# US 11,309,072 B2 · Systems and methods for functional imaging > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 11,309,072 B2 - Document ID: US11309072B2 - Status: Granted - Kind: B2 - Application number: 16/854,603 - Filed: 2020-04-21 - Published: 2021-10-21 - Granted: 2022-04-19 - Earliest claimed: 2020-04-21 - Assignees: GE Precision Healthcare LLC - Applicants: GE Precision Healthcare LLC - Inventors: Raz Carmi - Web page: https://patentgrep.com/patent/US11309072B2 ## CPC - G16H 30/20: for handling medical images, e.g. DICOM, HL7 or PACS - G16H 30/40: for processing medical images, e.g. editing - G06T 7/0012: {Biomedical image inspection} - G06T 12/20: Inverse problem, i.e. transformations from projection space into object space - G06T 2207/20076: Probabilistic image processing - G06T 2207/30024: Cell structures in vitro; Tissue sections in vitro - G16H: HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA - G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL ## Abstract A system includes a structural imaging acquisition unit, a functional imaging acquisition unit, and one or more processors. The structural imaging acquisition unit is configured to perform a structural scan to acquire structural imaging information of a patient. The functional imaging acquisition unit is configured to perform a functional scan to acquire functional imaging information of a patient. The one or more processors are configured to generate a tissue-specific anatomical probability map using the structural imaging information; generate a tissue-non-specific anatomical probability map using the structural imaging information; generate local combined anatomical probability weights using the tissue-specific anatomical probability map, the tissue-non-specific anatomical probability map, and the functional image data; re-distribute the functional image data using the local combined anatomical probability weights to provide re-distributed functional volumetric data; and generate an image using the re-distributed functional volumetric data. ## Claims ### Claim 1 A system comprising: a structural imaging acquisition unit configured to perform a structural scan to acquire structural imaging information of a patient; a functional imaging acquisition unit configured to perform a functional scan to acquire functional imaging information of a patient; one or more processors configured to: generate a tissue-specific anatomical probability map using the structural imaging information; generate a tissue-non-specific anatomical probability map using the structural imaging information; generate local combined anatomical probability weights using the tissue-specific anatomical probability map, the tissue-non-specific anatomical probability map, and the functional image data; re-distribute the functional image data using the local combined anatomical probability weights to provide re-distributed functional volumetric data; and generate an image using the re-distributed functional volumetric data. ### Claim 2 (depends on 1) The system of claim 1, wherein the one or more processors are configured to determine the tissue-specific anatomical probability map using image intensities of the structural imaging information. ### Claim 3 (depends on 1) The system of claim 1, wherein the one or more processors are configured to determine the tissue-non-specific anatomical probability map using image gradients of the structural imaging information. ### Claim 4 (depends on 1) The system of claim 1, wherein the one or more processors are configured to: determine, for a source voxel and a target voxel, a direction of an activity difference; determine a difference on the tissue-non-specific anatomical probability map between the source voxel and the target voxel; if the activity of target voxel is greater than or equal to the activity of the source voxel, assign a positive sign to the difference; and if the activity of the target voxel is less than the activity of the source voxel, assign a negative sign to the difference. ### Claim 5 (depends on 1) The system of claim 1, wherein the one or more processors are configured to perform a multiplication of a tissue-specific probability weight and a tissue-non-specific probability weight to determine the local combined anatomical probability weights. ### Claim 6 (depends on 5) The system of claim 5, wherein the one or more processors are configured to re-distribute the functional volumetric data using the following equation: redistributedActivity=sourceActivity×Wproximity×Wactivity×Wanatomical_combined where: Wanatomical_combined=(Wanatomical_specific+bs)×(Wanatomical_non-specific+bn). ### Claim 7 (depends on 6) The system of claim 6, wherein the constants bs and bn are locally dependent. ### Claim 8 (depends on 1) The system of claim 1, wherein the one or more processors are configured to apply a regularization bias to a tissue-non-specific probability weight. ### Claim 9 A method comprising: obtaining structural imaging information of a patient including anatomical volumetric data; obtaining functional imaging information of the patient including functional volumetric data; generating a tissue-specific anatomical probability map using the structural imaging information; generating a tissue-non-specific anatomical probability map using the structural imaging information; generating local combined anatomical probability weights using the tissue-specific anatomical probability map, the tissue-non-specific anatomical probability map, and the functional image data; re-distributing the functional image data using the local combined anatomical probability weights to provide re-distributed functional volumetric data; and generating an image using the re-distributed functional volumetric data. ### Claim 10 (depends on 9) The method of claim 9, wherein the tissue-specific anatomical probability map is determined using image intensities of the structural imaging information. ### Claim 11 (depends on 9) The method of claim 9, wherein the tissue-non-specific anatomical probability map is determined using image gradients of the structural imaging information. ### Claim 12 (depends on 9) The method of claim 9, further comprising: determining, for a source voxel and a target voxel, a direction of an activity difference; determining a difference on the tissue-non-specific anatomical probability map between the source voxel and the target voxel; if the activity of target voxel is greater than or equal to the activity of the source voxel, assigning a positive sign to the difference; and if the activity of the target voxel is less than the activity of the source voxel, assigning a negative sign to the difference. ### Claim 13 (depends on 9) The method of claim 9, further comprising performing a multiplication of a tissue-specific probability weight and a tissue-non-specific probability weight to determine the local combined anatomical probability weights. ### Claim 14 (depends on 13) The method of claim 13, wherein the functional volumetric data is re-distributed using the following equation: redistributedActivity=sourceActivity×Wproximity×Wactivity×Wanatomical_combined where: Wanatomical_combined=(Wanatomical_specific+bs)×(Wanatomical_non-specific+bn). ### Claim 15 (depends on 14) The method of claim 14, wherein the constants bs and bn are locally dependent. ### Claim 16 (depends on 9) The method of claim 9, further comprising applying a regularization bias to a tissue-non-specific probability weight. ### Claim 17 A tangible and non-transitory computer readable medium comprising one or more computer software modules configured to direct one or more processors to: obtain structural imaging information of a patient including anatomical volumetric data; obtain a functional imaging information of the patient including functional volumetric data; generate a tissue-specific anatomical probability map using the structural imaging information; generate a tissue-non-specific anatomical probability map using the structural imaging information; generate local combined anatomical probability weights using the tissue-specific anatomical probability map, the tissue-non-specific anatomical probability map, and the functional image data; re-distribute the functional image data using the local combined anatomical probability weights to provide re-distributed functional volumetric data; and generate an image using the re-distributed functional volumetric data. ### Claim 18 (depends on 17) The tangible and non-transitory computer readable medium of claim 17, wherein the one or more computer software modules are further configured to direct the one or more processors to determine the tissue-specific anatomical probability map using image intensities of the structural imaging information. ### Claim 19 (depends on 17) The tangible and non-transitory computer readable medium of claim 17, wherein the one or more computer software modules are further configured to direct the one or more processors to determine the tissue-non-specific anatomical probability map using image gradients of the structural imaging information. ### Claim 20 (depends on 17) The tangible and non-transitory computer readable medium of claim 17, wherein the one or more computer software modules are further configured to direct the one or more processors to perform a multiplication of a tissue-specific probability weight and a tissue-non-specific probability weight to determine the local combined anatomical probability weights.