Learning Fourier-Constrained Diffusion Bridges for MRI Reconstruction

Deep generative models have gained recent traction in accelerated MRI reconstruction. Diffusion priors are particularly promising given their representational fidelity. Instead of the target transformation from undersampled to fully-sampled data required for MRI reconstruction, common diffusion prio...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	arXiv.org 2023-12
Hauptverfasser:	Mirza, Muhammad U, Onat Dalmaz, Bedel, Hasan A, Gokberk Elmas, Korkmaz, Yilmaz, Gungor, Alper, Salman UH Dar, Çukur, Tolga
Format:	Artikel
Sprache:	eng
Schlagworte:	Accuracy Degradation Image reconstruction Magnetic resonance imaging Normality Random noise Sampled data Transformations
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!