Method for high-dimensional image reconstruction using low-dimensional representations and deep learning
A method for MR imaging includes acquiring with an MR imaging apparatus undersampled k-space imaging data having one or more temporal dimensions and two or more spatial dimensions; transforming the undersampled k-space imaging data to image space data using zero-filled or sliding window reconstruction and sensitivity maps; decomposing the image space data into a compressed representation comprising a product of spatial and temporal parts, where the spatial part comprises spatial basis functions and the temporal part comprises temporal basis functions; processing the spatial basis functions and temporal basis functions to produce reconstructed spatial basis functions and reconstructed temporal basis functions, wherein the processing iteratively applies conjugate gradient and convolutional neural network updates using 2D or 3D spatial and 1D temporal networks; and decompressing the reconstructed spatial basis functions and reconstructed temporal basis functions to produce a reconstructed MRI image having one or more temporal dimensions and two or more spatial dimensions.
1. A method for MR imaging, the method comprising:
acquiring with an MR imaging apparatus undersampled k-space imaging data having one or more temporal dimensions and two or more spatial dimensions;
transforming the undersampled k-space imaging data to image space data using zero-filled or sliding window reconstruction and sensitivity maps;
decomposing the image space data into a compressed representation comprising a product of spatial and temporal parts, where the spatial part comprises spatial basis functions and the temporal part comprises temporal basis functions;
processing the spatial basis functions and temporal basis functions to produce reconstructed spatial basis functions and reconstructed temporal basis functions, wherein the processing iteratively applies conjugate gradient and convolutional neural network updates using 2D or 3D spatial and 1D temporal networks;
decompressing the reconstructed spatial basis functions and reconstructed temporal basis functions to produce a reconstructed MRI image having one or more temporal dimensions and two or more spatial dimensions.
2. The method of claim 1 further comprising:
dividing the image space data into image blocks;
wherein decomposing the image space data comprises decomposing the image blocks in a block-wise decomposition, wherein the spatial basis functions and temporal basis functions are block-wise spatial basis functions and block-wise temporal basis functions.
3. A method for MR imaging, the method comprising:
acquiring with an MR imaging apparatus undersampled k-space imaging data;
transforming the undersampled k-space imaging data to image space data;
decomposing the image space data into a compressed representation comprising a product of spatial and temporal parts, where the spatial part comprises spatial basis functions and the temporal part comprises temporal basis functions;
processing the spatial basis functions and temporal basis functions to produce reconstructed spatial basis functions and reconstructed temporal basis functions, wherein the processing iteratively applies conjugate gradient and convolutional neural network updates;
decompressing the reconstructed spatial basis functions and reconstructed temporal basis functions to produce a reconstructed MRI image.