| HAL : hal-00726197, version 1 |
| Fiche détaillée | Récupérer au format |
|
|
| IEEE Transactions on Medical Imaging 31, 8 (2012) 1651-1660 |
|
|
|
|
| Nonsupervised Ranking of Different Segmentation Approaches: Application to the Estimation of the Left Ventricular Ejection Fraction From Cardiac Cine MRI Sequences |
|
|
| Jessica Lebenberg 1, 2I. Buvat 3 |
|
|
| (30/05/2012) |
|
|
| A statistical methodology is proposed to rank several estimation methods of a relevant clinical parameter when no gold standard is available. Based on a regression without truth method, the proposed approach was applied to rank eightmethods without using any a priori information regarding the reliability of each method and its degree of automation. It was only based on a prior concerning the statistical distribution of the parameter of interest in the database. The ranking of the methods relies on figures of merit derived from the regression and computed using a bootstrap process. The methodology was applied to the estimation of the left ventricular ejection fraction derived from cardiac magnetic resonance images segmented using eight approaches with different degrees of automation: three segmentations were entirely manually performed and the others were variously automated. The ranking of methods was consistent with the expected performance of the estimation methods: the most accurate estimates of the ejection fraction were obtained using manual segmentations. The robustness of the ranking was demonstrated when at least three methods were compared. These results suggest that the proposed statistical approach might be helpful to assess the performance of estimation methods on clinical data for which no gold standard is available. |
|
|
|
|
|
|
|
|
|
|
| 1 : | Laboratoire d'Imagerie Fonctionnelle (LIF) |
| INSERM : U678 – IFR14 – IFR49 – Université Pierre et Marie Curie [UPMC] - Paris VI | |
| 2 : | PRIAM |
| ESME-Sudria | |
| 3 : | Imagerie et Modélisation en Neurobiologie et Cancérologie (IMNC) |
| CNRS : UMR8165 – IN2P3 – Université Paris XI - Paris Sud – Université Paris VII - Paris Diderot | |
| 4 : | Laboratoire Electronique, Informatique et Image (Le2i) |
| Université de Bourgogne – Arts et Métiers ParisTech – CNRS : UMR6306 | |
| 5 : | Centre de recherche en applications et traitement de l'image pour la santé (CREATIS) |
| Institut National des Sciences Appliquées (INSA) – CNRS : UMR5220 – Université Claude Bernard - Lyon I – INSERM : U1044 – Hospices Civils de Lyon | |
| 6 : | Laboratoire d'Informatique Gaspard-Monge (LIGM) |
| Université Paris-Est Marne-la-Vallée (UPEMLV) – ESIEE – Ecole des Ponts ParisTech – Fédération de Recherche Bézout – CNRS : UMR8049 | |
| 7 : | Groupe de Recherche en Informatique, Image, Automatique et Instrumentation de Caen (GREYC) |
| CNRS : UMR6072 – Université de Caen Basse-Normandie – Ecole Nationale Supérieure d'Ingénieurs de Caen | |
| 8 : | Image Science for Interventional Techniques (ISIT) |
| CNRS : UMR6284 – Université d'Auvergne - Clermont-Ferrand I | |
| 9 : | Laboratoire des sciences et matériaux pour l'électronique et d'automatique (LASMEA) |
| CNRS : UMR6602 – Université Blaise Pascal - Clermont-Ferrand II | |
| 10 : | Laboratoire Traitement du Signal et de l'Image (LTSI) |
| INSERM : U1099 – Université de Rennes 1 | |
|
|
|
|
|
|
|
|
| image |
|
|
|
|
| Domaine | : | Informatique/Imagerie médicale |
|
|
| Bootstrap process – cardiac image analysis – left ventricular ejection fraction – nonsupervised segmentation methods ranking – regression without truth |
|
|
| Liste des fichiers attachés à ce document : | |||||
|
|
|
| hal-00726197, version 1 | |
| http://hal.archives-ouvertes.fr/hal-00726197 | |
| oai:hal.archives-ouvertes.fr:hal-00726197 | |
| Contributeur : Alain Lalande | |
| Soumis le : Mercredi 29 Août 2012, 12:08:17 | |
| Dernière modification le : Jeudi 16 Mai 2013, 15:51:06 | |