A dual-energy calibration method and system based on a bone sclerosis model

Abstract

This invention discloses a dual-energy correction method and system based on a bone sclerosis model. The method includes: adjusting the pulse frequency of X-rays in the acquisition device to irradiate soft tissue and bone tissue in coordinate form, thereby more comprehensively reflecting the characteristics of soft tissue and bone tissue and improving image sampling accuracy; designing a weighting function based on bone mineral density, cortical bone mineral density, average trabecular bone thickness, and average cortical bone thickness to make the reconstructed bone sclerosis model more accurate; iteratively adjusting the parameters in the reconstructed model using artifact recognition results to achieve dynamic correction and improve the quality of the corrected image; comparing the corrected image with an actual bone image and displaying the model in three dimensions in a virtual reality environment; generating a report based on the comparison results of the model selected by the user, forming a personalized display result and improving the user experience.

Description

Technical Field

[0001] This invention relates to the field of image and model processing technology, and in particular to a dual-energy correction method and system based on a bone sclerosis model. Background Technology

[0002] X-ray imaging technology has played a vital role in medical imaging since its discovery. Traditional X-ray imaging techniques primarily rely on single-energy X-rays, which has limitations in distinguishing between soft and bone tissues. With technological advancements, dual-energy X-ray imaging technology has emerged. By acquiring images at different energy levels, it can better differentiate between soft and bone tissues, improving image contrast and diagnostic accuracy. However, despite the improvements in image quality, dual-energy X-ray imaging still presents challenges in practical applications, such as the appearance of sclerosis artifacts. These artifacts can affect image accuracy and, consequently, diagnostic results. Therefore, effectively correcting these artifacts and improving image quality has become a current research focus.

[0003] Current research and literature typically employ simple or complex image processing algorithms to correct sclerosis artifacts. However, these methods often rely heavily on bone density and structure, lacking a deep understanding and modeling of the sclerosis effect, resulting in unsatisfactory correction outcomes. Furthermore, they suffer from several shortcomings: First, single-frequency X-ray image sampling cannot fully reflect the complex characteristics of soft and bone tissues, making it difficult to effectively distinguish and correct artifacts caused by sclerosis. Second, traditional reconstruction weight adjustment methods lack comprehensive consideration of bone density and structural features, leading to insufficient precision in parameter adjustment during the correction process. Third, existing artifact recognition and correction methods are mostly static, lacking dynamic iterative adjustment mechanisms, resulting in suboptimal correction results. Summary of the Invention

[0004] The purpose of this section is to outline some aspects of embodiments of the present invention and to briefly describe some preferred embodiments. Simplifications or omissions may be made in this section, as well as in the abstract and title of this application, to avoid obscuring the purpose of these documents; however, such simplifications or omissions should not be construed as limiting the scope of the invention.

[0005] In view of the aforementioned existing problems, this invention is proposed. Therefore, this invention provides a dual-energy calibration method based on a bone sclerosis model to solve the problems mentioned in the background art.

[0006] To solve the above-mentioned technical problems, the present invention provides the following technical solution:

[0007] In a first aspect, the present invention provides a dual-energy calibration method based on a bone sclerosis model, comprising:

[0008] X-ray images at multiple frequencies were acquired within the soft tissue imaging energy range and the bone tissue imaging energy range using multi-frequency sampling technology.

[0009] By utilizing the density and structural features of bones, the reconstruction weights in the image are adjusted to reconstruct a bone sclerosis model, and artifacts caused by the sclerosis effect in the image are identified based on the reconstructed bone sclerosis model.

[0010] Based on the artifact recognition results, the parameters in the reconstruction model are iteratively adjusted, and the corrected image is output. The corrected image is then compared with the actual skeletal image.

[0011] As a preferred embodiment of the dual-energy correction method based on a bone sclerosis model described in this invention, the method involves acquiring X-ray images of multiple frequencies within both the soft tissue imaging energy range and the bone tissue imaging energy range using multi-frequency sampling technology, including:

[0012] Determine the energy range for soft tissue imaging and bone tissue imaging in the acquisition equipment;

[0013] The soft and bone tissues to be imaged are represented in the acquisition device using several coordinates;

[0014] The pulse frequency of X-rays in the acquisition device was adjusted to irradiate soft tissue and bone tissue in coordinate form, respectively, to obtain multiple sets of X-ray images of soft tissue and multiple sets of X-ray images of bone tissue.

[0015] As a preferred embodiment of the dual-energy correction method based on a bone sclerosis model described in this invention, the bone sclerosis model reconstruction is performed by adjusting the reconstruction weights in the image using the density and structural features of the bone, including:

[0016] The bone mineral density values ​​and cortical bone mineral density of pixels in multiple sets of soft tissue X-ray images and multiple sets of bone tissue X-ray images were calculated using the dual-energy X-ray absorption measurement formula.

[0017] The average thickness of the trabecular bone was obtained using a trabecular segmentation algorithm.

[0018] The average thickness of the cortical bone is obtained by using a cortical bone segmentation algorithm.

[0019] As a preferred embodiment of the dual-energy calibration method based on a bone sclerosis model described in this invention, it further includes:

[0020] A weighting function was designed based on bone mineral density values, cortical bone mineral density, average trabecular bone thickness, and average cortical bone thickness.

[0021] The osteosclerosis model is reconstructed based on the weighting function.

[0022] As a preferred embodiment of the dual-energy correction method based on a bone sclerosis model described in this invention, the method includes: identifying artifacts caused by sclerosis effects in the image based on the reconstructed bone sclerosis model, including:

[0023] A composite gradient operator is introduced to calculate the gradient caused by the image hardening effect;

[0024] The magnitude and direction of the gradient are calculated;

[0025] Non-maximum suppression is applied to the calculated amplitude value, and the high and low thresholds of the image are adjusted based on the calculated amplitude value.

[0026] The adjusted image height and low thresholds are used for edge connection to extract artifact features;

[0027] Based on the matching results between artifact features and the bone sclerosis model, artifact regions are marked.

[0028] As a preferred embodiment of the dual-energy correction method based on a bone sclerosis model described in this invention, the parameters in the reconstructed model are iteratively adjusted according to the artifact identification results, and the corrected image is output, including:

[0029] Define an error function to calculate the difference between the artifacts in the image and the expected artifacts;

[0030] The parameters in the bone sclerosis model are updated using the difference.

[0031] Calculate the gradient of the error function with respect to the parameters;

[0032] The image is corrected based on the updated parameters;

[0033] Repeat the above steps until the error function reaches the maximum number of iterations of the model, and then output the corrected image.

[0034] As a preferred embodiment of the dual-energy calibration method based on a bone sclerosis model described in this invention, the calibration image is compared with the actual bone image, including:

[0035] The corrected image is converted into a 3D model, which is then displayed in a virtual reality environment. A report is generated based on the comparison results selected by the user.

[0036] The report includes a difference chart, analytical data, and screenshots of the 3D model.

[0037] Secondly, the present invention provides a dual-energy calibration system based on a bone sclerosis model, comprising:

[0038] The multi-frequency image acquisition module is configured to acquire X-ray images of multiple frequencies in the soft tissue imaging energy range and the bone tissue imaging energy range using multi-frequency sampling technology.

[0039] The bone sclerosis model reconstruction and artifact recognition module is configured to use the density and structural features of bones to adjust the reconstruction weights in the image, reconstruct the bone sclerosis model, and identify artifacts caused by the sclerosis effect in the image based on the reconstructed bone sclerosis model.

[0040] The adaptive model parameter adjustment and visualization output module is configured to iteratively adjust the parameters in the reconstructed model based on the artifact recognition results, output the corrected image, and compare the corrected image with the actual skeleton image.

[0041] Thirdly, the present invention provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement any step of the above-described method.

[0042] Fourthly, the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements any step of the above-described method.

[0043] Compared with existing technologies, the invention has the following advantages: By adjusting the pulse frequency of X-rays in the acquisition device to irradiate the coordinate forms of soft tissue and bone tissue separately, the invention can more comprehensively reflect the characteristics of soft tissue and bone tissue and improve the sampling accuracy of images; by designing a weighting function based on bone mineral density values, cortical bone mineral density, average thickness of trabecular bone, and average thickness of cortical bone, the reconstructed bone sclerosis model becomes more accurate; by iteratively adjusting the parameters in the reconstructed model through artifact recognition results, dynamic correction is achieved, improving the quality of the corrected image; by comparing the corrected image with the actual bone image and displaying the model in three dimensions in a virtual reality environment, a report is generated based on the comparison results of the model of interest selected by the user, forming a personalized display result and improving the user experience. Attached Figure Description

[0044] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the following description of the embodiments will be briefly introduced. 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. Wherein:

[0045] Figure 1This is a flowchart illustrating the overall process of a dual-energy calibration method based on a bone sclerosis model according to an embodiment of the present invention.

[0046] Figure 2 This is a diagram illustrating the iterative adjustment process of a dual-energy calibration method based on a bone sclerosis model according to an embodiment of the present invention.

[0047] Figure 3 This is a comparison of experimental parameters for a dual-energy calibration method based on a bone sclerosis model according to an embodiment of the present invention;

[0048] Figure 4 This is a comparison diagram of SSIM and MSE for the dual-energy calibration method based on a bone sclerosis model according to an embodiment of the present invention. Detailed Implementation

[0049] To make the above-mentioned objects, features, and advantages of the present invention more apparent and understandable, specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of them. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the protection scope of the present invention.

[0050] Many specific details are set forth in the following description in order to provide a full understanding of the invention. However, the invention may also be practiced in other ways different from those described herein, and those skilled in the art can make similar extensions without departing from the spirit of the invention. Therefore, the invention is not limited to the specific embodiments disclosed below.

[0051] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The phrase "in one embodiment" appearing in different places in this specification does not necessarily refer to the same embodiment, nor is it a single or selective embodiment that is mutually exclusive with other embodiments.

[0052] This invention is described in detail with reference to the schematic diagrams. When detailing the embodiments of this invention, for ease of explanation, the cross-sectional views illustrating the device structure may be partially enlarged, not adhering to the usual scale. Furthermore, the schematic diagrams are merely examples and should not be construed as limiting the scope of protection of this invention. In actual fabrication, the three-dimensional spatial dimensions of length, width, and depth should be included.

[0053] Furthermore, in the description of this invention, it should be noted that the terms "upper," "lower," "inner," and "outer," etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. These terms are used solely for the convenience of describing the invention and for simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on the invention. In addition, the terms "first," "second," or "third" are used for descriptive purposes only and should not be construed as indicating or implying relative importance.

[0054] Unless otherwise explicitly specified and limited, the terms "installation," "connection," and "joining" in this invention should be interpreted broadly. For example, they can refer to fixed connections, detachable connections, or integral connections; similarly, they can refer to mechanical connections, electrical connections, or direct connections, or indirect connections through an intermediate medium, or internal connections between two components. Those skilled in the art can understand the specific meaning of the above terms in this invention based on the specific circumstances.

[0055] Example 1

[0056] Reference Figure 1 This is the first embodiment of the present invention, which provides a dual-energy calibration method based on a bone sclerosis model, comprising:

[0057] S1. X-ray images of multiple frequencies are acquired within the soft tissue imaging energy range and the bone tissue imaging energy range using multi-frequency sampling technology;

[0058] Furthermore, the imaging energy ranges for soft tissue and bone tissue in the acquisition equipment were determined;

[0059] Specifically, let the soft tissue imaging energy range be: E s =[E s_min E s_max [; Let the energy range for bone tissue imaging be: E] b =[E b_min E b_max ];

[0060] Furthermore, the soft and bone tissues to be imaged are represented in the acquisition device using several coordinates;

[0061] Specifically, the coordinate form in the data acquisition device is: (x i ,y i ,z i );

[0062] It should be noted that the imaging energy range and coordinate representation determine the X-ray acquisition range and pulse frequency;

[0063] Furthermore, by adjusting the pulse frequency of X-rays in the acquisition device to irradiate soft tissue and bone tissue in coordinate form, multiple sets of X-ray images of soft tissue and multiple sets of X-ray images of bone tissue were obtained.

[0064] Specifically, the pulse frequency received by the soft tissue is: f s The pulse frequency received by the bone tissue is: f b ;

[0065] Specifically, the X-ray images of multiple sets of soft tissue imaging and the X-ray images of multiple sets of bone tissue imaging are represented as follows:

[0066] I s ={I s1 ,I s2 ,I s3 ,…,I sn}

[0067] I b ={I b1 ,I b2 ,I b3 ,…,I bn}

[0068] It should be noted that by considering different pulse frequencies for soft tissue and bone tissue respectively, X-ray images of soft tissue and bone tissue at different frequencies were obtained, thus realizing the capture of complex features of soft tissue and bone tissue at different frequencies.

[0069] S2. Utilize the density and structural features of bones to adjust the reconstruction weights in the image, reconstruct the bone sclerosis model, and identify artifacts caused by the sclerosis effect in the image based on the reconstructed bone sclerosis model.

[0070] Furthermore, using the dual-energy X-ray absorption measurement formula, the bone mineral density values ​​and cortical bone mineral density of pixels in multiple sets of soft tissue X-ray images and multiple sets of bone tissue X-ray images were calculated.

[0071] Specifically, the formula for dual-energy X-ray absorption measurement is expressed as follows:

[0072]

[0073] Wherein, BMD is the bone mineral density value, and CMD is the mineral density of cortical bone; f(E s ,I s The function represents the energy range E for soft tissue imaging. s Internal soft tissue imaging image I s Contribution to bone mineral density (BMD) value; g(E) b ,I bThe function represents the energy range E for bone tissue imaging. b Internal bone tissue imaging image I b Contribution to bone mineral density (BMD) value; h(E) s ,I s The function represents the energy range E for soft tissue imaging. s Internal soft tissue imaging image I s Contribution to cortical bone mineral density (CMD); k(E) b ,I b The function represents the energy range E for bone tissue imaging. b Internal bone tissue imaging image I b Contribution to cortical bone mineral density (CMD);

[0074] Furthermore, the average thickness of the trabecular bone is obtained through a trabecular segmentation algorithm, expressed by the following formula:

[0075]

[0076] Where N is the total number of pixels representing the average thickness of the trabecular bone;

[0077] Furthermore, the average thickness of the cortical bone is obtained through a cortical bone segmentation algorithm, expressed by the formula:

[0078]

[0079] Where M is the total number of pixels representing the average thickness of the cortical bone;

[0080] Specifically, the second derivative is used to capture local curvature changes in an image, where changes in curvature can reflect the structural features of trabecular bone and cortical bone.

[0081] Furthermore, a weighting function was designed based on bone mineral density values, cortical bone mineral density, average trabecular bone thickness, and average cortical bone thickness.

[0082] Specifically, the weighting function is expressed as:

[0083] w=αBMD+βCMD+γT trab +δT cort

[0084] Wherein, α, β, γ, and δ represent bone mineral density (BMD), cortical bone mineral density (CMD), and average trabecular bone thickness (T), respectively. trab and the average thickness of cortical bone T cort Weighting coefficients in model reconstruction;

[0085] Furthermore, based on the weighting function, the bone sclerosis model is reconstructed, as follows:

[0086]

[0087] in, These are model parameters, w ij The combined weight of the i-th soft tissue image pixel and the j-th bone tissue image pixel;

[0088] Furthermore, a composite gradient operator is introduced to calculate the gradient caused by the image hardening effect, expressed as:

[0089] C x =S x +P x +R x +T x

[0090] C y =S y +P y +R y +T y

[0091] C z =S z +P z +R z +T z

[0092] Among them, S x Let P be the gradient component of the Sobel operator in the x-direction. x Let R be the gradient component of the Prewitt operator in the x-direction. x Let T be the gradient component of the Roberts operator in the x-direction. x S represents the gradient component of the Canny operator in the x-direction; y Let P be the gradient component of the Sobel operator in the y-direction. y Let R be the gradient component of the Prewitt operator in the y-direction. y Let T be the gradient component of the Roberts operator in the y-direction. y S represents the gradient component of the Canny operator in the y-direction; z Let P be the gradient component of the Sobel operator in the z-direction. z Let R be the gradient component of the Prewitt operator in the z-direction. z Let T be the gradient component of the Roberts operator in the z-direction. z Let be the gradient component of the Canny operator in the z-direction;

[0093] Furthermore, by calculating the magnitude G and direction θ of the gradient, we obtain:

[0094]

[0095] Furthermore, non-maximum suppression is applied to the calculated amplitude values, and the image height and low thresholds are adjusted based on the calculated amplitude values.

[0096] Specifically, nonmaximum suppression yields:

[0097]

[0098] The statement ifG(x,y,z)is a local maximum alongθ(x,y,z) means that the gradient magnitude G(x,y,z) is a local maximum along the gradient direction θ(x,y,z).

[0099] Specifically, adjusting the high and low thresholds and the low threshold of the image is expressed as follows:

[0100]

[0101] T low =μ G ―σ G

[0102] Where, μ G σ is the average value of the gradient magnitude. G The standard deviation of the gradient magnitude values;

[0103] Furthermore, the adjusted image height and low thresholds are used for edge connection to extract artifact features, represented as follows:

[0104]

[0105] in, This indicates that if the gradient magnitude G′(x,y,z) after non-maximum suppression is greater than the high threshold... Or it can be connected to a strong edge;

[0106] It should be noted that strong edges refer to pixels with gradient magnitudes greater than the high threshold; 1 and -1 represent retained and non-retained values, respectively.

[0107] Furthermore, based on the matching results between artifact features and the bone sclerosis model, artifact regions are marked;

[0108] Specifically, the extracted artifact features are matched with the bone sclerosis model, and the matching degree of each pixel at its coordinate position is calculated:

[0109]

[0110] Where eh(x,y,z) is the neighborhood of position (x,y,z);

[0111] Specifically, the artifact region is marked as follows:

[0112]

[0113] Where MatchingScore(x,y,z) represents the matching score between the artifact features at the coordinates and the bone sclerosis model;

[0114] S3. Based on the artifact recognition results, iteratively adjust the parameters in the reconstruction model, output the corrected image, and compare the corrected image with the actual skeleton image.

[0115] Furthermore, the iterative adjustment process is as follows;

[0116] S301. Define an error function to calculate the difference between the artifacts in the image and the expected artifacts.

[0117] Specifically, the error function is defined as follows:

[0118]

[0119] Among them, I actual To anticipate artifacts;

[0120] S302. Update the parameters in the bone sclerosis model using the difference, as expressed by the formula:

[0121]

[0122] Where η is the learning rate. Let the gradient of the error function be denoted as . For the current update parameters;

[0123] S303. Calculate the gradient of the error function with respect to the parameters, expressed by the formula:

[0124]

[0125] S304, Based on the updated parameters After correcting the image, we obtain:

[0126]

[0127] Among them, I corrected (x,y,z) is the corrected image;

[0128] S305. Repeat S302 to S304 until the error function reaches the maximum number of iterations of the model, and output the corrected image.

[0129] Specifically, error function Convergence or the error function reaching the maximum number of iterations of the model are both acceptable, where convergence requires the error function to reach its minimum value.

[0130] Specifically, if the model gradient is large, the maximum number of iterations is selected; if the model gradient is small, convergence to the minimum value is selected.

[0131] It should be noted that by selecting iteration or convergence based on the gradient magnitude, dynamic correction can be achieved while saving the model's computational resources, preventing the model from overfitting the training data in the high gradient region, reducing the risk of overfitting, avoiding underfitting, and improving the model's generalization ability.

[0132] Furthermore, the corrected image is converted into a 3D model, which is then displayed in a virtual reality environment. A report is generated based on the comparison results that the user is interested in.

[0133] Specifically, the virtual reality environment uses VR technology, and the comparison result is a 3D model and a 3D stereoscopic image of the actual skeleton.

[0134] The report includes a difference chart, analytical data, and screenshots of the 3D model.

[0135] Furthermore, this embodiment also provides a dual-energy calibration system based on a bone sclerosis model, comprising:

[0136] The multi-frequency image acquisition module is configured to acquire X-ray images of multiple frequencies in the soft tissue imaging energy range and the bone tissue imaging energy range using multi-frequency sampling technology.

[0137] The bone sclerosis model reconstruction and artifact recognition module is configured to use the density and structural features of bones to adjust the reconstruction weights in the image, reconstruct the bone sclerosis model, and identify artifacts caused by the sclerosis effect in the image based on the reconstructed bone sclerosis model.

[0138] The adaptive model parameter adjustment and visualization output module is configured to iteratively adjust the parameters in the reconstructed model based on the artifact recognition results, output the corrected image, and compare the corrected image with the actual skeleton image.

[0139] This embodiment also provides a computer device suitable for dual-energy calibration methods based on bone sclerosis models, including:

[0140] The system includes a memory and a processor. The memory stores computer-executable instructions, and the processor executes these instructions to implement the dual-energy correction method based on the osteosclerosis model as proposed in the above embodiments.

[0141] The computer device can be a terminal, comprising a processor, memory, communication interface, display screen, and input devices connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, carrier networks, NFC (Near Field Communication), or other technologies. The display screen can be an LCD screen or an e-ink screen. The input devices can be a touch layer covering the display screen, buttons, a trackball, or a touchpad on the computer device's casing, or an external keyboard, touchpad, or mouse.

[0142] This embodiment also provides a storage medium storing a computer program that, when executed by a processor, implements the dual-energy correction method based on a bone sclerosis model as proposed in the above embodiments.

[0143] The storage medium proposed in this embodiment and the data storage method proposed in the above embodiments belong to the same inventive concept. Technical details not described in detail in this embodiment can be found in the above embodiments, and this embodiment has the same beneficial effects as the above embodiments.

[0144] Example 2

[0145] Reference Figure 3 and Figure 4 This is the second embodiment of the present invention, which provides a dual-energy calibration method based on a bone sclerosis model, including: further verifying the beneficial effects involved in the present invention through simulation experiments;

[0146] The experiment used a GE Discovery CT750 HD dual-energy CT scanner with the following parameters: soft tissue imaging energy range: 40–80 kV, bone tissue imaging energy range: 80–120 kV, X-ray pulse frequency: 1 kHz in the initial state.

[0147] Four human skeletal images were selected, representing different age groups: 20, 30, 50, and 70 years old. Four skeletal models were randomly collected, simulating bones of different densities and structures. The experiment was conducted at a temperature of 22±2℃ and a humidity of 50±5℃. After the calculation and implementation of the present invention, a comparison was made between the corrected image and the actual skeletal image. Data results from two sets of comparison images were extracted, as shown in Tables 1 and 2.

[0148] Table 1 shows the results obtained from the comparison group (actual images) and the experimental group (corrected images).

[0149]

[0150]

[0151] As shown in Table 1, the BMD value of the experimental group was lower than that of the control group. This indicates that the method of the present invention, after removing the sclerosis artifact, can more accurately reflect the actual bone mineral density, reducing it by approximately 50 mg / cm³. 3 Furthermore, during the correction process, it effectively reduces errors caused by the hardening effect, improving image fidelity. The CMD value decreased by approximately 45 mg / cm². 3 and 50mg / cm 3 Although the average thickness data of trabecular bone and cortical bone are relatively close, combined with the sclerosis effect artifact, it can be seen that the artifacts are reduced from 15% and 14% to 5% and 4% respectively, which has a significant effect; secondly, in terms of image clarity, it can be seen that the image clarity after correction is significantly improved and the image quality is improved.

[0152] To further quantify the correction effect, the structural similarity index (SSIM) and mean squared error (MSE) are used to evaluate image quality, with the specific formulas as follows:

[0153]

[0154] Where μ represents the mean and σ represents the standard deviation;

[0155]

[0156] Where H is the total number of all pixels;

[0157] The results are shown in Table 2.

[0158] Table 2

[0159] parameter Comparison Group 1 Experimental group 1 Comparison Group 2 Experimental group 2 SSIM 0.85 0.95 0.87 0.96 MSE 0.012 0.004 0.011 0.003

[0160] Table 2 shows that the SSIM values ​​of the experimental group were significantly higher than those of the control group, reaching 0.95 and 0.96 respectively, while the control group's values ​​were only 0.85 and 0.87. This indicates that the corrected image is structurally more similar to the actual image, reflecting higher image quality. Furthermore, the MSE values ​​of the experimental group were significantly lower than those of the control group, at 0.004 and 0.003 respectively, while the control group's values ​​were 0.012 and 0.011. This indicates that the difference between the corrected image and the actual image is reduced, further verifying the effectiveness of the correction method.

[0161] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code. The solutions in the embodiments of this application can be implemented using various computer languages, such as the object-oriented programming language Java and the interpreted scripting language JavaScript.

[0162] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0163] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0164] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0165] Although preferred embodiments of this application have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments as well as all changes and modifications falling within the scope of this application.

[0166] Obviously, those skilled in the art can make various modifications and variations to this application without departing from the spirit and scope of this application. Therefore, if such modifications and variations fall within the scope of the claims of this application and their equivalents, this application also intends to include such modifications and variations.

Claims

1. A dual-energy calibration method based on a bone sclerosis model, characterized in that, include: X-ray images at multiple frequencies were acquired within the soft tissue imaging energy range and the bone tissue imaging energy range using multi-frequency sampling technology. By utilizing the density and structural features of bones, the reconstruction weights in the image are adjusted to reconstruct a bone sclerosis model, and artifacts caused by the sclerosis effect in the image are identified based on the reconstructed bone sclerosis model. The method of reconstructing a bone sclerosis model by adjusting the reconstruction weights in the image based on the density and structural features of the bone includes: The bone mineral density values ​​and cortical bone mineral density of pixels in multiple sets of soft tissue X-ray images and multiple sets of bone tissue X-ray images were calculated using the dual-energy X-ray absorption measurement formula. The formula for dual-energy X-ray absorption measurement is expressed as follows: Wherein, BMD is the bone mineral density value, and CMD is the mineral density of cortical bone; f(E s ,I s The function represents the energy range E for soft tissue imaging. s Internal soft tissue imaging image I s Contribution to bone mineral density (BMD) value; g(E) b ,I b The function represents the energy range E for bone tissue imaging. b Internal bone tissue imaging image I b Contribution to bone mineral density (BMD) value; h(E) s ,I s The function represents the energy range E for soft tissue imaging. s Internal soft tissue imaging image I s Contribution to cortical bone mineral density (CMD); k(E) b ,I b The function represents the energy range E for bone tissue imaging. b Internal bone tissue imaging image I b Contribution to cortical bone mineral density (CMD); The average thickness of the trabecular bone was obtained using a trabecular segmentation algorithm. The average thickness of the trabecular bone is obtained through a trabecular segmentation algorithm, expressed by the following formula: Where N is the total number of pixels representing the average thickness of the trabecular bone; The average thickness of the cortical bone was obtained using a cortical bone segmentation algorithm. The average thickness of the cortical bone is obtained through cortical bone segmentation algorithm, expressed by the following formula: Where M is the total number of pixels representing the average thickness of the cortical bone; It also includes: designing a weighting function based on bone mineral density values, cortical bone mineral density, average trabecular bone thickness, and average cortical bone thickness; The bone sclerosis model is reconstructed based on the weighting function. Based on the artifact recognition results, the parameters in the reconstruction model are iteratively adjusted, and the corrected image is output. The corrected image is then compared with the actual skeletal image.

2. The dual-energy calibration method based on a bone sclerosis model as described in claim 1, characterized in that, X-ray images at multiple frequencies are acquired within the soft tissue imaging energy range and the bone tissue imaging energy range using multi-frequency sampling techniques, including: Determine the energy range for soft tissue imaging and bone tissue imaging in the acquisition equipment; The soft and bone tissues to be imaged are represented in the acquisition device using several coordinates; The pulse frequency of X-rays in the acquisition device was adjusted to irradiate soft tissue and bone tissue in coordinate form, respectively, to obtain multiple sets of X-ray images of soft tissue and multiple sets of X-ray images of bone tissue.

3. The dual-energy calibration method based on a bone sclerosis model as described in claim 1, characterized in that, Based on the reconstructed bone sclerosis model, artifacts caused by sclerosis effects in the image are identified, including: A composite gradient operator is introduced to calculate the gradient caused by the image hardening effect; The magnitude and direction of the gradient are calculated; Non-maximum suppression is applied to the calculated amplitude value, and the high and low thresholds of the image are adjusted based on the calculated amplitude value. The adjusted image height and low thresholds are used for edge connection to extract artifact features; Based on the matching results between artifact features and the bone sclerosis model, artifact regions are marked.

4. The dual-energy calibration method based on a bone sclerosis model as described in claim 3, characterized in that, Based on the artifact identification results, the parameters in the reconstruction model are iteratively adjusted, and the corrected image is output, including: Define an error function to calculate the difference between the artifacts in the image and the expected artifacts; The parameters in the bone sclerosis model are updated using the difference. Calculate the gradient of the error function with respect to the parameters; The image is corrected based on the updated parameters; Repeat the above steps until the error function reaches the maximum number of iterations of the model, and then output the corrected image.

5. The dual-energy calibration method based on a bone sclerosis model as described in claim 4, characterized in that, The corrected image was compared with the actual skeletal image, including: The corrected image is converted into a 3D model, which is then displayed in a virtual reality environment. A report is generated based on the comparison results selected by the user. The report includes a difference chart, analytical data, and screenshots of the 3D model.

6. A dual-energy calibration system based on a bone sclerosis model, comprising the dual-energy calibration method based on a bone sclerosis model as described in any one of claims 1 to 5, characterized in that, include: The multi-frequency image acquisition module is configured to acquire X-ray images of multiple frequencies in the soft tissue imaging energy range and the bone tissue imaging energy range using multi-frequency sampling technology. The bone sclerosis model reconstruction and artifact recognition module is configured to use the density and structural features of bones to adjust the reconstruction weights in the image, reconstruct the bone sclerosis model, and identify artifacts caused by the sclerosis effect in the image based on the reconstructed bone sclerosis model. The adaptive model parameter adjustment and visualization output module is configured to iteratively adjust the parameters in the reconstructed model based on the artifact recognition results, output the corrected image, and compare the corrected image with the actual skeleton image.

7. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that: When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 5.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 5.

Images