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 proceedingConference contributionAcademicpeer-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 languageEnglish
Title of host publicationProceedings - 2009 IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2009
Place of PublicationPiscataway
PublisherInstitute of Electrical and Electronics Engineers
Pages1186-1189
Number of pages4
ISBN (Print)978-1-4244-3931-7
DOIs
Publication statusPublished - 2009
Externally publishedYes
Event6th IEEE International Symposium on Biomedical Imaging (ISBI 2009) - Boston, United States
Duration: 28 Jun 20091 Jul 2009
Conference number: 6
http://www.biomedicalimaging.org/archive/2009/

Conference

Conference6th IEEE International Symposium on Biomedical Imaging (ISBI 2009)
Abbreviated titleISBI 2009
CountryUnited States
CityBoston
Period28/06/091/07/09
Other"From Nano to Macro"
Internet address

Keywords

  • Atlas-based segmentation
  • Classifier combination
  • Label fusion
  • Prostate
  • STAPLE

Fingerprint Dive into the research topics of 'Label fusion using performance estimation with iterative label selection'. Together they form a unique fingerprint.

  • 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). [5193270] Institute of Electrical and Electronics Engineers. https://doi.org/10.1109/ISBI.2009.5193270