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

Jessica Lebenberg; Alain Lalande; Patrick Clarysse; Irene Buvat; Christopher Casta; Alexandre Cochet; Constantin Constantinidès; Jean Cousty; Alain de Cesare; Stéphanie Jehan-Besson; Muriel Lefort; Laurent Najman; Elodie Roullot; Laurent Sarry; Christophe Tilmant; Frouin Frederique; Mireille Garreau

doi:10.1371/journal.pone.0135715

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

Jessica Lebenberg ^{1, 2, *} Alain Lalande ³ Patrick Clarysse ⁴ Irene Buvat ⁵ Christopher Casta ⁴ Alexandre Cochet ³ Constantin Constantinidès ^{1, 2} Jean Cousty ⁶ Alain de Cesare ¹ Stéphanie Jehan-Besson ⁷ Muriel Lefort ¹ Laurent Najman ⁶ Elodie Roullot ² Laurent Sarry ⁸ Christophe Tilmant ⁹ Frouin Frederique ⁵ Mireille Garreau ¹⁰

* Corresponding author

1 LIB - Laboratoire d'Imagerie Biomédicale

2 Ecole spéciale de mécanique et d'électricité - Sudria

3 Le2i - Laboratoire Electronique, Informatique et Image [UMR6303]

4 MOTIVATE - Imagerie et modélisation Vasculaires, Thoraciques et Cérébrales

CREATIS - Centre de Recherche en Acquisition et Traitement de l'Image pour la Santé : 139739

5 Unité d'imagerie moléculaire in vivo

6 ligm - Laboratoire d'Informatique Gaspard-Monge

7 Equipe Image - Laboratoire GREYC - UMR6072

GREYC - Groupe de Recherche en Informatique, Image, Automatique et Instrumentation de Caen

8 ISIT - Image Science for Interventional Techniques

9 IP - Institut Pascal

10 LTSI - Laboratoire Traitement du Signal et de l'Image

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 bio-marker 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 differentautomated 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.

Document type :

Journal articles

Domain :

Life Sciences [q-bio] / Bioengineering

Complete list of metadatas

Cited literature [25 references] Display Hide Download

https://hal.sorbonne-universite.fr/hal-01235953
Contributor : Gestionnaire Hal-Upmc <>
Submitted on : Tuesday, December 1, 2015 - 9:32:28 AM
Last modification on : Thursday, February 20, 2020 - 4:54:28 PM
Long-term archiving on: Friday, April 28, 2017 - 11:29:07 PM

journal.pone.0135715.pdf

Publication funded by an institution

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

File

Licence

Identifiers

Collections

Citation

Export

Metrics

1459

647

Contact

Informations

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

File

Licence

Identifiers

Collections

Citation

Export

Share

Metrics

1459

647

Contact

Informations