Unsupervised resolution-agnostic quantitative susceptibility mapping using adaptive instance normalization

•Unsupervised deep learning with physical model for quantitative susceptibility mapping.•Adaptive instance normalization allows resolution-agnostic reconstruction.•The proposed method is generalizable to various resolution data without streaking artifacts. [Display omitted] Quantitative susceptibili...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	Medical image analysis 2022-07, Vol.79, p.102477-102477, Article 102477
Hauptverfasser:	Oh, Gyutaek, Bae, Hyokyoung, Ahn, Hyun-Seo, Park, Sung-Hong, Moon, Won-Jin, Ye, Jong Chul
Format:	Artikel
Sprache:	eng
Schlagworte:	Adaptive instance normalization Deep learning Dipoles Image reconstruction Kernels Magnetic permeability Magnetic resonance imaging Magnetic susceptibility Mapping Medical imaging Phase matching Quantitative susceptibility mapping Resolution-agnostic Spatial distribution Teaching methods Unsupervised deep learning
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Schreiben Sie den ersten Kommentar!