# US 11,308,662 B2 · System and method for image reconstruction > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 11,308,662 B2 - Document ID: US11308662B2 - Status: Granted - Kind: B2 - Application number: 16/448,052 - Filed: 2019-06-21 - Published: 2019-10-31 - Granted: 2022-04-19 - Earliest claimed: 2016-08-02 - Assignees: Shanghai United Imaging Healthcare Co., Ltd. - Applicants: Shanghai United Imaging Healthcare Co., Ltd. - Inventors: Yang Lyu; Yu Ding - Web page: https://patentgrep.com/patent/US11308662B2 ## CPC - G06T 12/20: Inverse problem, i.e. transformations from projection space into object space - G06T 5/50: using two or more images, e.g. averaging or subtraction - G06T 7/11: Region-based segmentation - G06T 7/50: Depth or shape recovery - G06T 2207/10028: Range image; Depth image; 3D point clouds - G06T 2207/10081: Computed x-ray tomography [CT] - G06T 2207/10104: Positron emission tomography [PET] - G06T 2207/10108: Single photon emission computed tomography [SPECT] - G06T 2207/20221: Image fusion; Image merging - G06T 2211/424: Iterative - G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL ## Abstract A system and method for image reconstruction are provided. A first region of an object may be determined. The first region may correspond to a first voxel. A second region of the object may be determined. The second region may correspond to a second voxel. Scan data of the object may be acquired. A first regional image may be reconstructed based on the scan data. The reconstruction of the first regional image may include a forward projection on the first voxel and the second voxel and a back projection on the first voxel. ## Claims ### Claim 1 A method for image reconstruction, comprising: determining an image matrix corresponding to a scanned region; dividing the image matrix into a plurality of sub-image matrixes, each sub-image matrix corresponding to a sub-scanned region of the scanned region; transforming at least one sub-image matrix of the plurality of sub-image matrixes to generate at least one transformed matrix; reconstructing the at least one sub-image matrix based on the at least one transformed matrix by: generating, based on a subset of scan data relating to the scanned region, at least one projection matrix by performing a forward projection on the at least one transformed matrix; generating at least one preliminary matrix by performing a back projection on the at least one projection matrix; inversely rearranging the at least one preliminary matrix; generating a rotated matrix by rotating the at least one rearranged preliminary matrix in a second direction, the second direction being opposite to the first direction; and generating, based on the rotated matrix, the at least one reconstructed sub-image matrix; and reconstructing the image matrix based on the at least one reconstructed sub-image matrix. ### Claim 2 (depends on 1) The method of claim 1, wherein the transforming at least one sub-image matrix includes at least one of compressing the at least one sub-image matrix or rearranging the at least one sub-image matrix. ### Claim 3 (depends on 2) The method of claim 2, further comprising: generating a lookup table that records position information relating to the at least one of the compressing of the at least one sub-image matrix or the rearranging of the at least one sub-image matrix. ### Claim 4 (depends on 3) The method of claim 3, wherein the transforming at least one sub-image matrix of the plurality of sub-image matrixes to generate at least one transformed matrix comprises: compressing the at least one sub-image matrix; rotating the at least one compressed sub-image matrix in a first direction; and generating the at least one transformed matrix by rearranging, based on the lookup table, the at least one rotated compressed sub-image matrix. ### Claim 5 (depends on 1) The method of claim 1, wherein the reconstructing the image matrix based on the at least one reconstructed sub-image matrix includes: decompressing the at least one reconstructed sub-image matrix; and generating, based on the at least one decompressed reconstructed sub-image matrix, the reconstructed image matrix. ### Claim 6 (depends on 5) The method of claim 5, further comprising: determining a main computing node and a plurality of subordinate computing nodes; and for each of the at least one sub-image matrix, assigning a subordinate computing node of the plurality of subordinate computing nodes to the sub-image matrix, wherein: the main computing node is configured to generate the reconstructed image matrix based on the at least one decompressed reconstructed sub-image matrix, and each subordinate computing node is configured to reconstruct the corresponding sub-image matrix. ### Claim 7 (depends on 1) The method of claim 1, wherein the reconstructing the at least one sub-image matrix is performed based on an Ordered Subset Expectation Maximization algorithm. ### Claim 8 A system, comprising: at least one storage device including a set of instructions for image reconstruction; and at least one processor configured to communicate with the at least one storage medium, wherein when executing the set of instructions, the at least one processor is configured to direct the system to perform operations including: determining an image matrix corresponding to a scanned region; dividing the image matrix into a plurality of sub-image matrixes, each sub-image matrix corresponding to a sub-scanned region of the scanned region; transforming at least one sub-image matrix of the plurality of sub-image matrixes to generate at least one transformed matrix; reconstructing the at least one sub-image matrix based on the at least one transformed matrix by: generating, based on a subset of scan data relating to the scanned region, at least one projection matrix by performing a forward projection on the at least one transformed matrix; generating at least one preliminary matrix by performing a back projection on the at least one projection matrix; inversely rearranging the at least one preliminary matrix; generating a rotated matrix by rotating the at least one rearranged preliminary matrix in a second direction, the second direction being opposite to the first direction; and generating, based on the rotated matrix, the at least one reconstructed sub-image matrix; and reconstructing the image matrix based on the at least one reconstructed sub-image matrix. ### Claim 9 (depends on 8) The system of claim 8, wherein the transforming at least one sub-image matrix includes at least one of compressing the at least one sub-image matrix or rearranging the at least one sub-image matrix. ### Claim 10 (depends on 9) The system of claim 9, the at least one processor is further configured to direct the system to perform additional operations including: generating a lookup table that records position information relating to the at least one of the compressing of the at least one sub-image matrix or the rearranging of the at least one sub-image matrix. ### Claim 11 (depends on 10) The system of claim 10, wherein to transform at least one sub-image matrix of the plurality of sub-image matrixes to generate at least one transformed matrix, the at least one processor is further configured to direct the system to perform additional operations including: compressing the at least one sub-image matrix; rotating the at least one compressed sub-image matrix in a first direction; and generating the at least one transformed matrix by rearranging, based on the lookup table, the at least one rotated compressed sub-image matrix. ### Claim 12 (depends on 8) The system of claim 8, wherein to reconstruct the image matrix based on the at least one reconstructed sub-image matrix, the at least one processor is further configured to direct the system to perform additional operations including: decompressing the at least one reconstructed sub-image matrix; and generating, based on the at least one decompressed reconstructed sub-image matrix, the reconstructed image matrix. ### Claim 13 (depends on 12) The system of claim 12, the at least one processor is further configured to direct the system to perform additional operations including: determining a main computing node and a plurality of subordinate computing nodes; and for each of the at least one sub-image matrix, assigning a subordinate computing node of the plurality of subordinate computing nodes to the sub-image matrix, wherein: the main computing node is configured to generate the reconstructed image matrix based on the at least one decompressed reconstructed sub-image matrix, and each subordinate computing node is configured to reconstruct the corresponding sub-image matrix. ### Claim 14 (depends on 8) The system of claim 8, wherein the reconstructing the at least one sub-image matrix is performed based on an Ordered Subset Expectation Maximization algorithm. ### Claim 15 A non-transitory computer readable medium, comprising a set of instructions for image reconstruction, wherein when executed by at least one processor, the set of instructions direct the at least one processor to effectuate a method, the method comprising: determining an image matrix corresponding to a scanned region; dividing the image matrix into a plurality of sub-image matrixes, each sub-image matrix corresponding to a sub-scanned region of the scanned region; transforming at least one sub-image matrix of the plurality of sub-image matrixes to generate at least one transformed matrix; reconstructing the at least one sub-image matrix based on the at least one transformed matrix by: generating, based on a subset of scan data relating to the scanned region, at least one projection matrix by performing a forward projection on the at least one transformed matrix; generating at least one preliminary matrix by performing a back projection on the at least one projection matrix; inversely rearranging the at least one preliminary matrix; generating a rotated matrix by rotating the at least one rearranged preliminary matrix in a second direction, the second direction being opposite to the first direction; and generating, based on the rotated matrix, the at least one reconstructed sub-image matrix; and reconstructing the image matrix based on the at least one reconstructed sub-image matrix. ### Claim 16 (depends on 15) The non-transitory computer readable medium of claim 15, wherein the transforming at least one sub-image matrix includes at least one of compressing the at least one sub-image matrix or rearranging the at least one sub-image matrix.