Bone development image enhancement method and device, equipment, medium and product

Abstract

The invention discloses a bone development image enhancement method and device, equipment, a medium and a product, and relates to the field of image enhancement, and the method comprises the steps: applying a self-adaptive Prewitt operator and a self-adaptive Laplacian operator to a bone development image, and generating a first bone development image and a second bone development image; performing multi-scale processing on the bone development image, and applying a Sobel operator to the multi-scale bone development image to generate a third bone development image; fusing the three bone imaging images to generate a fused bone imaging image, performing CLAHE processing, and determining an equalized bone imaging image; performing non-local mean filtering on the equalized bone imaging image, determining a bone imaging image after non-local mean filtering, performing preprocessing, and determining a preprocessed bone imaging image; and performing connected domain analysis on the preprocessed bone development image, and determining the enhanced bone development image, thereby avoiding excessive enhancement and artifact generation of an area with overlarge pixel difference, inhibiting noise interference, and improving an image enhancement effect.

Description

Technical Field

[0001] The present application relates to the field of image enhancement, and in particular to a method, device, equipment, medium and product for enhancing bone imaging images. Background Art

[0002] Medical imaging technology is a technology that uses a variety of methods and equipment to obtain information about the internal structure and function of the human body. It plays an important role in clinical diagnosis, treatment and research, helping doctors understand pathological changes, formulate treatment plans and evaluate treatment effects.

[0003] Nuclear medicine imaging technology is a type of medical imaging technology that uses radioactive isotopes or tracers. By injecting radioactive isotopes or tracers into the body, then using detectors to capture photons or positrons released by radioactive decay and reconstructing them into images through computers, nuclear medicine imaging technology can provide information on organ function, metabolism and molecular levels. This technology is widely used in cancer diagnosis, cardiovascular disease assessment and neurological disease research.

[0004] Single-Photon Emission Computed Tomography (SPECT) is a common nuclear medicine imaging technique. Compared with other imaging techniques such as positron emission tomography (PET), SPECT is more affordable, less expensive and more popular worldwide. Many medical centers are equipped with SPECT equipment. SPECT equipment can use a variety of radioactive isotopes for imaging, each of which has different characteristics and uses to meet different clinical needs.

[0005] In clinical diagnosis, bone scintigraphy images provide information about organ function and metabolism. Doctors usually determine the location and extent of the lesion by analyzing the intensity distribution of radioisotopes in different areas of the image, and infer possible diseases based on the morphological structure of the lesion location. At the same time, doctors need to judge the relationship between the lesion location and the surrounding tissues, and combine the results of other imaging techniques (such as computed tomography (CT) or magnetic resonance imaging (MRI)) to confirm whether there is an abnormal lesion.

[0006] In recent years, image processing technology based on bone imaging images has received more and more attention and research. Since the original SPECT bone scan images have a narrow dynamic range and high noise content, and the image differences between patients are large due to individual metabolic differences, the clarity and detail presentation of the image are affected, which seriously affects the complexity of doctors' diagnosis. Image enhancement technology is an effective means to solve this problem. Existing SPECT image processing technology usually includes simple edge enhancement and contrast adjustment. Generally, operators such as Sobel operator and Laplacian operator are used for edge detection and enhancement, and linear contrast adjustment or histogram equalization is used to improve the visual effect of the image.

[0007] Due to the differences in metabolic activity between different tissues and organs, there are significant pixel differences in different areas of the bone scan image. However, existing enhancement technologies are often global processing, that is, the same enhancement rules are used for the entire image, and they lack the ability to adaptively process different areas. As a result, after applying them to process SPECT images, areas with large pixel differences, including bone edges, are over-enhanced during the enhancement process, resulting in overly sharp edges and even artifacts. At the same time, areas with large pixel differences are prone to noise after processing, all of which will affect the image enhancement effect. Summary of the invention

[0008] The purpose of the present application is to provide a method, device, equipment, medium and product for enhancing bone imaging images to solve the problems of over-enhancement in areas with large pixel differences, generation of artifacts and noise, etc., which affect the image enhancement effect.

[0009] To achieve the above objectives, this application provides the following solutions:

[0010] In a first aspect, the present application provides a method for enhancing a bone imaging image, comprising:

[0011] Applying an adaptive Prewitt operator to the bone imaging image to generate a first bone imaging image;

[0012] Applying an adaptive Laplacian operator to the bone imaging image to generate a second bone imaging image;

[0013] Performing multi-scale processing on the bone imaging image, and applying a Sobel operator to the multi-scale bone imaging image to generate a third bone imaging image;

[0014] fusing the first bone imaging image, the second bone imaging image, and the third bone imaging image to generate a fused bone imaging image;

[0015] Performing CLAHE processing on the fused bone imaging image to determine a balanced bone imaging image;

[0016] Applying non-local mean filtering to the equalized bone imaging image to determine a bone imaging image after non-local mean filtering;

[0017] A connected domain analysis is performed on the preprocessed bone imaging image to determine an enhanced bone imaging image.

[0018] In a second aspect, the present application provides a bone imaging image enhancement device, comprising:

[0019] A Prewitt operator detail enhancement module, used for applying an adaptive Prewitt operator to the bone imaging image to generate a first bone imaging image;

[0020] A Laplacian operator detail enhancement module, used for applying an adaptive Laplacian operator to the bone imaging image to generate a second bone imaging image;

[0021] A multi-scale Sobel operator detail enhancement module, used for performing multi-scale processing on the bone imaging image and applying the Sobel operator to the multi-scale bone imaging image to generate a third bone imaging image;

[0022] An image fusion module, used for fusing the first bone imaging image, the second bone imaging image and the third bone imaging image to generate a fused bone imaging image;

[0023] A CLAHE contrast enhancement module, used for performing CLAHE processing on the fused bone imaging image to determine a balanced bone imaging image;

[0024] A non-local mean filtering module, used for applying non-local mean filtering to the equalized bone imaging image to determine the bone imaging image after the non-local mean filtering;

[0025] A preprocessing module, used for preprocessing the bone imaging image after the non-local mean filtering, and determining the preprocessed bone imaging image;

[0026] The connected domain analysis module is used to perform connected domain analysis on the preprocessed bone imaging image to determine the enhanced bone imaging image.

[0027] In a third aspect, the present application provides a computer device, comprising: 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 any of the bone imaging image enhancement methods described above.

[0028] In a fourth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements any of the above-described bone imaging image enhancement methods.

[0029] In a fifth aspect, the present application provides a computer program product, including a computer program, which, when executed by a processor, implements any of the above-mentioned bone imaging image enhancement methods.

[0030] According to the specific embodiments provided by the present application, the present application discloses the following technical effects: the present application combines a multi-level and multi-angle adaptive enhancement technology of an adaptive differential (Prewitt) operator that can enhance the details of the bone edge of the image, an adaptive Laplacian operator (the Laplacian operator is a second-order differential operator) that further enhances the details with weak grayscale changes, and a Sobel operator that enhances the details with weak grayscale changes. Different operators are applied to different areas of the bone imaging image and different enhancement rules are adopted, thereby effectively enhancing the local areas with large pixel differences in the SPECT image and avoiding over-enhancement and artifact generation; and the image contrast can be further enhanced through contrast-limited adaptive histogram equalization (CLAHE), and the non-local mean filtering technology is used to further remove noise and retain image details. Finally, the background noise is shielded through the connected domain analysis technology, which further improves the image contrast and detail clarity, suppresses noise interference, and thus improves the image enhancement effect. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0032] Figure 1 This is a schematic flow chart of a method for enhancing a bone imaging image in one embodiment of the present application;

[0033] Figure 2 A schematic diagram of an original bone imaging image provided in an embodiment of the present application;

[0034] Figure 3 A schematic diagram of an enhanced bone imaging image provided in an embodiment of the present application. DETAILED DESCRIPTION

[0035] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0036] In order to make the above-mentioned objects, features and advantages of the present application more obvious and easy to understand, the present application is further described in detail below with reference to the accompanying drawings and specific implementation methods.

[0037] The bone imaging image enhancement method provided in the embodiment of the present application is executed by a computer device, and can be executed by a computer device such as a terminal or a server alone, or by a terminal and a server together. In the embodiment of the present application, the method includes the following steps 101 to 108. Among them:

[0038] Step 101: applying an adaptive Prewitt operator to the bone imaging image to generate a first bone imaging image.

[0039] Step 102: Apply an adaptive Laplacian operator to the bone imaging image to generate a second bone imaging image.

[0040] Step 103: performing multi-scale processing on the bone imaging image, and applying a Sobel operator to the multi-scale bone imaging image to generate a third bone imaging image.

[0041] Step 104: Fusing the first bone imaging image, the second bone imaging image, and the third bone imaging image to generate a fused bone imaging image.

[0042] Step 105: Perform CLAHE processing on the fused bone imaging image to determine a balanced bone imaging image.

[0043] Step 106: Apply non-local mean filtering to the equalized bone imaging image to determine the bone imaging image after non-local mean filtering.

[0044] Step 107: preprocessing the bone imaging image after the non-local mean filtering to determine the preprocessed bone imaging image.

[0045] Step 108: Perform connected domain analysis on the preprocessed bone imaging image to determine an enhanced bone imaging image. Figure 2-Figure 3 As shown, the difference between the original bone imaging image and the enhanced bone imaging image can be clearly seen.

[0046] In an exemplary embodiment, step 101 also includes: obtaining a bone imaging image matrix, and converting the data type of the bone imaging image in the bone imaging image matrix into a uint8 type. The data type conversion can facilitate subsequent processing.

[0047] In an exemplary embodiment, step 101 can also be replaced by the following steps: applying an adaptive Prewitt operator to the bone imaging image, dynamically adjusting edge detection parameters according to local grayscale changes of the bone imaging image, calculating the gradient of the bone imaging image in the horizontal and vertical directions, and determining the edge information of the bone imaging image; determining a comprehensive edge detection image processed by the adaptive Prewitt operator according to the edge information; adding the comprehensive edge detection image processed by the adaptive Prewitt operator to the bone imaging image element by element to generate a first bone imaging image; the edge detection parameters include a Prewitt kernel; the Prewitt kernel is fixed, kernel kernelx = [[1, 1, 1], [0, 0, 0], [-1, -1, -1]]; kernel kernelely = [[-1, 0, 1], [-1, 0, 1], [-1, 0, 1]], and then the dynamic weighting parameter alpha is calculated by the standard deviation of the gradient map to adaptively adjust the edge enhancement effect under different image contents.

[0048] Furthermore, the present application applies an adaptive Prewitt operator to the bone imaging image to enhance the bone edge details of the bone imaging image while suppressing noise amplification.

[0049] In an exemplary embodiment, step 102 can also be replaced by the following steps: smoothing the bone imaging image through a Gaussian filter to determine the bone imaging image after Gaussian filtering; applying an adaptive Laplacian operator to the bone imaging image after Gaussian filtering, calculating the Laplace transform of the image after Gaussian filtering, dynamically adjusting the weights, and determining the bone imaging image processed by the adaptive Laplacian operator; adding the bone imaging image processed by the adaptive Laplacian operator to the bone imaging image element by element to generate a second bone imaging image.

[0050] Furthermore, the present application smoothes the bone imaging image, thereby removing high-frequency noise in the image while retaining important image structures.

[0051] Furthermore, the present application further highlights the edge and bone detail information of the image by dynamically adjusting the weights, thereby avoiding artifacts caused by excessive enhancement of details.

[0052] Furthermore, the present application adds the bone imaging image processed by the adaptive Laplacian operator to the bone imaging image element by element to form an enhanced bone detail image.

[0053] In an exemplary embodiment, step 103 can also be replaced by the following steps: constructing the bone imaging image into a multi-layer Gaussian pyramid to generate multiple image levels of different scales; applying the Sobel operator at each scale, combining the local contrast of the image, adjusting the sensitivity of the Sobel operator, calculating the gradient information in the horizontal and vertical directions, and determining the Sobel processing result at each scale; uniformly adjusting the Sobel processing result at each scale to the size of the bone imaging image, and performing adaptive weighted averaging on the Sobel processing results of different scales, using the weighting coefficient to dynamically balance the information of each scale, and generating a third bone imaging image; the third bone imaging image is a multi-scale enhanced image.

[0054] In an exemplary embodiment, step 104 can also be replaced by the following steps: the first bone imaging image, the second bone imaging image and the third bone imaging image are fused by an adaptive weighted averaging method to form a fused image containing comprehensive detail information, and the weights are dynamically adjusted during the fusion process to ensure comprehensive detail information while avoiding background noise enhancement.

[0055] In an exemplary embodiment, step 105 can also be replaced by the following steps: applying the CLAHE algorithm to the preprocessed bone imaging image, adaptively adjusting the contrast enhancement strength according to the grayscale distribution characteristics of the local image, further improving the visibility of bone details, and avoiding excessive enhancement of local areas.

[0056] Furthermore, step 106 may be replaced by the following steps: applying non-local mean filtering to the equalized bone imaging image obtained in step 105 to smooth the noise in the image while retaining key bone details.

[0057] In an exemplary embodiment, step 107 may also be replaced by the following steps: performing grayscale power transformation on the bone imaging image after non-local mean filtering, adjusting the grayscale value distribution of the fused bone imaging image, and determining the adjusted bone imaging image. Applying a threshold segmentation method, by introducing local contrast evaluation, adaptively suppressing the background area of ​​the adjusted bone imaging image, and determining the preprocessed bone imaging image.

[0058] Furthermore, adjusting the grayscale value distribution of the fused bone imaging image can increase the contrast of the image.

[0059] Furthermore, the background area of ​​the adjusted bone imaging image is adaptively suppressed, so that the image background noise can be reduced.

[0060] Furthermore, step 108 may be replaced by the following steps: performing a connected domain analysis on the image after non-local mean filtering obtained in step 107 to obtain a connected domain; based on a morphological analysis method, retaining the maximum connected domain pixel, and removing independent noise points and artifacts.

[0061] The original SPECT images have a narrow dynamic range and high noise content, and there are large image differences between patients due to individual metabolic differences, which seriously affects the quality of doctors' diagnosis. The large pixel differences between different areas in bone imaging images make image enhancement extremely challenging.

[0062] This application has made effective improvements to these challenges through a series of adaptive image enhancement and noise suppression technologies. Specifically, it uses adaptive Prewitt operators, adaptive Laplacian operators and multi-scale Sobel operators to perform multi-level and multi-angle detail enhancement, effectively strengthening the bone details and edge information, making the image details clearer, and avoiding excessive detail enhancement and artifact generation while suppressing noise. It is very suitable for areas with large pixel differences; then, through Gaussian filtering preprocessing and combining adaptive contrast-limited CLAHE and non-local mean filtering technology, the image contrast and detail retention are further optimized, and the noise is effectively reduced. In addition, this application also uses grayscale power transformation and background suppression technology to enhance the overall contrast of the image and eliminate background noise, making the target area more prominent. In response to the noise interference problem in the image background, the connected domain analysis technology is used to retain the maximum connected domain and remove independent noise points to ensure the integrity and accuracy of the target area.

[0063] In summary, the present application effectively addresses the challenges brought about by large pixel differences in SPECT bone scan images through a systematic and adaptive bone imaging image enhancement method, enhances the structural texture details of the image, reduces noise interference, improves image quality and diagnostic accuracy, and greatly reduces the time and labor costs required for manual processing.

[0064] In order to simplify the complex image processing process, the present application can also modularize each processing step to facilitate integration and expansion in practical applications. Each module performs a specific image processing task and can be dynamically adjusted and optimized according to different needs.

[0065] Based on the same inventive concept, the embodiment of the present application also provides a bone imaging image enhancement device for implementing the bone imaging image enhancement method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in the embodiments of one or more bone imaging image enhancement devices provided below can refer to the limitations of the bone imaging image enhancement method above, and will not be repeated here.

[0066] In an exemplary embodiment, a bone imaging image enhancement device is provided, comprising:

[0067] The Prewitt operator detail enhancement module is used to apply the adaptive Prewitt operator to the bone imaging image to generate a first bone imaging image. The Prewitt operator detail enhancement module can highlight the edge information of the image.

[0068] The Laplacian operator detail enhancement module is used to apply an adaptive Laplacian operator to the bone imaging image to generate a second bone imaging image. The Laplacian operator detail enhancement module can further highlight the edges and details of the image.

[0069] The multi-scale Sobel operator detail enhancement module is used to perform multi-scale processing on the bone imaging image and apply the Sobel operator to the multi-scale bone imaging image to generate a third bone imaging image. The multi-scale Sobel operator detail enhancement module enhances edges and fine details in the image at different scales.

[0070] The image fusion module is used to fuse the first bone imaging image, the second bone imaging image and the third bone imaging image to generate a fused bone imaging image. The image fusion module can form an image containing comprehensive detail information.

[0071] The CLAHE contrast enhancement module is used to perform CLAHE processing on the fused bone imaging image to determine the equalized bone imaging image. The CLAHE contrast enhancement module applies contrast-limited adaptive histogram equalization processing to the fused image to enhance the local contrast of the image.

[0072] The non-local mean filtering module is used to apply non-local mean filtering to the equalized bone imaging image to determine the bone imaging image after the non-local mean filtering. The non-local mean filtering module can remove noise and retain key bone details.

[0073] The preprocessing module is used to preprocess the bone imaging image after the non-local mean filtering to determine the preprocessed bone imaging image. The preprocessing module can improve the contrast and detail resolution of the image, and perform background suppression to reduce the interference of background noise.

[0074] The connected domain analysis module is used to perform connected domain analysis on the preprocessed bone imaging image to determine the enhanced bone imaging image. The connected domain analysis module can retain the largest connected domain, remove independent noise points in the image, and retain the main bone imaging area.

[0075] In an exemplary embodiment, a computer device is provided, which may be a server or a terminal. The computer device includes a processor, a memory, an input / output interface (I / O for short) and a communication interface. The processor, the memory and the input / output interface are connected via a system bus, and the communication interface is connected to the system bus via the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store enhanced data of bone imaging images. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal via a network connection. When the computer program is executed by the processor, a method for enhancing bone imaging images is implemented.

[0076] In an exemplary embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above-mentioned method embodiments when executing the computer program.

[0077] In an exemplary embodiment, a computer-readable storage medium is provided, storing a computer program, and when the computer program is executed by a processor, the steps in the above method embodiments are implemented.

[0078] In an exemplary embodiment, a computer program product is provided, including a computer program, and when the computer program is executed by a processor, the steps in the above method embodiments are implemented.

[0079] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ReadOnlyMemory, ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (Magnetoresistive RandomAccess Memory, MRAM), ferroelectric random access memory (Ferroelectric RandomAccess Memory, FRAM), phase change memory (Phase Change Memory, PCM), graphene memory, etc. Volatile memory can include random access memory (RandomAccess Memory, RAM) or external cache memory, etc. By way of illustration and not limitation, RAM may be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).

[0080] The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. The non-relational database may include a distributed database based on blockchain, etc., but is not limited thereto. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but is not limited thereto.

[0081] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0082] This article uses specific examples to illustrate the principles and implementation methods of this application. The description of the above embodiments is only used to help understand the method and core ideas of this application. At the same time, for those skilled in the art, according to the ideas of this application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting this application.

Claims

1. A method for enhancing a bone imaging image, characterized in that: The bone imaging image enhancement method comprises: Applying an adaptive Prewitt operator to the bone imaging image to generate a first bone imaging image; Applying an adaptive Laplacian operator to the bone imaging image to generate a second bone imaging image; Performing multi-scale processing on the bone imaging image, and applying a Sobel operator to the multi-scale bone imaging image to generate a third bone imaging image; fusing the first bone imaging image, the second bone imaging image, and the third bone imaging image to generate a fused bone imaging image; Performing CLAHE processing on the fused bone imaging image to determine a balanced bone imaging image; Applying non-local mean filtering to the equalized bone imaging image to determine a bone imaging image after non-local mean filtering; Preprocessing the bone imaging image after the non-local mean filtering to determine the preprocessed bone imaging image; A connected domain analysis is performed on the preprocessed bone imaging image to determine an enhanced bone imaging image.

2. The bone imaging image enhancement method according to claim 1, characterized in that: Applying an adaptive Prewitt operator to the bone imaging image to generate a first bone imaging image, the method further includes: A bone imaging image matrix is ​​obtained, and the data type of the bone imaging image in the bone imaging image matrix is ​​converted into a uint8 type.

3. The bone imaging image enhancement method according to claim 1, characterized in that: Applying an adaptive Prewitt operator to the bone imaging image to generate a first bone imaging image specifically includes: Applying an adaptive Prewitt operator to the bone imaging image, dynamically adjusting edge detection parameters according to local grayscale changes of the bone imaging image, calculating the gradient of the bone imaging image in the horizontal direction and the vertical direction, and determining edge information of the bone imaging image; Determine a comprehensive edge detection image processed by an adaptive Prewitt operator according to the edge information; The integrated edge detection image processed by the adaptive Prewitt operator is added element by element to the bone imaging image to generate a first bone imaging image.

4. The bone imaging image enhancement method according to claim 1, characterized in that: Applying an adaptive Laplacian operator to the bone imaging image to generate a second bone imaging image specifically includes: Smoothing the bone imaging image by using a Gaussian filter to determine a bone imaging image after Gaussian filtering; Applying an adaptive Laplacian operator to the bone imaging image after Gaussian filtering, calculating the Laplace transform of the image after Gaussian filtering, dynamically adjusting the weights, and determining the bone imaging image after being processed by the adaptive Laplacian operator; The bone imaging image processed by the adaptive Laplacian operator is added element by element to the bone imaging image to generate a second bone imaging image.

5. The bone imaging image enhancement method according to claim 1, characterized in that: The bone imaging image is subjected to multi-scale processing, and a Sobel operator is applied to the multi-scale bone imaging image to generate a third bone imaging image, specifically comprising: constructing the bone imaging image into a multi-layer Gaussian pyramid to generate multiple image levels of different scales; Apply the Sobel operator at each scale, adjust the sensitivity of the Sobel operator based on the local contrast of the image, calculate the gradient information in the horizontal and vertical directions, and determine the Sobel processing result at each scale; The Sobel processing results at each scale are uniformly adjusted to the size of the bone imaging image, and the Sobel processing results at different scales are adaptively weighted averaged, and the weighted coefficient is used to dynamically balance the information of each scale to generate a third bone imaging image; the third bone imaging image is a multi-scale enhanced image.

6. The bone imaging image enhancement method according to claim 1, characterized in that: Preprocessing the bone imaging image after the non-local mean filtering to determine the preprocessed bone imaging image specifically includes: Performing grayscale power transformation on the bone imaging image after non-local mean filtering, adjusting the grayscale value distribution of the fused bone imaging image, and determining an adjusted bone imaging image; A threshold segmentation method is applied to adaptively suppress the background area of ​​the adjusted bone imaging image by introducing local contrast evaluation to determine the preprocessed bone imaging image.

7. A bone imaging image enhancement device, characterized in that: The bone imaging image enhancement device comprises: A Prewitt operator detail enhancement module, used for applying an adaptive Prewitt operator to the bone imaging image to generate a first bone imaging image; A Laplacian operator detail enhancement module, used for applying an adaptive Laplacian operator to the bone imaging image to generate a second bone imaging image; A multi-scale Sobel operator detail enhancement module, used for performing multi-scale processing on the bone imaging image and applying the Sobel operator to the multi-scale bone imaging image to generate a third bone imaging image; An image fusion module, used for fusing the first bone imaging image, the second bone imaging image and the third bone imaging image to generate a fused bone imaging image; A CLAHE contrast enhancement module, used for performing CLAHE processing on the fused bone imaging image to determine a balanced bone imaging image; A non-local mean filtering module, used for applying non-local mean filtering to the equalized bone imaging image to determine the bone imaging image after the non-local mean filtering; a module, used for preprocessing the bone imaging image after the non-local mean filtering to determine the preprocessed bone imaging image; The connected domain analysis module is used to perform connected domain analysis on the preprocessed bone imaging image to determine the enhanced bone imaging image.

8. A computer device comprising: 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 bone imaging image enhancement method according to any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the bone imaging image enhancement method described in any one of claims 1 to 6 is implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the bone imaging image enhancement method described in any one of claims 1 to 6 is implemented.

Images