Using simulated CBCT images in deep learning methods for real CBCT segmentation - LATIM - IMT Atlantique Accéder directement au contenu
Poster De Conférence Année : 2022

Using simulated CBCT images in deep learning methods for real CBCT segmentation

Résumé

Purpose or Objective Segmenting organs in Cone-Beam CT (CBCT) images would allow to adapt the dose delivered based on the organ deformations that occured between the treatment fractions. However, this is a difficult task because of the relative lack of contrast in CBCT images, leading to high inter-observer variability. Deep-learning based automatic segmentation approaches have shown impressive successes and may be of interest here but required to train a convolutional neural network (CNN) from a database of segmented CBCT images, which can be difficult to obtain. In this work, we propose to train a CNN from a database of artificial CBCT images simulated from planning CT for which it is easier to obtain the organ delineations.
Fichier non déposé

Dates et versions

hal-03706427 , version 1 (27-06-2022)

Identifiants

  • HAL Id : hal-03706427 , version 1

Citer

Nelly Abbani, Franklin Okoli, Vincent Jaouen, Julien Bert, David Sarrut. Using simulated CBCT images in deep learning methods for real CBCT segmentation. Estro 2022, May 2022, Copenhagen/ Virtual, Denmark. ⟨hal-03706427⟩
57 Consultations
0 Téléchargements

Partager

Gmail Facebook X LinkedIn More