X-ray detection equipment key parameter adaptive optimization method based on image quality feedback and related equipment

Abstract

The invention relates to an X-ray detection equipment key parameter adaptive optimization method based on image quality feedback and related equipment, and relates to the technical field of image processing, and the method comprises the steps: determining initial key parameters of X-ray detection equipment, and collecting an X-ray image of a detected object through the initial key parameters; performing quality evaluation on the X-ray image to obtain a quality evaluation result; under the condition that the quality evaluation result deviates from a set quality standard, adjusting the initial key parameter according to the initial key parameter and the quality evaluation result to obtain a new key parameter; and acquiring the X-ray image of the tested object again by using the new key parameters, taking the X-ray image acquired again as a new X-ray image, and returning to the step of evaluating the quality of the X-ray image until the quality evaluation result meets the set quality standard, thereby obtaining a target X-ray image and target key parameters for the tested object. By adopting the method, the reliability of the key parameters of the X-ray detection equipment can be improved.

Description

Technical Field

[0001] The present application relates to the field of image processing technology, and in particular to a method, apparatus, computer device, computer-readable storage medium and computer program product for adaptively optimizing key parameters of X-ray detection equipment based on image quality feedback. Background Art

[0002] At present, equipment samples are often observed through X-ray images. Due to the material thickness, density differences, and the environment in which the equipment samples are located, the X-ray images taken may not accurately reflect the internal conditions of the equipment samples. The current method for enhancing the quality of X-ray images is that the operator configures the parameters of the X-ray detection equipment according to the detection requirements and specific application scenarios before the detection. This method relies on the actual experience of the operator and is highly subjective. Therefore, the current optimization and adjustment method of the key parameters of the X-ray detection device has the problem of low reliability. Summary of the invention

[0003] Based on this, it is necessary to provide a method, device, computer equipment, computer-readable storage medium and computer program product for adaptive optimization of key parameters of X-ray detection equipment based on image quality feedback, which can improve the reliability of quality enhancement results of X-ray images in response to the above-mentioned technical problems.

[0004] In a first aspect, the present application provides a method for adaptively optimizing key parameters of X-ray detection equipment based on image quality feedback, comprising:

[0005] Determine initial key parameters of the X-ray detection equipment, and collect an X-ray image of the object to be detected by using the initial key parameters;

[0006] Performing quality assessment on the X-ray image to obtain a quality assessment result;

[0007] In the case where the quality assessment result deviates from the set quality standard, adjusting the initial key parameters according to the initial key parameters and the quality assessment result to obtain new key parameters;

[0008] An X-ray image of the object under test is acquired again with the new key parameters, and the re-acquired X-ray image is used as a new X-ray image, and the step of performing quality assessment on the X-ray image is returned to until the quality assessment result of the new X-ray image meets the set quality standard, thereby obtaining a target X-ray image and target key parameters for the object under test.

[0009] In one embodiment, the performing quality assessment on the X-ray image to obtain a quality assessment result includes:

[0010] Determining the brightness distribution, image quality index value and defect recognition rate of the X-ray image according to image parameters corresponding to the X-ray image;

[0011] The quality assessment result is obtained according to the brightness distribution, image quality index value and defect recognition rate.

[0012] In one of the embodiments, after obtaining the quality assessment result according to the brightness distribution, the image quality index value and the defect recognition rate, the method further includes:

[0013] When at least one of the brightness distribution, the image quality index value and the defect recognition rate is abnormal, it is determined that the quality assessment result deviates from the set quality standard.

[0014] In one embodiment, adjusting the initial key parameters according to the initial key parameters and the quality assessment results to obtain new key parameters includes:

[0015] Using a preset parameter adaptive adjustment algorithm to calculate the quality assessment result and the initial key parameter to obtain a plurality of candidate key parameters;

[0016] Select candidate key parameters corresponding to the results that make the objective function of the preset parameter adaptive adjustment algorithm obtain the results that meet the iterative calculation conditions, and determine the candidate key parameters as new key parameters; the objective function is obtained by fitting the X-ray images generated under different key parameters and the quality assessment results corresponding to the X-ray images.

[0017] In one embodiment, adjusting the initial key parameters according to the initial key parameters and the quality assessment results to obtain new key parameters includes:

[0018] Inputting the initial key parameters and the quality assessment results into a pre-trained parameter prediction model to obtain new key parameters;

[0019] The pre-trained parameter prediction model is obtained by training X-ray images generated under different key parameters and quality assessment results corresponding to the X-ray images.

[0020] In one embodiment, adjusting the initial key parameters according to the initial key parameters and the quality assessment results to obtain new key parameters includes:

[0021] Acquiring attribute data of the object under test;

[0022] The attribute data of the object to be tested, the quality assessment results and the initial key parameters are input into a pre-trained multimodal parameter prediction model to obtain new key parameters; the pre-trained multimodal parameter prediction model is trained by generating X-ray images under different parameters for different types of samples to be tested and the quality assessment results corresponding to the X-ray images.

[0023] In one of the embodiments, according to the method described in any one of the above embodiments, the key parameters of the X-ray detection equipment include the penetrability of the sample being tested, the tube voltage, tube current, focal spot size of the X-ray source, and the exposure time, focal spot size and focal distance of the X-ray detection equipment, and at least one of the flat panel detector parameters.

[0024] In a second aspect, the present application also provides an adaptive optimization device for key parameters of X-ray detection equipment based on image quality feedback, comprising:

[0025] An image acquisition module, used to determine initial key parameters of the X-ray detection equipment and to acquire an X-ray image of the object under test through the initial key parameters;

[0026] An image quality assessment module, used to perform quality assessment on the X-ray image to obtain a quality assessment result;

[0027] A parameter optimization module, used for adjusting the initial key parameters according to the initial key parameters and the quality evaluation results to obtain new key parameters when the quality evaluation results deviate from the set quality standards;

[0028] A parameter optimization module is used to re-acquire the X-ray image of the object under test with the new key parameters, and use the re-acquired X-ray image as a new X-ray image, and return to the step of performing quality assessment on the X-ray image until the quality assessment result of the new X-ray image meets the set quality standard, thereby obtaining a target X-ray image and target key parameters for the object under test.

[0029] In a third aspect, the present application further provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0030] Determine initial key parameters of the X-ray detection equipment, and collect an X-ray image of the object to be detected by using the initial key parameters;

[0031] Performing quality assessment on the X-ray image to obtain a quality assessment result;

[0032] In the case where the quality assessment result deviates from the set quality standard, adjusting the initial key parameters according to the initial key parameters and the quality assessment result to obtain new key parameters;

[0033] The X-ray image of the object to be measured is acquired again with the new key parameters, and the re-acquired X-ray image is used as a new X-ray image, and the step of performing quality assessment on the X-ray image is returned to until the quality assessment result of the new X-ray image meets the set quality standard, thereby obtaining the target X-ray image and target key parameters of the object to be measured.

[0034] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the following steps are implemented:

[0035] Determining initial key parameters of the X-ray detection equipment, and collecting an X-ray image of the object to be detected by using the initial key parameters;

[0036] Performing quality assessment on the X-ray image to obtain a quality assessment result;

[0037] In the case where the quality assessment result deviates from the set quality standard, adjusting the initial key parameters according to the initial key parameters and the quality assessment result to obtain new key parameters;

[0038] The X-ray image of the object to be measured is acquired again with the new key parameters, and the re-acquired X-ray image is used as a new X-ray image, and the step of performing quality assessment on the X-ray image is returned to until the quality assessment result of the new X-ray image meets the set quality standard, thereby obtaining the target X-ray image and target key parameters of the object to be measured.

[0039] In a fifth aspect, the present application further provides a computer program product, including a computer program, which implements the following steps when executed by a processor:

[0040] Determining initial key parameters of the X-ray detection equipment, and collecting an X-ray image of the object to be detected by using the initial key parameters;

[0041] Performing quality assessment on the X-ray image to obtain a quality assessment result;

[0042] In the case where the quality assessment result deviates from the set quality standard, adjusting the initial key parameters according to the initial key parameters and the quality assessment result to obtain new key parameters;

[0043] The X-ray image of the object to be measured is acquired again with the new key parameters, and the re-acquired X-ray image is used as a new X-ray image, and the step of performing quality assessment on the X-ray image is returned to until the quality assessment result of the new X-ray image meets the set quality standard, thereby obtaining the target X-ray image of the object to be measured.

[0044] The above-mentioned adaptive optimization method, device, computer equipment, computer-readable storage medium and computer program product for key parameters of X-ray detection equipment based on image quality feedback, the method determines the initial key parameters of the X-ray detection equipment, collects the X-ray image of the object to be detected through the initial key parameters, so as to understand the internal structure of the object to be detected through the X-ray image. And the quality of the X-ray image is evaluated to obtain the quality evaluation result, and it is determined whether the quality result of the X-ray image is qualified, so as to determine whether the key parameters of the X-ray detection equipment need to be optimized and adjusted to improve the image quality. In the case where the quality evaluation result deviates from the set quality standard, the initial key parameters are adjusted according to the initial key parameters and the quality evaluation result to obtain new key parameters. Furthermore, the X-ray image of the object to be detected is collected again with the new key parameters, and the re-collected X-ray image is used as the new X-ray image, and the step of quality evaluation of the X-ray image is returned until the quality evaluation result of the new X-ray image meets the set quality standard, and the target X-ray image and target key parameters for the object to be detected are obtained. The adaptive optimization of the key parameters of the X-ray detection equipment is realized, thereby realizing the adaptive enhancement of the X-ray image quality of the object being tested, and improving the efficiency of X-ray image enhancement and the update of the key parameters of the X-ray detection equipment. In addition, the quality assessment results of the X-ray image are used as the basis for image enhancement, avoiding reliance on human experience and improving the reliability of the update of the key parameters of the X-ray detection equipment. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] 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.

[0046] Figure 1 A diagram of an application environment of a method for adaptively optimizing key parameters of X-ray detection equipment based on image quality feedback in one embodiment;

[0047] Figure 2 It is a schematic flow chart of a method for adaptively optimizing key parameters of X-ray detection equipment based on image quality feedback in one embodiment;

[0048] Figure 3 A schematic diagram of a process for determining a quality assessment result in one embodiment;

[0049] Figure 4 is a schematic diagram of the structure of an image quality assessment model for X-ray images in one embodiment;

[0050] Figure 5 A schematic diagram of a process for determining new key parameters using an adaptive parameter optimization algorithm in one embodiment;

[0051] Figure 6 Schematic diagram of a training process of a multimodal parameter model in one embodiment;

[0052] Figure 7 It is a schematic flow chart of a method for adaptively optimizing key parameters of X-ray detection equipment based on image quality feedback in another embodiment;

[0053] Figure 8 It is a structural block diagram of a device for adaptively optimizing key parameters of X-ray detection equipment based on image quality feedback in one embodiment;

[0054] Fig. 9 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0055] 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.

[0056] As described in the background technology, the prior art X-ray detection equipment has the problem of low reliability in the key parameter adjustment and X-ray image acquisition. The inventors have found that the reason for this problem is that due to the material thickness and density differences of the object to be tested, if the parameters are not set properly, it is often impossible to take into account the details of different parts of the object to be tested, resulting in overexposure or underexposure of some areas, affecting the image contrast. The X-ray image has too much noise. If the tube voltage and tube current of the X-ray source are not set properly, or the exposure time is not set properly, the resulting image may have a high noise level, which not only affects the beauty of the imaging, but also affects the accuracy of subsequent defect identification. Limitations of manual parameter adjustment: In the methods currently widely used in detection equipment, the adjustment of parameters generally depends on the operator's experience and manual setting. This method requires high experience from the operator, is not only time-consuming and inefficient, but also easily introduces subjective human errors. Instability of image quality: Due to the lack of an effective parameter adaptive adjustment mechanism, the image quality is greatly affected by the test environment factors. Due to the adjustment of different operators, the image quality often varies, affecting the reliability of the detection results. Complexity of operation: The complex parameter adjustment process requires the operator to have rich professional knowledge. Not only must he have a full understanding of the detection equipment, but he must also have a clear understanding of the tested scenarios and objects. This increases the training cost and operation difficulty, and will also lead to over-reliance on the operator.

[0057] Based on the above reasons, the present application provides an adaptive optimization method for key parameters of X-ray detection equipment based on image quality feedback, which can improve the reliability of the optimization adjustment of key parameters of X-ray detection equipment and the corresponding image quality enhancement results of X-ray images.

[0058] The adaptive optimization method for key parameters of X-ray detection equipment based on image quality feedback provided in the embodiment of the present application can be applied to Figure 1In the application environment shown, the application environment includes: X-ray detection equipment 102, an object to be detected 104, a detector 106 and a server 108. The X-ray detection equipment 102 includes an X-ray source. The detector 106 communicates with the server 108 through a network. The server 104 can be an independent physical server, a server cluster or a distributed system composed of multiple physical servers, or a cloud server that provides cloud computing services. The server 108 determines the initial key parameters of the X-ray detection equipment 102, and collects an X-ray image of the object to be detected 104 through the initial key parameters, wherein the X-ray image is generated on the detector 106 by the X-ray detection equipment 102 emitting X-rays under the initial key parameters, and the detector 106 sends the X-ray image to the server 108 through the network. The computer and image processing software on the server 108 perform quality assessment on the X-ray image to obtain a quality assessment result. Further, when the quality assessment result deviates from the set quality standard, the server 108 adjusts the initial key parameters according to the initial key parameters and the quality assessment result to obtain new key parameters. Instruct the X-ray detection equipment 102 to collect an X-ray image of the object under test again with new key parameters, and the server 108 uses the re-collected X-ray image as a new X-ray image, and returns to the steps of adjusting the key parameters of the X-ray detection equipment and performing quality assessment on the X-ray image until the quality assessment result of the new X-ray image meets the set quality standards, thereby obtaining a target X-ray image and target key parameters for the object under test.

[0059] In an exemplary embodiment, Figure 2 As shown in the figure, a method for adaptive optimization of key parameters of X-ray detection equipment based on image quality feedback is provided. Figure 1 The server 108 in the example is used as an example to illustrate the method, which includes the following steps S202 to S208. Among them:

[0060] Step S202, determining initial key parameters of the X-ray detection equipment, and acquiring an X-ray image of the object to be detected by using the initial key parameters.

[0061] Among them, X-ray detection equipment is a device that uses X-ray technology to detect objects and analyze components, including an X-ray source. The X-ray source is a device that can generate X-rays and is widely used in medical imaging, material analysis, industrial detection and other fields. The working principle of the X-ray source is to allow high-speed electrons to collide with metal targets, causing electrons to collide with atoms, thereby generating X-rays. Among them, the initial key parameters can be the initial parameter configuration of the X-ray detection equipment, including the penetration of the object to be detected, and the tube voltage, tube current, and focal size of the X-ray source, as well as the exposure time, focal size and focal distance of the X-ray detection equipment, and at least one of the flat panel detector parameters.

[0062] The object to be tested may be an object whose internal structure needs to be tested, such as components, chips, etc. The X-ray image of the object to be tested may be an image formed on a detector after the X-rays emitted by the X-ray source penetrate the object to be tested.

[0063] Optionally, a parameter optimization system for X-ray detection equipment deployed on the server determines initial key parameters of the X-ray detection equipment based on experience or preset rules, and obtains X-ray images collected by the X-ray detection equipment for the object under test based on the initial key parameters, and uses the key parameters of the detection equipment and the quality assessment results of the X-ray images as inputs to the adaptive optimization system, and iteratively optimizes the key parameters until the key parameters of the X-ray detection equipment that meet the requirements for obtaining high-quality images are obtained.

[0064] Step S204: perform quality assessment on the X-ray image to obtain a quality assessment result.

[0065] The quality assessment may be a process of detecting whether the X-ray image is clear, accurate and reliable, such as detecting the clarity, contrast and noise level of the X-ray image. The quality assessment result may be an evaluation result of the image quality of the X-ray image, or may be a quantitative evaluation result of the image parameters of each dimension of the X-ray image using multiple quality assessment indicators.

[0066] Optionally, the system performs quality assessment on the X-ray image using preset quality assessment indicators to obtain a quality assessment result, determines whether the quality of the X-ray image is qualified based on the quality assessment result, and further determines whether image enhancement is required to improve image quality.

[0067] Step S206, when the quality assessment result deviates from the set quality standard, the initial key parameters are adjusted according to the initial key parameters and the quality assessment result to obtain new key parameters.

[0068] The set quality standard may be that the image quality evaluation result of the X-ray image satisfies the condition that the X-ray image can clearly and accurately display the internal structure of the object under test.

[0069] Optionally, when the quality assessment result deviates from the set quality standard, the quality of the X-ray image needs to be enhanced, and the system adjusts the initial key parameters of the X-ray source according to the initial key parameters and the quality assessment result to obtain new key parameters.

[0070] Step S208, re-acquire an X-ray image of the object to be measured with new key parameters, and use the re-acquired X-ray image as a new X-ray image, return to the step of performing quality assessment on the X-ray image, until the quality assessment result of the new X-ray image meets the set quality standards, and obtain the target X-ray image and target key parameters for the object to be measured.

[0071] The target X-ray image may be an X-ray image that can clearly and accurately identify the internal structure of the object being tested. The target key parameters may be key parameters configured by the X-ray detection equipment that acquires the target X-ray image, and are optimal key parameters adapted to the object being tested obtained by adaptively optimizing the initial key parameters based on the quality assessment results of the X-ray image.

[0072] Optionally, the system configures the new key parameters to the X-ray detection equipment, collects the X-ray image of the object to be detected again through the X-ray detection equipment, and uses the re-collected X-ray image as a new X-ray image. Return to the step of performing quality assessment on the X-ray image, perform quality assessment on the new X-ray image, and if the quality assessment result of the new X-ray image still deviates from the set quality standard, adjust the key parameters of the X-ray detection equipment until the quality assessment result of the new X-ray image meets the set quality standard, and obtain the target X-ray image and target key parameters for the object to be detected.

[0073] In the above-mentioned adaptive optimization method for key parameters of X-ray detection equipment based on image quality feedback, the method determines the initial key parameters of the X-ray detection equipment, collects the X-ray image of the object to be detected through the initial key parameters, so as to understand the internal structure of the object to be detected through the X-ray image. And the quality of the X-ray image is evaluated to obtain the quality evaluation result, and it is determined whether the quality result of the X-ray image is qualified, so as to determine whether the key parameters of the X-ray detection equipment need to be optimized and adjusted to improve the image quality. In the case where the quality evaluation result deviates from the set quality standard, the initial key parameters are adjusted according to the initial key parameters and the quality evaluation result to obtain new key parameters. Further, the X-ray image of the object to be detected is collected again with the new key parameters, and the X-ray image collected again is used as the new X-ray image, and the step of quality evaluation of the X-ray image is returned until the quality evaluation result of the new X-ray image meets the set quality standard, and the target X-ray image and target key parameters for the object to be detected are obtained. The adaptive optimization of the key parameters of the X-ray detection equipment is realized, thereby realizing the adaptive enhancement of the quality of the X-ray image of the object to be detected, and improving the enhancement of the X-ray image and the updating efficiency of the key parameters of the X-ray detection equipment. In addition, using the quality assessment results of X-ray images as the basis for image enhancement avoids reliance on human experience and improves the reliability of updating key parameters of X-ray detection equipment.

[0074] In an exemplary embodiment, Figure 3 As shown, step S204 performs quality assessment on the X-ray image, and obtaining the quality assessment result includes steps S302 to S304. Among them:

[0075] Step S302, according to the image parameters corresponding to the X-ray image, respectively determine the brightness distribution, image quality index value and defect recognition rate of the X-ray image.

[0076] Among them, image parameters can be numerical indicators or characteristics used to describe and quantify the quality and characteristics of X-ray images, such as contrast, clarity and noise.

[0077] The brightness distribution may refer to the change in brightness values ​​of different regions in the X-ray image. The brightness distribution is usually represented by an amplitude graph (or histogram) to reflect the degree of black and white corresponding to tissues of different densities in the image.

[0078] Among them, the image quality index value can be a numerical value of an evaluation standard for evaluating the image quality of an X-ray image, which is calculated by a preset algorithm. The image quality evaluation standard may include: peak signal-to-noise ratio PSNR (Peak Signal-to-Noise Ratio), structural similarity SSIM (Structural Similarity Index), sensory similarity LPIPS (Learned Perceptual Image Patch Similarity), contrast, etc.

[0079] The defect recognition rate can refer to the proportion of anomalies or other important structures that are successfully identified and detected in the X-ray image. This parameter is usually related to the quality of the image, the operating technology and the experience of the observer. For example, if there are 10 anomalies in the object under test and 8 anomalies are accurately identified through the X-ray image of the object under test, the defect recognition rate is 80%; for another example, if the abnormal area of ​​the object under test is 10 , the abnormal area detected by the X-ray image of the object is 8 , the defect recognition rate is 80%.

[0080] Optionally, the system generates a histogram corresponding to the X-ray image according to the grayscale values ​​in the image parameters corresponding to the X-ray image, and determines the brightness distribution of the X-ray image according to the histogram. The system calculates the index values ​​corresponding to the peak signal-to-noise ratio PSNR, structural similarity SSIM, sensory similarity LPIPS and contrast of the X-ray image according to the parameters of the X-ray image, and performs weighted summation calculation on the calculated multiple index values ​​according to the different assigned weights to obtain the image quality index value. The corresponding formula is as follows:

[0081]

[0082] in, is the mean square error between the X-ray image and the sample image; The peak signal-to-noise ratio is the maximum value that a pixel in an X-ray image can reach. The larger the value, the better the X-ray image effect.

[0083]

[0084] in, is the mean value of the X-ray image; is the standard deviation of the X-ray image. Structural similarity The value ranges from -1 to 1. The larger the value, the better the X-ray image effect.

[0085] Among them, sensory similarity uses a deep learning algorithm to train a model to simulate the perception of the human eye, thereby obtaining the similarity between the X-ray image and the sample image.

[0086] It should be noted that the above-mentioned image quality evaluation criteria are not limited to the above-mentioned method, and the image quality evaluation criteria corresponding to the X-ray image can also be calculated by pre-trained full-parameter model, semi-parameter model and no-parameter model. Figure 4 As shown, a structural schematic diagram of an image quality assessment model IQA (Image Quality Assessment) for X-ray images is provided.

[0087] Furthermore, the system can calculate the defect recognition rate of the X-ray image based on the ratio between the number of defects of the object to be measured that can be accurately identified by the X-ray image and the actual number of defects of the object to be measured.

[0088] Step S304, obtaining a quality assessment result according to the brightness distribution, the image quality index value and the defect recognition rate.

[0089] Optionally, the system integrates the brightness distribution, image quality index value and defect recognition rate obtained in the above steps to obtain a quality assessment result of the X-ray image.

[0090] In this embodiment, the system determines the image quality evaluation results in multiple dimensions based on the image parameters of the X-ray image, including brightness, image quality index value and defect recognition rate, which are used together as the quality evaluation results of the X-ray image. Through the quality evaluation in multiple dimensions, the accuracy of the quality evaluation of the X-ray image is improved, and the more accurate quality evaluation results are used as the basis for subsequent X-ray image enhancement, thereby improving the reliability of the quality enhancement results of the X-ray image.

[0091] In an exemplary embodiment, after obtaining the quality assessment result according to the brightness distribution, the image quality index value and the defect recognition rate in step S304, the method further includes:

[0092] When there is an abnormality in at least one of the brightness distribution, the image quality index value and the defect recognition rate, it is determined that the quality assessment result deviates from the set quality standard.

[0093] Optionally, the system determines that the brightness distribution is abnormal if it is overexposed or underexposed, that the image quality index value is lower than a preset index threshold value, and that the defect recognition rate is lower than a preset recognition threshold value. Therefore, when the system determines that at least one of the brightness distribution, the image quality index value, and the defect recognition rate is abnormal, it determines that the quality assessment result deviates from the set quality standard, indicating that the X-ray image cannot accurately identify the internal structure of the object being measured.

[0094] In this embodiment, the system detects the brightness distribution, image quality index and defect recognition rate of the X-ray image. As long as there is an abnormality in any one of them, it is judged that the quality assessment result deviates from the set quality standard and the X-ray image needs to be enhanced. While ensuring the quality of the X-ray image, the X-ray image can also be accurately enhanced according to the specific abnormal situation, further improving the reliability of the quality enhancement result of the X-ray image.

[0095] In an exemplary embodiment, according to the initial key acquisition parameters and the corresponding X-ray image quality assessment results, the key parameters of the X-ray detection equipment are adjusted to obtain new key parameters, including:

[0096] A preset parameter adaptive adjustment algorithm is used to calculate the quality assessment results and the initial key parameters to obtain multiple candidate key parameters; candidate key parameters corresponding to the results obtained by the objective function of the preset parameter adaptive adjustment algorithm that meet the iterative calculation conditions are selected, and the candidate key parameters are determined as new key parameters.

[0097] The preset parameter adaptive adjustment algorithm may be an algorithm for automatically optimizing key parameters of X-ray detection equipment, and its core purpose is to dynamically adjust key parameters to improve performance or adaptability according to changes in quality assessment results of X-ray images collected by the X-ray detection equipment. In this embodiment, a genetic algorithm or a gradient descent algorithm may be used as the preset parameter adaptive adjustment algorithm.

[0098] Among them, the objective function can be the fitness function in the genetic algorithm and the objective function in the gradient descent algorithm. The fitness function in the genetic algorithm is a function used to evaluate the quality or fitness of each individual (solution) in the genetic algorithm, which quantifies the individual's survival ability or degree of goal achievement in a given environment; the objective function in the gradient descent algorithm is also called the loss function or cost function, which usually measures the gap between the predicted value and the actual value during the execution of the algorithm.

[0099] Alternatively, if Figure 5 As shown, a flow chart of determining new key parameters using an adaptive parameter optimization algorithm is provided. The system uses a preset parameter adaptive adjustment algorithm to calculate the quality assessment results and the initial key parameters to obtain multiple candidate key parameters. From the multiple candidate key parameters, select the candidate key parameters that correspond to the results that make the objective function meet the iterative calculation conditions, and use the candidate key parameters as new key parameters. Specifically, each candidate key parameter is calculated as a variable of the objective function. During the iterative calculation of the candidate key parameters, when the result output by the objective function meets the iterative calculation conditions, the candidate key parameter corresponding to the result is determined as the new key parameter.

[0100] For example, a genetic algorithm is currently used. Based on the quality assessment results and the initial key parameters, multiple initial populations are generated with the goal of making the quality assessment results meet the set quality standards. Each initial population corresponds to a candidate key parameter. The candidate key parameters in the initial population are evaluated using a fitness function, and the population corresponding to the candidate key parameters with high fitness is selected for reproduction. The iterative calculation is performed until the preset number of iterations is met, or the difference between the fitness calculated by each candidate key parameter after the iteration is less than the preset threshold value, and the iterative calculation is terminated, and the candidate key parameter corresponding to the highest fitness output by the fitness function is used as the new key parameter.

[0101] For example, if the gradient descent algorithm is currently used, the gradient of the initial key parameter relative to the objective function is calculated, and iterative calculation is performed according to the preset learning rate and the step size of each update. During the iterative calculation process, the initial key parameter is continuously updated, and a corresponding candidate key parameter is obtained each time iteratively updated. When the iterative calculation reaches a fixed number of iterations, the norm of the gradient is less than a preset threshold, or the change in the objective function value is less than the preset threshold, the final updated candidate key parameter is obtained as the new key parameter.

[0102] In this embodiment, an adaptive adjustment algorithm (such as a genetic algorithm or a gradient descent algorithm) is used, and the system can respond to different quality assessment results of X-ray images in real time, and the key parameters of the X-ray detection equipment can be quickly adjusted, thereby ensuring that the best quality X-ray images are always obtained, and enhancing the adaptability and flexibility of the system. The use of optimization techniques such as genetic algorithms or gradient descent algorithms enables the system to find the optimal solution in a complex parameter space, realizes the system adaptively adjusting the key parameters of the X-ray detection equipment, reduces manual intervention and trial and error processes, and improves the reliability of updating the key parameters of the X-ray detection equipment.

[0103] In an exemplary embodiment, the initial key parameters are adjusted according to the initial key parameters and the quality assessment results to obtain new key parameters, including:

[0104] The initial key parameters and quality assessment results are input into the pre-trained parameter prediction model to obtain new key parameters.

[0105] The pre-trained parameter prediction model is obtained by training the X-ray images generated under different key parameters and the quality assessment results corresponding to the X-ray images. The training process can be: collecting X-ray images of various objects under a large number of different key parameters and their corresponding quality assessment results, and pre-processing each X-ray image, including denoising, enhancement and standardization. Feature extraction and normalization are performed on the quality assessment results and key parameters. The pre-processed X-ray images, quality assessment results and key parameters are used as training data sets to train the initial parameter prediction model until the preset training end conditions are met, and a trained parameter prediction model is obtained.

[0106] Optionally, the system preprocesses the initial key parameters and quality assessment results, and inputs the preprocessed initial key parameters and quality assessment results into a pre-trained parameter prediction model. The pre-trained parameter prediction model determines the parameters that need to be adjusted in the initial key parameters under the current quality assessment results, and the degree of adjustment, based on the experience accumulated during the training process, and outputs new key parameters. After the X-ray source acquires X-ray images of the object under test according to the new key parameters, the corresponding quality assessment results and new key parameters can be used as input to optimize the pre-trained parameter prediction model.

[0107] In this embodiment, the pre-trained parameter prediction model can use the experience in historical data to make intelligent judgments on the current quality assessment results and the corresponding initial key parameters, thereby determining the initial key parameters and adjustment ranges that need to be adjusted to optimize the quality assessment results. The automated decision-making process can reduce manual intervention, improve the efficiency of adaptive adjustment of key parameters and the reliability of image quality enhancement results of X-ray images.

[0108] In an exemplary embodiment, the initial key parameters are adjusted according to the initial key parameters and the quality assessment results to obtain new key parameters, including:

[0109] Acquire the attribute data of the object to be tested; input the attribute data of the object to be tested, the quality assessment results and the initial key parameters into a pre-trained multimodal parameter prediction model to obtain new key parameters.

[0110] The pre-trained multimodal parameter prediction model is obtained by training the X-ray images generated under different parameters for different types of samples and the quality assessment results corresponding to the X-ray images. Figure 6 As shown, a schematic diagram of the training process of the multimodal parameter model is provided. The training process can be: collecting X-ray images of different types of objects under a large number of different key parameters and their corresponding X-ray images, while recording the attribute data (such as density, thickness, etc.) of the objects under test, as well as environmental factors (such as temperature, humidity, etc.), and preprocessing each X-ray image, including denoising, enhancement and standardization. Feature extraction and normalization are performed on the quality assessment results, key parameters, attribute data and environmental factor data. The preprocessed data is used as a training data set to train the initial multimodal parameter prediction model until the preset training end conditions are met, and a trained multimodal parameter prediction model is obtained. It should be noted that during the training process of the multimodal parameter model, the training data is not limited to the data involved above, and can also include parameters such as FOD (Field of View) and FOV (focus-to-object distance) of the X-ray source.

[0111] Optionally, the system obtains the attribute data of the object under test, preprocesses the attribute data, quality assessment results and initial key parameters respectively, and inputs the preprocessed attribute data, quality assessment results and initial key parameters into a pre-trained multimodal parameter prediction model. The multimodal parameter prediction model determines the quality assessment results to be optimized under the attributes of the current object under test based on the experience accumulated during the training process, determines the parameters that need to be adjusted in the initial key parameters and the magnitude of the adjustment, thereby obtaining new key parameters.

[0112] In this embodiment, by obtaining the attribute data, quality assessment results and initial key parameters of the object under test and preprocessing them, data from different sources can be fully utilized. The multimodal model can comprehensively consider these different data sources to more accurately evaluate and optimize the key parameters. The multimodal parameter prediction model combines multiple data features and can capture potential complex relationships and patterns, thereby improving the accuracy of prediction of new key parameters and further improving the reliability of key parameter updates for X-ray detection equipment.

[0113] In an exemplary embodiment, Figure 7 As shown, another adaptive optimization method for key parameters of X-ray detection equipment based on image quality feedback is provided, including:

[0114] Step S1, setting the initial exposure time, tube voltage, tube current and other parameters of the X-ray source according to empirical values ​​or preset rules (corresponding to the initial key parameters in the above embodiment).

[0115] Step S2, using the initialization parameters to obtain an X-ray image of the object to be measured, and performing preprocessing operations such as blur removal, noise removal, and edge enhancement on the obtained image.

[0116] Step S3, image quality assessment: quantitatively assess the image quality according to a preset image quality evaluation standard (such as peak signal-to-noise ratio PSNR, structural similarity SSIM, contrast, etc.) to obtain an image quality assessment result (corresponding to the quality assessment result in the above embodiment).

[0117] Step S4: Based on the image quality assessment result, a parameter adaptive adjustment algorithm, a pre-trained parameter prediction model or a pre-trained multi-modal parameter prediction model is used to output a new parameter configuration (corresponding to new key parameters), and key parameters such as exposure time, tube voltage and tube current are adjusted according to the new parameter configuration.

[0118] Step S5, iterative optimization: repeat steps S2 to S5 until the image quality reaches a preset standard (corresponding to a preset condition).

[0119] In this embodiment, an objective evaluation method for the quality of X-ray images produced by X-ray detection equipment is established, and this standard is used to provide guidance for the adaptive adjustment of key parameters. A method that can automatically adjust key parameters (including exposure time, tube voltage and tube current of the radiation source, etc.) according to the quality feedback of the X-ray image is developed to ensure the acquisition of high-quality X-ray images. By adaptively optimizing parameters, it is ensured that consistent high-quality images can be obtained under different detection conditions, and the clarity and contrast of the image are improved, so that the image can accurately reflect the internal situation of the material, thereby improving the image effect and the accuracy of the detection. The parameter adjustment process is simplified and intelligentized, so that operators can complete high-quality evaluation without advanced professional knowledge and rich experience in related fields, thereby reducing training costs and operating difficulties. By automatically adjusting parameters, manual intervention is reduced, and the time required for each adjustment of equipment parameters is shortened, thereby improving the overall work efficiency of X-ray detection equipment; especially when the product produced on the production line is changed, the adaptive adjustment of relevant detection parameters can speed up the changeover.

[0120] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned 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 does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can 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 to be 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.

[0121] Based on the same inventive concept, the embodiment of the present application also provides an apparatus for adaptively optimizing key parameters of X-ray detection equipment based on image quality feedback for implementing the above-mentioned method for adaptively optimizing key parameters of X-ray detection equipment based on image quality feedback. The implementation scheme for solving the problem provided by the apparatus is similar to the implementation scheme recorded in the above-mentioned method, so the specific limitations in the embodiments of one or more apparatuses for adaptively optimizing key parameters of X-ray detection equipment based on image quality feedback provided below can refer to the limitations of the method for adaptively optimizing key parameters of X-ray detection equipment based on image quality feedback above, and will not be repeated here.

[0122] In an exemplary embodiment, Figure 8 As shown, a device 800 for adaptively optimizing key parameters of X-ray detection equipment based on image quality feedback is provided, comprising: an image acquisition module 802, an image quality assessment module 804, a parameter optimization module 806 and an image enhancement module 808, wherein:

[0123] The image acquisition module 802 is used to determine the initial key parameters of the X-ray detection equipment and to collect the X-ray image of the object to be detected according to the initial key parameters.

[0124] The image quality assessment module 804 is used to perform quality assessment on the X-ray image to obtain a quality assessment result.

[0125] The parameter optimization module 806 is used to adjust the initial key parameters according to the initial key parameters and the quality evaluation results to obtain new key parameters when the quality evaluation results deviate from the set quality standards.

[0126] The image enhancement module 808 is used to re-acquire the X-ray image of the object to be measured with new key parameters, and use the re-acquired X-ray image as a new X-ray image, and return to the step of performing quality assessment on the X-ray image until the quality assessment result of the new X-ray image meets the set quality standard, thereby obtaining the target X-ray image and target key parameters for the object to be measured.

[0127] Furthermore, in one embodiment, the image quality assessment module 804 is also used to determine the brightness distribution, image quality index value and defect recognition rate of the X-ray image according to the image parameters corresponding to the X-ray image; and obtain the quality assessment result according to the brightness distribution, image quality index value and defect recognition rate.

[0128] Furthermore, in one embodiment, the image quality assessment module 804 is also used to determine whether the quality assessment result deviates from the set quality standard when at least one of the brightness distribution, the image quality index value and the defect recognition rate is abnormal.

[0129] Furthermore, in one embodiment, the parameter optimization module 806 is also used to calculate the quality assessment results and the initial key parameters using a preset parameter adaptive adjustment algorithm to obtain a plurality of candidate key parameters; select candidate key parameters corresponding to the results that meet the iterative calculation conditions so that the objective function of the preset parameter adaptive adjustment algorithm is obtained, and determine the candidate key parameters as new key parameters; the objective function is obtained by fitting the X-ray images generated under different key parameters and the quality assessment results corresponding to the X-ray images.

[0130] Furthermore, in one embodiment, the parameter optimization module 806 is also used to input the initial key parameters and quality assessment results into a pre-trained parameter prediction model to obtain new key parameters; the pre-trained parameter prediction model is trained by X-ray images generated under different key parameters and the quality assessment results corresponding to the X-ray images.

[0131] Furthermore, in one embodiment, the parameter optimization module 806 is also used to obtain attribute data of the object to be tested; the attribute data of the object to be tested, the quality assessment results and the initial key parameters are input into a pre-trained multimodal parameter prediction model to obtain new key parameters; the pre-trained multimodal parameter prediction model is trained by generating X-ray images under different parameters for different types of samples to be tested and the quality assessment results corresponding to the X-ray images.

[0132] Each module in the above-mentioned device 800 for adaptively optimizing key parameters of X-ray detection equipment based on image quality feedback can be implemented in whole or in part by software, hardware, or 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.

[0133] 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. Fig. 9 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 initial key parameters, X-ray images, and quality assessment results. 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 adaptive optimization of key parameters of X-ray detection equipment based on image quality feedback is implemented.

[0134] Those skilled in the art will understand that Fig. 9 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.

[0135] In one embodiment, a computer device is further provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above method embodiments when executing the computer program.

[0136] 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-mentioned method embodiments are implemented.

[0137] In one embodiment, a computer program product is provided, including a computer program, which implements the steps in the above method embodiments when executed by a processor.

[0138] 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.

[0139] 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.

[0140] 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 adaptively optimizing key parameters of X-ray detection equipment based on image quality feedback, characterized in that: The method comprises: Determine initial key parameters of the X-ray detection equipment, and collect an X-ray image of the object to be detected by using the initial key parameters; Performing quality assessment on the X-ray image to obtain a quality assessment result; In the case where the quality assessment result deviates from the set quality standard, adjusting the initial key parameters according to the initial key parameters and the quality assessment result to obtain new key parameters; An X-ray image of the object under test is acquired again with the new key parameters, and the re-acquired X-ray image is used as a new X-ray image, and the step of performing quality assessment on the X-ray image is returned to until the quality assessment result of the new X-ray image meets the set quality standard, thereby obtaining a target X-ray image and target key parameters for the object under test.

2. The method according to claim 1, characterized in that The method performs quality assessment on the X-ray image to obtain a quality assessment result, including: Determining the brightness distribution, image quality index value and defect recognition rate of the X-ray image according to image parameters corresponding to the X-ray image; The quality assessment result is obtained according to the brightness distribution, image quality index value and defect recognition rate.

3. The method according to claim 2, characterized in that After obtaining the quality assessment result according to the brightness distribution, the image quality index value and the defect recognition rate, the method further includes: When at least one of the brightness distribution, the image quality index value and the defect recognition rate is abnormal, it is determined that the quality assessment result deviates from the set quality standard.

4. The method according to claim 1, characterized in that: The adjusting the initial key parameters according to the initial key parameters and the quality assessment results to obtain new key parameters includes: Using a preset parameter adaptive adjustment algorithm to calculate the quality assessment result and the initial key parameter to obtain a plurality of candidate key parameters; Select candidate key parameters corresponding to the results that make the objective function of the preset parameter adaptive adjustment algorithm obtain the results that meet the iterative calculation conditions, and determine the candidate key parameters as new key parameters; the objective function is obtained by fitting the X-ray images generated under different key parameters and the quality assessment results corresponding to the X-ray images.

5. The method according to claim 1, characterized in that The adjusting the initial key parameters according to the initial key parameters and the quality assessment results to obtain new key parameters includes: Inputting the initial key parameters and the quality assessment results into a pre-trained parameter prediction model to obtain new key parameters; The pre-trained parameter prediction model is obtained by training X-ray images generated under different key parameters and quality assessment results corresponding to the X-ray images.

6. The method according to claim 1, characterized in that The adjusting the initial key parameters according to the initial key parameters and the quality assessment results to obtain new key parameters includes: Acquiring attribute data of the object under test; The attribute data of the object to be tested, the quality assessment results and the initial key parameters are input into a pre-trained multimodal parameter prediction model to obtain new key parameters; the pre-trained multimodal parameter prediction model is trained by generating X-ray images under different parameters for different types of samples to be tested and the quality assessment results corresponding to the X-ray images.

7. The method according to any one of claims 1 to 6, characterized in that: The key parameters of the X-ray detection equipment include the penetrability of the object to be detected, the tube voltage, tube current, focal spot size of the X-ray source, the exposure time, focal spot size and focal distance of the X-ray detection equipment, and at least one of the flat panel detector parameters.

8. An adaptive optimization device for key parameters of X-ray detection equipment based on image quality feedback, characterized in that: The device comprises: An image acquisition module, used to determine initial key parameters of the X-ray detection equipment and to acquire an X-ray image of the object under test through the initial key parameters; An image quality assessment module, used to perform quality assessment on the X-ray image to obtain a quality assessment result; A parameter optimization module, used for adjusting the initial key parameters according to the initial key parameters and the quality evaluation results to obtain new key parameters when the quality evaluation results deviate from the set quality standards; The image enhancement module is used to re-acquire the X-ray image of the object under test with the new key parameters, and use the re-acquired X-ray image as a new X-ray image, and return to the step of performing quality assessment on the X-ray image until the quality assessment result of the new X-ray image meets the set quality standard, thereby obtaining a target X-ray image and target key parameters for the object under test.

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

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images