Deep Learning Segmentation in 2D echocardiography using the CAMUS dataset : Automatic Assessment of the Anatomical Shape Validity - CNRS - Centre national de la recherche scientifique Accéder directement au contenu
Communication Dans Un Congrès Année : 2019

Deep Learning Segmentation in 2D echocardiography using the CAMUS dataset : Automatic Assessment of the Anatomical Shape Validity

Pierre-Marc Jodoin
  • Fonction : Auteur
  • PersonId : 884870

Résumé

We recently published a deep learning study on the potential of encoder-decoder networks for the segmentation of the 2D CAMUS ultrasound dataset. We propose in this abstract an extension of the evaluation criteria to anatomical assessment, as traditional geometric and clinical metrics in cardiac segmentation do not take into account the anatomical correctness of the predicted shapes. The completed study sheds a new light on the ranking of models.
Fichier principal
Vignette du fichier
Leclerc_MIDL2019_final.pdf (983.6 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-02395245 , version 1 (05-12-2019)

Identifiants

  • HAL Id : hal-02395245 , version 1

Citer

Sarah Leclerc, Erik Smistad, Andreas Ostvik, Frederic Cervenansky, Florian Espinosa, et al.. Deep Learning Segmentation in 2D echocardiography using the CAMUS dataset : Automatic Assessment of the Anatomical Shape Validity. International conference on Medical Imaging with Deep Learning (MIDL 2019), Jul 2019, London, United Kingdom. ⟨hal-02395245⟩
125 Consultations
51 Téléchargements

Partager

Gmail Facebook X LinkedIn More