Label fusion using performance estimation with iterative label selection

T. R. Langerak; U.A.V.D. Heide; I.M. Lips; A.N.T.J. Kotte; M.  van Vulpen; J.P.W. Pluim

doi:10.1109/ISBI.2009.5193270

Label fusion using performance estimation with iterative label selection

T. R. Langerak, U.A.V.D. Heide, I.M. Lips, A.N.T.J. Kotte, M. van Vulpen, J.P.W. Pluim

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

4 Citations (Scopus)

Abstract

Atlas-based segmentation is a well-known method of automatically computing a segmentation. When multiple atlases are available, then each atlas can be used to compute a 'label', which is an estimation of the ground truth segmentation of a target image. By combining these labels, a more accurate approximation of the ground truth segmentation can be made. A common method tocombine labels is the STAPLE algorithm, but this method fails when the performance of the labels highly varies. Other methods select labels based on their estimated performance, but combine them using a simple majority vote procedure. In this paper, a simpler variant of the STAPLE algorithm is presented that iteratively selects labels. Results are given that show that the proposed method outperforms STAPLE in an application to segmentation of the prostate.

Original language	English
Title of host publication	Proceedings - 2009 IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2009
Place of Publication	Piscataway
Publisher	Institute of Electrical and Electronics Engineers
Pages	1186-1189
Number of pages	4
ISBN (Print)	978-1-4244-3931-7
DOIs	https://doi.org/10.1109/ISBI.2009.5193270
Publication status	Published - 2009
Externally published	Yes
Event	6th IEEE International Symposium on Biomedical Imaging (ISBI 2009) - Boston, United States Duration: 28 Jun 2009 → 1 Jul 2009 Conference number: 6 http://www.biomedicalimaging.org/archive/2009/

Conference

Conference	6th IEEE International Symposium on Biomedical Imaging (ISBI 2009)
Abbreviated title	ISBI 2009
Country/Territory	United States
City	Boston
Period	28/06/09 → 1/07/09
Other	"From Nano to Macro"
Internet address	http://www.biomedicalimaging.org/archive/2009/

Keywords

Atlas-based segmentation
Classifier combination
Label fusion
Prostate
STAPLE

Access to Document

10.1109/ISBI.2009.5193270

Cite this

Langerak, T. R., Heide, U. A. V. D., Lips, I. M., Kotte, A. N. T. J., van Vulpen, M., & Pluim, J. P. W. (2009). Label fusion using performance estimation with iterative label selection. In Proceedings - 2009 IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2009 (pp. 1186-1189). Article 5193270 Institute of Electrical and Electronics Engineers. https://doi.org/10.1109/ISBI.2009.5193270

@inproceedings{1dfd4a0ceea34d86b54d8dbb172ffdb0,

title = "Label fusion using performance estimation with iterative label selection",

abstract = "Atlas-based segmentation is a well-known method of automatically computing a segmentation. When multiple atlases are available, then each atlas can be used to compute a 'label', which is an estimation of the ground truth segmentation of a target image. By combining these labels, a more accurate approximation of the ground truth segmentation can be made. A common method tocombine labels is the STAPLE algorithm, but this method fails when the performance of the labels highly varies. Other methods select labels based on their estimated performance, but combine them using a simple majority vote procedure. In this paper, a simpler variant of the STAPLE algorithm is presented that iteratively selects labels. Results are given that show that the proposed method outperforms STAPLE in an application to segmentation of the prostate.",

keywords = "Atlas-based segmentation, Classifier combination, Label fusion, Prostate, STAPLE",

author = "Langerak, {T. R.} and U.A.V.D. Heide and I.M. Lips and A.N.T.J. Kotte and {van Vulpen}, M. and J.P.W. Pluim",

year = "2009",

doi = "10.1109/ISBI.2009.5193270",

language = "English",

isbn = "978-1-4244-3931-7",

pages = "1186--1189",

booktitle = "Proceedings - 2009 IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2009",

publisher = "Institute of Electrical and Electronics Engineers",

address = "United States",

note = "6th IEEE International Symposium on Biomedical Imaging (ISBI 2009), ISBI 2009 ; Conference date: 28-06-2009 Through 01-07-2009",

url = "http://www.biomedicalimaging.org/archive/2009/",

}

Langerak, TR, Heide, UAVD, Lips, IM, Kotte, ANTJ, van Vulpen, M & Pluim, JPW 2009, Label fusion using performance estimation with iterative label selection. in Proceedings - 2009 IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2009., 5193270, Institute of Electrical and Electronics Engineers, Piscataway, pp. 1186-1189, 6th IEEE International Symposium on Biomedical Imaging (ISBI 2009), Boston, Massachusetts, United States, 28/06/09. https://doi.org/10.1109/ISBI.2009.5193270

Label fusion using performance estimation with iterative label selection. / Langerak, T. R.; Heide, U.A.V.D.; Lips, I.M. et al.
Proceedings - 2009 IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2009. Piscataway: Institute of Electrical and Electronics Engineers, 2009. p. 1186-1189 5193270.

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

TY - GEN

T1 - Label fusion using performance estimation with iterative label selection

AU - Langerak, T. R.

AU - Heide, U.A.V.D.

AU - Lips, I.M.

AU - Kotte, A.N.T.J.

AU - van Vulpen, M.

AU - Pluim, J.P.W.

N1 - Conference code: 6

PY - 2009

Y1 - 2009

N2 - Atlas-based segmentation is a well-known method of automatically computing a segmentation. When multiple atlases are available, then each atlas can be used to compute a 'label', which is an estimation of the ground truth segmentation of a target image. By combining these labels, a more accurate approximation of the ground truth segmentation can be made. A common method tocombine labels is the STAPLE algorithm, but this method fails when the performance of the labels highly varies. Other methods select labels based on their estimated performance, but combine them using a simple majority vote procedure. In this paper, a simpler variant of the STAPLE algorithm is presented that iteratively selects labels. Results are given that show that the proposed method outperforms STAPLE in an application to segmentation of the prostate.

AB - Atlas-based segmentation is a well-known method of automatically computing a segmentation. When multiple atlases are available, then each atlas can be used to compute a 'label', which is an estimation of the ground truth segmentation of a target image. By combining these labels, a more accurate approximation of the ground truth segmentation can be made. A common method tocombine labels is the STAPLE algorithm, but this method fails when the performance of the labels highly varies. Other methods select labels based on their estimated performance, but combine them using a simple majority vote procedure. In this paper, a simpler variant of the STAPLE algorithm is presented that iteratively selects labels. Results are given that show that the proposed method outperforms STAPLE in an application to segmentation of the prostate.

KW - Atlas-based segmentation

KW - Classifier combination

KW - Label fusion

KW - Prostate

KW - STAPLE

UR - http://www.scopus.com/inward/record.url?scp=70449386873&partnerID=8YFLogxK

U2 - 10.1109/ISBI.2009.5193270

DO - 10.1109/ISBI.2009.5193270

M3 - Conference contribution

AN - SCOPUS:70449386873

SN - 978-1-4244-3931-7

SP - 1186

EP - 1189

BT - Proceedings - 2009 IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2009

PB - Institute of Electrical and Electronics Engineers

CY - Piscataway

T2 - 6th IEEE International Symposium on Biomedical Imaging (ISBI 2009)

Y2 - 28 June 2009 through 1 July 2009

ER -

Langerak TR, Heide UAVD, Lips IM, Kotte ANTJ, van Vulpen M, Pluim JPW. Label fusion using performance estimation with iterative label selection. In Proceedings - 2009 IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2009. Piscataway: Institute of Electrical and Electronics Engineers. 2009. p. 1186-1189. 5193270 doi: 10.1109/ISBI.2009.5193270

Label fusion using performance estimation with iterative label selection

Abstract

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this