PET detector target voltage determination method, computer equipment and PET detector power supply voltage regulation circuit

Abstract

The invention relates to a PET detector target voltage determining method and device, computer equipment, a readable storage medium and a PET detector power supply voltage adjusting circuit. Detector performance parameters corresponding to multiple alternative voltages are obtained, the detector performance parameters are input into a preset evaluation model, an evaluation result corresponding to each alternative voltage is obtained, and the evaluation model is a model representing different weights of the detector performance parameters of different dimensions in the evaluation result prediction process. The evaluation results corresponding to the multiple alternative voltages are compared, so that the alternative voltage with the optimal evaluation result is selected as the target voltage, and it is ensured that the performance of the PET detector can be optimal under the condition that the power supply voltage provided for the photomultiplier tube is provided. And closed-loop self-adaptive adjustment of the power supply voltage can be supported, so that the actual output voltage of the power supply circuit is stabilized at the target voltage, and the performance of the PET detector is improved.

Description

Technical Field

[0001] The present application relates to the technical field of PET detector voltage regulation, and in particular to a PET detector target voltage determination method, a computer device, and a PET detector power supply voltage regulation circuit. Background Art

[0002] The SiPM (Silicon photomultiplier) power supply voltage of the PET (Positron Emission Tomography) detector is very important. It affects the energy, signal amplitude, ASIC (Application Specific Integrated Circuit) scanning noise of the PET system, and the final TOF (Time of Flight) result. Therefore, the choice of power supply voltage is very important. Summary of the invention

[0003] Based on this, it is necessary to provide a PET detector target voltage determination method, a computer device and a PET detector power supply voltage adjustment circuit that can provide an adaptive power supply voltage for the photomultiplier tube in order to solve the above technical problems.

[0004] In a first aspect, the present application provides a method for determining a target voltage of a PET detector, the method comprising:

[0005] Obtaining detector performance parameters corresponding to a plurality of alternative voltages;

[0006] The detector performance parameters are input into a preset evaluation model to obtain an evaluation result corresponding to each candidate voltage; the evaluation model is a model that characterizes the different weights of detector performance parameters of different dimensions in the evaluation result prediction process;

[0007] The candidate voltage with the best evaluation result is selected as the target voltage.

[0008] In one embodiment, the detector performance parameters include flight time, energy resolution and sensitivity, and the training process of the preset evaluation model includes:

[0009] Acquire a first training sample set, wherein the first training sample set includes detector performance parameters corresponding to a plurality of voltage values ​​and corresponding actual evaluation results;

[0010] Inputting the detector performance parameters corresponding to the voltage values ​​in the first training sample set into a first preset learning model to obtain a prediction evaluation result;

[0011] Based on the deviation between the predicted evaluation result and the actual evaluation result corresponding to the voltage value, adjusting the weight of each detector performance parameter in the first preset learning model until a first end condition is met;

[0012] The trained first preset learning model is used as the evaluation model.

[0013] In one embodiment, the weight of flight time is greater than the weight of energy resolution, and the weight of energy resolution is greater than the weight of sensitivity.

[0014] In one embodiment, obtaining detector performance parameters corresponding to a plurality of candidate voltages includes:

[0015] The multiple candidate voltages are respectively input into a preset detector performance parameter prediction model to obtain the detector performance parameter corresponding to each of the candidate voltages.

[0016] In one embodiment, the training process of the detector performance parameter prediction model includes:

[0017] Acquire a second training sample set, wherein the second training sample set includes a plurality of voltage values ​​and actual performance parameters of the detector corresponding to each of the voltage values;

[0018] Inputting the voltage values ​​in the second training sample set into a second preset learning model to obtain the detector prediction performance parameters corresponding to the voltage values;

[0019] Based on the deviation between the predicted performance parameter of the detector and the actual performance parameter of the detector, adjusting the model parameters of the second preset learning model until a second end condition is reached;

[0020] The trained second preset learning model is used as the detector performance parameter prediction model.

[0021] In one embodiment, the step of obtaining the multiple candidate voltages includes:

[0022] Determine the initial voltage;

[0023] Taking the initial voltage as a reference, a plurality of candidate voltages are determined according to a preset voltage step.

[0024] In a second aspect, a computer device is provided, comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the above method when executing the computer program.

[0025] In a third aspect, a PET detector power supply voltage regulation circuit is provided, comprising:

[0026] A voltage acquisition circuit, wherein the input end of the voltage acquisition circuit is used to connect to the output end of the power supply circuit to acquire the actual output voltage of the power supply circuit;

[0027] A control circuit, wherein an input end of the control circuit is connected to an output end of the voltage acquisition circuit, an output end of the control circuit is used to connect to a controlled end of the power supply circuit, and the control circuit is used to adjust the power supply circuit according to a target voltage and the actual output voltage so that the actual output voltage is stabilized at the target voltage;

[0028] Wherein, the target voltage is determined by executing the steps of the above method.

[0029] In one embodiment, the voltage acquisition circuit includes:

[0030] an attenuator, wherein the input end of the attenuator is used to connect to the output end of the power supply circuit, and is used to attenuate the output voltage of the power supply circuit before outputting it;

[0031] An analog-to-digital sampling circuit, wherein the input end of the analog-to-digital sampling circuit is connected to the input end of the attenuator, and the analog-to-digital sampling circuit is used to amplify the input signal by a preset multiple after analog-to-digital conversion, and the preset multiple is the same as the attenuation multiple of the attenuator.

[0032] In one embodiment, the control circuit comprises:

[0033] A comparator, wherein an input terminal of the comparator is connected to an output terminal of the voltage acquisition circuit, and a reference terminal of the comparator is used to access a reference signal corresponding to the target voltage;

[0034] A feedback regulation network, wherein the input end of the feedback regulation network is connected to the output end of the comparator, the output end of the feedback regulation network is used to connect to the power supply circuit, and the feedback regulation network is used to adjust the size of the equivalent resistance connected to the power supply circuit so that the actual output voltage of the power supply circuit is stabilized at the target voltage.

[0035] The above-mentioned PET detector target voltage determination method, computer device and PET detector power supply voltage adjustment circuit obtain the detector performance parameters corresponding to multiple candidate voltages, input the detector performance parameters into a preset evaluation model, obtain the evaluation results corresponding to each candidate voltage, compare the evaluation results corresponding to multiple candidate voltages, and thus select the candidate voltage with the best evaluation result as the target voltage, so as to ensure that the performance of the PET detector can be optimized under the power supply voltage provided to the photomultiplier tube. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the drawings required for use in the embodiments of the present application or related technical descriptions will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0037] Figure 1 One of the flowcharts of the method for determining the target voltage of a PET detector in one or more embodiments;

[0038] Figure 2 A schematic diagram of a flow chart of a training step of a preset evaluation model in one or more embodiments;

[0039] Figure 3 The second flowchart of the method for determining the target voltage of a PET detector in one or more embodiments;

[0040] Figure 4 A schematic flow chart of the training steps of the detector performance parameter prediction model in one or more embodiments;

[0041] Figure 5 A schematic flow chart of the steps of determining multiple candidate voltages in one or more embodiments;

[0042] Figure 6 A structural block diagram of a device for determining a target voltage of a PET detector in one or more embodiments;

[0043] Figure 7 is an internal structure diagram of a computer device in one embodiment;

[0044] Figure 8 One of the circuit structure schematic diagrams of the PET detector power supply voltage regulation circuit in one or more embodiments;

[0045] Fig. 9 This is a second circuit structure schematic diagram of a PET detector power supply voltage regulation circuit in one or more embodiments. DETAILED DESCRIPTION

[0046] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0047] In an exemplary technique, the present application provides a method for determining a target voltage of a PET detector, such as Figure 1 As shown, the method includes:

[0048] S101, obtaining detector performance parameters corresponding to multiple alternative voltages. The multiple alternative voltages can be determined based on the commonly used power supply voltage of the PET detector, or can be determined by the user based on experience, or can be based on an initial voltage, and multiple alternative voltages are obtained by increasing and / or decreasing the initial voltage. The alternative voltage selected in this way is close to the power supply requirement of the PET detector, which can help to improve the processing speed of step S102 and step S103, thereby improving the efficiency of determining the target voltage. The acquisition of detector performance parameters can be obtained according to the NEMA2018 test method, or can be learned based on a preset learning model.

[0049] S102, input the detector performance parameters into the preset evaluation model to obtain the evaluation results corresponding to each alternative voltage. The detector performance parameters refer to the parameters that can characterize the performance of the PET detector when the PET detector is powered on, for example, may include but are not limited to flight time, energy resolution and sensitivity. The preset evaluation model refers to a model that can reflect the mapping relationship between the detector performance parameters and the evaluation results. And the preset evaluation model is a model that characterizes the different weights of detector performance parameters of different dimensions in the evaluation result prediction process, that is, the model can characterize the importance of the detector performance parameters of each dimension for evaluating the overall performance of the PET detector when the doctor actually uses the PET detector. The evaluation result is information used to characterize the overall performance of the PET detector. The form of the evaluation result may include but is not limited to scoring.

[0050] S103, selecting the candidate voltage with the best evaluation result as the target voltage. The candidate voltage with the best evaluation result is the candidate voltage when the detector performance is optimal.

[0051] Specifically, by obtaining detector performance parameters corresponding to multiple alternative voltages and inputting the detector performance parameters into a preset evaluation model, an evaluation result corresponding to each alternative voltage is obtained, and the evaluation results corresponding to the multiple alternative voltages are compared, so as to select the alternative voltage with the best evaluation result as the target voltage, thereby ensuring that the performance of the PET detector is optimal when the power supply circuit of the PET detector outputs the target voltage to the photomultiplier tube.

[0052] Under different PET detector voltages, changes in detector performance parameters in various dimensions may not be linear. There may be situations where the energy resolution is not the highest when the flight time is the shortest. Therefore, the evaluation model provided in the embodiment of the present application can simulate the doctor's evaluation process, and then select the optimal alternative voltage from multiple alternative voltages as the target voltage. Compared with the traditional manual method, this calculation process is fast and effective, and reduces labor costs. In addition, it will not cause uneven voltage determination results due to differences in personal levels of doctors, thereby improving the consistency and reliability of target voltage determination.

[0053] Exemplarily, the alternative voltages include 40V, 40.5V, 41V, 41.5V, 42V, 42.5V, 43V, 43.5V, 44V, 44.5V, and 45V. The detector performance parameters corresponding to these alternative voltages can be obtained according to the NEMA2018 test method. These detector performance parameters are input into the preset evaluation model, and the detector performance parameters of different dimensions have different weights in the evaluation result prediction process. For example, the flight time may account for 90%, the energy resolution weight may be 6%, and the sensitivity may account for 4%. Based on the evaluation results predicted by the evaluation model under this weight, the optimal alternative voltage for the evaluation result is 42.5V, and 42.5V can be used as the target voltage to guide the power supply of the PET detector.

[0054] Optionally, the detector performance parameters of different dimensions may have different weights in the evaluation result prediction process, which may be determined based on machine learning training or may be user-defined.

[0055] In one embodiment, the detector performance parameters include time of flight, energy resolution and sensitivity.

[0056] Among them, the time of flight (TOF) refers to the time difference from the generation of particles (such as the annihilation of positrons to produce two photons) to the capture of these particles by the detector. The unit of flight time is usually nanoseconds (ns). In PET imaging, two gamma photons are generated almost simultaneously and fly in opposite directions. By measuring the time difference between the two photons reaching the detector (i.e., the flight time), it can be determined whether they come from the same annihilation event, thereby helping to locate the location where the annihilation occurs, helping to improve the spatial resolution of the image and reduce background noise. During PET imaging, in addition to gamma photons from annihilation events, there are also noises from other sources, such as scattered photons or cosmic rays, which interfere with the clarity of the image. By reducing the flight time, the detector can more accurately distinguish between gamma photons from annihilation events and background noise, thereby reducing the impact of noise on the image and improving the signal-to-noise ratio and contrast of the image. Therefore, the shorter the flight time of the PET detector, the better.

[0057] Energy resolution refers to the ability of a detector to distinguish particles of different energies. It can be expressed as the ratio of the standard deviation of the energy distribution measured by the detector to the average energy. The unit of energy resolution is usually expressed as a percentage (%), or as the standard deviation of energy units (such as keV). In PET imaging, the energy of gamma photons is known (usually 511 keV), and the detector needs to be able to accurately measure the energy of these photons to distinguish between signals (i.e., gamma photons from annihilation events) and background noise (such as scattered photons or cosmic rays). The higher the energy resolution, the stronger the detector's ability to distinguish between signals and noise. Therefore, the higher the energy resolution of a PET detector, the better.

[0058] Sensitivity refers to the ability of a detector to detect particles. It is usually expressed as the ratio of the number of particles detected by the detector within a certain period of time to the number of incident particles. The unit of sensitivity is usually a percentage (%) or count rate (such as cps, counts per second). A highly sensitive detector can capture more gamma photons, thereby improving the statistical quality and signal-to-noise ratio of the image. Therefore, the higher the sensitivity of the PET detector, the better.

[0059] In one embodiment, if Figure 2 As shown, the training process of the preset evaluation model includes:

[0060] S201, obtaining a first training sample set, the first training sample set including detector performance parameters corresponding to a plurality of voltage values ​​and corresponding actual evaluation results. The actual evaluation results may be evaluation results fed back by users who use the PET detector clinically, and may indicate which dimension of the PET detector performance the user values ​​more when using the PET detector.

[0061] S202, input the detector performance parameters corresponding to the voltage values ​​in the first training sample set into the first preset learning model to obtain a prediction evaluation result. The first preset learning model can be a deep learning model or an AI model, or other models. For example, the first preset learning model can include a normalization model and a weight-based scoring model. The normalization model is used to normalize the detector performance parameters of multiple dimensions, and then the normalized results are input into the weight-based scoring model. The scoring model can be:

[0062] Y=Σ(Ki*Xi)

[0063] Wherein, Y is the evaluation result, Ki is the weight of the detector performance parameter in the i-th dimension, and Xi is the normalized result of the detector performance parameter in the i-th dimension. Taking the detector performance parameters including flight time, energy resolution and sensitivity as an example, the weight of flight time may be greater than the weight of energy resolution, and the weight of energy resolution may be greater than the weight of sensitivity.

[0064] S203, based on the deviation between the predicted evaluation result and the actual evaluation result corresponding to the voltage value, adjusting the weight of each detector performance parameter in the first preset learning model until the first end condition is met.

[0065] When the first preset learning model is different, the understanding of weights is different. For example, when the first preset learning model is a deep learning model, weights represent the strength between different neurons connecting the neural network, which determines the contribution of input data to the output of the deep learning model. The first end condition can be set according to the selected first preset learning model. For example, the first end condition can be that the preset maximum number of iterative training times is reached, or the deviation between the predicted evaluation result and the actual evaluation result corresponding to the voltage value is within a preset deviation range, or the training samples in the first sample training set have been traversed. The preset deviation range can be based on clinical usage requirements.

[0066] S204: Use the trained first preset learning model as an evaluation model.

[0067] The evaluation model trained based on the above steps can characterize the real needs of clinical doctors for detector performance parameters, and can ensure that the evaluation results obtained based on the evaluation model match the doctors' clinical evaluation of PET detectors. For example, in one embodiment, the weight of flight time is 90%, the weight of energy resolution is 7%, and the weight of sensitivity is 3%.

[0068] In one embodiment, the weight of the flight time is greater than the weight of the energy resolution, and the weight of the energy resolution is greater than or equal to the weight of the sensitivity.

[0069] During the evaluation model training process, the weight of flight time is greater than the weight of energy resolution, and the weight of energy resolution is greater than the weight of sensitivity. This is consistent with the importance of multi-dimensional performance parameters when doctors evaluate the overall performance of PET detectors in clinical practice, and can ensure that the trained evaluation model is close to the actual evaluation of doctors. Therefore, it can be ensured that when the target voltage determined based on the evaluation model is loaded on the PET detector, the flight time of the PET detector is short, and the energy resolution and sensitivity are high.

[0070] In one embodiment, if Figure 3As shown, step S101 of obtaining detector performance parameters corresponding to a plurality of candidate voltages includes:

[0071] S301, inputting a plurality of candidate voltages into a preset detector performance parameter prediction model respectively to obtain a detector performance parameter corresponding to each candidate voltage.

[0072] Under the traditional testing method, it takes about two weeks to test two alternative voltages. The testing cycle is very long, and the testing depends on various measuring instruments, and the testing equipment cost is high. In addition, each test requires an appointment with the radiologist in advance. The testing time depends on the time of the radiologist, the testing time flexibility is low, and medical resources are occupied. That is, when there are many alternative voltages, if the traditional actual testing method is used to obtain the detector performance parameters, the testing cycle will be very long, and the labor cost and equipment cost of the test are high. The method provided in the embodiment of the present application predicts the detector performance parameters of the PET detector when the alternative voltage is loaded by pre-training a detector performance parameter prediction model, and uses a deep learning model or an AI model.

[0073] The process of predicting detector performance parameters based on the detector performance parameter prediction model can be carried out at any time with high time flexibility. It can also be automatically executed when the staff is resting, which can greatly improve the efficiency of the detector performance parameter acquisition process. In addition, the execution process does not need to rely on professional medical staff, thus avoiding the occupation of medical resources. There is no need to transfer measuring instruments, thus reducing the hardware cost of the test process.

[0074] In one embodiment, if Figure 4 As shown, the training process of the detector performance parameter prediction model includes:

[0075] S401, obtaining a second training sample set, the second training sample set including a plurality of voltage values ​​and actual performance parameters of the detector corresponding to each voltage value. The second training sample set may be obtained based on the historical use record of the PET detector. The actual performance parameters of the detector are PET detector performance parameters determined based on the detection instrument, such as sensitivity, energy resolution, flight time, etc.

[0076] S402, inputting the voltage values ​​in the second training sample set into the second preset learning model to obtain the detector prediction performance parameters corresponding to the voltage values.

[0077] S403, based on the deviation between the predicted performance parameter of the detector and the actual performance parameter of the detector, adjusting the model parameters of the second preset learning model until the second end condition is met.

[0078] Among them, steps S402 to S403 can be executed in a loop: input the voltage values ​​in the second training sample set into the second preset learning model to obtain the detector prediction performance parameters corresponding to the voltage values, and based on the deviation between the detector prediction performance parameters and the detector actual performance parameters, adjust the model parameters of the second preset learning model until the second end condition is reached.

[0079] The second end condition can be set according to the selected second preset learning model. For example, the second end condition can be that the preset maximum number of iterative training times is reached, or the deviation between the predicted performance parameter of the detector and the actual performance parameter of the detector is within a preset deviation range, or the samples in the second training sample set have been traversed. The preset deviation range can be determined based on clinical usage requirements.

[0080] S404: Use the trained second preset learning model as a detector performance parameter prediction model.

[0081] In one embodiment, the step of obtaining multiple alternative voltages includes:

[0082] S501, determining an initial voltage. The initial voltage is a voltage value commonly used in PET detector application scenarios. For example, the initial voltage may be 40V.

[0083] S502, using the initial voltage as a reference, determine multiple candidate voltages according to a preset voltage step. The preset voltage step can be set according to the accuracy requirement of the target voltage. The higher the accuracy requirement, the smaller the preset voltage step should be. For example, in one embodiment, the preset voltage step is 0.5V.

[0084] In one embodiment, step S502 includes:

[0085] Taking the initial voltage as a reference, multiple candidate voltages are determined within a preset voltage range according to a preset voltage step. By generating the candidate voltages under the voltage range constraint, it is possible to avoid endlessly generating the candidate voltages, which would increase the amount of calculation in the process of determining the target voltage.

[0086] For example, the voltage range may be [38V-42V]. At this time, with 40V as the initial voltage and 0.5V as the preset voltage step, the following alternative voltages may be generated: 38V, 38.5V, 39V, 39.5V, 40V, 40.5V, 41V, 41.5V, 42V.

[0087] In one example, the preset voltage range can also be 40V-45V, the preset voltage step is 0.5V, and the initial voltage is 40V. By executing the above method steps, 11 alternative voltages (40V, 40.5V, 41V, 41.5V, 42V, 42.5V, 43V, 43.5V, 44V, 44.5V, 45V) can be automatically generated, and the above-mentioned detector performance parameter acquisition steps are performed under 11 alternative voltages to obtain the detector performance parameters under 11 alternative voltages.

[0088] It should be understood that, although the steps in the flowcharts involved in the above embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps is not strictly limited in order, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above embodiments may include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0089] Based on the same inventive concept, the embodiment of the present application further provides a PET detector target voltage determination device for implementing the above-mentioned PET detector target voltage determination method. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above-mentioned method, so the specific limitations in one or more PET detector target voltage determination device embodiments provided below can refer to the above-mentioned limitations on the PET detector target voltage determination method, and will not be repeated here.

[0090] In an exemplary embodiment, Figure 6 As shown, a device for determining a target voltage of a PET detector is provided, the device comprising: a performance parameter acquisition module 601, an evaluation module 602, and a target voltage determination module 603. Among them:

[0091] The performance parameter acquisition module 601 is used to acquire the detector performance parameters corresponding to a plurality of candidate voltages;

[0092] Evaluation module 602, used to input the detector performance parameters into a preset evaluation model to obtain an evaluation result corresponding to each candidate voltage;

[0093] The target voltage determination module 603 is used to select the candidate voltage with the best evaluation result as the target voltage.

[0094] Among them, for the definitions of terms such as detector performance parameters, please refer to the description in the above embodiments, which will not be repeated here.

[0095] Each module in the above-mentioned PET detector target voltage determination device can be implemented in whole or in part by software, hardware and a combination thereof. Each of the above-mentioned modules can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute operations corresponding to each of the above modules. The above-mentioned PET detector target voltage determination device can also include other modules or units to execute other steps in the above-mentioned method embodiment and achieve corresponding beneficial effects.

[0096] In an exemplary embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as shown in FIG. Figure 7 As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. Among them, the processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store data such as a first preset learning model, a second preset learning model, a first training sample set, and a second training sample set. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a method for determining a target voltage of a PET detector is implemented.

[0097] Those skilled in the art will understand that Figure 7 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0098] In an exemplary embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the steps in the above method embodiment are implemented and corresponding beneficial effects are achieved.

[0099] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above method embodiment are implemented and corresponding beneficial effects are achieved.

[0100] In one embodiment, a computer program product is provided, including a computer program. When the computer program is executed by a processor, the steps in the above method embodiment are implemented and corresponding beneficial effects are achieved.

[0101] A person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment method can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, an artificial intelligence (AI) processor, etc., but are not limited to this.

[0102] In one embodiment, Figure 8As shown, a PET detector power supply voltage regulation circuit is provided, comprising: a voltage acquisition circuit 801, and a control circuit 802. Among them:

[0103] The input end of the voltage acquisition circuit 801 is used to connect to the output end of the power supply circuit 803 to acquire the actual output voltage of the power supply circuit 803. The input end of the control circuit 802 is connected to the output end of the voltage acquisition circuit 801, and the output end of the control circuit 802 is used to connect to the controlled end of the power supply circuit 803. The control circuit 802 is used to adjust the power supply circuit 803 according to the target voltage and the actual output voltage, so that the actual output voltage is stabilized at the target voltage; wherein the target voltage is determined by executing the steps of the above method.

[0104] The actual output voltage output from the power supply circuit 803 to the photomultiplier tube 804 is collected by the voltage collection circuit 801 and input into the control circuit 802. The control circuit 802 then adjusts the power supply circuit 803 based on the target voltage and the actual output voltage to achieve closed-loop control. The output of the power supply circuit 803 can be adjusted based on the real-time output of the power supply circuit 803 to achieve closed-loop adaptive adjustment of the power supply voltage, thereby providing a stable target voltage for the photomultiplier tube and improving the performance of the PET detector.

[0105] It should be understood that the PET detector may include multiple photomultiplier tubes arranged in an array, in which case the power supply circuit may provide corresponding target voltages for the multiple photomultiplier tubes one by one. The supply voltage regulation of individual photomultiplier tubes may be independent of each other.

[0106] In one embodiment, if Fig. 9 As shown, the voltage acquisition circuit 801 includes: an attenuator 8011, and an analog-to-digital sampling circuit 8012. Among them:

[0107] The input end of the attenuator is used to connect to the output end of the power supply circuit, and is used to attenuate the output voltage of the power supply circuit and then output it; the input end of the analog-to-digital sampling circuit is connected to the input end of the attenuator, and the analog-to-digital sampling circuit is used to convert the input signal into analog-to-digital and then amplify the preset multiple, which is the same as the attenuation multiple of the attenuator.

[0108] The attenuator may be a resistor attenuator. For example, the attenuator may include a plurality of series-connected voltage-dividing resistors. After the resistor voltage division, the voltage after the voltage division may be less than the voltage at the output end of the power supply circuit, thereby achieving voltage reduction to match the input signal requirements of the analog-to-digital sampling circuit. For example, if the input port range of the analog-to-digital sampling circuit is 0-3.3V, then when selecting the attenuator, it is necessary to support attenuating the output voltage of the power supply circuit to the range of 0-3.3V to adapt to the input voltage requirements of the input port.

[0109] The analog-to-digital sampling circuit converts the input voltage into a digital signal after analog-to-digital conversion, so that in the backward transmission process, the subsequent circuit can use a digital circuit to reduce the overall volume of the voltage acquisition circuit. The analog-to-digital sampling circuit can specifically use analog-to-digital converters with different precision and bit numbers, which are selected according to the application scenario. The analog-to-digital sampling circuit is also used to multiply the voltage signal after analog-to-digital conversion by the attenuation multiple to restore it to the actual output voltage of the power supply.

[0110] In one embodiment, if Fig. 9 As shown, the control circuit 802 includes: a comparator 8021, and a feedback regulation network 8022. Wherein:

[0111] The input end of the comparator is connected to the output end of the voltage acquisition circuit, and the reference end of the comparator is used to access the reference signal corresponding to the target voltage; the input end of the feedback regulation network is connected to the output end of the comparator, and the output end of the feedback regulation network is used to connect to the power supply circuit. The feedback regulation network is used to adjust the equivalent resistance connected to the power supply circuit so that the actual output voltage of the power supply circuit is stabilized at the target voltage.

[0112] Among them, the larger the actual output voltage is, the smaller the equivalent resistance is. Conversely, the smaller the actual output voltage is, the larger the equivalent resistance is. The two are negatively correlated.

[0113] When the actual output voltage is inconsistent with the set target voltage, the difference is compensated through the feedback regulation network (which may include but is not limited to the use of DAC, digital potentiometer, analog switch, etc.). The feedback regulation network will monitor and control the output voltage of the power supply circuit in real time and achieve the function of adaptive regulation.

[0114] For example, the feedback regulation network may include a DAC digital-to-analog conversion circuit and a controller. The DAC digital-to-analog conversion circuit converts the digital output of the comparator into an analog voltage signal and inputs it into the controller. The controller generates a control command based on the output of the DAC digital-to-analog conversion circuit (the output represents the difference between the actual output voltage and the set target voltage) to control the on-off state of the digital potentiometer or analog switch to achieve the equivalent resistance of the power supply circuit, thereby adjusting the output voltage of the power supply circuit.

[0115] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0116] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A method for determining a target voltage of a PET detector, characterized in that: The method comprises: Obtaining detector performance parameters corresponding to a plurality of alternative voltages; The detector performance parameters are input into a preset evaluation model to obtain an evaluation result corresponding to each candidate voltage; the evaluation model is a model that characterizes the different weights of detector performance parameters of different dimensions in the evaluation result prediction process; The candidate voltage with the best evaluation result is selected as the target voltage.

2. The method according to claim 1, characterized in that The detector performance parameters include flight time, energy resolution and sensitivity. The training process of the preset evaluation model includes: Acquire a first training sample set, wherein the first training sample set includes detector performance parameters corresponding to a plurality of voltage values ​​and corresponding actual evaluation results; Inputting the detector performance parameters corresponding to the voltage values ​​in the first training sample set into a first preset learning model to obtain a prediction evaluation result; Based on the deviation between the predicted evaluation result and the actual evaluation result corresponding to the voltage value, adjusting the weight of each detector performance parameter in the first preset learning model until a first end condition is met; The trained first preset learning model is used as the evaluation model.

3. The method according to claim 2, characterized in that The weight of the flight time is greater than the weight of the energy resolution, and the weight of the energy resolution is greater than the weight of the sensitivity.

4. The method according to claim 1, characterized in that The step of obtaining detector performance parameters corresponding to a plurality of candidate voltages includes: The multiple candidate voltages are respectively input into a preset detector performance parameter prediction model to obtain the detector performance parameter corresponding to each of the candidate voltages.

5. The method according to claim 4, characterized in that The training process of the detector performance parameter prediction model includes: Acquire a second training sample set, wherein the second training sample set includes a plurality of voltage values ​​and actual performance parameters of the detector corresponding to each of the voltage values; Inputting the voltage values ​​in the second training sample set into a second preset learning model to obtain the detector prediction performance parameters corresponding to the voltage values; Based on the deviation between the predicted performance parameter of the detector and the actual performance parameter of the detector, adjusting the model parameters of the second preset learning model until a second end condition is reached; The trained second preset learning model is used as the detector performance parameter prediction model.

6. The method according to any one of claims 1 to 5, characterized in that: The step of obtaining the multiple candidate voltages comprises: Determine the initial voltage; Taking the initial voltage as a reference, a plurality of candidate voltages are determined according to a preset voltage step.

7. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 5 are implemented.

8. A PET detector power supply voltage regulation circuit, characterized in that: include: A voltage acquisition circuit, wherein the input end of the voltage acquisition circuit is used to connect to the output end of the power supply circuit to acquire the actual output voltage of the power supply circuit; A control circuit, wherein an input end of the control circuit is connected to an output end of the voltage acquisition circuit, an output end of the control circuit is used to connect to a controlled end of the power supply circuit, and the control circuit is used to adjust the power supply circuit according to a target voltage and the actual output voltage so that the actual output voltage is stabilized at the target voltage; Wherein, the target voltage is determined by executing the steps of the method according to any one of claims 1-6.

9. The circuit according to claim 8, characterized in that The voltage acquisition circuit comprises: an attenuator, wherein the input end of the attenuator is used to connect to the output end of the power supply circuit, and is used to attenuate the output voltage of the power supply circuit before outputting it; An analog-to-digital sampling circuit, wherein the input end of the analog-to-digital sampling circuit is connected to the input end of the attenuator, and the analog-to-digital sampling circuit is used to amplify the input signal by a preset multiple after analog-to-digital conversion, and the preset multiple is the same as the attenuation multiple of the attenuator.

10. The circuit according to claim 8, characterized in that The control circuit comprises: A comparator, wherein an input terminal of the comparator is connected to an output terminal of the voltage acquisition circuit, and a reference terminal of the comparator is used to access a reference signal corresponding to the target voltage; A feedback regulation network, wherein the input end of the feedback regulation network is connected to the output end of the comparator, the output end of the feedback regulation network is used to connect to the power supply circuit, and the feedback regulation network is used to adjust the size of the equivalent resistance connected to the power supply circuit so that the actual output voltage of the power supply circuit is stabilized at the target voltage.

Images