X-ray tube filament current correction method and device, equipment and storage medium

By constructing a filament current prediction model and generating a correction value database, the problems of low efficiency and poor accuracy of the filament current correction of X-ray tubes are solved, and efficient and accurate correction effects are achieved, which are suitable for the same type of X-ray tubes.

CN119071989APending Publication Date: 2024-12-03SUZHOU POWERSITE ELECTRIC CO LTD
View PDF 0 Cites 3 Cited by

Patent Information

Application Number
CN202411476961.X
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-10-22
Publication Date
2024-12-03

AI Technical Summary

Technical Problem

The existing X-ray tube filament current correction methods are inefficient and have poor accuracy, resulting in waste of X-ray tube life and inaccurate measurement.

Method used

By obtaining the filament current calibration data set of the X-ray tube, a filament current prediction model is constructed and a correction value database is generated to correct the target X-ray tube to improve measurement accuracy and applicability.

Benefits of technology

It improves the correction efficiency and accuracy of the filament current of the X-ray tube, reduces the number of exposures, and is suitable for other X-ray tubes of the same type, enhancing the universality and popularization of the method.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119071989A_ABST
    Figure CN119071989A_ABST
Patent Text Reader

Abstract

The invention relates to the technical field of medical instruments, and discloses an X-ray tube filament current correction method, device and equipment and a storage medium, and the method comprises the steps: obtaining a filament current calibration data set of a first X-ray tube, building a filament current prediction model based on the filament current calibration data set, and obtaining a filament current prediction model; processing each tube current and tube voltage of the first X-ray tube in the filament current calibration data set according to a filament current prediction model to obtain each prediction result, and taking the deviation between each prediction result and the corresponding measured value as a correction value corresponding to each tube current and tube voltage of the first X-ray tube, and generating a correction value database. According to the invention, the filament current calibration data set of the first X-ray tube is obtained, the filament current prediction model is constructed based on the calibration data set, the deviation between the prediction result and the actual measurement is calculated to obtain the correction value database, and the correction value database is used for correcting the filament current of the X-ray tubes of the same type.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of medical devices, and in particular to a correction method, device, equipment and storage medium for an X-ray tube filament current. Background Art

[0002] X-ray detection has important applications in hospital patient diagnosis, industrial non-destructive testing, station security inspection and other fields. As the core component of X-ray detection, the X-ray tube is a vacuum diode working under high voltage. The X-ray tube contains two electrodes, the anode and the cathode: one is a filament used to emit electrons, which serves as the cathode, and the other is a target material used to receive electron bombardment, which serves as the anode. There is a strong nonlinear relationship between the tube current and the filament current, so before each X-ray tube is used, the corresponding nonlinear relationship between the tube current and the filament current needs to be calibrated.

[0003] The commonly used methods at present include: 1) exposing at each working point of the filament current and testing to obtain the corresponding tube current value. Due to the large number of working points, a large number of tests are required to obtain the corresponding relationship between the tube current and the filament current. This method has the problems of too many exposure points, large amount of data, waste of X-ray tube life and low efficiency; 2) directly using the relevant parameters provided by the manufacturer, but the accuracy and consistency are very poor, and there are differences in the filament current modulation methods due to different high-voltage generator systems. Summary of the invention

[0004] In view of this, the present invention provides a correction method, device, equipment and storage medium for an X-ray tube filament current to solve the problems of low correction efficiency and poor accuracy of traditional correction methods.

[0005] In a first aspect, the present invention provides a method for correcting an X-ray tube filament current, the method comprising:

[0006] Acquire a filament current calibration data set of the first X-ray tube; the filament current calibration data set includes a tube current, a tube voltage, and filament current data corresponding to the tube current and the tube voltage of the first X-ray tube;

[0007] Based on the filament current calibration data set, a filament current prediction model is constructed;

[0008] Processing each tube current and tube voltage of the first X-ray tube in the filament current calibration data set according to the filament current prediction model to obtain each prediction result;

[0009] Deviations between each predicted result and the corresponding measured value are used as correction values ​​corresponding to each tube current and tube voltage of the first X-ray tube, respectively, to generate a correction value database; the correction value database is used to correct the filament current of the target X-ray tube to obtain a correction result; the target X-ray tube and the first X-ray tube are of the same type.

[0010] The method for correcting the filament current of an X-ray tube provided in an embodiment of the present invention obtains a filament current calibration data set of a first X-ray tube, and builds a filament current prediction model based on these data, compares the prediction result with the measured value, obtains a correction value, and stores it in a correction value database, which can be subsequently used to correct the filament current of other X-ray tubes of the same type, thereby improving the accuracy of the measurement. In addition, the method is applicable to X-ray tubes of the same type, and only needs to calibrate the first X-ray tube and establish a correction value database, and can be quickly applied to other devices of the same type, so it has strong versatility and extensibility.

[0011] In an optional implementation, a filament current prediction model is constructed based on the filament current calibration data set, including:

[0012] Determining the weight of each data in the filament current calibration data set based on the use condition of the first X-ray tube;

[0013] A filament current prediction model is established based on the filament current calibration data set and weights.

[0014] The correction method for the filament current of an X-ray tube provided in an embodiment of the present invention can more accurately reflect the state of the X-ray tube in actual work by considering the operating conditions of the X-ray tube, and adjust the weight of the data according to the operating conditions, so that the data points with a greater impact on the prediction results are given more attention, thereby ensuring that the prediction model is closer to the actual situation and improving the accuracy of the prediction.

[0015] In an optional embodiment, the method further includes:

[0016] The target tube current and target tube voltage of the target X-ray tube are processed based on the filament current prediction model to obtain a target prediction result;

[0017] Obtaining a target correction value corresponding to a target prediction result in a correction value database;

[0018] The sum of the target prediction result and the target correction value is taken as the correction result.

[0019] The correction method for the filament current of an X-ray tube provided in an embodiment of the present invention can obtain a preliminary target prediction result by directly using the filament current prediction model to process the target X-ray tube, and can further improve the correction accuracy by combining the target correction value in the correction value database. This method is not only applicable to the first X-ray tube itself, but also to other X-ray tubes of the same type, which greatly enhances the applicability of the method.

[0020] In an optional implementation, obtaining a target correction value corresponding to a target prediction result in a correction value database includes:

[0021] If there is target data identical to the target tube current and the target tube voltage in the correction value database, the correction value corresponding to the target data is confirmed as the target correction value;

[0022] If the correction value database does not contain target data identical to the target tube current and the target tube voltage, the target correction value is obtained based on adjacent data; the adjacent data includes data adjacent to the target tube current and the target tube voltage in the correction value database.

[0023] The correction method for the filament current of an X-ray tube provided by an embodiment of the present invention directly uses the corresponding correction value for correction when there is data in the correction value database that is completely identical to the target tube current and the target tube voltage, thereby ensuring the high accuracy of the correction result; when there is no completely matching data, the target correction value is obtained based on the adjacent data, so that the method is not only applicable to the case where there is completely matching data in the database, but also applicable to the case where there is no completely matching data but correction is required, thereby greatly enhancing the applicability and flexibility of the method.

[0024] In an optional implementation, if there is no target data identical to the target tube current and the target tube voltage in the correction value database, the target correction value is obtained based on adjacent data of the target data, including:

[0025] The adjacent correction values ​​corresponding to the adjacent data are interpolated to obtain the target correction value.

[0026] The correction method for the filament current of an X-ray tube provided in an embodiment of the present invention can estimate the target correction value based on adjacent known correction values ​​through interpolation calculation, thereby maintaining the continuity and smoothness of the correction result to a certain extent, so as to avoid abrupt jumps between data points, improve the overall correction accuracy, and make the corrected filament current closer to the true value. In addition, since the interpolation calculation is applicable to various types of data distribution, whether it is a linear or nonlinear relationship, a more accurate estimation result can be obtained by selecting a suitable interpolation method, which enhances the applicability and flexibility of the method.

[0027] In an optional embodiment, the method further includes:

[0028] Expose the target X-ray tube a preset number of times to obtain a target measured value of the filament current of the target X-ray tube;

[0029] The filament current prediction model is adjusted based on the target measured value to obtain a target prediction model, so that the target error between the correction result obtained based on the target prediction model and the target measured value is within a preset range.

[0030] The X-ray tube filament current correction method provided by the embodiment of the present invention performs actual exposure on the target X-ray tube and measures the filament current. These data can be used to fine-tune the filament current prediction model to obtain a target prediction model. The target prediction model is closer to the actual operating conditions of the target X-ray tube and closer to the measured value, thereby improving the measurement accuracy of the target X-ray tube.

[0031] In an optional implementation, adjusting the filament current prediction model based on the target measured value to obtain a target prediction model includes:

[0032] Obtain each coefficient in the filament current prediction model;

[0033] Calculate the rate of change of each coefficient relative to the predicted result;

[0034] According to the magnitude of the change rate, a preset number of first coefficients are selected from each coefficient from high to low;

[0035] The first coefficient is adjusted based on the target error to obtain a target prediction model so that the target error is within a preset range.

[0036] The correction method for the filament current of an X-ray tube provided in an embodiment of the present invention can more effectively optimize the model by selecting the coefficient with the greatest influence on the prediction result, that is, the coefficient with the largest change rate as the first coefficient for adjustment, so that it can more accurately reflect the actual data. In addition, only adjusting the key coefficients can significantly reduce the amount of calculation because there is no need to recalculate or optimize the entire model. This targeted adjustment method is more efficient than comprehensively adjusting all coefficients, while maintaining the stability and robustness of the model.

[0037] In a second aspect, the present invention provides a device for correcting the filament current of an X-ray tube, the device comprising:

[0038] An acquisition module is used to acquire a filament current calibration data set of the first X-ray tube; the filament current calibration data set includes a tube current and a tube voltage of the first X-ray tube and filament current data corresponding to the tube current and the tube voltage;

[0039] A building module for building a filament current prediction model based on a filament current calibration data set;

[0040] A processing module, used for processing each tube current and tube voltage of the first X-ray tube in the filament current calibration data set according to the filament current prediction model to obtain each prediction result;

[0041] A generation module is used to use the deviation between each prediction result and the corresponding measured value as the correction value corresponding to each tube current and tube voltage of the first X-ray tube, so as to generate a correction value database; the correction value database is used to correct the filament current of the target X-ray tube to obtain a correction result; the target X-ray tube and the first X-ray tube are of the same type.

[0042] In a third aspect, the present invention provides a computer device, comprising: a memory and a processor, the memory and the processor being communicatively connected to each other, the memory storing computer instructions, and the processor executing the method for correcting the X-ray tube filament current of the first aspect or any corresponding embodiment thereof by executing the computer instructions.

[0043] In a fourth aspect, the present invention provides a computer-readable storage medium having computer instructions stored thereon, the computer instructions being used to enable a computer to execute the method for correcting the X-ray tube filament current of the first aspect or any corresponding embodiment thereof. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] In order to more clearly illustrate the specific implementation methods of the present invention or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0045] Figure 1 is a flow chart of a method for correcting an X-ray tube filament current according to an embodiment of the present invention;

[0046] Figure 2 is a schematic diagram of a weight function of a method for correcting an X-ray tube filament current according to an embodiment of the present invention;

[0047] Figure 3 is a schematic diagram of a deviation data set of a method for correcting an X-ray tube filament current according to an embodiment of the present invention;

[0048] Figure 4 is a structural block diagram of a device for correcting filament current of an X-ray tube according to an embodiment of the present invention;

[0049] Figure 5 It is a schematic diagram of the hardware structure of a computer device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0050] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0051] X-ray detection has important applications in hospital patient diagnosis, industrial non-destructive testing, station security inspection and other fields.

[0052] The X-ray tube has a cathode and an anode, and the filament current is set at the cathode. During the operation of the X-ray tube, the cathode filament passes through the current, the filament temperature rises, and it has the ability to emit electrons. At this time, a high voltage is applied to the positive and negative electrodes to convert part of the electrical energy into the tube current of the X-ray. Because there is a strong nonlinear relationship between the tube current and the filament current. Before each X-ray tube is used, the corresponding nonlinear relationship between the tube current and the filament current needs to be calibrated.

[0053] The commonly used methods at present include: 1) by exposing at each working point of the filament current, testing to obtain the corresponding tube current value, due to the large number of working points, a large number of tests are required to obtain the corresponding relationship between the tube current and the filament current. This method has too many exposure points, a large amount of data, and waste of the life of the X-ray tube; 2) The tube data manual provided by some manufacturers usually contains a calibration curve diagram of the filament current and the tube current under some tube voltages. Some manufacturers can provide detailed calibration data tables between tube voltage, tube current and filament current, and directly use the relevant parameters provided by the manufacturer. Compared with the above process, this parameter does not need to be corrected, but the accuracy and consistency are very poor, and there are differences in the filament current modulation method due to different high-voltage generator systems. For the same type of X-ray tube, the present invention only needs to use the intelligent tube training mode, through a small number of exposures, to solve some key coefficients, that is, to complete the solution of the filament current prediction function, which not only avoids multiple exposures and wastes the life of the X-ray tube, but also ensures the prediction accuracy.

[0054] According to an embodiment of the present invention, an embodiment of a method for correcting the filament current of an X-ray tube is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0055] In this embodiment, a method for correcting the filament current of an X-ray tube is provided. Figure 1is a flow chart of a method for correcting the filament current of an X-ray tube according to an embodiment of the present invention, such as Figure 1 As shown, the process includes the following steps:

[0056] Step S101, obtaining a filament current calibration data set of a first X-ray tube.

[0057] Specifically, the filament current calibration data set includes the tube current and tube voltage of the first X-ray tube and the filament current data corresponding to the tube current and tube voltage.

[0058] Furthermore, the filament current calibration data set of the first X-ray tube can be derived from the following two methods: first, the X-ray tube data manual is used to obtain the original data or waveform of the X-ray tube filament current calibration curve, which usually includes a calibration curve diagram of the filament current and the tube current under a fixed tube voltage. Some manufacturers can provide a detailed calibration data set between the tube current and the filament current under a fixed tube voltage. Second, the same type of tube is subjected to a traditional exposure mode to obtain the tube current output by the X-ray tube at different tube voltages and different filament currents to form a calibration data set.

[0059] Step S102: constructing a filament current prediction model based on the filament current calibration data set.

[0060] Specifically, a filament current prediction model library is established based on the machine learning regression model library, and different types of filament current prediction model families are selected according to the computing power of the CPU.

[0061] Furthermore, a polynomial regression prediction model can be used for low-computing power CPUs, a Gaussian process regression model can be used for medium-computing power CPUs, and a support vector machine model can be used for high-computing power CPUs.

[0062] Furthermore, the selected machine learning model is trained using the training set data. During the training process, the model learns the mapping relationship between the tube current and the tube voltage and the filament current, and obtains the filament current prediction model.

[0063] Optionally, for the selected model, perform parameter tuning, which includes adjusting the model's hyperparameters, such as the polynomial degree in polynomial regression, kernel function parameters in Gaussian process regression, C parameter and gamma parameter in support vector machine, etc., to find the best model configuration.

[0064] In some optional implementations, the above step S102 includes:

[0065] Step a1: determining the weight of each data in the filament current calibration data set based on the operating condition of the first X-ray tube;

[0066] Step a2: Establish a filament current prediction model based on the filament current calibration data set and weights.

[0067] Based on the X-ray tube usage conditions, the weight rules are determined. For example, for medical CT, the usage conditions need to be classified according to the exposure conditions of children, adults and their transmission parts. For example, they can be divided into different working condition categories such as children's scanning, adult chest scanning, and adult head scanning. Different weights are applied to the calibration data set respectively. The weight can be a value between 0 and 1, indicating the importance of the data in building the prediction model.

[0068] According to the weight rule determined in step a1, each data point in the filament current calibration data set is weighted, and the weighted data set will pay more attention to those data points that are more important to specific working conditions. Based on the selected filament current prediction model family, under the corresponding weight rule, through regression analysis, machine learning, swarm intelligence optimization algorithm and other algorithms, the root mean square error between the calibration data set and the prediction result meets the allowable error.

[0069] Step S103, processing each tube current and tube voltage of the first X-ray tube in the filament current calibration data set according to the filament current prediction model to obtain each prediction result.

[0070] Specifically, the tube current and tube voltage are extracted from the filament current calibration data set as inputs of the prediction model, and by calling the prediction function or method of the model, the model calculates the predicted filament current value according to the input characteristic data.

[0071] In step S104, the deviation between each prediction result and the corresponding measured value is used as a correction value corresponding to each tube current and tube voltage of the first X-ray tube, so as to generate a correction value database.

[0072] Specifically, the correction value database is used to correct the filament current of the target X-ray tube to obtain a correction result; the target X-ray tube and the first X-ray tube are of the same type.

[0073] Furthermore, the deviation between the predicted result and the measured value is calculated. There is a one-to-one correspondence between the predicted result, the measured value and the deviation. The deviation corresponding to the predicted result can be obtained by a simple subtraction operation, that is, deviation = measured value - predicted result, and the calculated deviation is used as the correction value. For each paired data point, the correction value is the opposite of the deviation of the point, which is used to adjust the predicted result to be closer to the measured value.

[0074] Furthermore, each correction value is stored together with the corresponding tube current and tube voltage in a correction value database. The correction value database should be easily indexed and retrieved so as to correct the filament current of the target X-ray tube when necessary.

[0075] In summary, the correction method of the filament current of an X-ray tube provided in an embodiment of the present invention first obtains data according to an X-ray tube data manual or performs traditional exposure on a tube of the same type to form a calibration data set, wherein the filament current calibration data set includes the tube current and tube voltage of the first X-ray tube and the filament current data corresponding to the tube current and tube voltage, and then constructs a weight function w(Vset, Iset) based on the use condition of the X-ray tube of this model, collects the use condition data of the X-ray tube of this model, analyzes the historical data such as the working (tube voltage, tube current) frequency, output power, reliability, etc., and automatically determines the weight function w(Vset, Iset) using a statistical method or a machine learning algorithm, such as Figure 2 As shown, the weight can be a value between 0 and 1, indicating the importance of the data in building the prediction model. Then, each data point in the filament current calibration data set is weighted, and the weighted data set will pay more attention to those data points that are more important to specific working conditions. Then, a filament current prediction model library is established based on the machine learning regression model library, and different types of filament current prediction model families are selected according to the CPU computing power. The selected machine learning model is trained using the training set data to build a filament current prediction model.

[0076] After the filament current prediction model is obtained, the tube current and tube voltage are extracted from the filament current calibration data set as the input of the prediction model. By calling the prediction function or method of the model, the model calculates each predicted filament current value according to the input characteristic data. Three model families are given here for reference.

[0077] 1. Polynomial model library:

[0078] I f01 (V set, I set )=Coe*[1,V set ,I set ,V set ^2,V set *I set ,I set ^2…V set ^(a-1)*I set +V set ^a…V set *I set ^(b-1)+I set ^b];

[0079] Among them, Coe is the polynomial correlation coefficient matrix, a and b are V set and I set The highest order.

[0080] 2. Gaussian regression model library:

[0081] I f02 (V set, I set )=I f01 (V set, I set )+a 11 *e (-((Vset-b11) / c11)^2) +a 21 *e (-((Iset-b21) / c21)^2) +…;

[0082] Among them, a 11 、b 11 、c 11 、a 21 、b 21 、c 21 is the Gaussian regression correlation coefficient.

[0083] 3. Regression tree model library:

[0084] I f03 (V set, I set )=ave(I i |(V set, I set )∈lea fm );

[0085] Among them, I i is the output of the training set elements.

[0086] Based on the selected data training set X, the weight function w(V set, I set ) and the filament current prediction model family, and repeatedly iterate through machine learning until the root mean square error RMSE of the data training set meets the convergence condition, the filament current prediction function I f0 (V set, I set ).

[0087] Finally, based on the selected filament current prediction function I f0 (V set, I set ) to obtain the prediction result, and solve its deviation in the calibration data set to form a prediction deviation data set, such as Figure 3 As shown, the yellow dots are used to represent the predicted values, and the blue dots are used to represent the measured values. The deviations calculated above are used as correction values, and each correction value is stored in the correction value database together with the corresponding tube current and tube voltage to generate the correction value I of this type of X-ray tube. f1 Database, so as to correct the filament current of the target X-ray tube when necessary, the filament current value I during actual exposure f =I f0 (V set, Iset )+I f1 .

[0088] In some optional embodiments, the method further comprises:

[0089] The target tube current and target tube voltage of the target X-ray tube are processed based on the filament current prediction model to obtain a target prediction result;

[0090] Obtaining a target correction value corresponding to a target prediction result in a correction value database;

[0091] The sum of the target prediction result and the target correction value is taken as the correction result.

[0092] For the target X-ray tube, the filament current prediction model can be used to perform a small number of exposures on the target X-ray tube to obtain the prediction results of each target. f1 The target correction value corresponding to the target prediction result is found in the database, and the sum of the target prediction result and the target correction value is taken as the correction result.

[0093] In some optional implementations, obtaining a target correction value corresponding to a target prediction result in a correction value database includes:

[0094] If there is target data identical to the target tube current and the target tube voltage in the correction value database, the correction value corresponding to the target data is confirmed as the target correction value;

[0095] If the correction value database does not contain target data identical to the target tube current and the target tube voltage, the target correction value is obtained based on adjacent data; the adjacent data includes data adjacent to the target tube current and the target tube voltage in the correction value database.

[0096] The target tube current and target tube voltage of the target X-ray tube are used as input data, and a data point that completely matches the target data is searched in the correction value database, that is, whether there is a data record identical to the target tube current and the target tube voltage. If a data point that completely matches the target data is found, the correction value corresponding to the data point is directly confirmed as the target correction value.

[0097] If there is no target data with the same target tube current and target tube voltage, several adjacent data points are selected from the correction value database, and the data values ​​of these adjacent data points in the two dimensions of tube current and tube voltage are close to the values ​​of the target tube current and target tube voltage, respectively. The target correction value is calculated based on the adjacent data points.

[0098] In some optional implementations, if there is no target data identical to the target tube current and the target tube voltage in the correction value database, obtaining the target correction value based on adjacent data includes:

[0099] The adjacent correction values ​​corresponding to the adjacent data are interpolated to obtain the target correction value.

[0100] If there is no target data identical to the target tube current and the target tube voltage, after screening out adjacent data points whose data values ​​in the two dimensions of tube current and tube voltage are close to the values ​​of the target tube current and the target tube voltage respectively in the correction value database, a suitable interpolation method is selected, such as linear interpolation, quadratic interpolation, cubic spline interpolation, etc. Finally, interpolation calculation is performed based on the correction values ​​of the adjacent data points and the corresponding tube current and tube voltage to obtain the target correction value.

[0101] In some optional embodiments, the method further comprises:

[0102] Expose the target X-ray tube a preset number of times to obtain a target measured value of the filament current of the target X-ray tube;

[0103] The filament current prediction model is adjusted based on the target measured value to obtain a target prediction model, so that the target error between the correction result obtained based on the target prediction model and the target measured value is within a preset range.

[0104] According to the use requirements and working conditions of the target X-ray tube, a series of tube current (Iset) and tube voltage (Vset) conditions are set. Under the preset exposure conditions, the target X-ray tube is exposed several times, and the actual value of the filament current, i.e. the target measured value, is recorded during each exposure. The tube current and tube voltage data of the target X-ray tube are input into the initial prediction model to obtain the predicted filament current value.

[0105] The predicted filament current value is compared with the target measured value, and the prediction error, such as the root mean square error RMSE, is calculated. The distribution of the prediction error is checked. According to the results of the error analysis, the parameters of the prediction model are adjusted, such as the coefficients of the polynomial model, the correlation coefficient of the Gaussian regression model, the depth of the regression tree, etc., to reduce the prediction error and obtain an updated prediction model.

[0106] In some optional implementations, adjusting the filament current prediction model based on the target measured value to obtain a target prediction model includes:

[0107] Obtain each coefficient in the filament current prediction model;

[0108] Calculate the rate of change of each coefficient relative to the predicted result;

[0109] According to the magnitude of the change rate, a preset number of first coefficients are selected from each coefficient from high to low;

[0110] The first coefficient is adjusted based on the target error to obtain a target prediction model so that the target error is within a preset range.

[0111] Load the trained filament current prediction model from the storage, extract all relevant coefficients from the model, which may include the coefficients of the polynomial model, the Gaussian kernel parameters of the Gaussian regression model, and the node splitting conditions of the regression tree model, etc. Calculate the change rate of each coefficient relative to the prediction result, sort the coefficients from large to small according to the calculated change rate, and select the first n coefficients as the first coefficient.

[0112] The first selected coefficient is adjusted iteratively. The prediction result is recalculated each time and compared with the target measured value to calculate the target error. If the target error exceeds the preset range, the coefficient is appropriately increased or decreased according to the sign and size of the error; if the target error converges stably within the preset range after multiple iterations, the adjustment process is considered to be completed to obtain the target prediction model.

[0113] In this embodiment, a correction device for the filament current of an X-ray tube is also provided, and the device is used to implement the above-mentioned embodiments and preferred implementation modes, and the descriptions that have been made will not be repeated. As used below, the term "module" can be a combination of software and / or hardware that implements a predetermined function. Although the device described in the following embodiments is preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceivable.

[0114] This embodiment provides a correction device for the filament current of an X-ray tube, such as Figure 4 As shown, including:

[0115] The acquisition module 401 is used to acquire a filament current calibration data set of a first X-ray tube; the filament current calibration data set includes a tube current and a tube voltage of the first X-ray tube and filament current data corresponding to the tube current and the tube voltage;

[0116] A construction module 402 is used to construct a filament current prediction model based on the filament current calibration data set;

[0117] The processing module 403 is used to process each tube current and tube voltage of the first X-ray tube in the filament current calibration data set according to the filament current prediction model to obtain each prediction result;

[0118] The generation module 404 is used to use the deviation between each prediction result and the corresponding measured value as the correction value corresponding to each tube current and tube voltage of the first X-ray tube, so as to generate a correction value database; the correction value database is used to correct the filament current of the target X-ray tube to obtain a correction result; the target X-ray tube and the first X-ray tube are of the same type.

[0119] In some optional implementations, the construction module 402 includes:

[0120] The weight determination submodule is used to determine the weight of each data in the filament current calibration data set based on the use condition of the first X-ray tube.

[0121] A submodule is established to establish a filament current prediction model based on the filament current calibration data set and weights.

[0122] In some optional embodiments, the device further comprises:

[0123] The prediction module is used to process the target tube current and target tube voltage of the target X-ray tube based on the filament current prediction model to obtain a target prediction result.

[0124] The correction value acquisition module is used to obtain the target correction value corresponding to the target prediction result in the correction value database.

[0125] The summation module is used to take the sum of the target prediction result and the target correction value as the correction result.

[0126] In some optional implementations, the correction value acquisition module includes:

[0127] The direct acquisition submodule is used to confirm the correction value corresponding to the target data as the target correction value if there is target data identical to the target tube current and the target tube voltage in the correction value database.

[0128] The indirect acquisition submodule is used to obtain the target correction value based on adjacent data if there is no target data identical to the target tube current and the target tube voltage in the correction value database; the adjacent data includes data adjacent to the values ​​of the target tube current and the target tube voltage in the correction value database.

[0129] In some optional implementations, the indirect acquisition submodule includes:

[0130] The interpolation unit is used to perform interpolation calculation on adjacent correction values ​​corresponding to adjacent data to obtain a target correction value.

[0131] In some optional embodiments, the device further comprises:

[0132] The exposure module is used to expose the target X-ray tube for a preset number of times to obtain a target measured value of the filament current of the target X-ray tube.

[0133] The adjustment module is used to adjust the filament current prediction model based on the target measured value to obtain the target prediction model so that the target error between the correction result obtained based on the target prediction model and the target measured value is within a preset range.

[0134] In some optional implementations, the adjustment module includes:

[0135] The coefficient acquisition submodule is used to obtain various coefficients in the filament current prediction model.

[0136] The change rate calculation submodule is used to calculate the change rate of each coefficient relative to the predicted result.

[0137] The sorting submodule is used to select a preset number of first coefficients from each coefficient from high to low according to the magnitude of the change rate.

[0138] The adjustment coefficient submodule is used to adjust the first coefficient based on the target error to obtain a target prediction model so that the target error is within a preset range.

[0139] The further functional description of each of the above modules and units is the same as that of the above corresponding embodiments and will not be repeated here.

[0140] The correction device for the X-ray tube filament current in this embodiment is presented in the form of a functional unit, where the unit refers to an ASIC (Application Specific Integrated Circuit) circuit, a processor and memory that executes one or more software or fixed programs, and / or other devices that can provide the above functions.

[0141] The embodiment of the present invention also provides a computer device having the above Figure 4 The correction device for the filament current of the X-ray tube is shown.

[0142] See also Figure 5 , Figure 5 is a schematic diagram of the structure of a computer device provided by an optional embodiment of the present invention, such as Figure 5 As shown, the computer device includes: one or more processors 10, a memory 20, and interfaces for connecting various components, including high-speed interfaces and low-speed interfaces. Various components are connected to each other using different buses for communication, and can be installed on a common mainboard or installed in other ways as needed. The processor can process the instructions executed in the computer device, including instructions stored in or on the memory to display the graphical information of the GUI on an external input / output device (such as, a display device coupled to the interface). In some optional embodiments, if necessary, multiple processors and / or multiple buses can be used together with multiple memories and multiple memories. Similarly, multiple computer devices can be connected, and each device provides some necessary operations (for example, as a server array, a group of blade servers, or a multi-processor system). Figure 5 A processor 10 is taken as an example.

[0143] The processor 10 may be a central processing unit, a network processor or a combination thereof. The processor 10 may further include a hardware chip. The hardware chip may be a dedicated integrated circuit, a programmable logic device or a combination thereof. The programmable logic device may be a complex programmable logic device, a field programmable gate array, a general purpose array logic or any combination thereof.

[0144] The memory 20 stores instructions executable by at least one processor 10, so that the at least one processor 10 executes the method shown in the above embodiment.

[0145] The memory 20 may include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function; the data storage area may store data created according to the use of the computer device, etc. In addition, the memory 20 may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some optional embodiments, the memory 20 may optionally include a memory remotely arranged relative to the processor 10, and these remote memories may be connected to the computer device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0146] The memory 20 may include a volatile memory, such as a random access memory; the memory may also include a non-volatile memory, such as a flash memory, a hard disk or a solid state drive; the memory 20 may also include a combination of the above types of memory.

[0147] The computer device also includes an input device 30 and an output device 40. The processor 10, the memory 20, the input device 30 and the output device 40 may be connected via a bus or other means. Figure 5 The example of connecting through bus is taken in the following.

[0148] The input device 30 can receive input digital or character information, and generate key signal input related to the user settings and function control of the computer device, such as a touch screen, a keypad, a mouse, a track pad, a touch pad, an indicator bar, one or more mouse buttons, a trackball, a joystick, etc. The output device 40 may include a display device, an auxiliary lighting device (e.g., an LED) and a tactile feedback device (e.g., a vibration motor), etc. The above-mentioned display device includes but is not limited to a liquid crystal display, a light emitting diode, a display and a plasma display. In some optional embodiments, the display device can be a touch screen.

[0149] The embodiment of the present invention also provides a computer-readable storage medium. The method according to the embodiment of the present invention can be implemented in hardware, firmware, or can be implemented as a computer code that can be recorded in a storage medium, or can be implemented as a computer code that is originally stored in a remote storage medium or a non-temporary machine-readable storage medium and will be stored in a local storage medium through a network download, so that the method described herein can be stored in such software processing on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. Among them, the storage medium can be a magnetic disk, an optical disk, a read-only storage memory, a random access memory, a flash memory, a hard disk or a solid-state hard disk, etc.; further, the storage medium can also include a combination of the above types of memories. It can be understood that a computer, a processor, a microprocessor controller, or programmable hardware includes a storage component that can store or receive software or computer code. When the software or computer code is accessed and executed by a computer, a processor, or hardware, the method shown in the above embodiment is implemented.

[0150] A part of the present invention may be applied as a computer program product, such as a computer program instruction, which, when executed by a computer, can call or provide the method and / or technical solution according to the present invention through the operation of the computer. Those skilled in the art should understand that the existence of the computer program instruction in a computer-readable medium includes, but is not limited to, a source file, an executable file, an installation package file, etc., and accordingly, the way in which the computer program instruction is executed by the computer includes, but is not limited to: the computer directly executes the instruction, or the computer compiles the instruction and then executes the corresponding compiled program, or the computer reads and executes the instruction, or the computer reads and installs the instruction and then executes the corresponding installed program. Here, the computer-readable medium may be any available computer-readable storage medium or communication medium accessible to the computer.

[0151] Although the embodiments of the present invention have been described in conjunction with the accompanying drawings, those skilled in the art may make various modifications and variations without departing from the spirit and scope of the present invention, and such modifications and variations are all within the scope defined by the appended claims.

Claims

1. A method for correcting the filament current of an X-ray tube, characterized in that: The method comprises: Acquire a filament current calibration data set of a first X-ray tube; the filament current calibration data set includes a tube current and a tube voltage of the first X-ray tube and filament current data corresponding to the tube current and the tube voltage; Based on the filament current calibration data set, constructing a filament current prediction model; Processing each tube current and tube voltage of the first X-ray tube in the filament current calibration data set according to the filament current prediction model to obtain each prediction result; Deviations between the predicted results and the corresponding measured values ​​are used as correction values ​​corresponding to the tube currents and tube voltages of the first X-ray tube, respectively, to generate a correction value database; the correction value database is used to correct the filament current of a target X-ray tube to obtain a correction result; the target X-ray tube and the first X-ray tube are of the same type.

2. The method according to claim 1, characterized in that: The step of constructing a filament current prediction model based on the filament current calibration data set includes: Determining the weight of each data in the filament current calibration data set based on the use condition of the first X-ray tube; The filament current prediction model is established according to the filament current calibration data set and the weight.

3. The method according to claim 2, characterized in that The method further comprises: Processing the target tube current and the target tube voltage of the target X-ray tube based on the filament current prediction model to obtain a target prediction result; Obtaining a target correction value corresponding to the target prediction result in the correction value database; The sum of the target prediction result and the target correction value is taken as the correction result.

4. The method according to claim 3, characterized in that The obtaining of the target correction value corresponding to the target prediction result in the correction value database includes: If the correction value database contains target data identical to the target tube current and the target tube voltage, the correction value corresponding to the target data is confirmed as the target correction value; If the correction value database does not contain target data identical to the target tube current and the target tube voltage, the target correction value is obtained based on adjacent data; the adjacent data includes data in the correction value database adjacent to the values ​​of the target tube current and the target tube voltage.

5. The method according to claim 4, characterized in that If the target data identical to the target tube current and the target tube voltage does not exist in the correction value database, obtaining the target correction value based on adjacent data includes: Interpolation calculation is performed on adjacent correction values ​​corresponding to the adjacent data to obtain the target correction value.

6. The method according to any one of claims 1 to 5, characterized in that: The method further comprises: Expose the target X-ray tube a preset number of times to obtain a target measured value of the filament current of the target X-ray tube; The filament current prediction model is adjusted based on the target measured value to obtain a target prediction model, so that a target error between a correction result obtained based on the target prediction model and the target measured value is within a preset range.

7. The method according to claim 6, characterized in that The step of adjusting the filament current prediction model based on the target measured value to obtain a target prediction model includes: Obtaining various coefficients in the filament current prediction model; Calculating the change rate of each coefficient relative to the prediction result; According to the magnitude of the change rate, a preset number of first coefficients are selected from the coefficients from high to low; The first coefficient is adjusted based on the target error to obtain the target prediction model so that the target error is within a preset range.

8. A device for correcting the filament current of an X-ray tube, characterized in that: The device comprises: An acquisition module, used for acquiring a filament current calibration data set of a first X-ray tube; the filament current calibration data set includes a tube current and a tube voltage of the first X-ray tube and filament current data corresponding to the tube current and the tube voltage; A construction module, configured to construct a filament current prediction model based on the filament current calibration data set; a processing module, configured to process each tube current and tube voltage of the first X-ray tube in the filament current calibration data set according to the filament current prediction model to obtain each prediction result; A generation module is used to use the deviations between the predicted results and the corresponding measured values ​​as correction values ​​corresponding to the tube currents and tube voltages of the first X-ray tube, respectively, to generate a correction value database; the correction value database is used to correct the filament current of the target X-ray tube to obtain a correction result; the target X-ray tube and the first X-ray tube are of the same type.

9. A computer device, characterized in that: include: A memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the method for correcting the X-ray tube filament current according to any one of claims 1 to 7 by executing the computer instructions.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a computer to execute the method for correcting the X-ray tube filament current according to any one of claims 1 to 7.

Citation Information

Cited By

  • Calibration method, device, equipment, medium, X-ray generator and CT equipment

    CN119676922A

  • X-ray source dose control method and device

    CN121078603A

  • A method and apparatus for controlling X-ray source dose

    CN121078603B