Multi-Mask Self-Supervised Learning for Physics-Guided Neural Networks in Highly Accelerated MRI

Self-supervised learning has shown great promise due to its capability to train deep learning MRI reconstruction methods without fully-sampled data. Current self-supervised learning methods for physics-guided reconstruction networks split acquired undersampled data into two disjoint sets, where one...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	arXiv.org 2022-06
Hauptverfasser:	Yaman, Burhaneddin, Gu, Hongyi, Seyed Amir Hossein Hosseini, Demirel, Omer Burak, Moeller, Steen, Ellermann, Jutta, Uğurbil, Kâmil, Akçakaya, Mehmet
Format:	Artikel
Sprache:	eng
Schlagworte:	Brain Computer Science - Computer Vision and Pattern Recognition Computer Science - Learning Data acquisition Deep learning Image reconstruction Knee Magnetic resonance imaging Neural networks Physics - Medical Physics Sampled data Self-supervised learning Training
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!