Physically-primed deep-neural-networks for generalized undersampled MRI reconstruction
AssigneeTechnion Research & Development Foundation Limited
InventorsMordechay Pinchas Freiman, Nitzan Avidan
Life of this patent
Estimating the term…
Abstract
A method for reconstructing spatial information, the method includes: (i) Obtaining an under-sampled frequency domain representation (FDR) of the spatial information. The under-sampled FDR was obtained by sampling an FDR of the spatial information with a sampling mask. (ii) Feeding the under-sampled FDR and the sampling mask to a machine learning process. (iii) Reconstructing the spatial information by the machine learning process. The machine learning process was trained using a training data set that includes training under-sampled FRDs of training spatial information, and one or more training sampling masks that were used to sample FDRs of training spatial information.
Claims20
A method for reconstructing spatial information, the method comprises:
- obtaining an frequency domain representation (FDR) of the spatial information, wherein the under-sampled FDR was obtained by sampling an FDR of the spatial information with a sampling mask;
- feeding the under-sampled FDR and the sampling mask to a machine learning process;
- and
- reconstructing the spatial information by the machine learning process;
- wherein the machine learning process was trained using a training data set that comprises training undersampled FDRs of training spatial information, and one or more training sampling masks that were used to sample FDRs of training spatial information.
A non-transitory computer readable medium for reconstructing spatial information, the non-transitory computer readable medium stores instructions for:
- obtaining an frequency domain representation (FDR) of the spatial information, wherein the under-sampled FDR was obtained by sampling an FDR of the spatial information with a sampling mask;
- feeding the under-sampled FDR and the sampling mask to a machine learning process;
- and
- reconstructing the spatial information by the machine learning process;
- wherein the machine learning process was trained using a training data set that comprises training undersampled FDRs of training spatial information, and one or more training sampling masks that were used to sample FDRs of training spatial information.
A computerized system comprises a processor that is configured to:
- obtain an frequency domain representation (FDR) of the spatial information, wherein the under-sampled FDR was obtained by sampling an FDR of the spatial information with a sampling mask;
- implement a machine learning process that once fed with the under-sampled FDR and the sampling mask, reconstructs the spatial information;
- wherein the machine learning process was trained using a training data set that comprises training undersampled FDRs of training spatial information, and one or more training sampling masks that were used to sample FDRs of training spatial information.
Dependencies are inferred from the claim text.