Label Fusion Strategy Selection

Label fusion is used in medical image segmentation to combine several different labels of the same entity into a single discrete label, potentially more accurate, with respect to the exact, sought segmentation, than the best input element. Using simulated data, we compared three existing label fusio...

Full description

Saved in:
Bibliographic Details
Main Authors: Nicolas Robitaille, Simon Duchesne
Format: Article
Language:English
Published: Wiley 2012-01-01
Series:International Journal of Biomedical Imaging
Online Access:http://dx.doi.org/10.1155/2012/431095
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850157880201707520
author Nicolas Robitaille
Simon Duchesne
author_facet Nicolas Robitaille
Simon Duchesne
author_sort Nicolas Robitaille
collection DOAJ
description Label fusion is used in medical image segmentation to combine several different labels of the same entity into a single discrete label, potentially more accurate, with respect to the exact, sought segmentation, than the best input element. Using simulated data, we compared three existing label fusion techniques—STAPLE, Voting, and Shape-Based Averaging (SBA)—and observed that none could be considered superior depending on the dissimilarity between the input elements. We thus developed an empirical, hybrid technique called SVS, which selects the most appropriate technique to apply based on this dissimilarity. We evaluated the label fusion strategies on two- and three-dimensional simulated data and showed that SVS is superior to any of the three existing methods examined. On real data, we used SVS to perform fusions of 10 segmentations of the hippocampus and amygdala in 78 subjects from the ICBM dataset. SVS selected SBA in almost all cases, which was the most appropriate method overall.
format Article
id doaj-art-6277df7d199a49bcbec07f2b727704ca
institution OA Journals
issn 1687-4188
1687-4196
language English
publishDate 2012-01-01
publisher Wiley
record_format Article
series International Journal of Biomedical Imaging
spelling doaj-art-6277df7d199a49bcbec07f2b727704ca2025-08-20T02:24:01ZengWileyInternational Journal of Biomedical Imaging1687-41881687-41962012-01-01201210.1155/2012/431095431095Label Fusion Strategy SelectionNicolas Robitaille0Simon Duchesne1Centre de Recherche de l'Institut Universitaire en Santé Mentale de Québec, 2601, Chemin de la Canardière, QC, G1J 2G3, CanadaCentre de Recherche de l'Institut Universitaire en Santé Mentale de Québec, 2601, Chemin de la Canardière, QC, G1J 2G3, CanadaLabel fusion is used in medical image segmentation to combine several different labels of the same entity into a single discrete label, potentially more accurate, with respect to the exact, sought segmentation, than the best input element. Using simulated data, we compared three existing label fusion techniques—STAPLE, Voting, and Shape-Based Averaging (SBA)—and observed that none could be considered superior depending on the dissimilarity between the input elements. We thus developed an empirical, hybrid technique called SVS, which selects the most appropriate technique to apply based on this dissimilarity. We evaluated the label fusion strategies on two- and three-dimensional simulated data and showed that SVS is superior to any of the three existing methods examined. On real data, we used SVS to perform fusions of 10 segmentations of the hippocampus and amygdala in 78 subjects from the ICBM dataset. SVS selected SBA in almost all cases, which was the most appropriate method overall.http://dx.doi.org/10.1155/2012/431095
spellingShingle Nicolas Robitaille
Simon Duchesne
Label Fusion Strategy Selection
International Journal of Biomedical Imaging
title Label Fusion Strategy Selection
title_full Label Fusion Strategy Selection
title_fullStr Label Fusion Strategy Selection
title_full_unstemmed Label Fusion Strategy Selection
title_short Label Fusion Strategy Selection
title_sort label fusion strategy selection
url http://dx.doi.org/10.1155/2012/431095
work_keys_str_mv AT nicolasrobitaille labelfusionstrategyselection
AT simonduchesne labelfusionstrategyselection