MRI reconstruction based on neural networks
AssigneeSiemens Healthineers AG
InventorMario Zeller
Life of this patent
Estimating the term…
Abstract
In a method for processing fully sampled k-space MRI imaging data associated with a tissue of interest within a FOV, a neural network may be trained using undersampled k-space MRI imaging data associated with the tissue of interest. At least one subset of the fully sampled k-space MRI imaging data may be obtained based on an input dimension of the trained neural network such that a dimension of each one of the at least one subset is the same as the input dimension. Each one of the at least one subset of the fully sampled k-space MRI imaging data may be processed by the trained neural network, respectively. Spatial domain MRI imaging data associated with the tissue of interest within the FOV may be accordingly determined based on corresponding output of the trained neural network.
Claims15
A computer-implemented method for processing fully sampled k-space magnetic resonance imaging (MRI) imaging data associated with a tissue of interest within a field of view, comprising:
- obtaining, based on an input dimension of a trained neural network, at least one subset of the fully sampled k-space MRI imaging data such that a dimension of each one of the at least one subset is the same as the input dimension, the trained neural network being trained using undersampled k-space MRI imaging data associated with the tissue of interest;
- processing, by the trained neural network, each one of the at least one subset of the fully sampled k-space MRI imaging data, respectively;
- determining spatial domain MRI imaging data associated with the tissue of interest within the field of view based on corresponding output of the trained neural network;
- and
- providing an electronic signal representing the spatial domain MRI imaging data as an output.
A computing device comprising:
- a processor;
- and
- a memory storing program code that when executed by the processor, causes the processor to:
- obtain, based on an input dimension of a trained neural network, at least one subset of the fully sampled k-space MRI imaging data such that a dimension of each one of the at least one subset is the same as the input dimension, the trained neural network being trained using undersampled k-space MRI imaging data associated with a tissue of interest;
- process, using the trained neural network, each one of the at least one subset of the fully sampled k-space MRI imaging data, respectively;
- determine spatial domain MRI imaging data associated with the tissue of interest within a field of view based on corresponding output of the trained neural network;
- and
- generate and provide an electronic signal representing the spatial domain MRI imaging data as an output of the computing device.
Dependencies are inferred from the claim text.