A Cautionary Analysis of STAPLE Using Direct Inference of Segmentation Truth

Koen Van Leemput, Mert R. Sabuncu

Research output: Chapter in Book/Report/Conference proceedingArticle in proceedingsResearchpeer-review

Abstract

In this paper we analyze the properties of the well-known segmentation fusion algorithm STAPLE, using a novel inference technique that analytically marginalizes out all model parameters. We demonstrate both theoretically and empirically that when the number of raters is large, or when consensus regions are included in the model, STAPLE devolves into thresholding the average of the input segmentations. We further show that when the number of raters is small, the STAPLE result may not be the optimal segmentation truth estimate, and its model parameter estimates might not reflect the individual raters’ actual segmentation performance. Our experiments indicate that these intrinsic weaknesses are frequently exacerbated by the presence of undesirable global optima and convergence issues. Together these results cast doubt on the soundness and usefulness of typical STAPLE outcomes.
Original languageEnglish
Title of host publicationProceedings of the 17th International Conference Medical Image Computing and Computer-Assisted Intervention (MICCAI 2014) : Part I
PublisherSpringer
Publication date2014
Pages398-406
ISBN (Print)978-3-319-10403-4
ISBN (Electronic)978-3-319-10404-1
DOIs
Publication statusPublished - 2014
Event17th International Conference on Medical Image Computing and Computer Assisted Intervention - Massachusetts Institute of Technology, Cambridge, MA, Boston, United States
Duration: 14 Sep 201418 Sep 2014
Conference number: 17
http://miccai2014.org/
http://miccai2014.org/cfp.html

Conference

Conference17th International Conference on Medical Image Computing and Computer Assisted Intervention
Number17
LocationMassachusetts Institute of Technology, Cambridge, MA
CountryUnited States
CityBoston
Period14/09/201418/09/2014
Internet address
SeriesLecture Notes in Computer Science
Volume8673
ISSN0302-9743

Fingerprint Dive into the research topics of 'A Cautionary Analysis of STAPLE Using Direct Inference of Segmentation Truth'. Together they form a unique fingerprint.

Cite this