Fully 3D Implementation of the End-to-end Deep Image Prior-based PET Image Reconstruction Using Block Iterative Algorithm

Deep image prior (DIP) has recently attracted attention owing to its unsupervised positron emission tomography (PET) image reconstruction, which does not require any prior training dataset. In this paper, we present the first attempt to implement an end-to-end DIP-based fully 3D PET image reconstruc...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	arXiv.org
Hauptverfasser:	Hashimoto, Fumio, Onishi, Yuya, Ote, Kibo, Tashima, Hideaki, Yamaya, Taiga
Format:	Paper
Sprache:	Englisch
Veröffentlicht:	Ithaca Cornell University Library, arXiv.org 22.12.2022
Schlagworte:	Brain Computer simulation Datasets Graphics processing units Image contrast Image enhancement Image quality Image reconstruction Iterative algorithms Iterative methods Medical imaging Monte Carlo simulation Noise (mathematics) Optimization Positron emission Projection model Training
ISSN:	2331-8422
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Schreiben Sie den ersten Kommentar!