Automatic 3D segmentation of MRI data for detection of head and neck cancerous lymph nodes

Baixiang Zhao; John Soraghan; Gaetano Di Caterina; Lykourgos Petropoulakis; Derek Grose; Trushali Doshi

doi:10.23919/SPA.2018.8563420

Automatic 3D segmentation of MRI data for detection of head and neck cancerous lymph nodes

Baixiang Zhao, John Soraghan, Gaetano Di Caterina, Lykourgos Petropoulakis, Derek Grose, Trushali Doshi

Electronic And Electrical Engineering

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

2 Citations (Scopus)

38 Downloads (Pure)

Abstract

A novel algorithm for automatic 3D segmentation of magnetic resonance imaging (MRI) data for detection of head and neck cancerous lymph nodes (LN)) is presented in this paper. The proposed algorithm pre-processes the MRI data slices to enhance quality and reduce artefacts. A modified Fuzzy c-mean process is performed through all slices, followed by a probability map which refines the clustering results, to detect the approximate position of cancerous lymph nodes. Fourier interpolation is applied to create an isotropic 3D MRI volume. A new 3D level set method segments the tumour from the interpolated MRI volume. The proposed algorithm is tested on synthetic and real MRI data. The results show that the novel cancerous lymph nodes 3D volume extraction algorithm has over 0.9 Dice similarity score on synthetic data and 0.7 on real MRI data. The F-measure is 0.92 on synthetic data and 0.75 on real data.

Original language	English
Title of host publication	2018 Signal Processing
Subtitle of host publication	Algorithms, Architectures, Arrangements, and Applications (SPA)
Place of Publication	Piscataway, NJ
Publisher	IEEE
Pages	298-303
Number of pages	6
ISBN (Electronic)	9788362065332
ISBN (Print)	9788362065318
DOIs	https://doi.org/10.23919/SPA.2018.8563420
Publication status	Published - 6 Dec 2018
Event	Signal Processing Algorithms, Architectures, Arrangements and Applications (SPA) - Poznan, Poland Duration: 19 Sept 2018 → 21 Sept 2018 Conference number: 22 https://zueps41p.cse.put.poznan.pl/

Conference

Conference	Signal Processing Algorithms, Architectures, Arrangements and Applications (SPA)
Country/Territory	Poland
City	Poznan
Period	19/09/18 → 21/09/18
Internet address	https://zueps41p.cse.put.poznan.pl/

Keywords

MRI data
head and neck cancer
modified fuzzy c-mean
probability map
3D level set method

Access to Document

10.23919/SPA.2018.8563420

Zhao-etal-SPA2018-Automatic-3D-segmentation-of-MRI-data-for-detection-of-headAccepted author manuscript, 1.17 MB

Cite this

@inproceedings{62f857a8bfcd4b6e9f987fa724a66a37,

title = "Automatic 3D segmentation of MRI data for detection of head and neck cancerous lymph nodes",

abstract = "A novel algorithm for automatic 3D segmentation of magnetic resonance imaging (MRI) data for detection of head and neck cancerous lymph nodes (LN)) is presented in this paper. The proposed algorithm pre-processes the MRI data slices to enhance quality and reduce artefacts. A modified Fuzzy c-mean process is performed through all slices, followed by a probability map which refines the clustering results, to detect the approximate position of cancerous lymph nodes. Fourier interpolation is applied to create an isotropic 3D MRI volume. A new 3D level set method segments the tumour from the interpolated MRI volume. The proposed algorithm is tested on synthetic and real MRI data. The results show that the novel cancerous lymph nodes 3D volume extraction algorithm has over 0.9 Dice similarity score on synthetic data and 0.7 on real MRI data. The F-measure is 0.92 on synthetic data and 0.75 on real data.",

keywords = "MRI data, head and neck cancer, modified fuzzy c-mean, probability map, 3D level set method",

author = "Baixiang Zhao and John Soraghan and {Di Caterina}, Gaetano and Lykourgos Petropoulakis and Derek Grose and Trushali Doshi",

year = "2018",

month = dec,

day = "6",

doi = "10.23919/SPA.2018.8563420",

language = "English",

isbn = "9788362065318",

pages = "298--303",

booktitle = "2018 Signal Processing",

publisher = "IEEE",

note = "Signal Processing Algorithms, Architectures, Arrangements and Applications (SPA) ; Conference date: 19-09-2018 Through 21-09-2018",

url = "https://zueps41p.cse.put.poznan.pl/",

}

Zhao, B , Soraghan, J , Di Caterina, G, Petropoulakis, L, Grose, D & Doshi, T 2018, Automatic 3D segmentation of MRI data for detection of head and neck cancerous lymph nodes. in 2018 Signal Processing: Algorithms, Architectures, Arrangements, and Applications (SPA). IEEE, Piscataway, NJ, pp. 298-303, Signal Processing Algorithms, Architectures, Arrangements and Applications (SPA), Poznan, Poland, 19/09/18. https://doi.org/10.23919/SPA.2018.8563420

Automatic 3D segmentation of MRI data for detection of head and neck cancerous lymph nodes. / Zhao, Baixiang ; Soraghan, John ; Di Caterina, Gaetano et al.
2018 Signal Processing: Algorithms, Architectures, Arrangements, and Applications (SPA). Piscataway, NJ: IEEE, 2018. p. 298-303.

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

TY - GEN

T1 - Automatic 3D segmentation of MRI data for detection of head and neck cancerous lymph nodes

AU - Zhao, Baixiang

AU - Soraghan, John

AU - Di Caterina, Gaetano

AU - Petropoulakis, Lykourgos

AU - Grose, Derek

AU - Doshi, Trushali

N1 - Conference code: 22

PY - 2018/12/6

Y1 - 2018/12/6

N2 - A novel algorithm for automatic 3D segmentation of magnetic resonance imaging (MRI) data for detection of head and neck cancerous lymph nodes (LN)) is presented in this paper. The proposed algorithm pre-processes the MRI data slices to enhance quality and reduce artefacts. A modified Fuzzy c-mean process is performed through all slices, followed by a probability map which refines the clustering results, to detect the approximate position of cancerous lymph nodes. Fourier interpolation is applied to create an isotropic 3D MRI volume. A new 3D level set method segments the tumour from the interpolated MRI volume. The proposed algorithm is tested on synthetic and real MRI data. The results show that the novel cancerous lymph nodes 3D volume extraction algorithm has over 0.9 Dice similarity score on synthetic data and 0.7 on real MRI data. The F-measure is 0.92 on synthetic data and 0.75 on real data.

AB - A novel algorithm for automatic 3D segmentation of magnetic resonance imaging (MRI) data for detection of head and neck cancerous lymph nodes (LN)) is presented in this paper. The proposed algorithm pre-processes the MRI data slices to enhance quality and reduce artefacts. A modified Fuzzy c-mean process is performed through all slices, followed by a probability map which refines the clustering results, to detect the approximate position of cancerous lymph nodes. Fourier interpolation is applied to create an isotropic 3D MRI volume. A new 3D level set method segments the tumour from the interpolated MRI volume. The proposed algorithm is tested on synthetic and real MRI data. The results show that the novel cancerous lymph nodes 3D volume extraction algorithm has over 0.9 Dice similarity score on synthetic data and 0.7 on real MRI data. The F-measure is 0.92 on synthetic data and 0.75 on real data.

KW - MRI data

KW - head and neck cancer

KW - modified fuzzy c-mean

KW - probability map

KW - 3D level set method

UR - https://zueps41p.cse.put.poznan.pl/

U2 - 10.23919/SPA.2018.8563420

DO - 10.23919/SPA.2018.8563420

M3 - Conference contribution book

SN - 9788362065318

SP - 298

EP - 303

BT - 2018 Signal Processing

PB - IEEE

CY - Piscataway, NJ

T2 - Signal Processing Algorithms, Architectures, Arrangements and Applications (SPA)

Y2 - 19 September 2018 through 21 September 2018

ER -

Automatic 3D segmentation of MRI data for detection of head and neck cancerous lymph nodes

Abstract

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this