Hierarchical tomographic reconstruction
The present disclosure relates to the use of a hierarchical tomographic reconstruction approach that employs data representations in intermediate steps are between a full line integral and a voxel (e.g., an intermediate line integral). Each of the steps is progressively more local in nature and therefore has computational advantages and is also amenable to a deep learning solution using trained neural networks. The proposed hierarchical structure provides a mechanism to divide a large-scale inverse problem into a series of smaller-scale problems.
1. A hierarchical tomographic reconstruction method, comprising:
acquiring or accessing a set of scan data, wherein the set of scan data is initially represented by a set of original measurements;
processing the set of scan data using a hierarchy of reconstruction steps, wherein at least a portion of the reconstruction steps process the set of original measurements through a progression of one or more intermediate integral representations, wherein at least one of the one or more intermediate integral representation is generated using a subset of the data in the neighboring reconstruction steps;
processing the intermediate integral representations to generate voxel values of a reconstructed image;
wherein the set of original measurements comprises a set of line integrals;
wherein the intermediate integral representations comprise partial line integrals; and
wherein each partial line integral refers to a set of estimated integrals over a partial line through the reconstructed image.
2. The hierarchical tomographic reconstruction method of claim 1 , wherein one or more reconstruction steps of the hierarchy of reconstruction steps processes the set of original measurements or a respective set of intermediate integral representations using a trained neural network.
3. The hierarchical tomographic reconstruction method of claim 2 , wherein the trained neural network comprises a plurality of layers and at least one layer generates one or more intermediate integral representations of the set of original measurements.
4. The hierarchical tomographic reconstruction method of claim 1 , wherein one or more reconstruction steps of the hierarchy of reconstruction steps comprises an iterative reconstruction step.
5. The hierarchical tomographic reconstruction method of claim 1 , wherein one or more reconstruction steps of the hierarchy of reconstruction steps comprises a direct inversion or analytical reconstruction step.
6. The hierarchical tomographic reconstruction method of claim 1 , wherein one or more reconstruction steps of the hierarchy of reconstruction steps comprises a Fourier-based reconstruction step.
7. The hierarchical tomographic reconstruction method of claim 1 , wherein the intermediate line integral representations comprise weighted line integrals.
8. An image processing system comprising:
a processor configured to execute one or more stored processor-executable routines; and
a memory storing the one or more executable-routines, wherein the one or more executable routines, when executed by the processor, cause acts to be performed comprising:
acquiring or accessing a set of scan data, wherein the set of scan data is initially represented by a set of original measurements;
processing the set of scan data using a hierarchy of reconstruction steps, wherein at least a portion of the reconstruction steps process the set of original measurements through a progression of one or more intermediate integral representations, wherein at least one of the one or more intermediate integral representation is generated using a subset of the data in the neighboring reconstruction steps;
processing the intermediate integral representations to generate voxel values of a reconstructed image;
wherein the set of original measurements comprises a set of line integrals;
wherein the intermediate integral representations comprise partial line integrals; and
wherein each partial line integral refers to a set of estimated integrals over a partial line through the reconstructed image.
9. The imaging processing system of claim 8 , wherein the set of scan data comprises computed tomography (CT) scan data, C-arm scan data, positron emission tomography (PET) scan data, single photon emission computed tomography (SPECT) scan data, or magnetic resonance imaging (MRI) scan data.
10. The imaging processing system of claim 8 , wherein one or more reconstruction steps of the hierarchy of reconstruction steps processes the set of original measurements or a respective set of intermediate integral representations using a trained neural network.
11. The imaging processing system of claim 8 , wherein one or more reconstruction steps of the hierarchy of reconstruction steps comprise one or more of: an iterative reconstruction step; a direct inversion or an analytical reconstruction step; or a Fourier-based reconstruction step.
12. The imaging processing system of claim 8 , wherein the intermediate line integral representation comprises weighted line integrals.