Scan-specific artifact reduction in k-space (SPARK) neural networks synergize with physics-based reconstruction to accelerate MRI

Scan-specific artifact reduction in k-space (SPARK) neural networks synergize with physics-based reconstruction to accelerate MRI

Purpose: To develop a scan-specific model that estimates and corrects k-space errors made when reconstructing accelerated MRI data. Methods: Scan-specific artifact reduction in k-space (SPARK) trains a convolutional-neural-network to estimate and correct k-space errors made by an input reconstructio...

Full description

Bibliographic Details
Main Authors: Adalsteinsson, E. (Author), Arefeen, Y. (Author), Beker, O. (Author), Bilgic, B. (Author), Cho, J. (Author), Yu, H. (Author)
Format: Article
Language:English
Published: John Wiley and Sons Inc 2022
Subjects:
accelerated imaging
Accelerated imaging
acceleration
algorithm
Algorithms
Artefact reduction
article
artifact
artifact reduction
Artifacts
Auto calibration
Backpropagation
calibration
Calibration signal
controlled study
Convolution
convolutional neural network
Convolutional neural network
convolutional neural networks
Convolutional neural networks
Errors
Generalized auto-calibrating partially parallel acquisitions
human
Image enhancement
image processing
Image Processing, Computer-Assisted
image quality
image reconstruction
Image reconstruction
Images reconstruction
K-space
machine learning
Magnetic resonance imaging
Magnetic Resonance Imaging
Mean square error
Neural Networks, Computer
nuclear magnetic resonance imaging
parallel imaging
Parallel imaging
physics
Physics
Reconstruction techniques
Online Access:View Fulltext in Publisher

Internet

View Fulltext in Publisher

Similar Items