Format

Send to

Choose Destination
PLoS One. 2015 Aug 19;10(8):e0135715. doi: 10.1371/journal.pone.0135715. eCollection 2015.

Improved Estimation of Cardiac Function Parameters Using a Combination of Independent Automated Segmentation Results in Cardiovascular Magnetic Resonance Imaging.

Author information

1
Laboratoire d'Imagerie Biomédicale, Institut National de la Santé et de la Recherche Médicale, Centre National de la Recherche Scientifique, Université Pierre et Marie Curie, Paris, France; École Spéciale de Mécanique et d'Électricité-Sudria, Ivry-sur-Seine, France.
2
Laboratoire Electronique, Informatique et Image, Centre National de la Recherche Scientifique, Université de Bourgogne, Dijon, France.
3
Centre de Recherche en Acquisition et Traitement de l'Image pour la Santé, Centre National de la Recherche Scientifique, Institut National de la Santé et de la Recherche Médicale, Institut National des Sciences Appliquées Lyon, Université de Lyon, Villeurbanne, France.
4
Unité d'Imagerie Moléculaire In Vivo, Service Hospitalier Frédéric Joliot, Institut National de la Santé et de la Recherche Médicale, Centre National de la Recherche Scientifique, Commissariat à l'Energie Atomique, Université Paris Sud, Orsay, France.
5
Laboratoire d'Informatique Gaspard Monge, Centre National de la Recherche Scientifique, Université Paris-Est Marne-la-Vallée, École Supérieure d'Ingénieurs en Électrotechnique et Électronique, Marne-la-Vallée, France.
6
Laboratoire d'Imagerie Biomédicale, Institut National de la Santé et de la Recherche Médicale, Centre National de la Recherche Scientifique, Université Pierre et Marie Curie, Paris, France.
7
Groupe de Recherche en Informatique, Image, Automatique et Instrumentation de Caen, Centre National de la Recherche Scientifique, Caen, France.
8
École Spéciale de Mécanique et d'Électricité-Sudria, Ivry-sur-Seine, France.
9
Image Science for Interventional Techniques, Centre National de la Recherche Scientifique, Université d'Auvergne, Clermont-Ferrand, France.
10
Institut Pascal, Centre National de la Recherche Scientifique, Université Blaise Pascal, Clermont-Ferrand, France.
11
Laboratoire de Traitement du Signal et des Images, Institut National de la Santé et de la Recherche Médicale, Université de Rennes, Rennes, France.

Abstract

This work aimed at combining different segmentation approaches to produce a robust and accurate segmentation result. Three to five segmentation results of the left ventricle were combined using the STAPLE algorithm and the reliability of the resulting segmentation was evaluated in comparison with the result of each individual segmentation method. This comparison was performed using a supervised approach based on a reference method. Then, we used an unsupervised statistical evaluation, the extended Regression Without Truth (eRWT) that ranks different methods according to their accuracy in estimating a specific biomarker in a population. The segmentation accuracy was evaluated by estimating six cardiac function parameters resulting from the left ventricle contour delineation using a public cardiac cine MRI database. Eight different segmentation methods, including three expert delineations and five automated methods, were considered, and sixteen combinations of the automated methods using STAPLE were investigated. The supervised and unsupervised evaluations demonstrated that in most cases, STAPLE results provided better estimates than individual automated segmentation methods. Overall, combining different automated segmentation methods improved the reliability of the segmentation result compared to that obtained using an individual method and could achieve the accuracy of an expert.

PMID:
26287691
PMCID:
PMC4545395
DOI:
10.1371/journal.pone.0135715
[Indexed for MEDLINE]
Free PMC Article

Supplemental Content

Full text links

Icon for Public Library of Science Icon for PubMed Central
Loading ...
Support Center