Providing a radiation exposure distribution for an imaging system with a radiation source

Abstract

The invention relates to a computer-implemented method (M1) for more accurately providing data of a load distribution (16) of a radiation (6) from a radiation source (4) of an imaging system (1), comprising the steps: - receiving setting data (10) of the imaging system (1); - receiving a radiation exposure characteristic (14) associated with the setting data (10); - receiving data of an intensity distribution (15) of the radiation (6) associated with the setting data (10) at a radiation detector (3) of the imaging system (1); - applying a trained first function (11) to the setting data (10), the load characteristic (14) and the intensity distribution data (15) as first input data of the trained first function (11), wherein the load distribution data (16) are generated as first output data of the trained first function (11); - Providing load distribution data (16). The invention further relates to a data processing device (2), a computer-implemented training method (M2), a computer program product (8) and an imaging system (1).

Description

The invention relates to a computer-implemented method for providing data of a load distribution of radiation from a radiation source of an imaging system, and to a computer-implemented training method for training a function, to a corresponding data processing device, to a computer program product and to an imaging system.In imaging systems with a radiation source for generating ionizing radiation, it is desirable, for example for regulatory reasons, to document the radiation exposure for patients and medical personnel as exactly as possible. For this purpose, a corresponding radiation load characteristic variable can be measured during operation of the imaging system.In the case of X-ray-based imaging systems, for example X-ray-based angiography systems, for this purpose, a dose area product, DAP (dose area product), can be measured as a radiation loading characteristic by means of a measuring device, referred to as a DAP chamber, in the beam path of the imaging system. The measured DAP can be used not only for the regulatory requirements mentioned but also for regulating the radiation source.However, such a DAP may only indicate a summed load over the irradiated area, but not a distribution of the load over this area. It cannot be assumed in particular that the load on the surface is distributed identically, i.e. homogeneously, but rather the load on the radiation can be distributed inhomogeneously on the surface. In particular, the radiation source radiates an inhomogeneously distributed radiation onto the surface, which can lead to the inhomogeneous stress distribution of this radiation onto the irradiated surface. Thus, an estimate of the local exposure of the radiation, which can have an effect on the skin, vessels, organs or the like, for example, in the X-ray-based angiography systems, is also incorrect based only on the DAP. Rather, the local load may be higher than the notionally homogeneously distributed load based on the DAP.It is an object of the invention to determine the stress distribution of the radiation from a radiation source of an imaging system more accurately.The object is achieved by the subject matters of the independent claims. Advantageous refinements of the invention are described by the dependent patent claims, the following description and the figures.The invention is based on the concept of generating data of the stress distribution as first output data at a radiation detector at least using a trained function based on setting data of the imaging system, the stress characteristic variable and data of the intensity distribution of the radiation.According to one aspect of the invention, a computer-implemented method for providing data of a stress distribution of a radiation from a radiation source, in particular a radiation source for generating ionizing radiation, of an imaging system is provided.The stress distribution can also be referred to as dose distribution. For example, the data of the stress distribution may be present as image data that maps the distribution of the stress on a two-dimensional surface. A pixel value of the image can indicate the local exposure to the radiation at the pixel.In a step of the computer-implemented method, setting data of the imaging system are received. In a further step, a load characteristic variable or dose characteristic variable of the radiation associated with the setting data is received. In a further step, data of an intensity distribution of the radiation associated with the setting data are received at a radiation detector of the imaging system.In a further step, a trained, first function is applied to the received setting data, the received load characteristic variable and the received data of the intensity distribution as first input data of the first function. The data of the load distribution is generated based on the input data as first output data of the trained, first function. The generated data of the load distribution can then be provided in a further step.The provided data of the load distribution can be estimated in particular by the trained function without a measurement having to be carried out for this purpose in order to record the load distribution. Accordingly, such a measuring method can be advantageously dispensed with.In particular, the data of the load distribution can be stored or at least temporarily stored in the form of a corresponding computer-readable file, preferably a two-dimensional image file which comprises the two-dimensional intensity distribution, on a corresponding storage medium. The provision of the data of the load distribution can be effected, for example, by storing the computer-readable file on the storage medium.For example, this data can be used for documentation, for example in an electronic patient record. It can also be provided that the data of the load distribution can be provided to an electronic system with a computing unit, which can process these data further.Unless otherwise stated, all steps of the computer-implemented method can be carried out by a data processing device which has at least one arithmetic unit. In particular, the at least one computing unit is configured or adapted to carry out the steps of the computer-implemented method. For this purpose, the at least one computing unit can store, for example, one or more computer programs, the execution of which causes the at least one computing unit to carry out the computer-implemented method.Advantageously, improved data of the load distribution can be provided by the method. In particular, the improved data do not underestimate local stress peaks which can act on the skin of a patient, for example, at local sites. For example, redness of the skin, which may occur even weeks later after radiation treatment at a local location of the irradiated area, can be attributed to the stress peaks by the improved data. Furthermore, on the basis of the knowledge of stress peaks on local sites of the irradiated area, the radiation treatment can be adapted, so that consequences, such as, for example, the redness of the skin, can be reduced.The setting data, also referred to as setting of the imaging system, can preferably be individually set by a user of the imaging system, for example by an attending physician or administrator. In particular, this setting data can be stored or at least temporarily stored in the form of a corresponding computer-readable file which comprises the setting data on a corresponding storage medium. The setting data can be received, for example, by reading the computer-readable file from the storage medium.The load characteristic is a quantity in dosimetry and the basis for calculating the radiation load for an irradiated body or an irradiated area during irradiation with the radiation source, for example, in X-ray imaging with an X-ray apparatus such as fluoroscopic imaging, angiography, or the like. The load characteristic corresponds to the sum of the radiation load which impinges on the irradiated surface in the beam path of the radiation source. The unit of measurement of the value of the load characteristic is the cGy×cm 2 or Gy×m 2. The radiation exposure characteristic can correspond, for example, to a dose area product, DFP (DAP).In the case of X-ray-based imaging systems, for example X-ray-based angiography systems, for this purpose, the dose surface product can be measured as a load characteristic by means of a measuring device, referred to as a DAP chamber, in the beam path of the imaging system, which sums the load over an irradiated area of the radiation to form a value.The load characteristic variable is in particular dependent on the respective imaging system and its setting data. If the setting data changes, the load characteristic therefore also changes. In this respect, the received load characteristic corresponds to that which has been measured or alternatively determined in the imaging system set with the received setting data. In particular, this load characteristic variable can be stored or at least temporarily stored in the form of a corresponding computer-readable file which comprises the load characteristic variable on a corresponding storage medium. The load characteristic variable can be received, for example, by reading the computer-readable file from the storage medium.The received intensity distribution corresponds to that which has been measured at the radiation detector in the imaging system set with the received setting data or has been determined alternatively, i.e. not by measurement, at the radiation detector.The data of the intensity distribution can correspond to a detector image of the radiation detector, which shows in particular graphically the intensity distribution of the radiation on an irradiated detector surface of the radiation detector. In particular, this intensity distribution can be stored or at least temporarily stored in the form of a corresponding computer-readable file, preferably a two-dimensional image file which comprises the two-dimensional intensity distribution, on a corresponding storage medium. The intensity distribution can be received, for example, by reading the computer-readable file from the storage medium.In a less preferred embodiment, the intensity distribution can be provided by irradiating the radiation detector with the radiation of the radiation source under the setting data of the imaging system, wherein no object or a homogeneous object is located in the beam path, wherein the radiation detector provides the intensity distribution as a two-dimensional detector image. A homoante object can be understood to mean an object which does not influence the intensity distribution. For example, acrylic glass with an appropriate thickness can be used for this purpose.The setting data, the load characteristic variable and the data of the intensity distribution can now serve as input data of the trained, first function. The trained, first function can preferably be based on an artificial, neural network (ANN), in particular with at least one convolution level. In particular, the trained function can be based on a generic, inverse algorithm. In particular, a computing unit can be designed to use the trained function as first output data for generating the load data.A KNN can be understood as a software code or a collection of a plurality of software code components, wherein the software code can comprise a plurality of software modules for different functions, for example one or more encoder modules and one or more decoder modules.A KNN may be understood as a nonlinear model or algorithm that maps an input to an output, where the input is given by an input feature vector or sequence of inputs, and the output may be an output category for a classification task or predicted sequence.The ANN may be provided, for example, in computer readable form.The neural network may include multiple modules including an encoding module and a decoder module. These modules can be understood as software modules or corresponding parts of the neural network. A software module may be understood as software code functionally connected and combined with a unit. A software module may include or implement multiple processing steps and / or data structures.The modules can in particular themselves represent neural networks or sub-networks. Unless stated otherwise, a module of the neural network can be understood to mean a trainable and, in particular, trained module of the neural network. For example, the neural network and thus all its trainable modules can be trained continuously before the method is carried out. However, in other implementations, different modules may be individually trained or pre-trained. In other words, the method according to the invention can correspond to a use phase of the trained, first function, in particular of the ANN.The trained, first function can be trained in particular in such a way that it is suitable for generating realistic and meaningful data of the load distribution as output data. The trained, first function can preferably be trained and provided by means of a computer-implemented training method for training a first function.By using the trained first function, the stress distribution can be predicted extremely precisely and individually. Furthermore, using the trained, first function, the computing unit can be capable of generating the data of the load distribution extremely quickly, robust and with a lower computing power.The trained, first function can be provided in particular as a general function for a series of imaging systems of identical construction or at least similar type or can be applied to each, specific imaging system of this series.The proposed method can be used in particular during irradiation of a body by means of the imaging system, for example during a medical procedure, but also in material testing.According to at least one embodiment, it is provided that the data of the intensity distribution is provided by applying a trained second function to the setting data as second input data of the trained second function, wherein the data of the intensity distribution is generated as second output data of the second function.This is advantageous at least in that no actual irradiation or no actual measurement for determining the intensity distribution based on the setting data has to be carried out in order to provide the intensity distribution. Rather, the provision of the intensity distribution can be effected purely in a computer-implemented manner.In particular, the second output data of the trained, second function can thus form part of the first input data of the trained, first function. For this purpose, the trained, second function provides the intensity distribution as a digital, two-dimensional image, in particular as a corresponding image file.The trained, second function can be provided in particular as a specific function for a single, specific imaging system of a series of imaging systems of identical construction or at least similar construction or can be applied only to the specific imaging system of this series. By linking the first trained function, which can generally be applied for the series of imaging systems, to the second trained function, the trained first function can be specified quasi to the specific imaging system.In particular, the trained, first and trained, second functions are combined with one another during application, for example during a medical intervention with a patient in the beam. This results in a further advantage in the sense that, when this combination is used in the application, the computing unit only has to receive the setting data and the load characteristic variable, so that it can generate the load distribution. This clearly accelerates and simplifies the method.The trained, second function can be trained in particular in such a way that it is suitable for generating realistic and meaningful data of the intensity distribution as output data. The trained, second function can preferably be trained and provided by means of a computer-implemented training method for training a second function. The trained, second function can preferably be based on an artificial, neural network (ANN), in particular with at least one convolution level. In particular, the trained, second function can be based on a generic, inverse algorithm. In particular, a computing unit can be designed to use the trained, second function as second output data for generating the intensity distribution.According to at least one embodiment, it is provided that the trained, second function is provided by a computer-implemented, second training method. The computer-implemented, second training method has, in particular, the steps:receiving second input training data comprising setting data of the imaging system;receiving second output training data comprising data of the intensity distribution, wherein the second output training data is related to the second input training data;training a second function based on the second input training data and the second output training data by generating second output data by applying the second function to the second input training data and adjusting parameters of the second function based on a comparison of the second output data with the second output training data;providing the trained, second function.According to at least one embodiment, it is provided that the load characteristic variable is provided by applying a trained, third function to the setting data as third input data of the third function, wherein the load characteristic variable is generated as third output data of the third function.This is advantageous at least in that no actual irradiation or no actual measurement for determining the load characteristic variable based on the setting data has to take place in order to provide the load characteristic variable. Rather, the load characteristic variable can be provided purely in a computer-implemented manner.In particular, the third output data of the trained, third function can thus form part of the first input data of the trained, first function. The trained, third function provides the load characteristic variable as a value for this purpose.The trained, third function can be provided in particular as a specific function for a single, specific imaging system of a series of imaging systems of identical construction or at least similar construction or can be applied only to the specific imaging system of this series.A further advantage is thus obtained from a combination of the trained, third function with the trained, second function and the trained, first function. When using this combination, the computing unit only has to receive the setting data, so that it can generate the load distribution. This greatly accelerates and simplifies the process.The trained, third function can be trained in particular in such a way that it is suitable for generating realistic and meaningful load characteristics as output data. The trained, third function can preferably be trained and provided by means of a computer-implemented training method for training a third function. The trained, third function can preferably be based on an artificial, neural network (ANN), in particular with at least one convolution level. In particular, the trained, third function can be based on a generic, inverse algorithm. In particular, a computing unit can be designed to use the trained, third function as third output data for generating the load characteristic variable.According to at least one embodiment, it is provided that the trained, third function is provided by a computer-implemented, third training method. The computer-implemented, third training method has, in particular, the steps:receiving third input training data comprising setting data of the imaging system,receiving third output training data comprising load characteristics, the third output training data being related to the third input training data;training a third function based on the third input training data and the third output training data by generating third output data by applying the third function to the third input training data and adjusting parameters of the third function based on a comparison of the third output data with the third output training data;providing the trained, third function.According to at least one embodiment, it is provided that the load characteristic variable is a dose area product or a variable dependent on the dose area product.For example, the radiation source in this case is an X-ray tube. However, similar quantities also result for other ionizing radiation types.According to at least one embodiment, it is provided that the data of the intensity distribution is a two-dimensional X-ray projection image. For example, the intensity distribution can be represented on the basis of the color intensity of the individual pixels of the X-ray projection image.The X-ray projection image, also referred to as detector image, can in particular graphically represent a two-dimensional array of pixels, wherein the pixel values can represent measured values of individual radiation sensors of the radiation detector.According to at least one embodiment, it is provided that the data of the load distribution is a two-dimensional image of the load distribution at an interventional reference point. The interventional reference point can correspond to the location at which it is provided to place the body to be irradiated in the beam path. Thus, the stress distribution can also indicate exactly that which acts or would act on the body to be irradiated.According to at least one embodiment, it is provided that the setting data of the imaging system comprise at least operating parameters of the radiation source and / or of a collimator of the imaging system.If the radiation source is, for example, an X-ray radiation source, i.e., in particular an X-ray tube, the operating parameters of the radiation source can include, in particular, a peak kilovolt voltage, kVp (peak kilovoltage), i.e., a maximum tube voltage, which is applied to the X-ray tube as ionizing radiation when generating the X-ray radiation. The operating parameters of the radiation source may also include a tube current of the x-ray tube and / or a focal spot size (focal spot size), and so forth.A collimator is a physical barrier that focuses or parallelizes high-energy electromagnetic waves such as x-ray or gamma radiation. For example, the spatial limitation of the beam of the radiation source can be specified or set on the basis of the operating parameters of the collimator.According to at least one embodiment, it is provided that the imaging system is an X-ray-based imaging system and the radiation source is an X-ray radiation source, in particular an X-ray tube.A further aspect of the invention relates to a computer-implemented, first training method for providing a trained, first function which generates data of a load distribution of radiation from a radiation source of an imaging system. This method can be carried out in particular by a computing unit and has in particular the following steps.In a first step of the method, first input training data are received. These comprise setting data of the imaging system, and load characteristics of the radiation associated with the setting data, and data of an intensity distribution of the radiation at a radiation detector of the imaging system associated with the setting data.In a second step of the method, first initial training data are received, which comprise data of the load distribution. The output training data are in this case related to the input training data.In a third step, a first function is trained based on the first input training data and the first output training data by generating first output data by applying the first function to the first input training data and adjusting parameters of the first function based on a comparison of the first output data with the first output training data.In a fourth step, the trained, first function is provided.The input training data can be received in particular with a first training interface of an electronic training system, and the output training data can be received from a second training interface of the electronic training system. The trained, first function can be provided with a third training interface of the electronic training system.The first function can preferably be based on an artificial, neural network (ANN), in particular with at least one convolution level. In particular, the function can be based on a generic, inverse algorithm. In particular, the electronic training system can be configured to train the first function. The first function can be trained in particular in such a way that it is suitable as a trained, first function for generating or predicting realistic and meaningful data of the load distribution of the radiation as output data.By comparing the output data with the output training data, an error of the function can be determined in particular. For example, a so-called cost function can be calculated for quantifying the error. For example, the parameters of the function can be adapted by means of a known algorithm in such a way that the cost function is minimized, in particular iteratively.According to at least one embodiment of the computer-implemented, first training method, it is provided that the initial training data are provided by dosimetric measurements and / or dosimetric simulations.The dosimetric measurements as output training data are to be carried out here under the corresponding associated setting data as input training data. A dosimetric measurement can be carried out in particular by means of a radiochromatic film. The film contains a dye which changes color upon irradiation with ionizing radiation so that the degree of irradiation, the beam profile and the stress distribution of the radiation can be characterized. The film can be digitized in particular by scanning and digitally processed accordingly, so that a two-dimensional, digital image is produced.Alternatively, the data of the load distribution can be provided as initial training data by dosimetric simulation, based on the associated setting data, the load characteristic variable and the intensity distribution. For example, a Monte Carlo simulation can be carried out for this purpose.The intensity distribution and / or the load characteristic variable as input training data can likewise be provided on the basis of measurements and / or simulations and / or by means of a trained function.According to at least one embodiment of the computer-implemented, first training method, it is provided that the trained, first function is provided for a series of imaging systems.The trained, first function can be provided in particular as a general function for a series of imaging systems of identical construction or at least similar type or can be applied to each, specific imaging system of this series.According to at least one embodiment of the computer-implemented method for providing data of a load distribution, it is provided that the trained, first function is provided by the computer-implemented, first training method.A further aspect of the invention relates to a computer-implemented, second training method for providing a trained, second function which generates data of an intensity distribution of radiation at a radiation detector of an imaging system having a radiation source. This method can be carried out in particular by a computing unit and has in particular the following steps.In a first step of the method, second input training data can be received, which comprise setting data of the imaging system.In a second step of the method, second initial training data can be received, which comprise data of the intensity distribution. The second output training data are in this case related to the second input training data.In a third step, a second function is trained based on the second input training data and the second output training data by generating second output data by applying the second function to the second input training data and adjusting parameters of the second function based on a comparison of the second output data with the second output training data.In a fourth step, the trained, second function is provided.The input training data can be received in particular with a first training interface of an electronic training system, and the output training data can be received from a second training interface of the electronic training system. The trained, second function can be provided with a third training interface of the electronic training system.The second function can preferably be based on an artificial, neural network (ANN), in particular with at least one convolution level. In particular, the function can be based on a generic, inverse algorithm. In particular, the electronic training system can be configured to train the second function. The second function can be trained in particular in such a way that it is suitable as a trained, second function for generating or predicting realistic and meaningful data of the intensity distribution of the radiation as output data.By comparing the output data with the output training data, an error of the function can be determined in particular. For example, a so-called cost function can be calculated for quantifying the error. For example, the parameters of the function can be adapted by means of a known algorithm in such a way that the cost function is minimized, in particular iteratively.According to at least one embodiment of the computer-implemented, second training method, it is provided that the trained, second function is provided specifically for a specific imaging system of a series of imaging systems. The series of imaging systems can have imaging systems of identical construction or at least similar construction.The second initial training data for the training of the specific, second function can be provided in particular by means of the associated, specific system. In particular, the data of the intensity distribution of the specific system can be carried out as second initial training data by measurements by means of the specific system, wherein no object or a homogeneous object is located in the beam path. Such measurements can be provided or have been provided, in particular, by regular, for example annual, service measurements.In particular, it may already be sufficient for training the second function to train it with a relatively small number of training data. This can be caused in particular by the trained, second function being linked to the trained, first function when applied in the computer-implemented method for providing data of the load distribution. The trained, second function is used only to specify the trained, first function to the specific system of the associated, trained, second function, wherein the trained, first function was trained with a relatively large number of training data. In this combination, the relatively small number of training data is consequently sufficient for the training of the second function.According to at least one embodiment of the computer-implemented method for providing data of a load distribution, it is provided that the trained, second function is provided by the computer-implemented, second training method.A further aspect of the invention relates to a computer-implemented, third training method for providing a trained, third function, which generates data a load characteristic variable of a radiation from a radiation source of an imaging method. This method can be carried out in particular by a computing unit and has in particular the following steps.In a first step of the method, third input training data can be received, which comprise setting data of the imaging system.In a second step of the method, second initial training data can be received, which comprise load characteristics. The third output training data are in this case related to the third input training data.In a third step, a third function is trained based on the third input training data and the third output training data by generating third output data by applying the third function to the third input training data and adjusting parameters of the third function based on a comparison of the third output data with the third output training data.In a fourth step, the trained, third function is provided.The input training data can be received in particular with a first training interface of an electronic training system, and the output training data can be received from a second training interface of the electronic training system. The trained, third function can be provided with a third training interface of the electronic training system.The third function can preferably be based on an artificial, neural network (ANN), in particular with at least one convolution level. In particular, the function can be based on a generic, inverse algorithm. In particular, the electronic training system can be configured to train the second function. The second function can be trained in particular in such a way that it is suitable as a trained, second function for generating or predicting realistic and meaningful data of the intensity distribution of the radiation as output data.By comparing the output data with the output training data, an error of the function can be determined in particular. For example, a so-called cost function can be calculated for quantifying the error. For example, the parameters of the function can be adapted by means of a known algorithm in such a way that the cost function is minimized, in particular iteratively.According to at least one embodiment of the computer-implemented, third training method, it is provided that the trained, third function is provided specifically for a specific imaging system of a series of imaging systems. The series of imaging systems can have imaging systems of identical construction or at least similar construction.The third initial training data for the training of the specific, third function can be provided in particular by means of the associated, specific system. In particular, the load characteristics of the specific system can be carried out as third initial training data by measurements by means of the specific system.According to at least one embodiment of the computer-implemented method for providing data of a load distribution, it is provided that the trained, third function is provided by the computer-implemented, third training method.A further aspect of the invention relates to a data processing device having at least one arithmetic unit which is adapted to carry out a computer-implemented method according to the invention for providing data of a load distribution of radiation from a radiation source of an imaging system.In particular, the data processing device for providing data of a load distribution of radiation from a radiation source of an imaging system is specified, having:a first interface for receiving setting data of the imaging system;a second interface for receiving a load characteristic of the radiation associated with the setting data;a third interface for receiving data of an intensity distribution of the radiation associated with the setting data at a radiation detector of the imaging system;a computing unit for applying a trained first function to the setting data, the load characteristic variable and the data of the intensity distribution as first input data of the first function, wherein the data of the load distribution is generated as first output data of the first function;a fourth interface for providing the data of the load distribution.A computing unit can be understood in particular as a data processing device which contains a processing circuit. The computing unit can therefore process data in particular for carrying out computing operations. This also includes operations to perform indexed accesses to a data structure, for example a look-up table (LUT).The computing unit can in particular contain one or more computers, one or more microcontrollers and / or one or more integrated circuits, for example one or more application-specific integrated circuits, ASICs (application-specific integrated circuit), one or more field programmable gate arrays, FPGAs, and / or one or more single-chip systems, SoCs (system on a chip). The computing unit may also contain one or more processors, for example one or more microprocessors, one or more central processing units, CPUs (central processing units), one or more graphics processing units, GPUs (graphics processing units) and / or one or more signal processors, in particular one or more digital signal processors, DSPs. The computing unit may also include a physical or virtual group of computers or other of the aforementioned units.In various exemplary embodiments, the computing unit contains one or more hardware and / or software interfaces and / or one or more memory units.A memory unit can be used as volatile data memory, for example as dynamic random access memory, DRAM (dynamic random access memory) or static random access memory, SRAM (static random access memory), or as nonvolatile data memory, for example as read-only memory, ROM (read-only memory), as programmable read-only memory, PROM (programmable read-only memory), as erasable programmable read-only memory, EPROM (erasable programmable read-only memory), as electrically erasable programmable read-only memory, EEPROM (electrically erasable programmable read-only memory), as flash memory or flash EEPROM, as ferroelectric random access memory, FRAM (ferroelectric random access memory), as magnetoresistive random access memory, MRAM (magnetoresistive random access memory) or as phase-change random access memory, PCRAM (phase-change random access memory).Further embodiments of the data processing device according to the invention follow directly from the various embodiments of the associated method according to the invention and vice versa. In particular, individual features and corresponding explanations and advantages with respect to the various embodiments can be transferred analogously to corresponding embodiments of the data processing device according to the invention in relation to the method according to the invention.A further aspect of the invention provides a computer program comprising instructions. When the instructions are executed by at least one data processing device, in particular a data processing device according to the invention, the instructions cause the data processing device to carry out the method according to the invention for providing data of a load distribution of radiation from a radiation source of an imaging system.The instructions can be present, for example, as program code. The program code can be provided, for example, as binary code or assembler and / or as source code of a programming language, for example C, and / or as a program script, for example Python.A further aspect of the invention relates to an electronically readable data carrier comprising instructions which, when the data carrier is executed on at least one data processing device, in particular on a data processing device according to the invention, cause the data processing device to carry out the method according to the invention for providing data of a load distribution of radiation from a radiation source of an imaging system.The computer program and the computer-readable storage medium are each computer program products having the instructions.According to another aspect of the invention, an imaging system is provided. The imaging system has a data processing device according to the invention, a radiation source for generating, in particular, ionizing radiation, and a radiation detector for detecting parts of the radiation, in particular parts of the ionizing radiation that have passed through an object to be imaged.A further aspect of the invention relates to a first electronic training system for providing a trained, first function which generates data of a load distribution of radiation from a radiation source of an imaging system, having:a first training interface for receiving first input training data, comprisingsetting data of the imaging system,load characteristics of the radiation associated with the setting data, anddata of an intensity distribution of the radiation at a radiation detector of the imaging system, which data are associated with the setting data, depending on the setting data;a second training interface for receiving first output training data comprising load distribution data, the output training data being related to the input training data;a computing unit for training a first function based on the first input training data and the first output training data by generating first output data by applying the first function to the first input training data and adjusting parameters of the first function based on a comparison of the first output data with the first output training data;a third training interface for providing the trained, first function.The electronic, first training system is in particular configured to carry out the computer-implemented, first training method.Further embodiments of the training system according to the invention follow directly from the various embodiments of the training method according to the invention and vice versa. In particular, individual features and corresponding explanations and advantages with respect to the various embodiments can be transferred analogously to corresponding embodiments of the training system according to the invention in relation to the training method according to the invention.A further aspect of the invention relates to a second electronic training system for providing a trained, second function which generates data of an intensity distribution of a radiation at a radiation detector of an imaging system having a radiation source, having:a fourth training interface for receiving second input training data comprising setting data of the imaging system;a fifth training interface for receiving second output training data comprising data of the intensity distribution, wherein the output training data is related to the input training data;a computing unit for training a second function based on the second input training data and the second output training data by generating second output data by applying the second function to the second input training data and adjusting parameters of the second function based on a comparison of the second output data with the second output training data;a sixth training interface for providing the trained, second function.The electronic, second training system is in particular configured to carry out the computer-implemented, second training method.Further embodiments of the training system according to the invention follow directly from the various embodiments of the training method according to the invention and vice versa. In particular, individual features and corresponding explanations and advantages with respect to the various embodiments can be transferred analogously to corresponding embodiments of the training system according to the invention in relation to the training method according to the invention.A further aspect of the invention relates to a third electronic training system for providing a trained, third function which generates a load characteristic variable of a radiation from a radiation source of an imaging system, having:a seventh training interface for receiving third input training data, comprising setting data of the imaging system,an eighth training interface for receiving first output training data comprising load characteristics, the output training data being related to the input training data;a computing unit for training a third function based on the third input training data and the third output training data by generating third output data by applying the third function to the third input training data and adjusting parameters of the third function based on a comparison of the third output data with the third output training data;a ninth training interface for providing the trained third function.The electronic, third training system is in particular configured to carry out the computer-implemented, third training method.Further embodiments of the training system according to the invention follow directly from the various embodiments of the training method according to the invention and vice versa. In particular, individual features and corresponding explanations and advantages with respect to the various embodiments can be transferred analogously to corresponding embodiments of the training system according to the invention in relation to the training method according to the invention.Further aspects of the invention relate to computer training programs, comprising instructions which, when the respective computer program is executed on an electronic training system, cause the electronic training system to carry out a respective training method according to the invention.Further aspects of the invention relate to electronically readable training data carriers comprising instructions which, when the respective data carrier is executed on an electronic training system, cause the electronic training system to carry out a respective training method according to the invention.For use cases or application situations which can result from the described methods or training methods and which are not explicitly described here, it can be provided that, according to the method, an error message and / or a request for inputting a user feedback is output and / or a default setting and / or a predetermined initial state is set.Further features and combinations of features of the invention are evident from the figures and their description and from the claims. In particular, further embodiments of the invention need not necessarily include all features of any of the claims. Further embodiments of the inventions may comprise features or combinations of features not mentioned in the claims.The invention is explained in more detail below with reference to specific exemplary embodiments and associated schematic drawings. In the figures, identical or functionally identical elements can be provided with the same reference numerals. The description of identical or functionally identical elements may not necessarily be repeated with respect to different figures.The figures show: FIG. 1 is a schematic illustration of an exemplary embodiment of an imaging system according to the invention; FIG. 2 shows a schematic flow diagram of an exemplary embodiment of a computer-implemented method according to the invention for providing data of a load distribution; FIG. 3 shows a schematic representation of an exemplary embodiment of the computer-implemented method according to the invention for providing data of a load distribution; FIG. 4 shows a schematic flow diagram of an exemplary embodiment of a computer-implemented first training method according to the invention for providing a trained first function; FIG. 5 shows a schematic flow diagram of an exemplary embodiment of a computer-implemented second training method according to the invention for providing a trained second function; FIG. 6 shows a schematic flow diagram of an exemplary embodiment of a computer-implemented third training method according to the invention for providing a trained third function; FIG. 7 shows a schematic structure of an exemplary embodiment of a trained, first function; FIG. 8 shows a schematic structure of an exemplary embodiment of a trained, second function; FIG. 9 shows a schematic illustration of a first exemplary embodiment of an artificial neural network (ANN) of a trained function; FIG. 10 shows a schematic illustration of a first exemplary embodiment of a foldable ANN of a trained function.FIG. 1 schematically illustrates an exemplary embodiment of an imaging system 1 according to the invention. The imaging system 1 comprises at least one data processing device 2, and an imaging modality comprising a radiation source 4 for generating ionizing radiation 6 and a radiation detector 3 for detecting portions of the ionized radiation 6. For example, the imaging modality is configured as an X-ray-based imaging modality, for example as an X-ray-based angiography system, and has an X-ray source as radiation source 4 and an X-ray detector as radiation detector 3. Furthermore, a patient is shown as the object 5 to be imaged, which is located at an interventional reference point 9 of the imaging system 1.The data processing device 2 has at least one arithmetic unit 7, 17. The at least one computing unit 7 is configured to carry out a computer-implemented method M 1 according to the invention for providing data of a load distribution of the radiation 6 from the radiation source 4 of the imaging system 1. A schematic flow diagram of an exemplary embodiment of such a method M 1 is illustrated in FIG. 2. For this purpose, a corresponding computer program product 8 can be executed on the data processing device 2.FIG. 2 shows a schematic flow diagram and FIG. 3 shows a schematic illustration of an exemplary embodiment of a computer-implemented method M 1 according to the invention for providing data of a load distribution 16, which can be carried out in particular by the arithmetic unit 7, in particular the data processing device 2. Figures 2 and 3 are discussed in common below.In a first step S 1 of method M 1, setting data 10 of imaging system 1 may be received by computing unit 7. In one exemplary embodiment, this setting data 10 of the imaging system 1 can have at least operating parameters of the radiation source 4 and / or of a collimator of the imaging system 1.In a second step S 2 of method M 1, data of an intensity distribution 15 of the radiation 6 associated with the setting data 10 can be received at a radiation detector 3 of the imaging system 1 by the computing unit 7. For example, the data of the intensity distribution 15 can represent a detector image, in particular a two-dimensional X-ray projection image.Preferably, the data of the intensity distribution 15 can be provided by applying a trained second function 12 to the setting data 10 as second input data of the trained second function 12, wherein the data of the intensity distribution 15 is generated as second output data of the trained second function 12. The trained, second function 12 can be applied in particular by the further arithmetic unit 17, wherein the further arithmetic unit 17 and the arithmetic unit 7 can be designed as a common arithmetic unit 7.In a third step S 3 of method M 1, a load characteristic variable 14 of radiation 6 associated with setting data 10 may be received by computing unit 7. For example, the load characteristic variable 14 can be a dose area product (DAP) or a variable dependent on the dose area product.The load characteristic variable 14 can preferably be provided by applying a trained third function 13 to the setting data 10 as third input data of the trained third function 13, wherein the load characteristic variable 14 is generated as third output data of the trained third function 13. The trained, third function 13 can be applied in particular by the further arithmetic unit 17, wherein the further arithmetic unit 17 and the arithmetic unit 7 can be designed as a common arithmetic unit 7.Alternatively, the load characteristic can be measured by means of a DAP chamber in the beam path of the imaging system.In a fourth step S 4 of the method M 1, a trained first function 11 can be applied to the setting data 10, the load characteristic variable 14 and the data of the intensity distribution 15 as first input data of the trained first function 11, wherein the data of the load distribution 16 is generated as first output data of the trained first function.The data of the load distribution 16 can in particular represent a two-dimensional image of the load distribution 16 at the interventional reference point 9 of the imaging system 1.In a fifth step S 5, the data of the load distribution 16 are provided.FIG. 4 shows a schematic flow diagram of an exemplary embodiment of a computer-implemented first training method M 2 according to the invention for providing a trained first function 11, which can be carried out, for example, by a first electronic training system 18 having at least one arithmetic unit.In a first step S21, first input training data are received, which comprise setting data 10' of an imaging system 1, load characteristics 14' of the radiation 6 associated with the setting data (10'), and data of an intensity distribution 15' of the radiation 6 associated with the setting data 10' at a radiation detector 3 of the imaging system 1.In a second step S22, first output training data are received, comprising data of the load distribution (16'), wherein the first output training data are related to the first input training data.In a third step S 23, a first function is trained based on the first input training data and the first output training data by generating first output data by applying the first function to the first input training data and adjusting parameters of the first function based on a comparison of the first output data with the first output training data.In a fourth step S 24, the trained, first function 11 is provided.FIG. 5 shows a schematic flow diagram of an exemplary embodiment of a computer-implemented second training method M 3 according to the invention for providing a trained second function 12, which can be carried out, for example, by a second electronic training system 19 having at least one arithmetic unit.In a first step S31, second input training data are received, which comprise setting data 10' of an imaging system 1In a second step S32, second output training data are received, comprising data of the intensity distribution (15'), wherein the second output training data are related to the second input training data.In a third step S 33, a second function is trained based on the second input training data and the second output training data by generating second output data by applying the second function to the second input training data and adjusting parameters of the second function based on a comparison of the second output data with the second output training data.In a fourth step S 34, the trained, second function 12 is provided.FIG. 6 shows a schematic flow diagram of an exemplary embodiment of a computer-implemented third training method M 4 according to the invention for providing a trained third function 13, which can be carried out, for example, by a third electronic training system 20 having at least one arithmetic unit.In a first step S41, third input training data are received, which comprise setting data 10' of an imaging system 1In a second step S42, third output training data are received, comprising load characteristics (14'), wherein the third output training data are related to the third input training data.In a third step S 43, a third function is trained based on the third input training data and the third output training data by generating third output data by applying the third function to the third input training data and adjusting parameters of the third function based on a comparison of the third output data with the third output training data.In a fourth step S 44, the trained, third function 13 is provided.FIG. 7 shows a schematic structure of an exemplary embodiment of a trained first function 11.In particular, the data of the intensity distribution 15, which is shown here, for example, as a graph in which the beam intensity of a two-dimensional XY surface is plotted on a Z axis, can serve as input data for the encoder, wherein data of the intensity distribution 15 with variable length can be encoded into a sequence with fixed length. The setting data 10 and the load characteristic variable 14 preferably already have a sequence with a fixed length and can thus serve directly as input data for the decoder 22. The decoder 22 is then designed to generate, based on the input data, the data of the stress distribution 16, which are shown here, for example, as a graph in which the stress intensity of a two-dimensional XY surface is plotted on a Z axis.FIG. 8 shows a schematic structure of an exemplary embodiment of a trained second function 12. The setting data 10 preferably already have a sequence with a fixed length and can thus serve directly as input data for the decoder 22. The decoder 22 is then designed to generate, based on the input data, the data of the intensity distribution 15, which are shown here, for example, as a graph in which the radiation intensity of a two-dimensional XY surface is plotted on a Z axis.FIG. 9 shows an embodiment of an artificial neural network, ANN, 100 for a function or for a trained function, in particular for a trained first function 11 and / or a trained second function 12 and / or for a trained third function 13.The artificial neural network 100 comprises nodes 120,..., 132 and edges 140,..., 142, wherein each edge 140,..., 142 is a directed connection from a first node 120,..., 132 to a second node 120,..., 132. In general, the first node 120,..., 132 and the second node 120,..., 132 are different nodes 120,..., 132, it is also possible that the first node 120,..., 132 and the second node 120,..., 132 are identical. In FIG. 6, for example, edge 140 is a directed link from node 120 to node 123 and edge 142 is a directed link from node 130 to node 132. An edge 140,..., 142 from a first node 120,..., 132 to a second node 120,..., 132 is also referred to as an "incoming edge" for the second node 120,..., 132 and an "outgoing edge" for the first node 120,..., 132.In this embodiment, the nodes 120,..., 132 of the artificial neural network 100 may be arranged in layers 110,..., 113, wherein the layers may have an intrinsic order introduced between the nodes 120,..., 132 by the edges 140,..., 142. In particular, the edges 140,..., 142 may exist only between adjacent layers of nodes. In the embodiment shown, there is an input layer 110 that includes only nodes 120,..., 122 without incoming edges, an output layer 113 that includes only nodes 131, 132 without outgoing edges, and hidden layers 111, 112 between the input layer 110 and the output layer 113. In general, the number of hidden layers 111, 112 may be arbitrarily selected. The number of nodes 120,..., 122 within the input layer 110 typically refers to the number of input values of the neural network, and the number of nodes 131, 132 within the output layer 113 typically refers to the number of output values of the neural network.In particular, each node 120,..., 132 of the neural network 100 can be assigned a (real) number as a value. Here, x(n)i denotes the value of the i-th node 120,..., 132 of the n-th layer 110,..., 113. The values of the nodes 120,..., 122 of the input layer 110 correspond to the input values of the neural network 100, and the values of the nodes 131, 132 of the output layer 113 correspond to the output value of the neural network 100. Further, each edge 140,..., 142 may have a weight that is a real number, in particular, the weight is a real number within the interval [-1, 1] or within the interval [0, 1]. Here, w(m,n)i,j denotes the weight of the edge between the i-th node 120,..., 132 of the m-th layer 110,..., 113 and the j-th node 120,..., 132 of the n-th layer 110,..., 113. Furthermore, the abbreviation w(n)i,jis defined for the weight w(n,n+1)i,j.In order to calculate the output values of the neural network 100, in particular, the input values are propagated through the neural network. In particular, the values of the nodes 120,..., 132 of the (n+1)-th layer 110,..., 113 may be calculated based on the values of the nodes 120,..., 132 of the n-th layer 110,..., 113 byHere, the function f is a transfer function (another term is "activation function"). Known transfer functions are step functions, sigmoid functions (e.g. the logistic function, the generalized logistic function, the hyperbolic tangent, the arctangent function, the error function, the smoothstep function) or rectifier functions. The transfer function is mainly used for normalization.In particular, the values are propagated layer by layer through the neural network, the values of the input layer 110 are given by the input of the neural network 100, the values of the first hidden layer 111 can be calculated on the basis of the values of the input layer 110 of the neural network, the values of the second hidden layer 112 can be calculated on the basis of the values of the first hidden layer 111, etc.To set the values w(m,n)i,j for the edges, the neural network 100 must be trained with training data. The training data includes, in particular, training input data and training output data (denoted as ti). In a training step, the neural network 100 is applied to the training input data to generate calculated output data. In particular, the training data and the calculated output data comprise a number of values corresponding to the number of nodes of the output layer.In particular, a comparison between the calculated output data and the training data is used to recursively adapt the weights within the neural network 100 (backpropagation algorithm). Specifically, the weights are changed according to where γ is a learning rate, and the numbers δ(n)jcan be recursively calculated based on δ (n+1)j, when the (n+1)thlayer is not the output layer, and when the (n+1)thlayer is the output layer 113, where f' is the first derivative of the activation function and y(n+1)jis the comparison training value for the jthnode of the output layer 113.FIG. 10 shows an embodiment of a convolutional neural network 200 for the function or trained function. In the illustrated embodiment, convolutional neural network 200 includes an input layer 210, a convolutional layer 211, a pooling layer 212, a fully connected layer 213, and an output layer 214. Alternatively, convolutional neural network 200 may also include multiple convolutional layers 211, multiple pooling layers 212, and multiple fully-linked layers 213, as well as other types of layers. The order of the layers can be chosen arbitrarily, usually fully linked layers 213 are used as the last layers before the output layer 214.In particular, in a convolutional neural network 200, the nodes 220,..., 224 of a layer 210,..., 214 can be viewed as a d-dimensional matrix or as a d-dimensional image. Specifically, in the two-dimensional case, the value of the node 220,..., 224in the nthlayer 210,..., 214indicated with i and j may be referred to as x(n)[i,j]. However, the arrangement of nodes 220,..., 224 of a layer 210,..., 214 has no effect on the calculations performed in convolutional neural network 200 as such, since these are given solely by the structure and weights of the edges.In particular, a convolution layer 211 is characterized by the structure and weights of the incoming edges that form a convolution operation based on a certain number of cores. In particular, the structure and the weights of the incoming edges are chosen such that the values x (n)k of the nodes 221 of the convolution layer 211 are calculated as a convolution x (n)k= K k* x (n-1) on the basis of the values x (n-1) of the nodes 220 of the preceding layer 210, wherein the convolution in the two-dimensional case is defined asHere, the k-th core K k is a d-dimensional matrix (in this case, a two-dimensional matrix) that is generally small compared to the number of nodes 220,..., 224 (e.g., a 3x3 matrix or a 5x5 matrix). This means in particular that the weights of the incoming edges are not independent, but are chosen so that they yield the said convolution equation. In particular, for a kernel that is a 3x3 matrix, there are only 9 independent weights (each entry of the kernel matrix corresponds to an independent weight) regardless of the number of nodes 220,..., 224 in the respective layer 210,..., 214. In particular, for a convolution layer 211, the number of nodes 221 in the convolution layer is equal to the number of nodes 220 in the previous layer 210 multiplied by the number of kernels.When the nodes 220 of the previous layer 210 are arranged as a d-dimensional matrix, the use of a plurality of cores may be interpreted as adding another dimension (referred to as a "depth" dimension) such that the nodes 221 of the convolutional layer 221 are arranged as a (d+1)-dimensional matrix. If the nodes 220 of the preceding layer 210 are already arranged as a (d+1)-dimensional matrix having a depth dimension, then the use of a plurality of cores can be interpreted as an extension along the depth dimension, such that the nodes 221 of the convolution layer 221 are also arranged as a (d+1)-dimensional matrix, wherein the size of the (d+1)-dimensional matrix with respect to the depth dimension is greater by a factor of the number of cores than in the preceding layer 210.The advantage of using convolutional layers 211 is that a spatially local correlation of the input data can be exploited by forcing a local connectivity pattern between nodes of adjacent layers, in particular by connecting each node only to a small area of the nodes of the previous layer.In the illustrated embodiment, the input layer 210 includes 36 nodes 220 arranged as a 6x6 two-dimensional matrix. The convolution layer 211 comprises 72 nodes 221 arranged as two two-dimensional 6x6 matrices, each of the two matrices being the result of convolution of the values of the input layer with a kernel. Equivalently, the nodes 221 of the convolutional layer 211 may be interpreted as a 6x6x2 tridimensional matrix, the last dimension being the depth dimension.A pooling layer 212 may be characterized by the structure and weights of the incoming edges and the activation function of their nodes 222 forming a pooling operation based on a non-linear pooling function f. In the two-dimensional case, for example, the values x (n) of the nodes 222 of the pooling layer 212 can be calculated based on the values x (n-1) of the nodes 221 of the preceding layer 211 as follows:In other words, by using a pooling layer 212, the number of nodes 221, 222 may be reduced by replacing a number d1, d2of neighbor nodes 221 in the previous layer 211 with a single node 222 calculated as a function of the values of the number of neighbor nodes in the pooling layer. The pooling function f can be, in particular, the max function, the average or the L2normal. In particular, at pooling layer 212, the weights of the incoming edges are fixed and are not changed by the training.The advantage of using a pooling layer 212 is that the number of nodes 221, 222 and the number of parameters is reduced. This leads to a reduction in the computing effort in the network and to a control of the overfitting.In the embodiment shown, pooling layer 212 is a max pooling in which four neighboring nodes are replaced with only one node, the value being the maximum of the values of the four neighboring nodes. Max pooling is applied to each d-dimensional matrix of the previous layer; in this embodiment, max pooling is applied to each of the two two-dimensional matrices, thereby reducing the number of nodes from 72 to 18.A fully connected layer 213 may be characterized in that a plurality, in particular all edges, are present between the nodes 222 of the preceding layer 212 and the nodes 223 of the fully connected layer 213, and wherein the weight of each of the edges may be individually adjusted.In this embodiment, nodes 222 of parent layer 212 of fully-linked layer 213 are represented as both two-dimensional matrices and additionally as non-contiguous nodes (represented as a row of nodes, with the number of nodes reduced for ease of representation). In this embodiment, the number of nodes 223 in the fully connected layer 213 is equal to the number of nodes 222 in the previous layer 212. Alternatively, the number of nodes 222 and 223 may be different.Also, in this embodiment, the values of nodes 224 of output layer 214 are determined by applying the softmax function to the values of nodes 223 of previous layer 213. By applying the softmax function, the sum of the values of all nodes 224 of the output layer is 1, and all values of all nodes 224 of the output layer are real numbers between 0 and 1.A convolutional neural network 200 may also include a ReLU layer (acronym for "rectified linear units"). Specifically, the number of nodes and the structure of nodes in a ReLU layer correspond to the number of nodes and the structure of nodes in the previous layer. Specifically, the value of each node in the ReLU layer is calculated by applying a rectification function to the value of the corresponding node of the previous layer. Examples of rectification functions are f(x)=max(0,x), the tangential hyperbolic function or the sigmoid function.Convolutional neural networks 200 can be trained in particular on the basis of the backpropagation algorithm. To prevent overfitting, regularization methods may be used, e.g., omission of nodes 220,..., 224, stochastic pooling, use of artificial data, weight loss based on the L1 or L2 norm, or max norm constraints.Overall, the examples show how machine learning method for estimating an X-ray exposure distribution can be provided.An inhomogeneous X-ray beam leads to an inhomogeneous stress distribution. The resulting estimates of the skin (organ) Doses are not correct because the dose is locally higher / lower than determined with the DAP chamber.An important aspect of an exemplary embodiment of the invention is the prediction of an inhomogeneous beam (dose distribution) with the aid of a machine learning model, in particular a trained function, which has been trained on the basis of measured stress and detector intensity distributions. An inhomogeneous beam results in an inhomogeneous stress distribution on the beam and an inhomogeneous intensity distribution at the detector.An important aspect of an embodiment of the invention is therefore to use the intensity distribution of the detector of a particular system to "personalize" a general load distribution model.An important aspect of an exemplary embodiment of the invention is to combine two machine learning models, in particular the trained first function and the trained second function. The trained first function can predict the dose distribution in the beam based on the intensity distribution of the detector (no or homogeneous object in the beam), the tube and collimator settings, and the DAP (dose area product). This function can be trained using dosimetry measurements (e.g., with films) or simulations (e.g., Monte Carlo simulations) of multiple systems and detector images, as well as tube and collimator settings.The trained second function predicts the system specific detector intensity distribution (no or homogeneous object in the beam) from the tube and collimator settings. This model can be trained from data (detector images as well as tube and collimator settings) collected, for example, during annual service measurements.During application, for example during a medical intervention with a patient in the beam, the two models, i.e. the trained first function and the trained second function, can be combined, which enables a prediction of the dose distribution in the beam on the basis of the settings of tube and collimator.This advantageously ensures more accurate calculations of the X-ray dose. In particular, it can be ensured that the local peak dose (skin dose) is not underestimated.Regardless of the grammatical sex of a certain term, individuals with male, female or other sex identity are included.

Claims

Computer-implemented method (M1) for providing data of a load distribution (16) of a radiation (6) from a radiation source (4) of an imaging system (1), comprising the steps of: - receiving setting data (10) of the imaging system (1); - receiving a load characteristic variable (14) of the radiation (6) associated with the setting data (10); - receiving data of an intensity distribution (15) of the radiation (6) associated with the setting data (10) at a radiation detector (3) of the imaging system (1); - applying a trained, first function (11) to the setting data (10), the load characteristic variable (14) and the data of the intensity distribution (15) as first input data of the trained, first function (11), wherein the data of the load distribution (16) is generated as first output data of the trained, first function (11); providing the data of the load distribution (16).Computer-implemented method (M1) according to Claim 1, wherein the data of the intensity distribution (15) are provided by applying a trained, second function (12) to the setting data (10) as second input data of the trained, second function (12), wherein the data of the intensity distribution (15) are generated as second output data of the trained, second function (12).The computer-implemented method (M1) according to claim 2, wherein the trained second function (12) is provided by a computer-implemented second training method (M3), comprising the steps of: - receiving second input training data comprising setting data (10') of the imaging system (1); - receiving second output training data comprising data of the intensity distribution (15'), wherein the second output training data are related to the second input training data; - training a second function based on the second input training data and the second output training data by generating second output data by applying the second function to the second input training data and adjusting parameters of the second function based on a comparison of the second output data with the second output training data; - providing the trained second function (12).Computer-implemented method (M1) according to one of the preceding claims, wherein the load characteristic variable (14) is provided by applying a trained, third function (13) to the setting data (10) as third input data of the trained, third function (13), wherein the load characteristic variable (14) is generated as third output data of the trained, third function (13).The computer-implemented method (M1) according to claim 4, wherein the trained third function (13) is provided by a computer-implemented third training method (M4), comprising the steps of: - receiving third input training data comprising setting data (10') of the imaging system (1), - receiving third output training data comprising load characteristics (14'), wherein the third output training data are related to the third input training data; - training a third function based on the third input training data and the third output training data by generating third output data by applying the third function to the third input training data and adjusting parameters of the third function based on a comparison of the third output data with the third output training data; - providing the trained third function (13).Computer-implemented method (M1) according to one of the preceding claims, wherein the load characteristic variable (14) is a dose area product or a variable dependent on the dose area product.The computer-implemented method (M1) according to any one of the preceding claims, wherein the data of the intensity distribution (15) is a two-dimensional X-ray projection image.The computer-implemented method (M1) according to any of the preceding claims, wherein the data of the load distribution (16) is a two-dimensional image of the load distribution (16) at an interventional reference point (9) of the imaging system (1).Computer-implemented method (M1) according to one of the preceding claims, wherein the setting data (10) of the imaging system (1) comprise at least operating parameters of the radiation source (4) and / or of a collimator of the imaging system (1).The computer-implemented method (M1) according to any one of the preceding claims, wherein the imaging system (1) is an X-ray based imaging system and the radiation source (4) is an X-ray radiation source.Computer-implemented training method (M2) for providing a trained, first function (11) which generates data of a load distribution (16) of a radiation (6) from a radiation source (4) of an imaging system (1), having the steps of: - receiving first input training data, comprising - setting data (10') of the imaging system (1), - load characteristics (14') of the radiation (6) associated with the setting data (10'), and - data of an intensity distribution (15') of the radiation (6) associated with the setting data (10') at a radiation detector (3) of the imaging system (1); - receiving first output training data, comprising data of the load distribution (16'), wherein the first output training data are related to the first input training data; training a first function based on the first input training data and the first output training data by generating first output data by applying the first function to the first input training data and adjusting parameters of the first function based on a comparison of the first output data with the first output training data; providing the trained, first function (11).The computer-implemented training method (M2) according to claim 11, wherein the initial training data is provided by dosimetric measurements and / or dosimetric simulations.Data processing device (2) having at least one arithmetic unit (7) which is adapted to carry out a computer-implemented method (M1) according to one of Claims 1 to 10.A computer program product (8) comprising instructions which, when the computer program product (8) is executed on a data processing device (2), cause the data processing device (2) to perform the method (M1) according to any one of claims 1 to 10.Imaging system (1) comprising a data processing device (2) according to claim 13, a radiation source (4) for generating radiation (6), and a radiation detector (3) for detecting parts of the ionizing radiation (6), in particular parts of the radiation (6) that have passed through an object (5) to be imaged.

Images