An intelligent imaging classification diagnosis system and method for fractures based on big data

Abstract

The present invention provides an intelligent imaging classification diagnosis system and method for fractures based on big data, which relates to the field of medical diagnosis technology. The method includes the following steps: obtaining a fracture image quality impact value; obtaining an image fracture displacement assessment accuracy value; obtaining an image fracture tilt assessment accuracy value; and fracture classification. The present invention obtains a fracture image quality impact value by combining fracture imaging data and reference image quality data and determines whether to perform image quality adjustment, then obtains qualified fracture imaging data after image quality adjustment, obtains an image fracture displacement assessment accuracy value based on the fracture image quality impact value and fracture displacement data, and finally obtains an image fracture tilt assessment accuracy value based on the fracture image quality impact value and fracture tilt angle data, thereby achieving the effect of improving the accuracy of fracture classification diagnosis and solving the problem of low accuracy of fracture classification diagnosis in the prior art.

Description

Technical Field

[0001] The present invention relates to the field of medical diagnosis technology, and in particular to a big data-based intelligent imaging classification diagnosis system and method for fractures. Background Art

[0002] With the continuous advancement of medical imaging technology, such as the popularization of imaging examination methods such as X-rays, CT (Computed Tomograph), and MRI (Magnetic Resonance Imaging), doctors can obtain more and more detailed information about fractures. These imaging data not only contain key information such as the location, morphology, and range of the fracture, but also reflect characteristics such as the direction of the fracture line, the type and degree of the fracture, providing a rich data foundation for the classification and diagnosis of fractures. In recent years, big data and artificial intelligence technologies have developed rapidly and have been widely used in the medical field. Through big data processing and analysis technology, massive amounts of medical imaging data can be efficiently integrated and utilized to explore the patterns and characteristics therein. At the same time, algorithm models based on deep learning can automatically learn and identify the imaging characteristics of fractures, realizing accurate classification and diagnosis of fractures.

[0003] Existing methods are based on the comprehensive use of imaging technologies such as X-rays, CT, and MRI to classify fractures. X-rays can quickly and preliminarily determine the type and location of the fracture; CT examinations can further clarify the details and extent of the fracture; and MRI can assess the soft tissue damage around the fracture and the fracture healing process.

[0004] However, in the process of implementing the technical solutions of the embodiments of the present invention, the present invention found that the above technology has at least the following technical problems:

[0005] In existing technologies, the quality of fracture imaging data directly affects the extraction and identification of fracture features. Low-quality data makes it difficult to accurately capture fracture features, resulting in low accuracy in fracture classification diagnosis. Summary of the Invention

[0006] The present invention provides an intelligent imaging classification diagnosis system and method for fractures based on big data. The system obtains a fracture image quality impact value by using acquired fracture imaging data and reference image quality data. Whether to perform image quality adjustment is determined based on the fracture image quality impact value. Then, qualified fracture imaging data after image quality adjustment is obtained. An accurate value of imaging fracture displacement assessment is obtained based on the fracture image quality impact value, fracture displacement data, and reference displacement data. Finally, an accurate value of imaging fracture tilt assessment is obtained based on the fracture image quality impact value, fracture inclination angle data, and a preset inclination angle threshold, thereby improving the accuracy of fracture classification diagnosis.

[0007] In order to solve the above-mentioned purpose of the invention, the technical solution provided by the present invention is as follows:

[0008] A method for intelligent imaging classification and diagnosis of fractures based on big data, comprising the following steps: S1, obtaining a fracture image quality impact value through acquired fracture imaging data and reference image quality data, judging whether to perform image quality adjustment based on the fracture image quality impact value, wherein the fracture image quality impact value is used to evaluate the degree of influence of fracture image quality on fracture displacement and fracture inclination; S2, obtaining qualified fracture imaging data after image quality adjustment, obtaining an accurate value of image fracture displacement assessment based on the fracture image quality impact value, fracture displacement data and reference displacement data, wherein the qualified fracture imaging data indicates that image quality adjustment has been performed. The fracture imaging data corresponding to the fracture image quality impact value that is not higher than the preset quality impact threshold after adjustment, the qualified fracture imaging data includes fracture displacement data and fracture inclination data, and the image fracture displacement assessment accuracy value is used to quantitatively assess the accuracy of the fracture displacement degree in the fracture image; S3, based on the fracture image quality impact value, the fracture inclination angle data and the preset inclination angle threshold, the image fracture inclination assessment accuracy value is obtained, and the image fracture inclination assessment accuracy value is used to quantitatively assess the accuracy of the fracture inclination degree in the fracture image; S4, fracture classification is performed based on the image fracture displacement assessment accuracy value and the image fracture inclination assessment accuracy value.

[0009] Optionally, the fracture imaging data includes a first brightness value, a second brightness value, image signal intensity and image noise intensity; the first brightness value represents the maximum brightness value of the fracture image; the second brightness value represents the minimum brightness value of the fracture image; the reference image quality data includes a preset image contrast threshold, a preset image signal-to-noise ratio threshold, a preset first quality impact weight and a preset second quality impact weight.

[0010] Optionally, the specific process of obtaining the fracture image quality impact value by obtaining the fracture imaging data and the reference image quality data is as follows: obtaining an initial contrast according to the first brightness value and the second brightness value, the initial contrast representing the ratio of the difference between the first brightness value and the second brightness value to the sum of the two, and the initial contrast being used to reflect the brightness situation in the fracture image; obtaining a contrast deviation value according to the initial contrast and a preset image contrast threshold, the contrast deviation value being represented by the ratio of the difference between the preset image contrast threshold and the initial contrast to the preset image contrast threshold, and the contrast deviation value being used to reflect the deviation of the contrast in the fracture image; performing a ratio operation on the image signal intensity and the image noise intensity to obtain an initial image signal-to-noise ratio, and the initial image signal-to-noise ratio being used to reflect the deviation of the contrast in the fracture image. noise interference situation in the fracture image; obtaining an image signal-to-noise ratio deviation value according to a preset image signal-to-noise ratio threshold and an initial image signal-to-noise ratio, wherein the image signal-to-noise ratio deviation value is represented by the ratio of the difference between the preset image signal-to-noise ratio threshold and the initial image signal-to-noise ratio and the preset image signal-to-noise ratio threshold, and the image signal-to-noise ratio deviation value is used to reflect the signal-to-noise ratio deviation situation in the fracture image; judging whether the contrast deviation value and the image signal-to-noise ratio deviation value are both greater than 0, if both are greater than 0, combining the preset first quality influence weight, the preset second quality influence weight contrast deviation value and the image signal-to-noise ratio deviation value to obtain the fracture image quality influence value, otherwise the corresponding values of the contrast deviation value and the image signal-to-noise ratio deviation value that are not greater than 0 are recorded as 0 and then combined with the preset first quality influence weight and the preset second quality influence weight to obtain the fracture image quality influence value.

[0011] Optionally, the limiting expression of the fracture image quality impact value is as follows:

[0012]

[0013] Where, represents the fracture image quality impact value of the mth fracture image, m=1,2,...,r, m represents the fracture image number, r represents the total number of fracture images, represents the contrast deviation value of the mth fracture image, represents the image signal-to-noise ratio deviation value of the mth fracture image, represents the first brightness value of the mth fracture image, represents the second brightness value of the mth fracture image, represents the image signal intensity of the mth fracture image, represents the image noise intensity of the mth fracture image, Indicates the preset image contrast threshold, represents the preset image signal-to-noise ratio threshold, ω1 represents the preset first quality impact weight, and ω2 represents the preset second quality impact weight.

[0014] Optionally, the specific process of judging whether to adjust the image quality based on the fracture image quality impact value is as follows: AS1, judging whether the fracture image quality impact value is not higher than the preset quality impact threshold. When the fracture image quality impact value is not higher than the preset quality impact threshold, no image quality adjustment is performed, otherwise AS2 is executed; AS2, sending a prompt to the preset personnel to increase the exposure time of the fracture image by a preset multiple to a preset maximum exposure time. When the monitored fracture image quality impact value is not higher than the preset quality impact threshold, the adjustment is stopped. If the monitored fracture image quality impact value after increasing the exposure time of the fracture image by a preset multiple to the preset maximum exposure time is higher than the preset quality impact threshold, AS3 is executed; AS3, performing image stretching, when the monitored fracture image quality impact value is not higher than the preset quality impact threshold, the adjustment is stopped. If the monitored fracture image quality impact value after image stretching is higher than the preset quality impact threshold, AS4 is executed; AS4, performing fracture area image enhancement, when the monitored fracture image quality impact value is not higher than the preset quality impact threshold, the adjustment is stopped. If the monitored fracture image quality impact value after fracture area image enhancement is higher than the preset quality impact threshold, feedback is given to the preset personnel to delete the corresponding fracture image.

[0015] Optionally, the fracture displacement data includes a first fracture coordinate and a second fracture coordinate; the first fracture coordinate represents the position coordinate of the predicted point of the left fracture line in the fracture image; the second fracture coordinate represents the position coordinate of the predicted point of the right fracture line in the fracture image; the reference displacement data includes a preset lateral displacement distance threshold and a preset longitudinal displacement distance threshold.

[0016] Optionally, the specific process of obtaining the accurate value of the image fracture displacement assessment based on the fracture image quality impact value, fracture displacement data and reference displacement data is as follows: the initial lateral displacement and the initial longitudinal displacement are obtained according to the first fracture coordinate and the second fracture coordinate, the initial lateral displacement is represented by the result of performing a mean operation on the square root of the sum of the squares of the differences between the horizontal coordinates of the fracture line prediction points corresponding to the left fracture line prediction point and the right fracture line prediction point, the initial longitudinal displacement is represented by the result of performing a mean operation on the square root of the sum of the squares of the differences between the vertical coordinates of the fracture line prediction points corresponding to the left fracture line prediction point and the right fracture line prediction point, the initial lateral displacement is used to reflect the lateral displacement of the two ends of the fracture in the fracture image, and the initial longitudinal displacement is used to reflect the longitudinal displacement of the two ends of the fracture in the fracture image; A relative error calculation is performed between the initial lateral displacement and the preset lateral displacement distance threshold to obtain a lateral displacement deviation value, which is used to reflect the deviation of the lateral displacement at both ends of the fracture in the fracture image; a relative error calculation is performed between the initial longitudinal displacement and the preset longitudinal displacement distance threshold to obtain a longitudinal displacement deviation value, which is used to reflect the deviation of the longitudinal displacement at both ends of the fracture in the fracture image; it is determined whether the lateral displacement deviation value and the longitudinal displacement deviation value are both greater than 0. If both are greater than 0, the fracture image quality impact value, the lateral displacement deviation value and the longitudinal displacement deviation value are combined to obtain the accurate value of the image fracture displacement assessment; otherwise, the corresponding values of the lateral displacement deviation value and the longitudinal displacement deviation value that are not greater than 0 are recorded as 0 and then combined with the fracture image quality impact value to obtain the accurate value of the image fracture displacement assessment.

[0017] Optionally, the fracture inclination angle data includes a fracture height difference and a fracture horizontal distance; the fracture height difference represents the longitudinal extension length of the fracture line in the fracture image; and the fracture horizontal distance represents the transverse separation length of the fracture ends in the fracture image.

[0018] Optionally, the specific process of obtaining the accurate value of the image fracture tilt assessment based on the fracture image quality impact value, the fracture inclination angle data and the preset inclination angle threshold is as follows: an initial inclination angle value is obtained according to the fracture height difference and the fracture horizontal distance, and the initial inclination angle value is represented by substituting the result of the ratio operation of the fracture height difference and the fracture horizontal distance into the result of the inverse tangent function, and the initial inclination angle value is used to reflect the change in the angle of the two ends of the fracture in the fracture image; the initial inclination angle value and the preset inclination angle threshold are calculated to obtain a inclination angle deviation value, and the inclination angle deviation value is used to reflect the deviation of the fracture inclination in the fracture image; it is judged whether the inclination angle deviation value is greater than 0. If it is greater than 0, the accurate value of the image fracture tilt assessment is obtained by combining the inclination angle deviation value and the fracture image quality impact value. Otherwise, the inclination angle deviation value is recorded as 0 and then combined with the fracture image quality impact value to obtain the accurate value of the image fracture tilt assessment.

[0019] The embodiment of the present invention provides an intelligent imaging classification and diagnosis system for fractures based on big data, including a fracture image quality impact value acquisition module, an imaging fracture displacement assessment accuracy value acquisition module, an imaging fracture inclination assessment accuracy value acquisition module and a fracture classification module; wherein, the fracture image quality impact value acquisition module is used to obtain a fracture image quality impact value through the acquired fracture imaging data and reference image quality data, and judge whether to adjust the image quality based on the fracture image quality impact value, and the fracture image quality impact value is used to evaluate the degree of influence of the fracture image quality on the fracture displacement and fracture inclination; the imaging fracture displacement assessment accuracy value acquisition module is used to obtain qualified fracture imaging data after image quality adjustment, and obtain a fracture image quality impact value based on the fracture image quality impact value, the fracture displacement data and the reference displacement data. The accurate value of the image fracture displacement assessment is taken, and the qualified fracture imaging data represents the fracture imaging data corresponding to the fracture image quality impact value that is not higher than the preset quality impact threshold after image quality adjustment. The qualified fracture imaging data includes fracture displacement data and fracture inclination data. The accurate value of the image fracture displacement assessment is used to quantitatively assess the accuracy of the fracture displacement degree in the fracture image; the accurate value acquisition module for the image fracture inclination assessment is used to obtain the accurate value of the image fracture inclination assessment based on the fracture image quality impact value, the fracture inclination angle data and the preset inclination angle threshold. The accurate value of the image fracture inclination assessment is used to quantitatively assess the accuracy of the fracture inclination degree in the fracture image; the fracture classification module is used to classify the fracture based on the accurate value of the image fracture displacement assessment and the accurate value of the image fracture inclination assessment.

[0020] One or more technical solutions provided in the embodiments of the present invention have at least the following technical effects or advantages:

[0021] 1. The fracture image quality impact value is obtained through the fracture imaging data and the reference image quality data to determine whether to adjust the image quality. Then, qualified fracture imaging data after the image quality adjustment is obtained. The accurate value of the image fracture displacement assessment is obtained based on the fracture image quality impact value and the fracture displacement data. Finally, the accurate value of the image fracture tilt assessment is obtained based on the fracture image quality impact value and the fracture inclination angle data, thereby achieving an improvement in the fracture image quality, and then achieving an improvement in the accuracy of fracture classification diagnosis, effectively solving the problem of low accuracy of fracture classification diagnosis in the existing technology.

[0022] 2. By combining the obtained preset first quality influence weight, the preset second quality influence weight contrast deviation value and the image signal-to-noise ratio deviation value, the fracture image quality influence value is obtained, thereby improving the reliability of evaluating the degree of fracture displacement in the fracture image, and further improving the accuracy of quantitatively evaluating the degree of fracture displacement in the fracture image.

[0023] 3. By combining the obtained tilt angle deviation value and the fracture image quality impact value, the accurate value of the image fracture tilt assessment is obtained, thereby improving the reliability of the quantitative assessment of the fracture tilt degree in the fracture image, and further improving the accuracy of the quantitative assessment of the fracture tilt degree in the fracture image. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0025] Figure 1 A flowchart of a method for intelligent imaging classification and diagnosis of fractures based on big data provided by an embodiment of the present invention;

[0026] Figure 2 A statistical diagram showing changes in the fracture image quality impact value provided by an embodiment of the present invention;

[0027] Figure 3 A schematic structural diagram of a big data-based intelligent imaging classification and diagnosis system for fractures provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0028] To make the purpose, technical solutions, and advantages of the embodiments of the present invention more clear, the technical solutions of the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the described embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0029] Unless otherwise defined, the technical or scientific terms used in the present invention shall have the usual meaning understood by persons of ordinary skill in the field to which the present invention belongs. The words "first", "second" and similar terms used in the present invention do not indicate any order, quantity or importance, but are only used to distinguish different components. Similarly, words such as "one", "an" or "the" do not indicate a quantity limitation, but rather indicate the presence of at least one. Words such as "include" or "comprise" mean that the elements or objects preceding the word include the elements or objects listed after the word and their equivalents, without excluding other elements or objects. Words such as "connect" or "connected" are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect.

[0030] It should be noted that the terms "up", "down", "left", "right", "front" and "back" used in the present invention are only used to indicate relative position relationships. When the absolute position of the object being described changes, the relative position relationship may also change accordingly.

[0031] The present invention obtains a fracture image quality impact value through fracture imaging data and reference image quality data, determines whether to perform image quality adjustment based on the fracture image quality impact value, then obtains qualified fracture imaging data after image quality adjustment, obtains an accurate value of image fracture displacement assessment based on the fracture image quality impact value, fracture displacement data and reference displacement data, and finally obtains an accurate value of image fracture tilt assessment based on the fracture image quality impact value, fracture inclination angle data and a preset inclination angle threshold, thereby improving the accuracy of fracture classification diagnosis.

[0032] like Figure 1 As shown, it is a flow chart of an intelligent imaging classification and diagnosis method for fractures based on big data provided by an embodiment of the present invention, comprising the following steps: S1, obtaining a fracture image quality impact value: obtaining a fracture image quality impact value through the obtained fracture imaging data and reference image quality data, judging whether to perform image quality adjustment based on the fracture image quality impact value, the fracture image quality impact value is used to evaluate the degree of influence of the fracture image quality on the fracture displacement and fracture inclination, and the image quality adjustment is used to adjust the fracture image quality impact value to no higher than a preset quality impact threshold; S2, obtaining an image fracture displacement assessment accuracy value: obtaining qualified fracture imaging data after image quality adjustment, obtaining an image fracture displacement assessment accuracy value based on the fracture image quality impact value, the fracture displacement data and the reference displacement data. The qualified fracture imaging data refers to the fracture imaging data corresponding to the fracture imaging quality impact value that is not higher than the preset quality impact threshold after image quality adjustment. The qualified fracture imaging data includes fracture displacement data and fracture inclination data. The imaging fracture displacement assessment accuracy value is used to quantitatively assess the accuracy of the fracture displacement degree in the fracture image; S3, obtain the imaging fracture inclination assessment accuracy value: obtain the imaging fracture inclination assessment accuracy value based on the fracture image quality impact value, the fracture inclination angle data and the preset inclination angle threshold. The imaging fracture inclination assessment accuracy value is used to quantitatively assess the accuracy of the fracture inclination degree in the fracture image; S4, fracture classification: fracture classification is performed based on the imaging fracture displacement assessment accuracy value and the imaging fracture inclination assessment accuracy value. Fracture classification is used to divide fractures into different types.

[0033] In this embodiment, if the image quality adjustment is not performed, the qualified fracture imaging data are all fracture imaging data. The fracture image quality impact value is the basis for evaluating the accuracy of fracture displacement and tilt. The higher the fracture image quality, the smaller the fracture image quality impact value, and the more it can improve the fracture image quality impact value and the fracture image quality impact value. The fracture imaging data uses big data technology and data mining technology (such as cluster analysis, association rule mining, etc.) to collect imaging data (including X-rays, etc.) of fracture patients from multiple hospitals or medical institutions to extract useful information and patterns.

[0034] Fracture classification is achieved by using a convolutional neural network model within a deep learning algorithm and comparing it to existing standard fracture classifications. Reference fracture data, including fracture type, degree of displacement, and fracture inclination, are collected. Using a mature convolutional neural network model such as ResNet50 as the underlying architecture, the ResNet50 convolutional neural network model is trained using the reference fracture data and the corresponding correct classification results. This trained convolutional neural network model then inputs qualified fracture imaging data, accurate fracture displacement estimates from the images, and accurate fracture inclination estimates, producing a fracture classification result. Fracture types include closed, open, stable, unstable, incomplete, and complete fractures. This classification is then used to accurately assess fracture displacement and inclination, improving the diagnostic accuracy of fracture classification.

[0035] Optionally, the fracture imaging data includes a first brightness value, a second brightness value, an image signal intensity and an image noise intensity; the first brightness value represents the maximum brightness value of the fracture image; the second brightness value represents the minimum brightness value of the fracture image; the reference image quality data includes a preset image contrast threshold, a preset image signal-to-noise ratio threshold, a preset first quality influence weight and a preset second quality influence weight; the preset first quality influence weight is used to evaluate the degree of influence of the fracture image contrast on the fracture image quality influence value, and the preset second quality influence weight is used to evaluate the degree of influence of the fracture image signal-to-noise ratio on the fracture image quality influence value.

[0036] In this embodiment, the preset image contrast threshold is represented by the average value of fracture image contrast data in a historical time period in a preset database, and the preset image signal-to-noise ratio threshold is represented by the average value of fracture image signal-to-noise ratio data in a historical time period in a preset database.

[0037] Specifically, the sum of the preset first quality impact weight and the preset second quality impact weight is 1. For example, the preset first quality impact weight is 0.5, and the preset second quality impact weight is 0.5. The preset first quality impact weight is the weight corresponding to the preset image contrast value in the preset database, which represents the degree of influence of the image contrast value on the fracture image quality impact value. When used, the weight corresponding to the preset image contrast value can be directly obtained from the preset database. The corresponding relationship can be a pre-set mapping relationship. For example, the image contrast in the fracture image classification training set and the weight corresponding to the preset image contrast value in the preset database form a mapping set, and the real-time image contrast is input into the mapping set to obtain the corresponding weight. The mapping relationship can be a one-to-one correspondence or a many-to-one relationship. In this example, its value range is [0, 1]; a quantitative evaluation of the accuracy of fracture classification diagnosis is achieved.

[0038] Optionally, the specific process of obtaining the fracture image quality impact value by using the acquired fracture imaging data and reference image quality data is as follows: obtaining an initial contrast based on the first brightness value and the second brightness value, the initial contrast representing the ratio of the difference between the first brightness value and the second brightness value to the sum of the two, and the initial contrast being used to reflect the brightness situation in the fracture image; obtaining a contrast deviation value based on the initial contrast and a preset image contrast threshold, the contrast deviation value being represented by the ratio of the difference between the preset image contrast threshold and the initial contrast to the preset image contrast threshold, and the contrast deviation value being used to reflect the deviation of the contrast in the fracture image; performing a ratio operation on the image signal intensity and the image noise intensity to obtain an initial image signal-to-noise ratio, and the initial image signal-to-noise ratio being used to reflect the noise interference in the fracture image. interference situation; obtain an image signal-to-noise ratio deviation value according to a preset image signal-to-noise ratio threshold and an initial image signal-to-noise ratio, and the image signal-to-noise ratio deviation value is expressed by the ratio of the difference between the preset image signal-to-noise ratio threshold and the initial image signal-to-noise ratio and the preset image signal-to-noise ratio threshold. The image signal-to-noise ratio deviation value is used to reflect the signal-to-noise ratio deviation situation in the fracture image; judge whether the contrast deviation value and the image signal-to-noise ratio deviation value are both greater than 0; if both are greater than 0, then combine the preset first quality influence weight, the preset second quality influence weight, the contrast deviation value and the image signal-to-noise ratio deviation value to obtain the fracture image quality influence value; otherwise, record the corresponding values of the contrast deviation value and the image signal-to-noise ratio deviation value that are not greater than 0 as 0, and then combine them with the preset first quality influence weight and the preset second quality influence weight to obtain the fracture image quality influence value.

[0039] Specifically, the limiting expression of the fracture image quality impact value is as follows:

[0040]

[0041] Where, represents the fracture image quality impact value of the mth fracture image, m=1,2,...,r, m represents the fracture image number, r represents the total number of fracture images, represents the contrast deviation value of the mth fracture image, represents the image signal-to-noise ratio deviation value of the mth fracture image, represents the first brightness value of the mth fracture image, represents the second brightness value of the mth fracture image, represents the image signal intensity of the mth fracture image, represents the image noise intensity of the mth fracture image, Indicates the preset image contrast threshold, represents the preset image signal-to-noise ratio threshold, ω1 represents the preset first quality impact weight, and ω2 represents the preset second quality impact weight.

[0042] The algorithm of this embodiment combines the fracture imaging data for comprehensive analysis to obtain the fracture image quality impact value. In the algorithm of this embodiment, the fracture imaging data does not exist independently, but is interrelated. The greater the image signal intensity, the smaller the fracture image quality impact value. The influence of the first brightness value, the second brightness value and the image noise intensity should also be comprehensively considered. In the fracture image, the signal intensity of the fracture site and its surrounding tissues increases, which often leads to a corresponding increase in the brightness value of the area. The presence of noise may cause the brightness value of the area to fluctuate. The higher the noise intensity, the lower the clarity of the high brightness value area may be. The parameters of the algorithm of this embodiment need to be considered together and their impact on the results.

[0043] Assumed contrast deviation value The range is 0-10, the image signal-to-noise ratio deviation value The range is 0-5, the first quality impact weight ω1 is preset to 0.5, and the second quality impact weight ω2 is preset to 0.5. Figure 2 As shown in FIG, the statistical diagram of the change of the fracture image quality impact value provided by the embodiment of the present invention is shown. Figure 2 It can be seen that when the contrast deviation value is 0, as the image signal-to-noise ratio deviation value gradually increases, the fracture image quality impact value gradually increases. When the image signal-to-noise ratio deviation value is 0, as the contrast deviation value gradually increases, the fracture image quality impact value gradually increases, which means that the influence of fracture image quality on fracture displacement and fracture tilt increases; the quantitative evaluation of fracture displacement and fracture tilt is achieved.

[0044] Optionally, the specific process of determining whether to adjust the image quality based on the fracture image quality impact value is as follows: AS1, determining whether the fracture image quality impact value is not higher than a preset quality impact threshold; when the fracture image quality impact value is not higher than the preset quality impact threshold, no image quality adjustment is performed; otherwise, AS2 is executed; AS2, sending a prompt to a preset person to increase the exposure time of the fracture image by a preset multiple to a preset maximum exposure time; when the monitored fracture image quality impact value is not higher than the preset quality impact threshold, the adjustment is stopped; if the monitored fracture image quality impact value is higher than the preset quality impact threshold after increasing the exposure time of the fracture image by a preset multiple to the preset maximum exposure time, AS3 is executed; AS4 3. Perform image stretching. When the monitored fracture image quality impact value is not higher than the preset quality impact threshold, stop adjusting. If the monitored fracture image quality impact value after image stretching is higher than the preset quality impact threshold, execute AS4. Image stretching means enhancing the details of the fracture image through minimum-maximum stretching; AS4. Perform fracture area image enhancement. When the monitored fracture image quality impact value is not higher than the preset quality impact threshold, stop adjusting. If the monitored fracture image quality impact value after fracture area image enhancement is higher than the preset quality impact threshold, feedback is given to the preset personnel to delete the corresponding fracture image. Fracture area image enhancement means highlighting the fracture area features in the fracture image through a composite enhancement algorithm.

[0045] In this embodiment, the preset quality impact threshold is represented by the minimum value of the fracture image contrast data of the historical time period in the preset database, and the preset exposure time maximum value is represented by the maximum value of the fracture image exposure time data of the historical time period in the preset database. By adjusting the exposure time, the brightness of the image can be changed, and the details in the image can be ensured to be clearly visible, and noise and blur can be reduced, thereby improving the overall quality of the image. Image stretching includes: traversing each pixel of the fracture image through minimum-maximum stretching to find the minimum and maximum values of the pixel values in the image, and linearly mapping each pixel value of the original image to a new grayscale range (0 to 255) based on the found minimum and maximum values. Fracture area image enhancement includes: applying a composite enhancement algorithm. The composite enhancement algorithm can enhance specific features of the fracture area, such as fracture lines, fracture ends, callus formation, etc., and can further highlight the detailed features of the fracture area, such as fracture lines, fracture fragments, etc., providing more accurate information for the doctor's diagnosis; thereby improving the accuracy of fracture classification diagnosis.

[0046] Optionally, the specific process of obtaining the accurate value of the image fracture displacement assessment based on the fracture image quality impact value, fracture displacement data and reference displacement data is as follows: the initial transverse displacement and the initial longitudinal displacement are obtained according to the first coordinate of the fracture and the second coordinate of the fracture, the initial transverse displacement is represented by the result of the mean operation of the square root of the sum of the squares of the differences between the horizontal coordinates of the fracture line prediction points corresponding to the left fracture line prediction point and the right fracture line prediction point, the initial longitudinal displacement is represented by the result of the mean operation of the square root of the sum of the squares of the differences between the vertical coordinates of the fracture line prediction points corresponding to the left fracture line prediction point and the right fracture line prediction point, the initial transverse displacement is used to reflect the transverse displacement of the two ends of the fracture in the fracture image, and the initial longitudinal displacement is used to reflect the longitudinal displacement of the two ends of the fracture in the fracture image; the initial transverse displacement is used to reflect the transverse ... The relative error between the lateral displacement and the preset lateral displacement distance threshold is calculated to obtain the lateral displacement deviation value, which is used to reflect the deviation of the lateral displacement of the two ends of the fracture in the fracture image; the relative error between the initial longitudinal displacement and the preset longitudinal displacement distance threshold is calculated to obtain the longitudinal displacement deviation value, which is used to reflect the deviation of the longitudinal displacement of the two ends of the fracture in the fracture image; it is judged whether the lateral displacement deviation value and the longitudinal displacement deviation value are both greater than 0. If both are greater than 0, the fracture image quality impact value, the lateral displacement deviation value and the longitudinal displacement deviation value are combined to obtain the accurate value of the image fracture displacement assessment; otherwise, the corresponding values of the lateral displacement deviation value and the longitudinal displacement deviation value that are not greater than 0 are recorded as 0 and then combined with the fracture image quality impact value to obtain the accurate value of the image fracture displacement assessment.

[0047] Specifically, the fracture displacement data includes the first fracture coordinate and the second fracture coordinate; the first fracture coordinate represents the position coordinate of the predicted point of the left fracture line in the fracture image; the second fracture coordinate represents the position coordinate of the predicted point of the right fracture line in the fracture image; the reference displacement data includes a preset lateral displacement distance threshold and a preset longitudinal displacement distance threshold.

[0048] Among them, the limiting expression of the accurate value of imaging fracture displacement assessment is as follows:

[0049]

[0050] Where, represents the fracture displacement assessment accuracy of the mth fracture image, m=1,2,...,r, m represents the fracture image number, r represents the total number of fracture images, represents the lateral displacement deviation value of the mth fracture image, represents the longitudinal displacement deviation value of the mth fracture image, Indicates the first fracture coordinate corresponding to the nth left fracture line prediction point in the mth fracture image, n=1,2,...,s, n represents the number of the fracture line prediction point, s represents the total number of fracture line prediction points, Indicates the second coordinate of the fracture corresponding to the predicted point of the nth right fracture line in the mth fracture image, represents the fracture image quality impact value of the mth fracture image, Indicates the preset lateral displacement distance threshold, represents the preset longitudinal displacement distance threshold, and e represents a natural constant.

[0051] In this embodiment, the left fracture line prediction point refers to the point on the fracture line on the left bone, and the right fracture line prediction point refers to the point on the fracture line on the right bone (each person's bone structure, physiological characteristics and activity habits are different, so the left and right fracture lines may have individual differences in shape, direction, length and depth). The left fracture line prediction point and the right fracture line prediction point are set by the preset personnel and the number is equal. The lateral displacement deviation value and longitudinal displacement deviation When the size is larger, the degree of displacement is greater, and it is easier to identify and classify. ( The horizontal coordinate of the first fracture coordinate corresponding to the predicted point of the nth left fracture line in the mth fracture image, The ordinate of the first fracture coordinate corresponding to the predicted point of the nth left fracture line in the mth fracture image, The horizontal coordinate of the second fracture coordinate corresponding to the predicted point of the nth right fracture line in the mth fracture image, The vertical coordinate of the second coordinate of the fracture corresponding to the nth right fracture line prediction point in the mth fracture image) The preset lateral displacement distance threshold is represented by the average value of the fracture lateral displacement distance data in the fracture images of the historical time period in the preset database, and the preset longitudinal displacement distance threshold is represented by the average value of the fracture longitudinal displacement distance data in the fracture images of the historical time period in the preset database.

[0052] It should be understood that the algorithm of this embodiment combines the fracture displacement data for comprehensive analysis to obtain the accurate value of the image fracture displacement assessment. The fracture displacement data in the algorithm of this embodiment does not exist independently, but is interrelated. The larger the horizontal coordinate corresponding to the right fracture line prediction point, the larger the vertical coordinate corresponding to the right fracture line prediction point, which does not mean that the accurate value of the image fracture displacement assessment is larger. The influence of the horizontal coordinate corresponding to the left fracture line prediction point, the vertical coordinate corresponding to the left fracture line prediction point and the fracture image quality impact value should also be comprehensively considered. The larger the fracture image quality impact value, the lower the accuracy of the quantitative assessment of the degree of fracture displacement in the fracture image. When the fracture image quality is poor, the accuracy of the quantitative assessment will be reduced, resulting in inaccurate first coordinate data of the fracture, and then inaccurate first coordinate data of the fracture. The parameters of the algorithm of this embodiment need to consider the impact on the results together, thereby improving the accuracy of fracture classification diagnosis.

[0053] Optionally, the specific process of obtaining the accurate value of the image fracture tilt assessment based on the fracture image quality impact value, the fracture inclination angle data and the preset inclination angle threshold is as follows: an initial inclination angle value is obtained according to the fracture height difference and the fracture horizontal distance, and the initial inclination angle value is represented by substituting the result of the ratio operation of the fracture height difference and the fracture horizontal distance into the result of the inverse tangent function. The initial inclination angle value is used to reflect the change in the angle of the two ends of the fracture in the fracture image; the initial inclination angle value and the preset inclination angle threshold are calculated for relative error to obtain the inclination angle deviation value, and the inclination angle deviation value is used to reflect the deviation of the fracture inclination in the fracture image; it is judged whether the inclination angle deviation value is greater than 0. If it is greater than 0, the accurate value of the image fracture tilt assessment is obtained by combining the inclination angle deviation value and the fracture image quality impact value. Otherwise, the inclination angle deviation value is recorded as 0 and then combined with the fracture image quality impact value to obtain the accurate value of the image fracture tilt assessment.

[0054] Specifically, the fracture inclination angle data includes the fracture height difference and the fracture horizontal distance; the fracture height difference represents the longitudinal extension length of the fracture line in the fracture image; and the fracture horizontal distance represents the transverse separation length of the fracture ends in the fracture image.

[0055] The limiting expression for the accuracy of image fracture tilt assessment is as follows:

[0056]

[0057] Where, represents the accuracy of image fracture tilt assessment of the mth fracture image, m=1,2,...,r, m represents the number of the fracture image, r represents the total number of fracture images, represents the tilt angle deviation value of the mth fracture image, represents the fracture image quality impact value of the mth fracture image, represents the fracture height difference of the mth fracture image, represents the fracture horizontal distance of the mth fracture image, Indicates the preset tilt angle threshold.

[0058] In this embodiment, the preset tilt angle threshold is represented by the average value of the fracture tilt angle data in the fracture images in the historical time period in the preset database.

[0059] It should be understood that the algorithm of this embodiment combines the fracture inclination angle data for comprehensive analysis to obtain the accurate value of the image fracture inclination assessment. The fracture inclination angle data in the algorithm of this embodiment does not exist independently, but is interrelated. The greater the fracture height difference, the greater the accuracy of the image fracture inclination assessment. The influence of the horizontal distance of the fracture should also be considered comprehensively. The greater the inclination angle, the greater the shear force between the fracture ends, resulting in a more unstable fracture, which may cause the longitudinal extension and lateral separation of the fracture to increase. The greater the impact value of the fracture image quality, the lower the accuracy of the quantitative assessment of the fracture inclination in the fracture image. The parameters of the algorithm of this embodiment need to be considered together and their impact on the results.

[0060] Specifically, assuming that the tilt angle deviation value The range is 0-1, and the fracture image quality impact value The range is 0-1, as shown in Table 1, which is a statistical table of changes in the accuracy of image fracture tilt assessment provided by an embodiment of the present invention:

[0061]

[0062] Table 1 Statistics of changes in the accuracy of image fracture tilt assessment

[0063] As shown in Table 1, as the tilt angle deviation value The gradual increase of the inclination means that the greater the degree of inclination, the easier it is to identify and classify. The fracture image quality impact value The gradual decrease of the fracture tilt assessment accuracy The gradual increase means that the accuracy of quantitative assessment of the degree of fracture inclination in fracture images is gradually improved, achieving an improvement in the accuracy of fracture classification diagnosis.

[0064] like Figure 3As shown, it is a structural diagram of an intelligent imaging classification and diagnosis system for fractures based on big data provided by an embodiment of the present invention. An embodiment of the present invention provides an intelligent imaging classification and diagnosis system for fractures based on big data, including a fracture image quality impact value acquisition module, an imaging fracture displacement assessment accuracy value acquisition module, an imaging fracture tilt assessment accuracy value acquisition module and a fracture classification module; wherein, the fracture image quality impact value acquisition module is used to obtain the fracture image quality impact value through the acquired fracture imaging data and reference image quality data, and judge whether to adjust the image quality based on the fracture image quality impact value, the fracture image quality impact value is used to evaluate the influence of the fracture image quality on the fracture displacement and fracture tilt, and the image quality adjustment is used to adjust the fracture image quality impact value to not higher than a preset quality impact threshold; the imaging fracture displacement assessment accuracy value acquisition module is used to obtain the image quality impact value for image quality adjustment The qualified fracture imaging data after adjustment is used to obtain the accurate value of imaging fracture displacement assessment based on the fracture image quality impact value, fracture displacement data and reference displacement data. The qualified fracture imaging data represents the fracture imaging data corresponding to the fracture image quality impact value that is not higher than the preset quality impact threshold after image quality adjustment. The qualified fracture imaging data includes fracture displacement data and fracture inclination data. The accurate value of imaging fracture displacement assessment is used to quantitatively assess the accuracy of the fracture displacement degree in the fracture image; the module for obtaining the accurate value of imaging fracture inclination assessment is used to obtain the accurate value of imaging fracture inclination assessment based on the fracture image quality impact value, fracture inclination angle data and the preset inclination angle threshold. The accurate value of imaging fracture inclination assessment is used to quantitatively assess the accuracy of the fracture inclination degree in the fracture image; the fracture classification module is used to classify fractures based on the accurate value of imaging fracture displacement assessment and the accurate value of imaging fracture inclination assessment.

[0065] In this embodiment, a comprehensive fracture assessment is performed based on the accuracy of fracture displacement and tilt assessments. Fractures are then classified into different types based on the assessment results. This helps doctors develop targeted treatment plans and improve treatment outcomes, ultimately increasing the accuracy of fracture classification diagnosis.

[0066] There are a few points to note:

[0067] (1) The drawings of the embodiments of the present invention only relate to the structures related to the embodiments of the present invention. Other structures may refer to conventional designs.

[0068] (2) For the sake of clarity, the thickness of layers or regions in the drawings used to describe the embodiments of the present invention are exaggerated or reduced, that is, these drawings are not drawn to scale. It is understood that when an element such as a layer, film, region, or substrate is referred to as being "on" or "under" another element, the element may be "directly" "on" or "under" the other element or intervening elements may be present.

[0069] (3) In the absence of conflict, the embodiments of the present invention and the features therein may be combined with each other to form new embodiments.

[0070] The above are only specific embodiments of the present invention, but the protection scope of the present invention is not limited thereto. The protection scope of the present invention shall be based on the protection scope of the claims.

Claims

1. A method for intelligent imaging classification and diagnosis of fractures based on big data, characterized in that: The following steps are involved: S1, obtaining a fracture image quality impact value based on the acquired fracture imaging data and reference image quality data, and determining whether to perform image quality adjustment based on the fracture image quality impact value, wherein the fracture image quality impact value is used to assess the degree of influence of the fracture image quality on fracture displacement and fracture tilt; The fracture imaging data includes a first brightness value, a second brightness value, an image signal intensity, and an image noise intensity; the first brightness value represents the maximum brightness value of the fracture image; the second brightness value represents the minimum brightness value of the fracture image; the reference image quality data includes a preset image contrast threshold, a preset image signal-to-noise ratio threshold, a preset first quality impact weight, and a preset second quality impact weight; The specific process of obtaining the fracture image quality impact value by using the acquired fracture imaging data and reference image quality data is as follows: An initial contrast is obtained according to the first brightness value and the second brightness value, the initial contrast representing the ratio of the difference between the first brightness value and the second brightness value to the sum of the two, and the initial contrast is used to reflect the brightness situation in the fracture image; a contrast deviation value is obtained according to the initial contrast and a preset image contrast threshold, the contrast deviation value is represented by the ratio of the difference between the preset image contrast threshold and the initial contrast to the preset image contrast threshold, and the contrast deviation value is used to reflect the deviation of the contrast in the fracture image; an initial image signal-to-noise ratio is obtained by performing a ratio operation on the image signal intensity and the image noise intensity, and the initial image signal-to-noise ratio is used to reflect the noise interference situation in the fracture image; an image signal-to-noise ratio deviation value is obtained according to the preset image signal-to-noise ratio threshold and the initial image signal-to-noise ratio, the image signal-to-noise ratio deviation value is represented by the ratio of the difference between the preset image signal-to-noise ratio threshold and the initial image signal-to-noise ratio to the preset image signal-to-noise ratio threshold, and the image signal-to-noise ratio deviation value is used to reflect the deviation of the signal-to-noise ratio in the fracture image; Determine whether the contrast deviation value and the image signal-to-noise ratio deviation value are both greater than 0. If both are greater than 0, combine the preset first quality influence weight and the preset second quality influence weight, the contrast deviation value and the image signal-to-noise ratio deviation value to obtain the fracture image quality influence value. Otherwise, the corresponding values of the contrast deviation value and the image signal-to-noise ratio deviation value that are not greater than 0 are recorded as 0 and then combined with the preset first quality influence weight and the preset second quality influence weight to obtain the fracture image quality influence value. S2, obtaining qualified fracture imaging data after image quality adjustment, and obtaining an image fracture displacement assessment accuracy value based on the fracture image quality impact value, the fracture displacement data, and the reference displacement data, wherein the qualified fracture imaging data represents fracture imaging data corresponding to the fracture image quality impact value that is not higher than a preset quality impact threshold after image quality adjustment, the qualified fracture imaging data includes fracture displacement data and fracture tilt data, and the image fracture displacement assessment accuracy value is used to quantitatively assess the accuracy of the degree of fracture displacement in the fracture image; S3, obtaining an image fracture tilt assessment accuracy value based on the fracture image quality impact value, the fracture tilt angle data, and a preset tilt angle threshold, wherein the image fracture tilt assessment accuracy value is used to quantitatively assess the accuracy of the fracture tilt degree in the fracture image; S4. Fracture classification based on the accuracy of radiographic fracture displacement assessment and radiographic fracture tilt assessment.

2. The intelligent imaging classification diagnosis method for fractures based on big data according to claim 1, characterized in that: The limiting expression of the fracture image quality impact value is as follows: Where, represents the fracture image quality impact value of the mth fracture image, m=1,2,...,r, m represents the fracture image number, r represents the total number of fracture images, represents the contrast deviation value of the mth fracture image, represents the image signal-to-noise ratio deviation value of the mth fracture image, represents the first brightness value of the mth fracture image, represents the second brightness value of the mth fracture image, represents the image signal intensity of the mth fracture image, represents the image noise intensity of the mth fracture image, Indicates the preset image contrast threshold, represents the preset image signal-to-noise ratio threshold, ω1 represents the preset first quality impact weight, and ω2 represents the preset second quality impact weight.

3. The intelligent imaging classification diagnosis method for fractures based on big data according to claim 2, characterized in that: The specific process of determining whether to adjust the image quality based on the fracture image quality impact value is as follows: AS1: Determine whether the fracture image quality impact value is not higher than the preset quality impact threshold. If the fracture image quality impact value is not higher than the preset quality impact threshold, no image quality adjustment is performed. Otherwise, AS2 is executed. AS2: Send a prompt to the preset personnel to increase the exposure time of the fracture image by a preset multiple to the preset maximum exposure time. When the monitored fracture image quality impact value is not higher than the preset quality impact threshold, stop the adjustment. If the monitored fracture image quality impact value is higher than the preset quality impact threshold after increasing the fracture image exposure time by the preset multiple to the preset maximum exposure time, execute AS3; AS3, performing image stretching. When the monitored fracture image quality impact value is no higher than the preset quality impact threshold, the adjustment is stopped. If the monitored fracture image quality impact value after image stretching is higher than the preset quality impact threshold, AS4 is executed. AS4 performs image enhancement of the fracture area. When the quality impact value of the monitored fracture image is not higher than the preset quality impact threshold, the adjustment stops. If the quality impact value of the monitored fracture image after image enhancement of the fracture area is higher than the preset quality impact threshold, the feedback is sent to the preset personnel to delete the corresponding fracture image.

4. The intelligent imaging classification diagnosis method for fractures based on big data according to claim 1, characterized in that: The fracture displacement data includes a first fracture coordinate and a second fracture coordinate; The first fracture coordinate represents the position coordinate of the predicted point of the left fracture line in the fracture image; The second fracture coordinate represents the position coordinate of the predicted point of the right fracture line in the fracture image; The reference displacement data includes a preset lateral displacement distance threshold and a preset longitudinal displacement distance threshold.

5. The intelligent imaging classification diagnosis method for fractures based on big data according to claim 4, characterized in that: The specific process of obtaining the accurate value of image fracture displacement assessment based on the fracture image quality impact value, fracture displacement data and reference displacement data is as follows: An initial transverse displacement and an initial longitudinal displacement are obtained according to the first fracture coordinate and the second fracture coordinate. The initial transverse displacement is represented by the result of performing a mean operation on the square root of the sum of the squares of the differences between the horizontal coordinates of the fracture line prediction points corresponding to the left fracture line prediction point and the right fracture line prediction point. The initial longitudinal displacement is represented by the result of performing a mean operation on the square root of the sum of the squares of the differences between the vertical coordinates of the fracture line prediction points corresponding to the left fracture line prediction point and the right fracture line prediction point. The initial transverse displacement is used to reflect the transverse displacement of the two ends of the fracture in the fracture image, and the initial longitudinal displacement is used to reflect the longitudinal displacement of the two ends of the fracture in the fracture image. A relative error calculation is performed between the initial lateral displacement and a preset lateral displacement distance threshold to obtain a lateral displacement deviation value, which is used to reflect the deviation of the lateral displacement at both ends of the fracture in the fracture image; A relative error calculation is performed between the initial longitudinal displacement and a preset longitudinal displacement distance threshold to obtain a longitudinal displacement deviation value, wherein the longitudinal displacement deviation value is used to reflect the deviation of the longitudinal displacement at both ends of the fracture in the fracture image; Determine whether the lateral displacement deviation value and the longitudinal displacement deviation value are both greater than 0. If both are greater than 0, the fracture image quality impact value, the lateral displacement deviation value, and the longitudinal displacement deviation value are combined to obtain the accurate value of the imaging fracture displacement assessment. Otherwise, the corresponding values of the lateral displacement deviation value and the longitudinal displacement deviation value that are not greater than 0 are recorded as 0 and then combined with the fracture image quality impact value to obtain the accurate value of the imaging fracture displacement assessment.

6. The intelligent imaging classification diagnosis method for fractures based on big data according to claim 1, characterized in that: The fracture inclination angle data includes fracture height difference and fracture horizontal distance; The fracture height difference represents the longitudinal extension length of the fracture line in the fracture image; The fracture horizontal distance represents the transverse separation length of the fracture ends in the fracture image.

7. The intelligent imaging classification diagnosis method for fractures based on big data according to claim 6, characterized in that: The specific process of obtaining the accurate value of image fracture tilt assessment based on the fracture image quality impact value, fracture tilt angle data and the preset tilt angle threshold is as follows: An initial tilt angle value is obtained based on the fracture height difference and the fracture horizontal distance. The initial tilt angle value is expressed by substituting the result of the ratio operation of the fracture height difference and the fracture horizontal distance into the result of the arc tangent function. The initial tilt angle value is used to reflect the change in the angles at both ends of the fracture in the fracture image; The initial tilt angle value and the preset tilt angle threshold are used to calculate the relative error to obtain a tilt angle deviation value, which is used to reflect the deviation of the fracture tilt in the fracture image; Determine whether the tilt angle deviation value is greater than 0. If it is greater than 0, the tilt angle deviation value and the fracture image quality impact value are combined to obtain the accurate value of the image fracture tilt assessment. Otherwise, the tilt angle deviation value is recorded as 0 and then combined with the fracture image quality impact value to obtain the accurate value of the image fracture tilt assessment.

8. An intelligent imaging classification and diagnosis system for fractures based on big data, the system being used to implement the method according to any one of claims 1 to 7, characterized in that: It includes a module for obtaining the impact value of fracture image quality, a module for obtaining the accurate value of image fracture displacement assessment, a module for obtaining the accurate value of image fracture tilt assessment, and a module for fracture classification; The fracture image quality impact value acquisition module is used to obtain the fracture image quality impact value through the acquired fracture imaging data and reference image quality data, and determine whether to adjust the image quality based on the fracture image quality impact value. The fracture image quality impact value is used to evaluate the degree of influence of the fracture image quality on fracture displacement and fracture tilt. The imaging fracture displacement assessment accuracy value acquisition module is used to acquire qualified fracture imaging data after image quality adjustment, and acquire the imaging fracture displacement assessment accuracy value based on the fracture image quality impact value, the fracture displacement data, and the reference displacement data. The qualified fracture imaging data represents the fracture imaging data corresponding to the fracture image quality impact value that is not higher than the preset quality impact threshold after image quality adjustment. The qualified fracture imaging data includes fracture displacement data and fracture tilt data. The imaging fracture displacement assessment accuracy value is used to quantitatively assess the accuracy of the fracture displacement degree in the fracture image. The image fracture tilt assessment accurate value acquisition module is used to acquire the image fracture tilt assessment accurate value based on the fracture image quality impact value, the fracture tilt angle data and the preset tilt angle threshold, and the image fracture tilt assessment accurate value is used to quantitatively assess the accuracy of the fracture tilt degree in the fracture image; The fracture classification module is used to classify fractures based on an accurate value of an image fracture displacement assessment and an accurate value of an image fracture tilt assessment.

Images