A two-axis linkage-based x-ray image processing method and system

Abstract

This invention discloses an X-Ray image processing method and system based on two-axis linkage, belonging to the field of image processing technology. The processing method includes the following steps: constructing an image management system to store each generated X-Ray image and generate corresponding imaging records; performing multi-dimensional analysis on the X-Ray images stored in any imaging record and detecting the image quality of the X-Ray images; identifying the effectiveness of the imaging positions of the two axes and constraining the safe area for any magnification; analyzing the dynamic change trend of the region position and image quality to obtain the effective imaging area for any magnification and the allowable error range for any magnification; evaluating the quality of the real-time generated X-Ray images to determine the optimal magnification; extracting the allowable error range of the optimal magnification and identifying anomalies in the generated image quality; and helping the two axes to lock the optimal imaging position more quickly.

Description

Technical Field

[0001] This invention relates to the field of image processing technology, specifically to an X-Ray image processing method and system based on two-axis linkage. Background Technology

[0002] In X-ray imaging systems, image magnification is usually achieved by adjusting the relative positions of the X-ray source and the flat panel detector. Traditional methods use a single-axis independent adjustment mode, which changes the distance between the X-ray source or the flat panel detector to adjust the magnification.

[0003] However, there are infinitely many possible position combinations for the same magnification. Theoretically, the closer the X-ray source is to the flat panel detector, the greater the number of photons received per unit area and the optimal signal-to-noise ratio. However, due to the conical beam characteristics of X-rays, an excessively close distance will prevent the imaging area from covering the effective detection surface of the FPD, resulting in the loss of edge information. Current technology relies on manual step-by-step adjustment of the dual-axis position. Operators need to repeatedly try to approach the optimal imaging point, which is inefficient and cannot guarantee the global optimal solution. Furthermore, there is a lack of real-time monitoring of mechanical collisions or abnormal beam coverage, which seriously affects the quality of X-ray image generation. Summary of the Invention

[0004] The purpose of this invention is to provide an X-Ray image processing method and system based on two-axis linkage to solve the problems raised in the prior art.

[0005] To achieve the above objectives, the present invention provides the following technical solution: an X-Ray image processing method based on two-axis linkage, the processing method comprising the following steps:

[0006] Step S100: Build an image management system to store each generated X-Ray image, and synchronously acquire the imaging position and magnification of the two axes to generate corresponding imaging records;

[0007] Step S200: Perform multi-dimensional analysis on the X-ray images stored in any imaging record and detect the image quality of the X-ray images; the X-ray source and the flat panel detector each have a motion axis that can adjust the distance between them. Adjusting the position of the X-ray source and the flat panel detector can change the image magnification. There are countless combinations of the two axis positions for the same magnification. Through the linkage of the two axes, the magnification can be adjusted automatically by one click based on the real-time distance between the two axes.

[0008] Step S300: Based on the detection results of image quality in any imaging record, identify the validity of the imaging position of the two axes; based on the valid imaging position of each imaging record corresponding to any magnification, constrain the safe area of ​​any magnification.

[0009] Step S400: Compare each imaging record at any magnification, analyze the dynamic change trend of region location and image quality, obtain the effective imaging area at any magnification, and obtain the allowable error range of any magnification based on the image quality difference;

[0010] Step S500: Control the two axes to move the effective imaging position at any magnification in real time, evaluate the quality of the real-time generated X-Ray image, determine the optimal magnification, extract the allowable error range of the optimal magnification, determine whether the generated image quality is abnormal and issue an abnormality alert.

[0011] Furthermore, step S100 includes the following steps:

[0012] Step S101: Establish a two-dimensional Cartesian coordinate system and display the position coordinates of the X-ray source and the flat panel detector in the coordinate system. Whenever the X-ray source and the flat panel detector generate an X-ray image, acquire the position coordinates of the X-ray source and the flat panel detector respectively. Set the position coordinates of the X-ray source as (x0, y0) and the position coordinates of the flat panel detector as (x1, y1). Simultaneously acquire the fixed position coordinates of the object being measured as (x2, y2), according to the formula:

[0013] ;

[0014] The magnification M of the generated X-ray image is calculated; the magnification is the ratio of the distance between the X-ray source and the object to the distance between the flat panel detector and the object. Since the two axes need to move synchronously, the position coordinates of the object are fixed, which is beneficial for analyzing the relationship between the two axes.

[0015] Step S102: Summarize the three acquired position coordinates to obtain the imaging position group of the X-Ray image. Summarize and store the generated X-Ray image, imaging position group and magnification in the image management system, and generate the corresponding imaging record in the image management system.

[0016] Furthermore, step S200 includes the following steps:

[0017] Step S201: Randomly select an imaging record from the image management system and extract the generated X-Ray image from the selected imaging record; preset several evaluation indicators for the X-Ray image and preset a data range for any evaluation indicator; use image recognition technology to collect data for any evaluation indicator of the X-Ray image, compare the collected data with the indicator data range, and obtain the error value of any evaluation indicator; the evaluation indicators for the X-Ray image may include conventional indicators such as noise, contrast, resolution, signal-to-noise ratio, and coverage;

[0018] Step S202: Preset corresponding evaluation weights for each evaluation indicator, and set the evaluation weight of the i-th evaluation indicator as Q. i Obtain the error value P of the i-th evaluation index. i According to the formula:

[0019] ;

[0020] Where 'a' represents the number of preset evaluation indicators; the comprehensive error value Z for extracting the X-Ray image is calculated; and an anomaly evaluation threshold Z is preset. th If Z > Z th If the X-Ray image is not properly defined, it will be classified as an anomalous image. The evaluation weight of each evaluation metric reflects the importance of the metric. For example, although the resolution affects the clarity of the image, a small deviation will not affect image recognition. However, the coverage will directly affect the recognition of image integrity. Therefore, there is a significant difference in the evaluation weight between the two.

[0021] Furthermore, step S300 includes the following steps:

[0022] Step S301: Randomly select an imaging record, and extract the imaging position group and X-Ray image from the selected imaging record respectively. If the X-Ray image is an abnormal image, the extracted imaging position group is set as the abnormal imaging position group. If the X-Ray image is not an abnormal image, the extracted imaging position group is set as the normal imaging position group.

[0023] Step S302: Obtain the magnification of each imaging record, divide each imaging record according to the magnification, and obtain an imaging position set with arbitrary magnification, wherein the imaging position set contains several imaging position groups.

[0024] Step S303: Arbitrarily select an imaging position set with a magnification of 100%. Extract all abnormal imaging position groups from the selected imaging position set, and obtain the position coordinates of the X-ray source and the position coordinates of the flat panel detector in each abnormal imaging position group to obtain the abnormal coordinate range of the X-ray source and the abnormal coordinate range of the flat panel detector. Set the abnormal abscissa range of the X-ray source as (x0... ex1 ,x0 ex2 ) and the range of abnormal ordinates is (y0) ex1 ,y0 ex2 By analogy, the characteristic anomalous region of the X-ray source can be obtained, and the characteristic anomalous region of the flat panel detector can be obtained in the same way.

[0025] Step 3204: Extract all normal imaging position groups from the selected imaging position set. Randomly select one normal imaging position group and obtain the position coordinates of the X-ray source and the flat panel detector in the selected normal imaging position group. If the position coordinates of the X-ray source or the flat panel detector are in the feature anomaly region, obtain the distance between the X-ray source and the flat panel detector in each normal imaging position group, and select the distance with the largest value as the maximum safe distance. Set the position coordinates in the feature anomaly region of the selected normal imaging position group as feature coordinates. Randomly select one position coordinate from the two feature anomaly regions. If the distance between the selected position coordinate and the feature coordinate is less than the maximum safe distance, set the selected position coordinate as the safe position coordinate. Exclude all safe position coordinates from the feature anomaly region to obtain the adjusted feature anomaly region. Since the two axes move synchronously, the abnormal position of the image recognition anomaly is affected by both axes. Therefore, the anomaly region obtained by only the abnormal position of the abnormal image is a general area. However, the position coordinates of the normal image can effectively screen the anomaly region, thus obtaining a more accurate anomaly region.

[0026] Step S305: Using the fixed position coordinates of the object under test as the center and the maximum safe distance as the radius, construct a desired region. Compare the desired region with the adjusted abnormal feature region and exclude the adjusted abnormal feature region from the desired region to obtain a safe region for selecting the magnification. Set the constraint condition in the safe region as follows: the distance between the X-ray source and the flat panel detector is less than and equal to the maximum safe distance. Since the maximum safe distance between the two axes has been determined, the range of motion of the two axes has also been confirmed. Therefore, it is only necessary to check the abnormal region from the range of motion to accurately determine the desired region and significantly reduce the area where the imaging position is located.

[0027] Furthermore, step S400 includes the following steps:

[0028] Step S401: Randomly select a magnification, set the imaging record corresponding to the selected magnification as the target imaging record, arbitrarily obtain a normal target imaging record that is not an abnormal record, extract the X-Ray image and imaging position group from the obtained normal target imaging record, and obtain the comprehensive error value of the X-Ray image.

[0029] Step S402: Obtain the comprehensive error value of all normal target imaging records, select the normal target imaging record with the smallest comprehensive error value, and extract the imaging position group of the selected normal target imaging record to obtain the distance between the two axes in the selected normal target imaging record as L1; extract several target imaging records with a distance between the two axes of L1 from each normal target imaging record, and obtain the comprehensive error value of the X-Ray image in the several target imaging records respectively, and select the error comprehensive value Z1 with the largest value. ’ The error comprehensive value for selecting normal target imaging records is set to Z1. ’’ The error range (Z1) between the two axes with a distance L1 is obtained. ’’ Z1 ’ );

[0030] Step S403: Obtain the comprehensive error value of the X-ray images in the remaining normal target imaging records. If the comprehensive error value of a certain normal target imaging record is within the error range (Z1)... ’’ Z1 ’ If the image position group is extracted from a certain normal target imaging record, the image position group extracted from the other normal target imaging records and the image position group with a distance of L1 between the two axes are summarized and compared with the safe area and its constraints of the selected magnification to obtain the effective imaging area of ​​the selected magnification.

[0031] Step S404: Obtain the comprehensive error value of the X-ray image in the normal target imaging record of each imaging position group in the effective imaging area, and extract the comprehensive error value Z1 with the largest value. max The allowable error for selecting the magnification factor, f = (Z1), is calculated. max -Z1 ’’ ) / Z1 ’’ .

[0032] Furthermore, step S500 includes the following steps:

[0033] Step S501: Whenever the two axes are controlled to generate an X-Ray image, the effective imaging area of ​​each magnification is obtained respectively. An effective imaging area of ​​any magnification is selected, and an imaging position group is selected from the effective imaging area. An X-Ray image is generated in real time in the selected imaging position group, and the real-time error comprehensive value of the generated X-Ray image is obtained.

[0034] Step S502: Obtain the real-time error comprehensive value of the X-Ray image generated by the selected imaging position group in each magnification, and set the magnification corresponding to the minimum real-time error comprehensive value as the optimal magnification.

[0035] Step S503: Control the two axes to traverse and image each imaging position group in the effective imaging area of ​​the optimal magnification, obtain the real-time error comprehensive value of all X-Ray images, and select the real-time error comprehensive value with the smallest value as the optimal comprehensive value.

[0036] Step S504: Acquire several imaging records containing the optimal magnification, and select the minimum error composite value among the several imaging records as the desired composite threshold (Z). now ) th The optimal overall value is set to (Z). now ) best If |(Z now ) th -(Z now ) best | / (Z now ) th If f1 > f1, where f1 is the allowable error level of the optimal magnification, then an abnormality alert will be issued for the generated X-Ray image.

[0037] To better implement the above methods, an X-Ray image processing system is also proposed. The processing system includes a historical imaging acquisition module, an imaging quality assessment module, a linkage position analysis module, a decision bias analysis module, and a real-time anomaly analysis module.

[0038] The historical imaging acquisition module is used to build an image management system to store each generated X-Ray image and to synchronously acquire the imaging position and magnification of the two axes to generate corresponding imaging records.

[0039] The imaging quality assessment module is used to perform multi-dimensional analysis on X-Ray images stored in any imaging record and to detect the image quality of the X-Ray images.

[0040] The linkage position analysis module is used to identify the validity of the imaging position of the two axes based on the detection results of the image quality in any imaging record; and to constrain the safe area of ​​any magnification based on the valid imaging position of each imaging record corresponding to any magnification.

[0041] The decision deviation analysis module is used to compare each imaging record at any magnification, analyze the dynamic change trend of region location and image quality, obtain the effective imaging area at any magnification, and obtain the allowable error range of any magnification based on the image quality difference.

[0042] The real-time anomaly analysis module is used to control the movement of the effective imaging position of the two axes at any magnification in real time, evaluate the quality of the real-time generated X-Ray image, determine the optimal magnification, extract the allowable error range of the optimal magnification, judge whether the quality of the generated image is abnormal and provide an anomaly alert.

[0043] Furthermore, the linkage position analysis module includes an effective position identification unit and a safety boundary constraint unit;

[0044] The effective position recognition unit is used to identify the effectiveness of the imaging position of the two axes based on the detection results of the image quality in any imaging record; the safety boundary constraint unit is used to constrain the safety area of ​​any magnification based on the effective imaging position of each imaging record corresponding to any magnification.

[0045] Furthermore, the decision deviation analysis module includes a location decision optimization unit and an allowable deviation analysis unit;

[0046] The location decision optimization unit is used to compare each imaging record at any magnification, analyze the dynamic change trend of regional location and image quality, and obtain the effective imaging area at any magnification; the allowable deviation analysis unit is used to obtain the allowable error range for any magnification based on the differences in image quality.

[0047] Furthermore, the real-time anomaly analysis module includes a real-time linked imaging unit and an anomaly deviation identification unit;

[0048] The real-time linkage imaging unit is used to control the movement of the effective imaging position of the two axes at any magnification in real time, and to evaluate the quality of the real-time generated X-Ray image to determine the optimal magnification. The abnormal deviation identification unit is used to extract the allowable error range of the optimal magnification, determine whether the quality of the generated image is abnormal, and provide an abnormality warning.

[0049] Compared with the prior art, the beneficial effects of the present invention are:

[0050] 1. This invention enables the synchronous movement of the X-ray source and the flat panel detector through two-axis linkage. By analyzing historical imaging data, the effective imaging area at each magnification can be obtained, which helps the two axes to lock the best imaging position more quickly. This can significantly improve the imaging time while ensuring the imaging quality of the image.

[0051] 2. This invention analyzes historical abnormal images, defines safe areas at different magnifications, and constrains the safe distance between the two axes, which can effectively eliminate a large portion of the moving area and indirectly improve imaging time.

[0052] 3. This invention analyzes the relationship between position and image quality in historical imaging records, extracts the effective imaging area and allowable error range for each magnification, and dynamically determines the optimal magnification and optimal imaging position, which can ensure that the imaging quality is within the expected range and provides a certain guarantee for the imaging quality. Attached Figure Description

[0053] Figure 1 This is a schematic diagram illustrating the steps of an X-Ray image processing method based on two-axis linkage.

[0054] Figure 2 This is a schematic diagram of the structure of an X-Ray image processing system based on two-axis linkage;

[0055] Figure 3 This is a flowchart of step S300. Detailed Implementation

[0056] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0057] Example: Figures 1 to 3 As shown, this invention provides an X-Ray image processing method based on two-axis linkage, the processing method including the following steps:

[0058] Step S100: Build an image management system to store each generated X-Ray image, and synchronously acquire the imaging position and magnification of the two axes to generate corresponding imaging records;

[0059] Step S100 includes the following steps:

[0060] Step S101: Establish a two-dimensional Cartesian coordinate system and display the position coordinates of the X-ray source and the flat panel detector in the coordinate system. Whenever the X-ray source and the flat panel detector generate an X-ray image, acquire the position coordinates of the X-ray source and the flat panel detector respectively. Set the position coordinates of the X-ray source as (x0, y0) and the position coordinates of the flat panel detector as (x1, y1). Simultaneously acquire the fixed position coordinates of the object being measured as (x2, y2), according to the formula:

[0061] ;

[0062] The magnification M of the generated X-Ray image is calculated;

[0063] Step S102: Summarize the three acquired position coordinates to obtain the imaging position group of the X-Ray image. Summarize and store the generated X-Ray image, imaging position group and magnification in the image management system, and generate the corresponding imaging record in the image management system.

[0064] Step S200: Perform multi-dimensional evaluation on the X-Ray images stored in any imaging record, and identify anomalies in the image quality of the X-Ray images;

[0065] Step S200 includes the following steps:

[0066] Step S201: Select an imaging record arbitrarily from the image management system and extract the generated X-Ray image from the selected imaging record; preset several evaluation indicators for the X-Ray image and preset an indicator data range for any evaluation indicator; use image recognition technology to collect data for any evaluation indicator of the X-Ray image; compare the collected data with the indicator data range to obtain the error value of any evaluation indicator.

[0067] Step S202: Preset corresponding evaluation weights for each evaluation indicator, and set the evaluation weight of the i-th evaluation indicator as Q. i Obtain the error value P of the i-th evaluation index. i According to the formula:

[0068] ;

[0069] Where 'a' represents the number of preset evaluation indicators; the comprehensive error value Z for extracting the X-Ray image is calculated; and an anomaly evaluation threshold Z is preset. th If Z > Z th If so, the extracted X-Ray image will be set as an anomalous image;

[0070] Example 1: Three preset evaluation indicators are set as contrast, resolution, and noise, with evaluation weights of 0.5 for contrast, 0.3 for resolution, and 0.2 for noise. The error values ​​for contrast are 0.1, resolution 0.2, and noise 0.15. The overall error value of the X-Ray image is calculated as Z = 0.5 × 0.1 + 0.3 × 0.2 + 0.2 × 0.15 = 0.05 + 0.06 + 0.03 = 0.14. A preset anomaly evaluation threshold Z is also set. th =0.2, therefore the X-Ray image is not an anomalous image.

[0071] Step S300: Based on the anomaly judgment results of image quality in any imaging record, the validity of the imaging position of the two axes is identified; based on the valid imaging position of each imaging record corresponding to any magnification, the safe area of ​​any magnification is constrained.

[0072] Step S300 includes the following steps:

[0073] Step S301: Randomly select an imaging record, and extract the imaging position group and X-Ray image from the selected imaging record respectively. If the X-Ray image is an abnormal image, the extracted imaging position group is set as the abnormal imaging position group. If the X-Ray image is not an abnormal image, the extracted imaging position group is set as the normal imaging position group.

[0074] Step S302: Obtain the magnification of each imaging record, divide each imaging record according to the magnification, and obtain an imaging position set with arbitrary magnification, wherein the imaging position set contains several imaging position groups.

[0075] Step S303: Arbitrarily select an imaging position set with a magnification of 100%. Extract all abnormal imaging position groups from the selected imaging position set, and obtain the position coordinates of the X-ray source and the position coordinates of the flat panel detector in each abnormal imaging position group to obtain the abnormal coordinate range of the X-ray source and the abnormal coordinate range of the flat panel detector. Set the abnormal abscissa range of the X-ray source as (x0... ex1 ,x0 ex2 ) and the range of abnormal ordinates is (y0) ex1 ,y0 ex2 By analogy, the characteristic anomalous region of the X-ray source can be obtained, and the characteristic anomalous region of the flat panel detector can be obtained in the same way.

[0076] Step S304: Extract all normal imaging position groups from the selected imaging position set. Randomly select one normal imaging position group and obtain the position coordinates of the X-ray source and the flat panel detector in the selected normal imaging position group. If the position coordinates of the X-ray source or the flat panel detector are in the characteristic anomaly region, obtain the distance between the X-ray source and the flat panel detector in each normal imaging position group and select the distance with the largest value as the maximum safe distance. Set the position coordinates in the characteristic anomaly region of the selected normal imaging position group as characteristic coordinates. Randomly select one position coordinate from the two characteristic anomaly regions. If the distance between the selected position coordinate and the characteristic coordinate is less than the maximum safe distance, set the selected position coordinate as the safe position coordinate. Exclude all safe position coordinates from the characteristic anomaly region to obtain the adjusted characteristic anomaly region.

[0077] Step S305: Using the fixed position coordinates of the object under test as the center and the maximum safe distance as the radius, construct a desired region and compare the desired region with the adjusted feature anomaly region. Exclude the adjusted feature anomaly region from the desired region to obtain a safe region for selecting the magnification. Set the constraint condition in the safe region as follows: the distance between the X-ray source and the flat panel detector is less than and equal to the maximum safe distance.

[0078] Step S400: Compare each imaging record at any magnification, analyze the dynamic change trend of region location and image quality, obtain the effective imaging area at any magnification, and obtain the allowable error range of any magnification based on the image quality difference;

[0079] Step S400 includes the following steps:

[0080] Step S401: Randomly select a magnification, set the imaging record corresponding to the selected magnification as the target imaging record, arbitrarily obtain a normal target imaging record that is not an abnormal record, extract the X-Ray image and imaging position group from the obtained normal target imaging record, and obtain the comprehensive error value of the X-Ray image.

[0081] Step S402: Obtain the comprehensive error value of all normal target imaging records, select the normal target imaging record with the smallest comprehensive error value, and extract the imaging position group of the selected normal target imaging record to obtain the distance between the two axes in the selected normal target imaging record as L1; extract several target imaging records with a distance between the two axes of L1 from each normal target imaging record, and obtain the comprehensive error value of the X-Ray image in the several target imaging records respectively, and select the error comprehensive value Z1 with the largest value. ’ The error comprehensive value for selecting normal target imaging records is set to Z1. ’’ The error range (Z1) between the two axes with a distance L1 is obtained. ’’ Z1 ’ );

[0082] Step S403: Obtain the comprehensive error value of the X-ray images in the remaining normal target imaging records. If the comprehensive error value of a certain normal target imaging record is within the error range (Z1)... ’’ Z1 ’ If the image position group is extracted from a certain normal target imaging record, the image position group extracted from the other normal target imaging records and the image position group with a distance of L1 between the two axes are summarized and compared with the safe area and its constraints of the selected magnification to obtain the effective imaging area of ​​the selected magnification.

[0083] Step S404: Obtain the comprehensive error value of the X-ray image in the normal target imaging record of each imaging position group in the effective imaging area, and extract the comprehensive error value Z1 with the largest value. max The allowable error for selecting the magnification factor, f = (Z1), is calculated. max -Z1 ’’ ) / Z1 ’’ ;

[0084] Example 2: Set the error comprehensive value of the normal target imaging record with the smallest error comprehensive value to 0.04, and the distance between the two axes to 1. Acquire all normal target imaging records with a distance of 1 between the two axes to obtain the error value range (0.04, 0.06). If the error comprehensive value corresponding to other distances is within the error value range, such as 0.05, then set the corresponding two-axis position group as a position coordinate of the effective imaging area. Select a maximum error comprehensive value of 0.06 from the effective imaging area, and calculate the allowable error range f = (0.06 - 0.04) / 0.04 = 50%.

[0085] Step S500: Real-time control of the two axes to move the effective imaging position at any magnification, and quality assessment of the real-time generated X-Ray image to determine the optimal magnification; extract the allowable error range of the optimal magnification, and perform anomaly identification on the generated image quality;

[0086] Step S500 includes the following steps:

[0087] Step S501: Whenever the two axes are controlled to generate an X-Ray image, the effective imaging area of ​​each magnification is obtained respectively. An effective imaging area of ​​any magnification is selected, and an imaging position group is selected from the effective imaging area. An X-Ray image is generated in real time in the selected imaging position group, and the real-time error comprehensive value of the generated X-Ray image is obtained.

[0088] Step S502: Obtain the real-time error comprehensive value of the X-Ray image generated by the selected imaging position group in each magnification, and set the magnification corresponding to the minimum real-time error comprehensive value as the optimal magnification.

[0089] Step S503: Control the two axes to traverse and image each imaging position group in the effective imaging area of ​​the optimal magnification, obtain the real-time error comprehensive value of all X-Ray images, and select the real-time error comprehensive value with the smallest value as the optimal comprehensive value.

[0090] Step S504: Acquire several imaging records containing the optimal magnification, and select the minimum error composite value among the several imaging records as the desired composite threshold (Z).now ) th The optimal overall value is set to (Z). now ) best If |(Z now ) th -(Z now ) best | / (Z now ) th If f1 > f1, where f1 is the allowable error level of the optimal magnification, then an abnormality alert will be issued for the generated X-Ray image.

[0091] An X-Ray image processing system, the processing system includes a historical imaging acquisition module, an imaging quality assessment module, a linkage position analysis module, a decision bias analysis module, and a real-time anomaly analysis module;

[0092] The historical imaging acquisition module is used to build an image management system to store each generated X-Ray image and to synchronously acquire the imaging position and magnification of the two axes to generate corresponding imaging records.

[0093] The imaging quality assessment module is used to perform multi-dimensional analysis on X-Ray images stored in any imaging record and to detect the image quality of the X-Ray images.

[0094] The linkage position analysis module is used to identify the validity of the imaging position of the two axes based on the detection results of the image quality in any imaging record; and to constrain the safe area of ​​any magnification based on the valid imaging position of each imaging record corresponding to any magnification.

[0095] The decision deviation analysis module is used to compare each imaging record at any magnification, analyze the dynamic change trend of region location and image quality, obtain the effective imaging area at any magnification, and obtain the allowable error range of any magnification based on the image quality difference.

[0096] The real-time anomaly analysis module is used to control the movement of the effective imaging position of the two axes at any magnification in real time, evaluate the quality of the real-time generated X-Ray image, determine the optimal magnification, extract the allowable error range of the optimal magnification, judge whether the quality of the generated image is abnormal and provide an anomaly alert.

[0097] The linkage position analysis module includes an effective position identification unit and a safety boundary constraint unit.

[0098] The effective position recognition unit is used to identify the effectiveness of the imaging position of the two axes based on the detection results of the image quality in any imaging record; the safety boundary constraint unit is used to constrain the safety area of ​​any magnification based on the effective imaging position of each imaging record corresponding to any magnification.

[0099] The decision deviation analysis module includes a location decision optimization unit and an allowable deviation analysis unit.

[0100] The location decision optimization unit is used to compare each imaging record at any magnification, analyze the dynamic change trend of regional location and image quality, and obtain the effective imaging area at any magnification; the allowable deviation analysis unit is used to obtain the allowable error range for any magnification based on the differences in image quality.

[0101] The real-time anomaly analysis module includes a real-time linkage imaging unit and an anomaly deviation identification unit.

[0102] The real-time linkage imaging unit is used to control the movement of the effective imaging position of the two axes at any magnification in real time, and to evaluate the quality of the real-time generated X-Ray image to determine the optimal magnification. The abnormal deviation identification unit is used to extract the allowable error range of the optimal magnification, determine whether the quality of the generated image is abnormal, and provide an abnormality warning.

[0103] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the invention can be implemented in other specific forms without departing from its spirit or essential characteristics. Therefore, the embodiments should be considered in all respects as exemplary and non-limiting, and the scope of the invention is defined by the appended claims rather than the foregoing description. Thus, all variations falling within the meaning and scope of equivalents of the claims are intended to be included within the present invention. No reference numerals in the claims should be construed as limiting the scope of the claims.

Claims

1. An X-Ray image processing method based on two-axis linkage, characterized in that: The processing method includes the following steps: Step S100: Build an image management system to store each generated X-Ray image, and synchronously acquire the imaging position and magnification of the two axes to generate corresponding imaging records; Step S200: Perform multi-dimensional analysis on the X-Ray images stored in any imaging record, and detect the image quality of the X-Ray images; Step S300: Based on the detection results of image quality in any imaging record, identify the validity of the imaging position of the two axes; based on the valid imaging position of each imaging record corresponding to any magnification, constrain the safe area of ​​any magnification. Step S400: Compare each imaging record at any magnification, analyze the dynamic change trend of region location and image quality, obtain the effective imaging area at any magnification, and obtain the allowable error range of any magnification based on the image quality difference; Step S500: Control the two axes to move the effective imaging position at any magnification in real time, and evaluate the quality of the real-time generated X-Ray image to determine the optimal magnification; extract the allowable error range of the optimal magnification, determine whether the quality of the generated image is abnormal and issue an abnormality alert; Step S300 includes the following steps: Step S301: Randomly select an imaging record, and extract the imaging position group and X-Ray image from the selected imaging record respectively. If the X-Ray image is an abnormal image, the extracted imaging position group is set as the abnormal imaging position group. If the X-Ray image is not an abnormal image, the extracted imaging position group is set as the normal imaging position group. Step S302: Obtain the magnification of each imaging record, divide each imaging record according to the magnification, and obtain an imaging position set with arbitrary magnification, wherein the imaging position set contains several imaging position groups. Step S303: Arbitrarily select an imaging position set with a magnification of 100%. Extract all abnormal imaging position groups from the selected imaging position set, and obtain the position coordinates of the X-ray source and the position coordinates of the flat panel detector in each abnormal imaging position group to obtain the abnormal coordinate range of the X-ray source and the abnormal coordinate range of the flat panel detector. Set the abnormal abscissa range of the X-ray source as (x0... ex1 ,x0 ex2 ) and the range of abnormal ordinates is (y0) ex1 ,y0 ex2 By analogy, the characteristic anomalous region of the X-ray source can be obtained, and the characteristic anomalous region of the flat panel detector can be obtained in the same way. Step S304: Extract all normal imaging position groups from the selected imaging position set. Randomly select one normal imaging position group and obtain the position coordinates of the X-ray source and the flat panel detector in the selected normal imaging position group. If the position coordinates of the X-ray source or the flat panel detector are in the characteristic anomaly region, obtain the distance between the X-ray source and the flat panel detector in each normal imaging position group and select the distance with the largest value as the maximum safe distance. Set the position coordinates in the characteristic anomaly region of the selected normal imaging position group as characteristic coordinates. Randomly select one position coordinate from the two characteristic anomaly regions. If the distance between the selected position coordinate and the characteristic coordinate is less than the maximum safe distance, set the selected position coordinate as the safe position coordinate. Exclude all safe position coordinates from the characteristic anomaly region to obtain the adjusted characteristic anomaly region. Step S305: Using the fixed position coordinates of the object under test as the center and the maximum safe distance as the radius, construct a desired region and compare the desired region with the adjusted feature anomaly region. Exclude the adjusted feature anomaly region from the desired region to obtain a safe region for selecting the magnification. Set the constraint condition in the safe region as follows: the distance between the X-ray source and the flat panel detector is less than and equal to the maximum safe distance.

2. The X-Ray image processing method based on two-axis linkage according to claim 1, characterized in that: Step S100 includes the following steps: Step S101: Establish a two-dimensional Cartesian coordinate system and display the position coordinates of the X-ray source and the flat panel detector in the coordinate system. Whenever the X-ray source and the flat panel detector generate an X-ray image, acquire the position coordinates of the X-ray source and the flat panel detector respectively. Set the position coordinates of the X-ray source as (x0, y0) and the position coordinates of the flat panel detector as (x1, y1). Simultaneously acquire the fixed position coordinates of the object being measured as (x2, y2), according to the formula: ； The magnification M of the generated X-Ray image is calculated; Step S102: Summarize the three acquired position coordinates to obtain the imaging position group of the X-Ray image. Summarize and store the generated X-Ray image, imaging position group and magnification in the image management system, and generate the corresponding imaging record in the image management system.

3. The X-Ray image processing method based on two-axis linkage according to claim 2, characterized in that: Step S200 includes the following steps: Step S201: Select an imaging record arbitrarily from the image management system and extract the generated X-Ray image from the selected imaging record; preset several evaluation indicators for the X-Ray image and preset an indicator data range for any evaluation indicator; use image recognition technology to collect data for any evaluation indicator of the X-Ray image; compare the collected data with the indicator data range to obtain the error value of any evaluation indicator. Step S202: Preset corresponding evaluation weights for each evaluation indicator, and set the evaluation weight of the i-th evaluation indicator as Q. i Obtain the error value P of the i-th evaluation index. i According to the formula: ； Where 'a' represents the number of preset evaluation indicators; the comprehensive error value Z for extracting the X-Ray image is calculated; and an anomaly evaluation threshold Z is preset. th If Z > Z th If so, the extracted X-Ray image will be set as an anomalous image.

4. The X-Ray image processing method based on two-axis linkage according to claim 3, characterized in that: Step S400 includes the following steps: Step S401: Randomly select a magnification, set the imaging record corresponding to the selected magnification as the target imaging record, arbitrarily obtain a normal target imaging record that is not an abnormal record, extract the X-Ray image and imaging position group from the obtained normal target imaging record, and obtain the comprehensive error value of the X-Ray image. Step S402: Obtain the comprehensive error value of all normal target imaging records, select the normal target imaging record with the smallest comprehensive error value, and extract the imaging position group of the selected normal target imaging record to obtain the distance between the two axes in the selected normal target imaging record as L1; extract several target imaging records with a distance between the two axes of L1 from each normal target imaging record, and obtain the comprehensive error value of the X-Ray image in the several target imaging records respectively, and select the error comprehensive value Z1 with the largest value. ’ The error comprehensive value for selecting normal target imaging records is set to Z1. ’’ The error range (Z1) between the two axes with a distance L1 is obtained. ’’ Z1 ’ ); Step S403: Obtain the comprehensive error value of the X-ray images in the remaining normal target imaging records. If the comprehensive error value of a certain normal target imaging record is within the error range (Z1)... ’’ Z1 ’ If the image position group is extracted from a certain normal target imaging record, the image position group extracted from the other normal target imaging records and the image position group with a distance of L1 between the two axes are summarized and compared with the safe area and its constraints of the selected magnification to obtain the effective imaging area of ​​the selected magnification. Step S404: Obtain the comprehensive error value of the X-ray image in the normal target imaging record of each imaging position group in the effective imaging area, and extract the comprehensive error value Z1 with the largest value. max The allowable error for selecting the magnification factor, f = (Z1), is calculated. max -Z1 ’’ ) / Z1 ’’ .

5. The X-Ray image processing method based on two-axis linkage according to claim 4, characterized in that: Step S500 includes the following steps: Step S501: Whenever the two axes are controlled to generate an X-Ray image, the effective imaging area of ​​each magnification is obtained respectively. An effective imaging area of ​​any magnification is selected, and an imaging position group is selected from the effective imaging area. An X-Ray image is generated in real time in the selected imaging position group, and the real-time error comprehensive value of the generated X-Ray image is obtained. Step S502: Obtain the real-time error comprehensive value of the X-Ray image generated by the selected imaging position group in each magnification, and set the magnification corresponding to the minimum real-time error comprehensive value as the optimal magnification. Step S503: Control the two axes to traverse and image each imaging position group in the effective imaging area of ​​the optimal magnification, obtain the real-time error comprehensive value of all X-Ray images, and select the real-time error comprehensive value with the smallest value as the optimal comprehensive value. Step S504: Acquire several imaging records containing the optimal magnification, and select the minimum error composite value among the several imaging records as the desired composite threshold (Z). now ) th The optimal overall value is set to (Z). now ) best If |(Z now ) th -(Z now ) best | / (Z now ) th If f1 > f1, where f1 is the allowable error level of the optimal magnification, then an abnormality alert will be issued for the generated X-Ray image.

6. An X-Ray image processing system for executing the X-Ray image processing method based on two-axis linkage as described in any one of claims 1-5, characterized in that: The processing system includes a historical imaging acquisition module, an imaging quality assessment module, a linkage location analysis module, a decision deviation analysis module, and a real-time anomaly analysis module. The historical imaging acquisition module is used to build an image management system to store each generated X-Ray image, and to synchronously acquire the imaging position and magnification of the two axes to generate corresponding imaging records. The imaging quality assessment module is used to perform multi-dimensional analysis on X-Ray images stored in any imaging record and to detect the image quality of the X-Ray images. The linkage position analysis module is used to identify the validity of the imaging position of the two axes based on the detection results of the image quality in any imaging record; and to constrain the safe area of ​​any magnification based on the valid imaging position of each imaging record corresponding to any magnification. The decision deviation analysis module is used to compare each imaging record at any magnification, analyze the dynamic change trend of region location and image quality, obtain the effective imaging area at any magnification, and obtain the allowable error range of any magnification based on the image quality difference. The real-time anomaly analysis module is used to control the movement of the two axes at the effective imaging position of any magnification in real time, evaluate the quality of the real-time generated X-Ray image, determine the optimal magnification, extract the allowable error range of the optimal magnification, determine whether the quality of the generated image is abnormal, and issue an anomaly alert.

7. An X-Ray image processing system according to claim 6, characterized in that: The linkage position analysis module includes an effective position identification unit and a safety boundary constraint unit; The effective position identification unit is used to identify the effectiveness of the imaging position of the two axes based on the detection results of the image quality in any imaging record; the safety boundary constraint unit is used to constrain the safety area of ​​any magnification based on the effective imaging position of each imaging record corresponding to any magnification.

8. An X-Ray image processing system according to claim 6, characterized in that: The decision deviation analysis module includes a location decision optimization unit and an allowable deviation analysis unit; The location decision optimization unit is used to compare each imaging record at any magnification, analyze the dynamic change trend of regional location and image quality, and obtain the effective imaging area at any magnification; the allowable deviation analysis unit is used to obtain the allowable error range of any magnification based on the difference in image quality.

9. An X-Ray image processing system according to claim 6, characterized in that: The real-time anomaly analysis module includes a real-time linkage imaging unit and an anomaly deviation identification unit. The real-time linkage imaging unit is used to control the movement of the two axes to the effective imaging position at any magnification in real time, and to evaluate the quality of the real-time generated X-Ray image to determine the optimal magnification. The abnormal deviation identification unit is used to extract the allowable error range of the optimal magnification, determine whether the quality of the generated image is abnormal, and provide an abnormality alert.

Images