# US 2025/0093531 A1 · Estimating a radiation load quantity for an imaging system having a radiation source > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 2025/0093531 A1 - Document ID: US20250093531A1 - Status: Published application - Kind: A1 - Application number: 18/828,470 - Filed: 2024-09-09 - Published: 2025-03-20 - Earliest claimed: 2023-09-18 - Assignees: Siemens Healthineers AG - Applicants: Siemens Healthineers AG - Inventors: Annette Birkhold; Philipp Roser - Web page: https://patentgrep.com/patent/US20250093531A1 ## CPC - A61B 6/542: {involving control of exposure} - G01T 1/02: Dosimeters (G01T1/15 takes precedence) - G06N 20/00: Machine learning - A61B 6/544: {dependent on patient size} - A61B: DIAGNOSIS; SURGERY; IDENTIFICATION (usefulness limited to only animals A61D) - G01T: MEASUREMENT OF NUCLEAR OR X-RADIATION (radiation analysis of materials, mass spectrometry G01N23/00; tubes for determining the presence, intensity, density or energy of radiation or particles H01J47/00) - G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS ## Abstract In order to estimate a radiation load quantity for an imaging system having a radiation source, a base model is obtained for determining the radiation load quantity depending on a set of input variables, which include at least one radiation-source operating parameter. Measurement data measured for the imaging system is obtained that includes the radiation load quantity for a multiplicity of different values of the at least one radiation-source operating parameter. A refined model is generated by adapting the base model depending on the measurement data. Actual values of the set of input variables are defined for the imaging system. The refined model is used to determine, depending on the actual values of the set of input variables, an estimated value of the radiation load quantity. ## Claims ### Claim 1 A method for estimating a radiation load quantity for an imaging system having a radiation source, the method comprising: obtaining a base model for determining the radiation load quantity depending on a set of input variables that comprise at least one radiation-source operating parameter; obtaining measurement data measured for the imaging system, wherein the measurement data comprises the radiation load quantity for a multiplicity of different values of the at least one radiation-source operating parameter; generating a refined model by adapting the base model depending on the measurement data; defining actual values of the set of input variables for the imaging system; and determining, using the refined model, an estimated value of the radiation load quantity depending on the actual values of the set of input variables. ### Claim 2 (depends on 1) The method of claim 1, further comprising: obtaining reference measurement data measured for at least one reference imaging system, wherein the reference measurement data comprises the radiation load quantity for a multiplicity of different values of the at least one radiation-source operating parameter; and generating the base model based on the reference measurement data. ### Claim 3 (depends on 2) The method of claim 2, further comprising: obtaining a physical initial model for determining the radiation load quantity depending on the set of input variables, wherein the base model is generated by adapting the physical initial model depending on the reference measurement data. ### Claim 4 (depends on 2) The method of claim 2, wherein the base model is generated by using the reference measurement data as a basis for training an algorithm trainable by machine learning. ### Claim 5 (depends on 1) The method of claim 1, wherein the set of input variables comprises at least one state parameter and/or at least one material parameter for a radiation filtering apparatus and/or a beam-forming apparatus, and wherein the measurement data comprises the radiation load quantity for a multiplicity of different values of the at least one state parameter and/or the at least one material parameter. ### Claim 6 (depends on 1) The method of claim 1, wherein the set of input variables comprises at least one exposure parameter, and wherein the measurement data comprises the radiation load quantity for a multiplicity of different values of the at least one exposure parameter. ### Claim 7 (depends on 1) The method of claim 1, wherein the radiation load quantity is a dose area product, a kerma, or a variable that depends on the dose area product and/or the kerma. ### Claim 8 (depends on 1) The method of claim 1, wherein, after an update period has elapsed after a measurement of the measurement data, the method further comprises: obtaining further measurement data measured for the imaging system that comprises the radiation load quantity for a further multiplicity of different values of the at least one radiation-source operating parameter; generating an updated model by adapting the refined model depending on the further measurement data; defining further values of the set of input variables for the imaging system; and determining, using the updated model, a further estimated value of the radiation load quantity depending on the further values of the set of input variables. ### Claim 9 (depends on 8) The method of claim 8, further comprising: obtaining image data generated by the imaging system, wherein the image data represents an object; obtaining a body model for the object; carrying out a consistency check based on the image data, the body model, values of the set of input variables, and the refined model, wherein the values were used to generate the image data; and ascertaining, depending on a result of the consistency check, whether the update period has elapsed. ### Claim 10 (depends on 9) The method of claim 9, further comprising: generating simulated image data based on the body model, the values of the set of input variables, and the refined model, and comparing the simulated image data with the image data for a purpose of the consistency check; and/or generating a comparative model based on the image data, the body model, and the values of the set of input variables, and comparing the comparative model with the refined model for the purpose of the consistency check; and/or generating a comparative body model based on the image data, the values of the set of input variables, and the refined model, and comparing the comparative body model with the body model for the purpose of the consistency check. ### Claim 11 (depends on 9) The method of claim 9, wherein the consistency check comprises applying a further algorithm, trained by machine learning, to input data that depends on the image data, the body model, the values of the set of input variables, and the refined model. ### Claim 12 (depends on 1) The method of claim 1, wherein the imaging system is an X-ray based imaging system, and wherein the radiation source is an X-ray radiation source. ### Claim 13 A data processing apparatus comprising: at least one computing unit configured to: obtain a base model for determining a radiation load quantity depending on a set of input variables that comprise at least one radiation-source operating parameter; obtain measurement data measured for an imaging system, wherein the measurement data comprises the radiation load quantity for a multiplicity of different values of the at least one radiation-source operating parameter; generate a refined model by adapting the base model depending on the measurement data; define actual values of the set of input variables for the imaging system; and determine, using the refined model, an estimated value of the radiation load quantity depending on the actual values of the set of input variables. ### Claim 14 An imaging system comprising: a radiation source for generating ionizing radiation; a radiation detector for detecting portions of the ionizing radiation; and a data processing apparatus having at least one computing unit configured to: obtain a base model for determining a radiation load quantity depending on a set of input variables that comprise at least one radiation-source operating parameter; obtain measurement data measured for the imaging system, wherein the measurement data comprises the radiation load quantity for a multiplicity of different values of the at least one radiation-source operating parameter; generate a refined model by adapting the base model depending on the measurement data; define actual values of the set of input variables for the imaging system; and determine, using the refined model, an estimated value of the radiation load quantity depending on the actual values of the set of input variables.