X-ray imaging and data processing system with dynamic compensation

Abstract

The invention discloses an X-ray imaging and data processing system with dynamic compensation, and relates to the technical field of X-ray imaging, and the system comprises an image collection module which is used for collecting an X-ray image of an object and converting a collected image signal into digital image data; the feature analysis module is used for analyzing features of the digital image data, determining image feature parameters, calculating a fluctuation range of the image feature parameters based on a statistical method and setting a dynamic threshold value; and the compensation decision module is used for judging whether the image characteristic parameters of the digital image data exceed a dynamic threshold value or not, if so, judging that the image has defects, carrying out compensation processing, and determining the compensation type. Through cooperative work of a plurality of links such as image acquisition, feature analysis and compensation decision, a clearer, more accurate and more reliable solution is provided for X-ray imaging, noise interference in the imaging process can be effectively reduced, the image contrast is enhanced, image details are clearly presented, and the imaging quality is remarkably improved.

Description

Technical Field

[0001] The present invention relates to the technical field of X-ray imaging, and specifically relates to an X-ray imaging and data processing system with dynamic compensation. Background Art

[0002] With the continuous development of fields such as medical diagnosis and industrial inspection, X-ray imaging technology has been widely used. In the imaging process of traditional X-ray imaging systems, they often rely on fixed parameter settings, lack the dynamic adaptation ability to changes in the imaging environment and objects, and the data processing methods are relatively simple. This makes the imaging results easily affected by factors such as noise and insufficient contrast, resulting in a decline in image quality and being unable to meet the strict requirements for image clarity and accuracy.

[0003] In the prior art, X-ray imaging systems face problems such as imaging defects and data processing errors. The noise interference in the imaging process will blur the image details and affect the recognition of the characteristics of the target object; insufficient contrast may lead to the omission of key information. These problems not only reduce the reliability of imaging, but also mislead subsequent analysis and diagnosis, affecting the work efficiency and accuracy in related fields. Therefore, how to improve X-ray imaging quality, optimize the data processing process, and eliminate the adverse factors in the imaging and data processing processes has become an important research direction in this field. Summary of the Invention

[0004] To solve the above technical problems, an X-ray imaging and data processing system with dynamic compensation is provided, and this technical solution solves the above problems.

[0005] To achieve the above object, the technical solution adopted by the present invention is as follows:

[0006] An X-ray imaging and data processing system with dynamic compensation, comprising:

[0007] An image acquisition module, configured to acquire X-ray images of an object and convert the acquired image signals into digital image data;

[0008] A feature analysis module, which analyzes the features of the digital image data, determines the image feature parameters, calculates the fluctuation range of the image feature parameters based on statistical methods, and sets dynamic thresholds;

[0009] A compensation decision module, which determines whether the image feature parameters of the digital image data exceed the dynamic threshold. If they exceed, it is determined that the image has defects and needs to be compensated, and the compensation type is determined;

[0010] A compensation execution module, which performs dynamic compensation on the defective digital image data according to the compensation type by using corresponding compensation algorithms;

[0011] A quality assessment module that assesses the quality of the digital image data after dynamic compensation and generates an image quality index;

[0012] A result output module that outputs a qualified X-ray imaging result according to the image quality index.

[0013] Preferably, the image acquisition module specifically includes:

[0014] A signal conversion unit that converts the analog signal collected by the X-ray detector into a digital signal;

[0015] A format regularization unit that regularizes the digital signal to form standard digital image data.

[0016] Preferably, the feature analysis module specifically includes:

[0017] A frequency domain conversion unit that converts the standard digital image data from the spatial domain to the frequency domain through discrete cosine transform. The formula is as follows:

[0018]

[0019] Where F(u, v) is the frequency domain data, f(x, y) is the spatial domain image data, N is the image size, and α(u) and α(v) are normalization coefficients;

[0020] A feature extraction unit that extracts image feature parameters based on the frequency domain data.

[0021] Preferably, calculating the fluctuation range of the image feature parameters based on the statistical method and setting the dynamic threshold specifically includes:

[0022] A data grouping unit that groups the image feature parameters according to the image acquisition batches;

[0023] A mean calculation unit that calculates the mean X of each group of image feature parameters. The formula is:

[0024]

[0025] Where X i is the i-th image feature parameter, and n is the number of parameters in each group;

[0026] A standard deviation calculation unit that calculates the standard deviation σ of each group of image feature parameters. The formula is:

[0027]

[0028] Where σ represents the standard deviation, which is used to measure the dispersion degree of the image feature parameters. X i is the i-th image feature parameter, X is the mean of each group of image feature parameters, and n is the number of parameters in each group;

[0029] A threshold setting unit that sets a dynamic threshold according to the mean value and the standard deviation.

[0030] Preferably, the compensation execution module adopts different algorithms for different compensation types:

[0031] When the compensation type is contrast compensation, the histogram equalization algorithm is adopted to redistribute the gray values of the digital image data. The formula is as follows:

[0032]

[0033] where s k is the equalized gray value, n j is the number of pixels with the gray value of j in the original image, and n is the total number of pixels in the image;

[0034] When the compensation type is noise removal, the median filtering algorithm is adopted to sort the neighborhood pixels of each pixel point in the digital image data, and the median value is taken as the new value of the pixel point.

[0035] Preferably, the quality evaluation module evaluates the quality of the digital image data after dynamic compensation by calculating the peak signal-to-noise ratio. The formula is as follows:

[0036]

[0037] where MSE is the mean square error, and the formula is:

[0038]

[0039] In the formula, I(i, j) is the pixel value of the original image, K(i, j) is the pixel value of the compensated image, and m and n are the image sizes.

[0040] Preferably, the result output module outputs a qualified X-ray imaging result when the peak signal-to-noise ratio is greater than the set threshold according to the image quality index.

[0041] Preferably, the set threshold of the peak signal-to-noise ratio in the result output module is determined according to the actual requirements of the imaging scenario:

[0042] When in a high-resolution imaging scenario, a higher peak signal-to-noise ratio threshold is set to ensure image details;

[0043] When in a low-noise sensitive scenario, a lower peak signal-to-noise ratio threshold is set to reduce the system operation pressure while ensuring the image recognizability.

[0044] Preferably, the system further includes a storage module for storing the collected digital image data, the intermediate data during the compensation process, and the final imaging result.

[0045] Preferably, the storage module adopts a hierarchical storage strategy and classifies and stores data according to the usage frequency and importance of the data.

[0046] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0047] The X-ray imaging and data processing system with dynamic compensation proposed by the present invention, through the collaborative work of multiple links such as image acquisition, feature analysis, compensation decision-making, compensation execution, quality evaluation, and result output, provides a clearer, more accurate, and more reliable solution for X-ray imaging. This system can effectively reduce the noise interference in the imaging process, enhance the image contrast, clearly present the image details, significantly improve the imaging quality, and reduce the omission of key information. In terms of data processing, the system conducts in-depth analysis and dynamic compensation on the imaging data based on statistical and image processing algorithms, greatly improving the accuracy of data processing and providing strong support for subsequent analysis and diagnosis. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] Figure 1 It is a system flowchart of the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0049] The following description is used to disclose the present invention so that those skilled in the art can implement the present invention. The preferred embodiments described below are only examples, and those skilled in the art can think of other obvious variations.

[0050] Referring to Figure 1 As shown, an X-ray imaging and data processing system with dynamic compensation, an image acquisition module, is used to acquire the X-ray image of an object and convert the acquired image signal into digital image data;

[0051] A feature analysis module analyzes the features of the digital image data, determines the image feature parameters, calculates the fluctuation range of the image feature parameters based on statistical methods, and sets the dynamic threshold;

[0052] A compensation decision-making module determines whether the image feature parameters of the digital image data exceed the dynamic threshold. If they exceed, it is determined that the image has defects and needs to be compensated, and the compensation type is determined;

[0053] A compensation execution module dynamically compensates the defective digital image data according to the compensation type by using the corresponding compensation algorithm;

[0054] A quality evaluation module evaluates the quality of the digital image data after dynamic compensation and generates an image quality index;

[0055] A result output module outputs a qualified X-ray imaging result according to the image quality index.

[0056] Specifically, the system is based on modular design. The image acquisition module, as the information entry of the system, quickly and accurately acquires the X-ray image of the object, converts the analog signal into digital image data, and completes the preliminary acquisition of information. The feature analysis module comprehensively analyzes the digital image data by means of statistics. By analyzing the fluctuation characteristics of the data, it determines the variation range of the image feature parameters, and then sets the corresponding dynamic threshold. The compensation decision module determines whether there are defects in the image by comparing the image feature parameters with the dynamic threshold. Once a defect is found, it quickly determines the compensation type. The compensation execution module, according to the instructions of the compensation decision module, applies the corresponding algorithm to perform dynamic compensation on the image data. The quality assessment module uses professional assessment methods to quantitatively analyze the quality of the compensated image data and generate intuitive image quality indicators. The result output module decides whether to output qualified X-ray imaging results based on the indicators given by the quality assessment module. The whole process is closely linked and constitutes an organic whole. Through the mutual cooperation and collaborative work of each module, the adaptability of the system to complex imaging environments is greatly improved, ensuring that the system can stably and efficiently output high-quality imaging results.

[0057] Specifically, the image acquisition module includes:

[0058] A signal conversion unit that converts the analog signal collected by the X-ray detector into a digital signal;

[0059] A format regularization unit that regularizes the digital signal to form standard digital image data.

[0060] Specifically, the signal conversion unit, as the front end of the image acquisition module, is responsible for converting the analog signal collected by the X-ray detector into a digital signal. This process is achieved through a high-precision analog-to-digital converter, providing a basis for subsequent digital processing. The format regularization unit then performs normalization processing on the converted digital signal. By unifying the data format, adjusting the resolution, etc., it converts it into standard digital image data to meet the consistency requirements of the data format for subsequent modules. After two-level processing, it not only ensures that the collected image data can smoothly enter the subsequent processing links, but also effectively avoids compatibility problems caused by inconsistent data formats, improving the overall data processing efficiency of the system.

[0061] Specifically, the feature analysis module includes:

[0062] A frequency domain conversion unit that converts the standard digital image data from the spatial domain to the frequency domain through discrete cosine transform. The formula is as follows:

[0063]

[0064] Among them, F(u, v) is the frequency-domain data, f(x, y) is the spatial-domain image data, N is the image size, and α(u) and α(v) are normalization coefficients;

[0065] The feature extraction unit extracts image feature parameters based on the frequency-domain data.

[0066] Specifically, the frequency-domain conversion unit uses the discrete cosine transform to convert the standard digital image data from the spatial domain to the frequency domain. In the frequency domain, the detailed information, texture features, etc. of the image can be presented as different frequency components. The feature extraction unit extracts representative image feature parameters based on the frequency-domain data by setting specific algorithms and parameters. These parameters can accurately reflect the essential features of the image and provide key data support for subsequent threshold setting and image analysis. Through frequency-domain analysis and feature extraction, the system can deeply analyze the image from multiple dimensions, comprehensively obtain the feature information of the image, and provide rich and accurate data basis for subsequent dynamic threshold setting. This not only improves the system's ability to analyze images but also provides a more accurate judgment basis for subsequent image compensation and quality assessment, helping to improve the system's adaptability to different types of images.

[0067] Calculating the fluctuation range of the image feature parameters based on the statistical method and setting the dynamic threshold specifically includes:

[0068] The data grouping unit groups the image feature parameters according to the image acquisition batches;

[0069] The mean calculation unit calculates the mean X of each group of image feature parameters. The formula is:

[0070]

[0071] where X i is the i-th image feature parameter, and n is the number of parameters in each group;

[0072] The standard deviation calculation unit calculates the standard deviation σ of each group of image feature parameters. The formula is:

[0073]

[0074] where σ represents the standard deviation, which is used to measure the dispersion degree of the image feature parameters. X i is the i-th image feature parameter, X is the mean of each group of image feature parameters, and n is the number of parameters in each group;

[0075] The threshold setting unit sets the dynamic threshold according to the mean and the standard deviation.

[0076] Specifically, the data grouping unit groups the image feature parameters according to the image acquisition batches, dividing a large amount of image data into multiple subsets for targeted statistical analysis. The mean calculation unit obtains the mean of each group of data by summing each group of image feature parameters and dividing by the number of parameters, and this mean reflects the average level of each group of data. The standard deviation calculation unit obtains the standard deviation by calculating the square root of the average of the sum of the squares of the differences between each feature parameter and the mean, which is used to measure the dispersion degree of the feature parameters. The threshold setting unit comprehensively considers the mean and the standard deviation, and uses statistical principles to set a dynamic threshold that can reflect the overall change trend of the data. Using statistical methods to set the dynamic threshold enables the system to flexibly adjust the threshold according to the actual changes in the image data under different imaging conditions, improving the scientificity and rationality of threshold setting. This dynamic threshold setting method can better adapt to the complex and changeable imaging environment, avoiding misjudgment or missed judgment caused by a fixed threshold, and improving the detection accuracy of the system for image defects.

[0077] The compensation execution module adopts different algorithms for different compensation types:

[0078] When the compensation type is contrast compensation, the histogram equalization algorithm is adopted to redistribute the gray values of the digital image data, and the formula is as follows:

[0079]

[0080] where s k is the equalized gray value, n j is the number of pixels with gray value j in the original image, and n is the total number of pixels in the image;

[0081] When the compensation type is noise removal, the median filtering algorithm is adopted to sort the neighborhood pixels of each pixel point in the digital image data, and the median value is taken as the new value of this pixel point.

[0082] Specifically, when the compensation type is contrast compensation, the compensation execution module adopts the histogram equalization algorithm to redistribute the gray values of the digital image data. By counting the number of pixels with different gray values in the original image, the new value of each gray value after equalization is calculated, thereby stretching the gray distribution of the image and enhancing the contrast of the image. When the compensation type is noise removal, the median filtering algorithm is adopted. Taking each pixel point as the center, a neighborhood of a certain size is selected, and the pixels in the neighborhood are sorted, and the median value is taken as the new value of this pixel point, effectively removing the noise interference in the image. For different image defects, the compensation execution module adopts special algorithms for processing, which has strong pertinence and effectiveness. This method can significantly improve the image quality and meet the diverse requirements for image quality in different application scenarios.

[0083] The quality assessment module evaluates the quality of the digitally compensated image data by calculating the peak signal-to-noise ratio. The formula is as follows:

[0084]

[0085] Where MSE is the mean squared error, and the formula is:

[0086]

[0087] In the formula, I(i,j) is the pixel value of the original image, K(i,j) is the pixel value of the compensated image, and m and n are the image dimensions.

[0088] Specifically, the quality assessment module evaluates the quality of the digitally compensated image data by calculating the peak signal-to-noise ratio. The calculation of the peak signal-to-noise ratio is based on the mean squared error. The mean squared error calculates the average of the sum of the squares of the differences by comparing the pixel values of the original image and the compensated image. Through this calculation process, the difference degree between the compensated image and the original image can be quantitatively reflected, so as to evaluate the image quality. The quality assessment module provides a quantitative evaluation index for the image quality, making the judgment of the image quality more objective and accurate. This quantitative index provides a clear judgment basis for the result output module, helps to ensure that the output imaging result meets the preset quality standard, avoids low-quality images from entering the subsequent application links, and ensures the reliability of the system output result.

[0089] The result output module outputs a qualified X-ray imaging result when the peak signal-to-noise ratio is greater than the set threshold according to the image quality index.

[0090] The set threshold of the peak signal-to-noise ratio in the result output module is determined according to the actual requirements of the imaging scenario:

[0091] When in a high-resolution imaging scenario, a higher peak signal-to-noise ratio threshold is set to ensure image details.

[0092] When in a low-noise sensitive scenario, a lower peak signal-to-noise ratio threshold is set to reduce the system operation pressure while ensuring the image recognizability.

[0093] Specifically, in the entire X-ray imaging and data processing system, the result output module undertakes the key responsibility of controlling the output imaging quality. This module obtains the image quality indicators generated by the quality assessment module and compares the peak signal-to-noise ratio with the set threshold. The set peak signal-to-noise ratio threshold is not fixed, but is flexibly adjusted according to the actual requirements of the imaging scenario. In high-resolution imaging scenarios, in order to completely retain the detailed information of the image, the module will set a higher peak signal-to-noise ratio threshold; while in low-noise sensitive scenarios, in order to balance the image recognizability and the system operation pressure, the module will set the peak signal-to-noise ratio threshold relatively low. When the peak signal-to-noise ratio of the compensated image is greater than the set threshold in the corresponding scenario, the result output module determines that the image quality meets the standard and outputs a qualified X-ray imaging result; otherwise, it does not output or promotes the image to enter the further processing process. Through this mechanism, the result output module can accurately judge whether the image is qualified, avoid low-quality images from flowing into subsequent application links, and greatly improve the quality and reliability of the system output results. At the same time, this method of dynamically adjusting the threshold according to the imaging scenario endows the system with stronger scene adaptability, effectively optimizes the system performance while ensuring the imaging quality. It avoids the problem of increased system operation burden caused by too high a threshold or the problem of affecting image quality caused by too low a threshold, and achieves a good balance between imaging quality and system performance.

[0094] The system also includes a storage module for storing the collected digital image data, intermediate data during the compensation process, and the final imaging results.

[0095] The storage module adopts a hierarchical storage strategy and classifies and stores data according to the usage frequency and importance of the data.

[0096] Specifically, the storage module is responsible for storing the acquired digital image data, intermediate data during the compensation process, and the final imaging results. By constructing a complete data storage structure and management mechanism, it classifies and stores different types of data to comprehensively ensure the security and accessibility of the data. At the same time, the storage module is equipped with data backup and recovery functions to effectively prevent data loss, greatly enhancing the stability and reliability of the system. The storage module adopts a hierarchical storage strategy and allocates storage resources differentially according to the usage frequency and importance of the data. For data that is frequently used and crucial, such as the currently processed image data and key intermediate results, the storage module stores them in high-speed and highly reliable storage media, which not only ensures the rapid access to the data but also maintains data security. For data with a lower usage frequency and relatively less importance, such as historical imaging data and general intermediate data, the storage module stores them in low-speed and low-cost storage media to reduce storage costs. It not only provides strong support for the data management of the system, facilitates researchers to trace back and analyze the entire imaging and data processing process, helps to deeply understand the system operation mechanism, discover potential problems, and provides data basis for the optimization and improvement of the system, but also can reasonably allocate storage resources according to the data characteristics, significantly improving the storage efficiency.

[0097] The above has shown and described the basic principles, main features, and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited by the above embodiments. What is described in the above embodiments and the specification is only the principle of the present invention. Without departing from the spirit and scope of the present invention, the present invention will have various changes and improvements, and these changes and improvements all fall within the scope of the present invention claimed.

Claims

1. An X-ray imaging and data processing system with dynamic compensation, characterized in that, Including: An image acquisition module, which is used to acquire X-ray images of an object and convert the acquired image signals into digital image data; A feature analysis module, which analyzes the features of the digital image data, determines image feature parameters, calculates the fluctuation range of the image feature parameters based on statistical methods, and sets a dynamic threshold; A compensation decision module, which determines whether the image feature parameters of the digital image data exceed the dynamic threshold. If they exceed, it is determined that the image has defects and compensation processing is required, and the compensation type is determined; A compensation execution module, which dynamically compensates the defective digital image data according to the compensation type by using corresponding compensation algorithms; A quality evaluation module, which evaluates the quality of the digital image data after dynamic compensation and generates an image quality index; A result output module, which outputs a qualified X-ray imaging result according to the image quality index.

2. The X-ray imaging and data processing system with dynamic compensation according to claim 1, characterized in that, The image acquisition module specifically includes: A signal conversion unit, which converts the analog signals acquired by an X-ray detector into digital signals; A format regularization unit, which regularizes the format of the digital signals to form standard digital image data.

3. A dynamic compensation-based X-ray imaging and data processing system according to claim 1, wherein The feature analysis module specifically includes: A frequency domain conversion unit, which converts the standard digital image data from the spatial domain to the frequency domain through discrete cosine transform. The formula is as follows: Where F(u, v) is the frequency domain data, f(x, y) is the spatial domain image data, N is the image size, and α(u) and α(v) are normalization coefficients; A feature extraction unit, which extracts image feature parameters based on the frequency domain data.

4. A dynamic compensation - enabled X - ray imaging and data processing system according to claim 1, characterized in that, The calculation of the fluctuation range of the image feature parameters based on statistical methods and the setting of the dynamic threshold specifically include: A data grouping unit, which groups the image feature parameters according to the image acquisition batches; A mean value calculation unit, which calculates the mean value X of each group of image feature parameters. The formula is: where X i is the i-th image feature parameter, and n is the number of parameters in each group; A standard deviation calculation unit, which calculates the standard deviation σ of each group of image feature parameters. The formula is: Among them, σ represents the standard deviation, which is used to measure the degree of dispersion of the image feature parameters, X i is the i-th image feature parameter, X is the mean value of each group of image feature parameters, and n is the number of parameters in each group; A threshold setting unit, which sets the dynamic threshold according to the mean value and the standard deviation.

5. A dynamic compensation-based X-ray imaging and data processing system according to claim 1, characterized in that, The compensation execution module adopts different algorithms for different compensation types: When the compensation type is contrast compensation, the histogram equalization algorithm is adopted to redistribute the gray values of the digital image data. The formula is as follows: Among them, s k is the equalized gray value, n j is the number of pixels with gray value j in the original image, and n is the total number of pixels in the image; When the compensation type is noise removal, the median filtering algorithm is adopted to sort the neighborhood pixels of each pixel point in the digital image data and take the middle value as the new value of the pixel point.

6. A dynamic compensation-based X-ray imaging and data processing system according to claim 1, characterized in that The quality evaluation module evaluates the quality of the digital image data after dynamic compensation by calculating the peak signal-to-noise ratio. The formula is as follows: Where MSE is the mean square error. The formula is: In the formula, I(i, j) is the original image pixel value, K(i, j) is the pixel value of the compensated image, and m and n are the image sizes.

7. A dynamic compensation - equipped X - ray imaging and data processing system according to claim 1, characterized in that, The result output module outputs a qualified X-ray imaging result according to the image quality index when the peak signal-to-noise ratio is greater than the set threshold.

8. An X-ray imaging and data processing system with dynamic compensation according to claim 7, characterized in that, The set threshold of the peak signal-to-noise ratio in the result output module is determined according to the actual requirements of the imaging scenario: When in a high-resolution imaging scenario, a higher peak signal-to-noise ratio threshold is set to ensure image details; When in a low-noise sensitive scenario, a lower peak signal-to-noise ratio threshold is set to reduce the system operation pressure while ensuring the image recognizability.

9. The X-ray imaging and data processing system with dynamic compensation according to claim 1, characterized in that, The system further includes a storage module for storing the acquired digital image data, intermediate data during the compensation process, and the final imaging result.

10. A dynamic compensation-based X-ray imaging and data processing system according to claim 9, characterized in that, The storage module adopts a hierarchical storage strategy and classifies and stores data according to the usage frequency and importance of the data.

Images