted (T1+Gd) MRI slices. In this algorithm, knowledge of tumour location is added to the objective function of standard fuzzy c-means (FCM) to extract the tumour region. Experimental results on 9 real MRI slices demonstrate that there is good agreement between manual and automatic extraction results with dice similarity coefficient (DSC) of 0.77±0.08.",
keywords = "Hessian analysis, MRI, automatic tumour extraction, fuzzy c-means, throat detection, magnetic resonance imaging, image segmentation, clustering algorithms",
author = "Trushali Doshi and John Soraghan and Derek Grose and Kenneth MacKenzie and Lykourgos Petropoulakis",
note = "(c) 2014 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other users, including reprinting/ republishing this material for advertising or promotional purposes, creating new collective works for resale or redistribution to servers or lists, or reuse of any copyrighted components of this work in other works.",
year = "2014",
month = "9",
day = "5",
language = "English",
isbn = "9780992862619",
pages = "2460 -- 2464",
booktitle = "2014 Proceedings of the 22nd European Signal Processing Conference (EUSIPCO)",
publisher = "IEEE",

}

Doshi, T, Soraghan, J, Grose, D, MacKenzie, K & Petropoulakis, L 2014, Modified fuzzy c-means clustering for automatic tongue base tumour extraction from MRI data. in 2014 Proceedings of the 22nd European Signal Processing Conference (EUSIPCO). IEEE, pp. 2460 - 2464, 22nd European Signal Processing Conference, Lisbon, Portugal, 1/09/14.

Modified fuzzy c-means clustering for automatic tongue base tumour extraction from MRI data. / Doshi, Trushali; Soraghan, John; Grose, Derek; MacKenzie, Kenneth; Petropoulakis, Lykourgos.

2014 Proceedings of the 22nd European Signal Processing Conference (EUSIPCO). IEEE, 2014. p. 2460 - 2464.

Research output: Chapter in Book/Report/Conference proceedingConference contribution book

TY - GEN

T1 - Modified fuzzy c-means clustering for automatic tongue base tumour extraction from MRI data

AU - Doshi, Trushali

AU - Soraghan, John

AU - Grose, Derek

AU - MacKenzie, Kenneth

AU - Petropoulakis, Lykourgos

N1 - (c) 2014 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other users, including reprinting/ republishing this material for advertising or promotional purposes, creating new collective works for resale or redistribution to servers or lists, or reuse of any copyrighted components of this work in other works.

PY - 2014/9/5

Y1 - 2014/9/5

N2 - Magnetic resonance imaging (MRI) is a widely used imaging modality to extract tumour regions to assist in radiotherapy and surgery planning. Extraction of a tongue base tumour from MRI is challenging due to variability in its shape, size, intensities and fuzzy boundaries. This paper presents a new automatic algorithm that is shown to be able to extract tongue base tumour from gadolinium-enhanced T1-weighted (T1+Gd) MRI slices. In this algorithm, knowledge of tumour location is added to the objective function of standard fuzzy c-means (FCM) to extract the tumour region. Experimental results on 9 real MRI slices demonstrate that there is good agreement between manual and automatic extraction results with dice similarity coefficient (DSC) of 0.77±0.08.

AB - Magnetic resonance imaging (MRI) is a widely used imaging modality to extract tumour regions to assist in radiotherapy and surgery planning. Extraction of a tongue base tumour from MRI is challenging due to variability in its shape, size, intensities and fuzzy boundaries. This paper presents a new automatic algorithm that is shown to be able to extract tongue base tumour from gadolinium-enhanced T1-weighted (T1+Gd) MRI slices. In this algorithm, knowledge of tumour location is added to the objective function of standard fuzzy c-means (FCM) to extract the tumour region. Experimental results on 9 real MRI slices demonstrate that there is good agreement between manual and automatic extraction results with dice similarity coefficient (DSC) of 0.77±0.08.

KW - Hessian analysis

KW - MRI

KW - automatic tumour extraction

KW - fuzzy c-means

KW - throat detection

KW - magnetic resonance imaging

KW - image segmentation

KW - clustering algorithms

UR - http://www.eusipco2014.org/

UR - http://ieeexplore.ieee.org/xpl/articleDetails.jsp?tp=&arnumber=6952892&openedRefinements%3D*%26filter%3DAND%28NOT%284283010803%29%29%26pageNumber%3D10%26rowsPerPage%3D100%26queryText%3D%28mri%29

M3 - Conference contribution book

SN - 9780992862619

SP - 2460

EP - 2464

BT - 2014 Proceedings of the 22nd European Signal Processing Conference (EUSIPCO)

PB - IEEE

ER -

Doshi T, Soraghan J, Grose D, MacKenzie K, Petropoulakis L. Modified fuzzy c-means clustering for automatic tongue base tumour extraction from MRI data. In 2014 Proceedings of the 22nd European Signal Processing Conference (EUSIPCO). IEEE. 2014. p. 2460 - 2464