# US 2021/0279862 A1 · Automatic organ finding framework > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 2021/0279862 A1 - Document ID: US20210279862A1 - Status: Published application - Kind: A1 - Application number: 16/807,198 - Filed: 2020-03-03 - Published: 2021-09-09 - Earliest claimed: 2020-03-03 - Assignees: Siemens Medical Solutions USA, Inc. - Applicants: Siemens Medical Solutions USA, Inc. - Inventors: Charles Hayden - Web page: https://patentgrep.com/patent/US20210279862A1 ## CPC - G06T 7/0012: {Biomedical image inspection} - G06T 3/4084: in the transform domain, e.g. fast Fourier transform [FFT] domain scaling - G06T 3/60: Rotation of whole images or parts thereof - G06T 5/20: using local operators - G06T 7/62: of area, perimeter, diameter or volume - G06T 7/73: using feature-based methods - G06T 2200/04: involving 3D image data - G06T 2207/10072: Tomographic images - G06T 2207/30048: Heart; Cardiac - G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL ## Abstract A framework for automatically finding an organ in image data. In accordance with one aspect, a predetermined view of the organ is approximated by transforming the original image data to generate transformed image data. A best-match region in the transformed image data that best matches a synthesized geometric shape may then be found. The best-match region may be transformed into a volume space of the original image data to generate a location of the organ. ## Claims ### Claim 1 A system for automatically finding a heart, comprising: a non-transitory memory device for storing computer readable program code; and a processor in communication with the memory device, the processor being operative with the computer readable program code to perform operations including receiving original image data of the heart, approximating a short-axis view of the heart by transforming the original image data to generate transformed image data, finding a best-match region in the transformed image data that best matches a synthesized cylinder, and transforming the best-match region into a volume space of the original image data to generate a location of the heart. ### Claim 2 (depends on 1) The system of claim 1 wherein the processor is operative with the computer readable program code to transform the original image data by rotating the original image data by predetermined angles. ### Claim 3 (depends on 2) The system of claim 2 wherein the processor is operative with the computer readable program code to transform the original image data by scaling the original image data to generate isotropic voxels. ### Claim 4 (depends on 3) The system of claim 3 wherein the processor is operative with the computer readable program code to transform the original image data by multiplying a scaling matrix, a z-axis rotation matrix and a y-axis rotation matrix. ### Claim 5 A method for automatically finding an organ, comprising: receiving original image data of the organ; approximating a predetermined view of the organ by transforming the original image data to generate transformed image data; finding a best-match region in the transformed image data that best matches a synthesized geometric shape; and transforming the best-match region into a volume space of the original image data to generate a location of the organ. ### Claim 6 (depends on 5) The method of claim 5 wherein the organ comprises a heart, liver, brain, spleen or stomach. ### Claim 7 (depends on 5) The method of claim 5 wherein the approximating the predetermined view of the organ comprises approximating a short-axis view of a heart. ### Claim 8 (depends on 5) The method of claim 5 wherein the transforming the original image data comprises rotating the original image data by predetermined angles. ### Claim 9 (depends on 8) The method of claim 8 wherein the transforming the original image data further comprises scaling the original image data to generate isotropic voxels. ### Claim 10 (depends on 9) The method of claim 9 wherein the transforming the original image data comprises multiplying a scaling matrix, a z-axis rotation matrix and a y-axis rotation matrix. ### Claim 11 (depends on 5) The method of claim 5 wherein finding the best-match region in the transformed image data that best matches the synthesized geometric shape comprises creating the synthesized geometric shape to approximate a shape of the organ in the predetermined view. ### Claim 12 (depends on 11) The method of claim 11 wherein creating the synthesized geometric shape comprises creating a three-dimensional cylinder. ### Claim 13 (depends on 12) The method of claim 12 wherein creating the three-dimensional cylinder comprises repeating a circle over multiple slices and performing low pass filtering. ### Claim 14 (depends on 5) The method of claim 5 wherein finding the best-match region in the transformed image data that best matches the synthesized geometric shape comprises performing a normalized cross correlation between the synthesized geometric shape and the transformed image data. ### Claim 15 (depends on 14) The method of claim 14 wherein performing the normalized cross correlation results in a three-dimensional surface, wherein a peak value of the three-dimensional surface defines the best-match region. ### Claim 16 (depends on 5) The method of claim 5 wherein finding the best-match region in the transformed image data that best matches the synthesized geometric shape comprises using multiple sizes of the synthesized geometric shape to find the best-match region. ### Claim 17 (depends on 5) The method of claim 5 wherein transforming the best-match region into the original image data comprises rotating the best-match region from the predetermined view to the volume space of the original image data. ### Claim 18 One or more non-transitory computer-readable media embodying instructions executable by machine to perform operations, comprising: receiving original image data of an organ; approximating a predetermined view of the organ by transforming the original image data to generate transformed image data; finding a best-match region in the transformed image data that best matches a synthesized geometric shape; and transforming the best-match region into a volume space of the original image data to generate a location of the organ. ### Claim 19 (depends on 18) The one or more non-transitory computer-readable media of claim 18 wherein the organ comprises a heart, liver, brain, spleen or stomach. ### Claim 20 (depends on 18) The one or more non-transitory computer-readable media of claim 18 wherein the synthesized geometric shape comprises a cylinder, cube, cuboid, sphere, spheroid, prism or polyhedron.