Unsupervised tumour segmentation in PET based on local and global intensity fitting active surface and alpha matting

Ziming Zeng; Tony Shepherd; Reyer Zwiggelaar

doi:10.1109/EMBC.2012.6346432

Unsupervised tumour segmentation in PET based on local and global intensity fitting active surface and alpha matting

Ziming Zeng, Tony Shepherd, Reyer Zwiggelaar

Adran Cyfrifiadureg

Allbwn ymchwil: Pennod mewn Llyfr/Adroddiad/Trafodion Cynhadledd › Trafodion Cynhadledd (Nid-Cyfnodolyn fathau)

2 Dyfyniadau (Scopus)

Crynodeb

This paper proposes an unsupervised tumour segmentation scheme for PET data. The method computes the volume of interests (VOIs) with subpixel precision by considering the limited resolution and partial volume effect. Firstly, it uses local and global intensity active surface modelling to segment VOIs, then an alpha matting method is used to eliminate false negative classification and refine the segmentation results. We have validated our method on real PET images of head-and-neck cancer patients as well as images of a custom designed PET phantom. Experiments show that our method can generate more accurate segmentation results compared with alternative approaches.

Iaith wreiddiol	Saesneg
Teitl	2012 Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2012
Is-deitl	EMBC 2012
Cyhoeddwr	IEEE Press
Tudalennau	2339-2342
Nifer y tudalennau	4
ISBN (Electronig)	978-1-4577-1787-1
ISBN (Argraffiad)	978-1-4244-4119-8
Dynodwyr Gwrthrych Digidol (DOIs)	https://doi.org/10.1109/EMBC.2012.6346432
Statws	Cyhoeddwyd - 28 Awst 2012

Cyfres gyhoeddiadau

Enw	Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS
ISSN (Argraffiad)	1557-170X

NDC y CU

Mae’r allbwn hwn yn cyfrannu at y Nod(au) Datblygu Cynaliadwy canlynol

Mynediad at Ddogfen

10.1109/EMBC.2012.6346432

Cysylltiad parhaol

Dolen barhaus

Ffeiliau eraill a chysylltiadau

Dolen i’r cyhoeddiad yn Scopus

Dyfynnu hyn

Zeng, Z., Shepherd, T., & Zwiggelaar, R. (2012). Unsupervised tumour segmentation in PET based on local and global intensity fitting active surface and alpha matting. Yn 2012 Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2012: EMBC 2012 (tt. 2339-2342). erthygl 6346432 (Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS). IEEE Press. https://doi.org/10.1109/EMBC.2012.6346432

Zeng, Ziming ; Shepherd, Tony ; Zwiggelaar, Reyer. / Unsupervised tumour segmentation in PET based on local and global intensity fitting active surface and alpha matting. 2012 Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2012: EMBC 2012. IEEE Press, 2012. tt. 2339-2342 (Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS).

@inproceedings{7dde0817529f4b0bb3d6fba2e769727d,

title = "Unsupervised tumour segmentation in PET based on local and global intensity fitting active surface and alpha matting",

abstract = "This paper proposes an unsupervised tumour segmentation scheme for PET data. The method computes the volume of interests (VOIs) with subpixel precision by considering the limited resolution and partial volume effect. Firstly, it uses local and global intensity active surface modelling to segment VOIs, then an alpha matting method is used to eliminate false negative classification and refine the segmentation results. We have validated our method on real PET images of head-and-neck cancer patients as well as images of a custom designed PET phantom. Experiments show that our method can generate more accurate segmentation results compared with alternative approaches.",

author = "Ziming Zeng and Tony Shepherd and Reyer Zwiggelaar",

year = "2012",

month = aug,

day = "28",

doi = "10.1109/EMBC.2012.6346432",

language = "English",

isbn = "978-1-4244-4119-8",

series = "Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS",

publisher = "IEEE Press",

pages = "2339--2342",

booktitle = "2012 Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2012",

address = "United States of America",

}

Zeng, Z, Shepherd, T & Zwiggelaar, R 2012, Unsupervised tumour segmentation in PET based on local and global intensity fitting active surface and alpha matting. yn 2012 Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2012: EMBC 2012., 6346432, Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS, IEEE Press, tt. 2339-2342. https://doi.org/10.1109/EMBC.2012.6346432

Unsupervised tumour segmentation in PET based on local and global intensity fitting active surface and alpha matting. / Zeng, Ziming; Shepherd, Tony; Zwiggelaar, Reyer.
2012 Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2012: EMBC 2012. IEEE Press, 2012. t. 2339-2342 6346432 (Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS).

Allbwn ymchwil: Pennod mewn Llyfr/Adroddiad/Trafodion Cynhadledd › Trafodion Cynhadledd (Nid-Cyfnodolyn fathau)

TY - GEN

T1 - Unsupervised tumour segmentation in PET based on local and global intensity fitting active surface and alpha matting

AU - Zeng, Ziming

AU - Shepherd, Tony

AU - Zwiggelaar, Reyer

PY - 2012/8/28

Y1 - 2012/8/28

N2 - This paper proposes an unsupervised tumour segmentation scheme for PET data. The method computes the volume of interests (VOIs) with subpixel precision by considering the limited resolution and partial volume effect. Firstly, it uses local and global intensity active surface modelling to segment VOIs, then an alpha matting method is used to eliminate false negative classification and refine the segmentation results. We have validated our method on real PET images of head-and-neck cancer patients as well as images of a custom designed PET phantom. Experiments show that our method can generate more accurate segmentation results compared with alternative approaches.

AB - This paper proposes an unsupervised tumour segmentation scheme for PET data. The method computes the volume of interests (VOIs) with subpixel precision by considering the limited resolution and partial volume effect. Firstly, it uses local and global intensity active surface modelling to segment VOIs, then an alpha matting method is used to eliminate false negative classification and refine the segmentation results. We have validated our method on real PET images of head-and-neck cancer patients as well as images of a custom designed PET phantom. Experiments show that our method can generate more accurate segmentation results compared with alternative approaches.

UR - http://www.scopus.com/inward/record.url?scp=84880941404&partnerID=8YFLogxK

U2 - 10.1109/EMBC.2012.6346432

DO - 10.1109/EMBC.2012.6346432

M3 - Conference Proceeding (Non-Journal item)

SN - 978-1-4244-4119-8

T3 - Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS

SP - 2339

EP - 2342

BT - 2012 Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2012

PB - IEEE Press

ER -

Zeng Z, Shepherd T, Zwiggelaar R. Unsupervised tumour segmentation in PET based on local and global intensity fitting active surface and alpha matting. Yn 2012 Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2012: EMBC 2012. IEEE Press. 2012. t. 2339-2342. 6346432. (Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS). doi: 10.1109/EMBC.2012.6346432

Unsupervised tumour segmentation in PET based on local and global intensity fitting active surface and alpha matting

Crynodeb

Cyfres gyhoeddiadau

NDC y CU

Mynediad at Ddogfen

Cysylltiad parhaol

Ffeiliau eraill a chysylltiadau

Ôl bys

Dyfynnu hyn