Auxiliary identification method for occult fracture based on image processing

Abstract

The present application relates to the technical field of patient bone X-ray image recognition, and particularly relates to a hidden fracture auxiliary recognition method based on image processing. A bone region and its connected soft tissue region are located in an X-ray image. A reference bone region is selected, and the fracture manifestation degree is evaluated by analyzing the similar gray pixel distribution and edge position of the reference bone region. For the soft tissue region, the soft tissue enhancement necessity degree is calculated according to the gray difference between the soft tissue region and the surrounding tissue, the gray difference between the two internal regions of the soft tissue region, and the distance between the soft tissue region and the bone. The bone enhancement necessity degree is determined by comprehensively considering the number of soft tissues connected to the bone, the soft tissue enhancement necessity degree of each soft tissue, and the fracture manifestation degree. The to-be-enhanced region is selected for image enhancement according to the bone enhancement necessity degree, and finally the accurate recognition of hidden fracture is realized. The present application can detect extremely small trabecular structure disorder or density change, thereby improving the recognition accuracy of related personnel on patients.

Description

Technical Field

[0001] This invention relates to the technical field of patient bone X-ray image recognition, and specifically to an image processing-based auxiliary identification method for occult fractures. Background Technology

[0002] With the rapid development of medical imaging technology and artificial intelligence, image processing-based methods for assisting in the identification of occult fractures have emerged, and their background and significance are becoming increasingly prominent. In clinical practice, occult fractures are easily missed due to their subtle signs and low contrast on routine X-ray films, especially for elderly people with osteoporosis or athletes undergoing high-intensity training. Delayed diagnosis can lead to serious complications such as fracture displacement and nonunion, increasing patient suffering and financial burden.

[0003] Occult fractures lack clear fracture lines and obvious cortical fractures. On X-rays, they only appear as extremely subtle trabecular structural disorder or density changes, which are easily overlooked in the early stages or in patients with osteoporosis, leading to a high rate of misdiagnosis. Summary of the Invention

[0004] To address the technical problem that occult fractures lack clear fracture lines and obvious cortical fractures, appearing only as extremely subtle trabecular structural disorder or density changes on X-ray images, and are easily overlooked in early stages or in patients with osteoporosis, leading to low accuracy in patient identification, this invention aims to provide an image processing-based auxiliary identification method for occult fractures. The specific technical solution is as follows: An image processing-based auxiliary identification method for occult fractures includes: acquiring X-ray images of the patient's skeletal region; obtaining all skeletal regions in the X-ray image and the soft tissue regions connected to each skeletal region; selecting one skeletal region as a reference region; performing threshold segmentation on the reference region to obtain all edge pixels within the reference region; and obtaining the bone structure of the reference region based on the distribution characteristics of pixels with similar gray values ​​and the positional distribution of edge pixels. The process involves several steps: First, determining the degree of fracture manifestation. This includes selecting a soft tissue region as the target region, performing threshold segmentation to divide it into two parts (the first and second parts), determining the soft tissue enhancement necessity of the target region based on the overall grayscale difference between the target region and surrounding soft tissue regions, the overall grayscale difference between the first and second parts within the target region, and the distances between the first and second parts and their connected bone regions. Second, determining the bone enhancement necessity of the reference region based on the number of soft tissue regions connected to the reference region, the soft tissue enhancement necessity of each soft tissue region, and the fracture manifestation degree of each reference region. Third, identifying all regions to be enhanced based on the bone enhancement necessity of each bone region. Fourth, enhancing all regions to be enhanced to obtain enhanced X-ray images. Finally, identifying occult fractures based on the enhanced X-ray images.

[0005] Furthermore, the method for obtaining the degree of fracture manifestation includes: randomly selecting a pixel in the reference area as a reference pixel, counting the number of similar pixels of the reference pixel in all preset directions with the reference pixel as the origin; similar pixels are pixels whose grayscale value difference from the reference pixel does not exceed a preset value; obtaining the degree of fracture manifestation according to the fracture manifestation degree calculation formula, which is shown below:

[0006] ;

[0007] In the formula, Indicates the reference area number; Indicates the index of the reference pixel; Indicates the degree of fracture manifestation in the reference area; This indicates the number of similar pixels in each preset direction within the reference area, with the reference pixel as the origin. This indicates the maximum number of similar pixels in each preset direction within the reference region, with the reference pixel as the origin. The number of pixels belonging to the reference area in the preset direction corresponding to the maximum number of similar pixels; Indicates the number of consecutive edge pixels within the reference area; This indicates the number of all edge pixels in the reference region; Indicates the activation function; This represents the maximum value function.

[0008] Furthermore, the method for obtaining the degree of soft tissue reinforcement necessity includes: obtaining the degree of soft tissue reinforcement necessity according to the calculation formula for the degree of soft tissue reinforcement necessity, as shown below:

[0009] ;

[0010] In the formula, Indicates the sequence number of the target region; Indicates the degree of soft tissue reinforcement required in the target area; Indicates the closest distance to the target area. The average gray level of each soft tissue region; This represents the average gray level of the target area; This represents the average grayscale value of the first part within the target area; This represents the average grayscale value of the second part within the target area; This represents the distance between the part with the largest grayscale mean in the first and second parts and the connected skeletal region; Represents the absolute value function; This represents the activation function.

[0011] Furthermore, the method for obtaining the degree of bone reinforcement necessity includes: identifying bone regions with fracture manifestation severity less than a preset first threshold as bone regions to be detected; identifying soft tissue regions connected to each bone region to be detected with a soft tissue reinforcement necessity degree less than a preset second threshold as soft tissue regions to be detected connected to the bone region to be detected; and analyzing the bone regions to be detected and their connected soft tissue regions to obtain a formula for calculating the degree of bone reinforcement necessity, as shown below:

[0012] ;

[0013] In the formula, Indicates the first The degree of bone enhancement required for the skeletal region to be tested; Indicates the first The number of soft tissue regions connected to each bone region to be detected; Indicates the first The first connection of the bone region to be detected The degree of soft tissue enhancement required for each soft tissue region to be tested; Indicates the first The degree of fracture manifestation in the bone region to be tested; This represents the activation function.

[0014] Furthermore, the method for obtaining the region to be enhanced includes: taking the detected bone region where the bone enhancement necessity is greater than a preset third threshold as the region to be enhanced.

[0015] Further, all regions to be enhanced are enhanced to obtain enhanced X-ray images, including: in each region to be enhanced, the region is divided equally according to the necessity of skeletal enhancement, obtaining all parts to be analyzed within each region; grayscale histogram processing is performed on each part to be analyzed, a preset cropping limit is set, and the number of excess pixels in the part to be analyzed is obtained according to the number of pixels, the number of gray levels of pixels, and the preset cropping limit; the number of excess pixels in the part to be analyzed is evenly distributed to each gray level of the part to be analyzed to obtain the histogram correction result; the part to be analyzed is enhanced according to the histogram correction result, and each part to be analyzed in each region to be enhanced is traversed to obtain the enhanced X-ray image.

[0016] An image processing-based occult fracture auxiliary identification system includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the steps of the image processing-based occult fracture auxiliary identification method described above.

[0017] A computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the above-described image processing-based occult fracture auxiliary identification method.

[0018] A computer device includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the steps of the above-described image processing-based occult fracture auxiliary identification method.

[0019] This invention has the following beneficial effects: It acquires X-ray images of the patient's skeletal region; since the skeletal region and the connected soft tissue region undergo significant changes after a fracture, these changes are utilized for subsequent analysis; because the main characteristic of occult fractures is the appearance of fracture lines in the trabeculae, the distribution characteristics of pixels with similar grayscale values ​​within the skeletal region and the positional distribution of edge pixels are used to obtain the degree of fracture manifestation within the skeletal region; because occult fractures cause soft tissue swelling, the soft tissue region exhibits diffuse high density, and its overall grayscale appearance differs from that of surrounding soft tissue regions, and this… The overall grayscale value of soft tissue regions near bone regions is higher. Therefore, the two parts of the soft tissue region segmented by a threshold are analyzed, and the overall grayscale difference between different soft tissue regions is used to obtain the degree of soft tissue enhancement necessity. If there is an occult fracture in a certain part of the patient's body, it is very likely that there is a problem with the connection between "bone + soft tissue". Therefore, the degree of bone enhancement necessity is obtained by combining the degree of fracture manifestation in the bone region and the degree of soft tissue enhancement necessity of the connected soft tissue regions. Then, all bone regions that need image enhancement are screened out and enhanced to obtain enhanced X-ray images. Occult fractures are identified based on the enhanced X-ray images. This invention can detect extremely small trabecular structural disorders or density changes, thereby improving the accuracy of patient identification by relevant personnel. Attached Figure Description

[0020] To more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0021] Figure 1 This is a flowchart of an image processing-based method for assisting in the identification of occult fractures, provided as an embodiment of the present invention. Detailed Implementation

[0022] To further illustrate the technical means and effects adopted by the present invention to achieve its intended purpose, the following, in conjunction with the accompanying drawings and preferred embodiments, details the specific implementation, structure, features, and effects of an image processing-based auxiliary identification method for occult fractures proposed according to the present invention. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. Furthermore, specific features, structures, or characteristics in one or more embodiments can be combined in any suitable form.

[0023] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains.

[0024] The following description, in conjunction with the accompanying drawings, details the specific scheme of the image processing-based auxiliary identification method for occult fractures provided by the present invention.

[0025] Please see Figure 1 This illustrates an embodiment of the present invention that provides an image processing-based method for assisting in the identification of occult fractures. The method includes: step S1: acquiring X-ray images of the patient's bone structure.

[0026] This invention is primarily applied to the identification of occult fractures in patients. Therefore, this invention first acquires X-ray images of the patient's bone structure for subsequent analysis. Since occult fractures typically lack obvious displacement or fracture lines, making them difficult to directly observe and identify, it is necessary to enhance the micro-fracture features within the bone region. The specific steps are as follows.

[0027] In one embodiment of the present invention, when acquiring X-ray images of the patient's skeletal parts, it is necessary to ensure that the image exposure is normal, the patient's position is standard, and the generation of motion artifacts is minimized. Secondly, the X-ray images are subjected to noise reduction processing. It should be noted that noise reduction methods can employ techniques such as Gaussian filtering; the specific methods and steps are well-known to those skilled in the art and are not limited or elaborated upon here.

[0028] Step S2: Obtain all skeletal regions and the soft tissue regions connected to each skeletal region in the X-ray image; select one skeletal region as a reference region; perform threshold segmentation on the reference region to obtain all edge pixels in the reference region; obtain the fracture manifestation degree of the reference region based on the distribution characteristics of pixels with similar gray values ​​and the positional distribution of edge pixels in the reference region; select one soft tissue region as a target region; perform threshold segmentation on the target region to divide the target region into two parts, namely the first part and the second part; obtain the soft tissue enhancement necessity of the target region based on the overall gray value difference between the target region and other surrounding soft tissue regions, the overall gray value difference between the first part and the second part in the target region, and the distances between the first part and the second part in the target region and the connected skeletal regions, respectively; obtain the bone enhancement necessity of the reference region based on the number of soft tissue regions connected to the reference region, the soft tissue enhancement necessity of each soft tissue region, and the fracture manifestation degree of each reference region.

[0029] Because a patient's bone and connected soft tissue regions undergo significant changes after a fracture, for example, the grayscale distribution of pixels within the bone region changes, as do the number and position of edge pixels; while the soft tissue region experiences swelling and hematoma, which manifests as large-area grayscale changes in X-ray images. Therefore, in this embodiment of the invention, the changes in the bone and connected soft tissue regions after a fracture are utilized for subsequent analysis.

[0030] Firstly, in one embodiment of the present invention, since the grayscale features of the skeletal region and the soft tissue region differ significantly, a threshold segmentation technique is used to divide the skeletal region and the soft tissue region in the image. It should be noted that the threshold segmentation technique is a well-known technique to those skilled in the art, and will not be limited or elaborated upon here.

[0031] Since the main characteristic of occult fractures in patients under normal circumstances is the appearance of fracture lines in the trabeculae, the degree of fracture manifestation in the bone region can be obtained by utilizing the distribution characteristics of pixels with similar gray values ​​in the bone region and the positional distribution of edge pixels.

[0032] Preferably, in one embodiment of the present invention, the method for obtaining the degree of fracture manifestation includes: selecting any pixel in the reference area as a reference pixel, and counting the number of similar pixels in all preset directions with the reference pixel as the origin; similar pixels are pixels whose grayscale value difference from the reference pixel does not exceed a preset value; in one embodiment of the present invention, the preset direction is set to 0°-360°, wherein the angle step is set to 1°; and the preset value is set to 10. It should be noted that the preset direction and the preset value can be set by themselves and are not limited here.

[0033] The degree of fracture manifestation is obtained according to the formula for calculating the degree of fracture manifestation, which is shown below:

[0034] ;

[0035] In the formula, Indicates the reference area number; Indicates the index of the reference pixel; Indicates the degree of fracture manifestation in the reference area; This indicates the number of similar pixels in each preset direction within the reference area, with the reference pixel as the origin. This indicates the maximum number of similar pixels in each preset direction within the reference region, with the reference pixel as the origin. The number of pixels belonging to the reference area in the preset direction corresponding to the maximum number of similar pixels; Indicates the number of consecutive edge pixels within the reference area; This indicates the number of all edge pixels in the reference region; Indicates the activation function; This represents the maximum value function.

[0036] In the formula for calculating the severity of a fracture, since the fracture line often appears in a direction perpendicular to the direction corresponding to the longest length of the bone region, it is used... To reflect the longest length of the reference area, because the grayscale of the pixel corresponding to the fracture line differs significantly from that of other pixels in the bone region, and also... To reflect the number of pixels with the longest continuous distribution in the direction corresponding to the longest length of the reference region after a possible fracture line, the calculation is performed. The larger the difference, the more likely the fracture line is to appear in the reference area, and the greater the degree of fracture in the reference area. Furthermore, the edge pixels of the reference area include the pixels corresponding to the fracture line. In order to describe the pixels corresponding to the fracture line, the number of continuous edge pixels in the reference area is counted. In the reference area, only the edge pixels of the fracture line are continuously distributed. Therefore, the more continuous edge pixels there are in the reference area, the more likely the fracture line is to appear in the reference area, and the greater the degree of fracture in the reference area.

[0037] When soft tissue swelling is caused by occult fractures, the soft tissue area exhibits diffuse high density, and its overall grayscale performance differs from that of surrounding soft tissue areas. Furthermore, the portion of this soft tissue area closer to the bone region has a higher overall grayscale value. Therefore, a soft tissue region is first selected as the target region. Threshold segmentation is then performed on the target region, dividing it into two parts, designated as the first and second parts. The grayscale features of the target region are then divided using these two parts to distinguish the portion closer to the bone region. Based on the overall grayscale difference between the target region and surrounding soft tissue areas, the overall grayscale difference between the first and second parts within the target region, and the distances between the first and second parts and their respective connected bone regions, the necessary degree of soft tissue enhancement for the target region is determined.

[0038] Preferably, in one embodiment of the present invention, the method for obtaining the degree of soft tissue enhancement necessity includes: obtaining the degree of soft tissue enhancement necessity according to a calculation formula for the degree of soft tissue enhancement necessity, the calculation formula for the degree of soft tissue enhancement necessity is as follows:

[0039] ;

[0040] In the formula, Indicates the sequence number of the target region; Indicates the degree of soft tissue reinforcement required in the target area; Indicates the closest distance to the target area. The average gray level of each soft tissue region; This represents the average gray level of the target area; This represents the average grayscale value of the first part within the target area; This represents the average grayscale value of the second part within the target area; This represents the distance between the part with the largest grayscale mean in the first and second parts and the connected skeletal region; Represents the absolute value function; This represents the activation function.

[0041] In the formula for calculating the necessity of soft tissue enhancement, the overall grayscale difference between the target area and the surrounding soft tissue area is considered. The larger the value, the more likely the target area is to be a swollen soft tissue area. In this case, the need for detailed enhancement of the target area is greater; that is, the need for soft tissue enhancement in the target area is greater. Because the density of soft tissue near the bone is greater than that of soft tissue farther from the bone due to the influence of the bone, therefore... The larger the gray value, and the closer the distance between the part with the largest gray value in the first and second parts and the connected bone region, the more the gray value of the target area near the bone changes, and the greater the need for soft tissue enhancement in the target area.

[0042] If a patient has a hidden fracture in a certain part of their body, it is very likely that there is a problem with the connection between the bone and soft tissue. Therefore, the degree of bone reinforcement required for the reference area is obtained based on the number of soft tissue areas connected to the reference area, the degree of soft tissue reinforcement required for each soft tissue area, and the degree of fracture manifestation in each reference area.

[0043] Preferably, in one embodiment of the present invention, the method for obtaining the necessity of bone enhancement includes: selecting bone regions with fracture manifestation severity less than a preset first threshold as bone regions to be detected; in one embodiment of the present invention, the preset first threshold is set to 0.6, and in other embodiments of the present invention, it can be set by the user and is not limited here. This is done to filter for subsequent image enhancement to reduce computational load.

[0044] Among the soft tissue regions connected to each bone region to be detected, those with a soft tissue enhancement requirement less than a preset second threshold are considered as the soft tissue regions connected to the bone regions to be detected. In one embodiment of the present invention, the preset second threshold is set to 0.7, and in other embodiments of the present invention, it can be set arbitrarily, and is not limited here. This is done to filter subsequent image enhancement processes and reduce computational load.

[0045] The analysis of the skeletal region to be tested and the connected soft tissue region to be tested yields the formula for calculating the necessity of bone enhancement, as shown below:

[0046] ;

[0047] In the formula, Indicates the first The degree of bone enhancement required for the skeletal region to be tested; Indicates the first The number of soft tissue regions connected to each bone region to be detected; Indicates the first The first connection of the bone region to be detected The degree of soft tissue enhancement required for each soft tissue region to be tested; Indicates the first The degree of fracture manifestation in the bone region to be tested; This represents the activation function.

[0048] In the formula for calculating the necessity of bone reinforcement, when there are abnormalities in the bone structure and simultaneously abnormalities in the soft tissue structures surrounding the bone (i.e., abnormalities in the trabecular bone structure and swelling in the soft tissue structures), reflecting in the above analysis that the fracture characteristics of the bone region are relatively weak, and the need for detailed reinforcement of the surrounding soft tissue regions is high, it indicates that there is a high probability of an occult fracture in that bone. The greater the need for bone enhancement in the bone region to be tested.

[0049] Step S3: Obtain all regions to be enhanced according to the degree of bone enhancement required for each bone region; enhance all regions to be enhanced to obtain enhanced X-ray images; identify occult fractures based on the enhanced X-ray images.

[0050] After obtaining the degree of bone enhancement necessity for the detected bone region, this step first filters out all bone regions that need image enhancement and then enhances these bone regions. The specific steps are as follows: First, preferably, in one embodiment of the present invention, the method for obtaining the region to be enhanced includes: selecting the detected bone regions whose bone enhancement necessity is greater than a preset third threshold as the regions to be enhanced. In one embodiment of the present invention, the preset third threshold is set to 0.4. It should be noted that the preset third threshold can be set arbitrarily and is not limited here.

[0051] Secondly, preferably, in one embodiment of the present invention, all regions to be enhanced are enhanced to obtain an enhanced X-ray image. It should be noted that image enhancement technology is a well-known technique among those skilled in the art. In this embodiment of the present invention, an image enhancement method is provided, specifically including: in each region to be enhanced, the region to be enhanced is divided equally according to the degree of bone enhancement required, to obtain all parts to be analyzed within each region to be enhanced; firstly, the number of equal divisions of the region to be enhanced is analyzed, and the calculation formula is as follows:

[0052] ;

[0053] In the formula, Indicates the first The number of regions to be enhanced are evenly divided; Indicates the first The degree of bone reinforcement required for the area to be strengthened.

[0054] Each part to be analyzed is processed using a grayscale histogram, and a preset cropping limit is set. In one embodiment of the present invention, the preset cropping limit is set to 5%. The number of excess pixels in each part to be analyzed is obtained based on the number of pixels, the number of grayscale levels of the pixels, and the preset cropping limit. The calculation formula is as follows: ;

[0055] ;

[0056] In the formula, Indicates the first The first area to be enhanced The number of pixels selected in each part to be analyzed; Indicates the first The first area to be enhanced The number of pixels in the part to be analyzed; Indicates the first The first area to be enhanced The number of gray levels of pixels within the region to be analyzed; Indicates the first The first area to be enhanced The number of excess pixels in the part to be analyzed.

[0057] The excess pixels in the part to be analyzed are evenly distributed to each gray level of the part to be analyzed to obtain the histogram correction result; the part to be analyzed is enhanced according to the histogram correction result, and each part to be analyzed in each region to be enhanced is traversed to obtain the enhanced X-ray image.

[0058] Thus, the enhanced X-ray image is obtained.

[0059] Finally, enhanced X-ray images were used to mark occult fracture points to assist relevant personnel in the auxiliary identification and analysis of occult fracture sites.

[0060] In summary, the following steps are taken: X-ray images of the patient's skeletal structures are acquired; all skeletal regions and their associated soft tissue regions are obtained from the X-ray images; one skeletal region is selected as a reference region; threshold segmentation is performed on the reference region to obtain all edge pixels; the fracture severity of the reference region is determined based on the distribution characteristics of pixels with similar grayscale values ​​and the positional distribution of edge pixels; one soft tissue region is selected as the target region; threshold segmentation is performed on the target region to divide it into two parts, designated as the first and second parts; the soft tissue enhancement necessity of the target region is determined based on the overall grayscale difference between the target region and surrounding soft tissue regions, the overall grayscale difference between the first and second parts within the target region, and the distances between the first and second parts and their associated skeletal regions; the bone enhancement necessity of the reference region is determined based on the number of soft tissue regions connected to the reference region, the soft tissue enhancement necessity of each soft tissue region, and the fracture severity of each reference region; all regions to be enhanced are obtained based on the bone enhancement necessity of each skeletal region; all regions to be enhanced are enhanced to obtain enhanced X-ray images; and occult fractures are identified based on the enhanced X-ray images.

[0061] A second objective of one embodiment of the present invention is to provide an image processing-based occult fracture auxiliary identification system. The system includes a memory, a processor, and a computer program, wherein the memory is used to store the corresponding computer program, the processor is used to run the corresponding computer program, and the computer program can implement the methods described in steps S1-S3 when running in the processor.

[0062] A third objective of this invention is to provide a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the methods described in steps S1-S3.

[0063] The fourth objective of this invention is to provide a computer-readable storage medium storing a computer program that, when executed by a processor, implements the method described in steps S1-S3.

[0064] It should be noted that the order of the above embodiments of the present invention is merely for descriptive purposes and does not represent the superiority or inferiority of the embodiments. The processes depicted in the accompanying drawings do not necessarily require a specific or sequential order to achieve the desired result. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0065] The various embodiments in this specification are described in a progressive manner. The same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on describing the differences from other embodiments.

Claims

1. An image processing-based auxiliary identification method for occult fracture, characterized in that, The method comprises: collecting an x-ray image of a patient's bone part; obtaining all bone regions in the x-ray image and soft tissue regions connected to each bone region; optionally taking one bone region as a reference region; performing threshold segmentation on the reference region to obtain all edge pixel points in the reference region; obtaining a fracture manifestation degree of the reference region according to the distribution characteristics of pixel points with similar gray values in the reference region and the position distribution of edge pixel points; optionally taking one soft tissue region as a target region; performing threshold segmentation on the target region to divide the target region into two parts as a first part and a second part; obtaining a soft tissue enhancement necessity degree of the target region according to the overall gray difference between the target region and other surrounding soft tissue regions, the overall gray difference between the first part and the second part in the target region, and the distance between the first part and the second part in the target region and the connected bone regions; obtaining a bone enhancement necessity degree of the reference region according to the number of soft tissue regions connected to the reference region, the soft tissue enhancement necessity degree of each soft tissue region, and the fracture manifestation degree of each reference region; obtaining all regions to be enhanced according to the bone enhancement necessity degree of each bone region; enhancing all regions to be enhanced to obtain an enhanced x-ray image; identifying occult fractures according to the enhanced x-ray image; the method for obtaining the fracture manifestation degree comprises: taking one pixel point in the reference region as a reference pixel point, and counting the number of similar pixel points of the reference pixel point in all preset directions with the reference pixel point as the origin; the similar pixel point is a pixel point with a gray value difference from the reference pixel point not more than a preset value; obtaining the fracture manifestation degree according to a fracture manifestation degree calculation formula, as shown below: ； In the formula, represents the serial number of the reference region; represents the serial number of the reference pixel point; represents the fracture manifestation degree of the reference region; represents the number of similar pixel points in each preset direction with the reference pixel point in the reference region as the origin; represents the maximum value of the number of similar pixel points in each preset direction with the reference pixel point in the reference region as the origin; represents the number of pixel points belonging to the reference region in the preset direction corresponding to the maximum value of the number of similar pixel points; represents the number of continuous edge pixel points in the reference region; represents the number of all edge pixel points in the reference region; represents an activation function; represents a maximum value function; The method for obtaining the soft tissue enhancement necessity degree comprises: obtaining the soft tissue enhancement necessity degree according to a soft tissue enhancement necessity degree calculation formula, as shown below: ； In the formula, Indicates the sequence number of the target region; Indicates the degree of soft tissue reinforcement required in the target area; Indicates the closest number to the target area. The average gray level of each soft tissue region; This represents the average gray level of the target area; This represents the average grayscale value of the first part within the target area; This represents the average grayscale value of the second part within the target area; This represents the distance between the part with the largest grayscale mean in the first and second parts and the connected skeletal region; Represents the absolute value function; Indicates the activation function; The method for obtaining the bone enhancement necessity degree comprises: taking a bone region with a fracture manifestation degree less than a preset first threshold value as a bone region to be detected; taking a soft tissue region connected to each bone region to be detected, with a soft tissue enhancement necessity degree less than a preset second threshold value, as a soft tissue region to be detected connected to the bone region to be detected; analyzing the bone region to be detected and the soft tissue region to be detected connected thereto to obtain a bone enhancement necessity degree calculation formula, as shown below: ； In the formula, Indicates the first The degree of bone enhancement required for the skeletal region to be tested; Indicates the first The number of soft tissue regions connected to each bone region to be detected; Indicates the first The first connection of the bone region to be detected The degree of soft tissue enhancement required for each soft tissue region to be tested; Indicates the first The degree of fracture manifestation in the bone region to be tested; This represents the activation function.

2. The image processing-based auxiliary identification method for occult fracture according to claim 1, characterized in that, The method for obtaining the region to be enhanced comprises: taking a bone region to be detected with a bone enhancement necessity degree greater than a preset third threshold value as a region to be enhanced. 3.The method of claim 1, wherein, The enhancement is performed on all the to-be-enhanced regions to obtain an enhanced X-ray image, including: in each to-be-enhanced region, the to-be-enhanced region is equally divided according to the necessity of bone enhancement of the to-be-enhanced region to obtain all to-be-analyzed parts in each to-be-enhanced region; a gray histogram processing is performed on each to-be-analyzed part, a preset clipping limit is set, the number of pixel points, the number of pixel point gray levels in each to-be-analyzed part and the preset clipping limit are obtained, and the number of excess pixel points in the to-be-analyzed part is obtained; the number of excess pixel points in the to-be-analyzed part is equally divided into each gray level of the to-be-analyzed part to obtain a histogram correction result; and the to-be-analyzed part is enhanced according to the histogram correction result, each to-be-analyzed part in each to-be-enhanced region is traversed, and the enhanced X-ray image is obtained.

4. An image processing based auxiliary identification system for occult fracture, the system comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, The processor executes the computer program to implement the steps of the auxiliary identification method for occult fracture based on image processing in any one of claims 1 to 3.

5. A computer-readable storage medium storing a computer program, the computer program comprising instructions that, when executed by a computer, cause the computer to perform the method of any one of claims 1 to 4. The computer program is executed by the processor to implement the steps of the auxiliary identification method for occult fracture based on image processing in any one of claims 1 to 3.

6. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, The processor executes the computer program to implement the steps of the auxiliary identification method for occult fracture based on image processing in any one of claims 1 to 3.

Images