Convergent ADMM Plug and Play PET Image Reconstruction - Archive ouverte HAL Accéder directement au contenu
Proceedings/Recueil Des Communications Année : 2023

Convergent ADMM Plug and Play PET Image Reconstruction

Résumé

In this work, we investigate hybrid PET reconstruction algorithms based on coupling a model-based variational reconstruction and the application of a separately learnt Deep Neural Network operator (DNN) in an ADMM Plug and Play framework. Following recent results in optimization, fixed point convergence of the scheme can be achieved by enforcing an additional constraint on network parameters during learning. We propose such an ADMM algorithm and show in a realistic [ 18 F]-FDG synthetic brain exam that the proposed scheme indeed lead experimentally to convergence to a meaningful fixed point. When the proposed constraint is not enforced during learning of the DNN, the proposed ADMM algorithm was observed experimentally not to converge.
Fichier principal
Vignette du fichier
fully3d_FCSureau_final.pdf (985.51 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04227608 , version 1 (03-10-2023)

Identifiants

Citer

Florent Sureau, Mahdi Latreche, Marion Savanier, Claude Comtat. Convergent ADMM Plug and Play PET Image Reconstruction. 2023. ⟨hal-04227608⟩
34 Consultations
39 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More