Wave Vibration Algorithm to Improve X-ray Image Quality

Abstract

The present invention discloses a wave vibration algorithm for improving the image quality level of an X-ray machine. The algorithm can transform and process two-dimensional signals into simulated three-dimensional signals and colored signals, provide more comprehensive and accurate signal analysis, and by screening out high-quality signals, can help optimize the rapid allocation of resources, reduce the time and demand for storage space, and can be applicable to a variety of different types of equipment and application scenarios. The algorithm can automatically calculate in real time to obtain the best feedback radiation signal for processing, can more accurately capture the quality characteristics of the identification and differentiation analysis signals, can dynamically adjust its processing parameters according to the signal characteristics to optimize the signal screening process, can quickly identify high-quality signals in the feedback signals, can effectively resist noise interference, improve the signal-to-noise ratio of the signal, and can still maintain a high performance under various adverse conditions such as signal distortion and noise interference, showing good robustness.

Description

Technical Field

[0001] The invention relates to the field of optical medical detection image processing science and technology, and in particular to a wave vibration algorithm for improving the image quality level of an X-ray machine. Background Art

[0002] Currently, digital X-ray machines and CT machines (computed tomography) are two commonly used devices in the field of medical imaging, and they play an important role in the diagnosis and treatment process.

[0003] Digital X-ray machine: 1. Advantages: (1) Low radiation dose: Compared with traditional X-ray machines, digital X-ray machines use digital sensor technology to reduce the patient's radiation exposure. (2) Real-time imaging: Digital X-ray machines can quickly acquire images and display them on the computer, which helps doctors make a quick diagnosis. (3) Low cost: Compared with CT machines, the purchase and maintenance costs of digital X-ray machines are generally lower. (4) Wide range of applications: Suitable for various simple imaging examinations, such as chest, limbs, etc. 2. Disadvantages: (1) Limited to planar imaging: Digital X-ray machines can only provide planar images, which may not be accurate enough for diagnoses that require more three-dimensional information. (2) Lack of detailed information: Compared with CT machines, digital X-ray machines lack clarity in providing detailed information. (3) Limited diagnostic capabilities: In some pathological conditions, digital X-ray machines may not be able to provide sufficient diagnostic information.

[0004] CT (Computed Tomography) 1. Advantages: (1) Three-dimensional imaging: CT can provide three-dimensional images, which helps doctors understand the condition more comprehensively. (2) High FB rate: CT can provide images with high FB rate, which helps detect small lesions and has strong image clarity. (3) More comprehensive diagnosis: CT can provide a relatively comprehensive medical diagnosis and help provide effective treatment plans. (4) Used for various parts: CT can be used to examine various parts of the body and has high versatility. 2. Disadvantages: (1) High radiation dose: Compared with digital X-ray machines, CT uses a higher radiation dose, which may pose certain risks to patients. (2) Expensive: The purchase and maintenance costs of CT are usually high, so not all medical institutions can easily afford it. (3) Longer scanning time: Compared with digital X-ray machines, CT takes longer to scan, especially for some emergency situations, which may not be fast enough.

[0005] CT has higher sensitivity and specificity in detecting early lung cancer. It can show nodules with smaller diameters and reduce the overlap of normal tissue structures, thereby increasing the detection rate of early lung cancer. Therefore, in lung cancer screening programs, CT is considered to be the best imaging method currently used to detect early lung cancer. CT examinations are more recommended for the screening and diagnosis of early lung cancer. If the X-ray results are abnormal or there are high-risk factors, doctors usually recommend further CT examinations or other related diagnostic procedures to confirm the diagnosis.

[0006] Under normal circumstances, a digital X-ray or CT scan will not have much impact on the human body. The comparison between digital X-ray and CT scans: CT scans have higher resolution, higher costs, and higher X-ray doses; X-ray scans have low radiation, are quick, and are inexpensive, but their resolution is not as good as CT.

[0007] In summary, a wave vibration algorithm is needed to improve the image quality level of X-ray machines to solve the shortcomings of the existing technology. Summary of the invention

[0008] In view of the deficiencies in the prior art, the present invention provides a wave vibration algorithm for improving the image quality level of an X-ray machine, aiming to solve the above-mentioned problems.

[0009] To achieve the above object, the present invention provides the following technical solution: a wave vibration algorithm for improving the image quality level of an X-ray machine, comprising the following steps:

[0010] Step S1: preliminary WVA calculation, according to the parameter information of the X-ray machine irradiating the patient's body, using the WVA function formula, forming a mathematical combination, performing calculations, and constructing a WV initial grayscale source image of the X-ray machine irradiating the patient's body;

[0011] Step S2: Preliminary image quality processing: using a combination of relevant WVA function formulas to perform WVA operations on the WV initial grayscale source image, and converting the WV initial grayscale source image into a WVPP image with clear texture and high image quality;

[0012] Step S3: mid-term WVA operation, designing several WVA function formulas to form a combination, processing the WVPP image, and changing the two-dimensional image into a simulated three-dimensional image, converting the WVPP image into a WVRH image, and highlighting the edge and detail information of the image;

[0013] Step S4: image color analysis and enhancement, using a combination of WVA function formulas to process the WVRH image and convert it into a WVHSV color image, so that the color of the lesion area is prominent and clear, and the image color analysis and feature enhancement are improved;

[0014] Step S5: Post-processing WVA calculation, using WVA function formula combination to perform subsequent WVYM image optimization and modification processing on the WVHSV color image to form a high-quality, high-definition X-ray WV image;

[0015] Step S6: forming an X-ray WV three-dimensional image, by acquiring X-ray radiation images from multiple angles, processing the images using a combination of WVA function formulas, and performing stereoscopic reconstruction of the X-ray WV three-dimensional image;

[0016] Step S7: Create a WVHSV colored three-dimensional image, use a WVA function formula combination to process the X-ray WV three-dimensional image, and convert it into a WVHSV colored three-dimensional image.

[0017] Optionally, the construction of the WV initial grayscale source image of the body of the patient being tested irradiated by the X-ray machine in step 1 is achieved by:

[0018] Step S11: Establishing a radiation expression, based on the X-ray radiation principle, establishing an X-ray image WV radiation expression;

[0019] Step S12: measurement and calculation, according to the material properties of the patient's body, measure or query the absorption coefficient of each point, determine the material thickness of each point through the measured value or known structure, and determine the initial radiation intensity or reference intensity and information parameters related to the patient's body according to the WVA theory and radiation data;

[0020] Step S13: Calculate the radiation amount of each coordinate point according to the radiation expression established in step S11;

[0021] Step S14: converting the calculated radiation amount into a grayscale value in the image.

[0022] Optionally, the radiation expression in step S11 is:

[0023] Radiation(x,y)=D*p(-E*Absorption_Coefficient(x,y) * Thickness(x, y))*Wvxs,

[0024] Where: Radiation(x,y) represents the X-ray radiation intensity at the coordinate (x,y), D is the WV radiation intensity or reference intensity of the digital X-ray machine to the patient's body, E is the information coefficient related to the patient's body, Absorption_Coefficient(x,y) is the radiation absorption coefficient of the patient's body to X-ray at the coordinate (x,y), Thickness(x,y) is the thickness of the patient's body that the X-ray passes through at the positioning coordinate (x,y), Wvxs is the WV parameter or variable, and p is the operation function;

[0025] The conversion formula in step S14 is:

[0026] Gray_Value = (A*sin(ω*t + φ)+B)* Radiation(x,y)* Wvxs,

[0027] Where Gray_Value is the gray value, A is the amplitude coefficient, B is the gray offset, Radiation(x, y) is the radiation intensity function, Wvxs is the WV parameter or variable, t is the spatial variable, ω is the angular frequency, and φ is the initial phase.

[0028] Optionally, the preliminary image quality processing in step S2 is implemented in the following manner:

[0029] Step S21: Based on the physical characteristics of the X-ray image, establish the WVDZ resolution expression of the X-ray image:

[0030] Resolution = C*(λ / d) f*(x,y)*Gray_Value*Wvxs,

[0031] Where C is a constant, λ is the wavelength of X-rays, d is the spacing of the detectors or related physical dimensions, f(x,y) is the image position function, Gray_Value is the gray value of the image, and Wvxs is the WV parameter or variable;

[0032] Step S22: Calculate the WVDZ resolution, determine the constant C, the X-ray wavelength λ and the detector spacing d, and obtain the gray value of each pixel from the X-ray WV initial gray source image, and use the formula in step S21 to calculate the WVDZ resolution of each coordinate point;

[0033] Step S23: Convert the WVDZ resolution into a WVPP image.

[0034] Optionally, the conversion formula in step S23 is:

[0035] Spectral_Image(f) = ∫∫[Resolution +…

[0036] +Resolution (x,y)exp(−2πifx)]dxdy*Wvxs,

[0037] where Spectral_Image(f ) is the WVPP image at frequency f, Resolution + ... +Resolution (x,y) represents the sum of all N WV resolution functions, exp(−2πifx) is the function that converts spatial information into frequency information, ∫∫ is the double integration of the entire image space, dxdy is the tiny area, and Wvxs is the WV parameter or variable.

[0038] Optionally, the mid-term WVA calculation in step S3 is implemented in the following manner:

[0039] Step S31: Based on the physical characteristics of the X-ray image and the WVNX project, establish the X-ray image WVNX project expression:

[0040] Reconstructed_Image(x,y) =

[0041] Inverse_Trans form [Fourier_Spectrum_Image(x,y)]

[0042] +Regularization_Term*Spectral_Image(f )*Wvxs,

[0043] Where Reconstructed_Image(x, y) is the value of the X-ray image reconstructed by the WVNX project at the coordinate (x, y), and the reconstructed WVRH image;

[0044] Inverse_Transform[Fourier_Spectrum_Image(x, y)] is the result of the inverse transform operation on the X-ray WVPP image, Regularization_Term is the regularization term, which is an image parameter, Spectral_Image(f) is the WVPP image at frequency f, and Wvxs is the WV parameter or variable;

[0045] Step S32: obtaining input data, executing the WVNX project, inputting data, performing an inverse transformation operation, calculating a product term, and then adding the inverse transformation result and the product term to obtain reconstructed image data;

[0046] Step S33: Calculate the WVRH image effect strength, and perform image processing and optimization to highlight the edge and detail information of the image.

[0047] Optionally, the conversion of the WVRH image into a WVHSV color image in step S4 is achieved by:

[0048] Step S41: Based on the physical characteristics of the X-ray image, establish an X-ray WV soft tissue imaging intensity expression.

[0049] I(x,y) = S * t * exp(-∫μ(x,y)ds) +F[Wv_Signal(x,y)]

[0050] +(Noise_Component)*Sharpening_Intensity *Wvxs,

[0051] Where: S is the sensitivity of the detector, t is the exposure time, ∫μ(x,y)ds is the integration of the attenuation coefficient along the path of the X-ray passing through the tissue, F is the WV transformation function, Wv_Signal(x,y) is the X-ray wave signal, Noise_Component is the noise component, Sharpening_Intensity is the intensity of the X-ray WVRH image, and Wvxs is a WV parameter or variable;

[0052] Step S42: By acquiring X-ray radiation images from multiple different angles, the X-ray WV three-dimensional image expression is:

[0053] I(x, y, z) = S*t*exp (-∫∫∫ μ(x, y, z, k)*Δl) dxdydz

[0054] + F (W v) G [∫∫∫Wv_Signal(x, y, z) dxdydz]*I(x,y)*Wvxs;

[0055] Where S is the sensitivity of the detector, t is the exposure time, (x, y, z, k) is a discrete point in three-dimensional space, Δl is a small length increment along the X-ray propagation path, F (Wv) is the wave function, G is the transformation function of the signal after integrating WV_Signal (x, y, z) in three-dimensional space, ∫∫∫WV_Signal(x, y, z)dxdydz is the integration of the X-ray wave signal in three-dimensional space, and Wvxs is the WV parameter or variable.

[0056] Optionally, the subsequent WVYM image optimization and modification processing of the WVHSV color image in step S5 is as follows:

[0057] The new dimension of color is introduced to enhance the X-ray WVHSV colored three-dimensional image. The expression of X-ray WVHSV colored three-dimensional image is:

[0058] HSV(x, y, z) = ((N - 1)*(360 / N) + (Wave_Value(x, y, z) - (N - 1)*W / N)*(360 / N)*I(x,y,z)*Wvxs,abs(Wave_Value(x,y,z)-0.5*W) / M*I(x,y, z)*Wvxs,Wave_Value(x, y, z) / W*I(x, y, z)*Wvxs),

[0059] Where N is the number of tone segments, Wave_Value(x, y, z) is the X-ray wave value at the coordinate (x, y, z), I (x, y, z) is the intensity of three-dimensional imaging, W is the maximum value of the X-ray wave value, abs is the absolute value, and Wvxs is the WV parameter or variable.

[0060] Optionally, the stereoscopic reconstruction of the X-ray WV three-dimensional image in step S6 is:

[0061] Step S61: Calculate each channel value, namely, calculate the red channel value, the green channel value and the blue channel value;

[0062] Step S62: combining color values, combining the calculated red channel value, green channel value and blue channel value to form the color at the coordinate (x, y, z);

[0063] Step S63: Repeat the calculation and processing for each pixel in the image, and repeat the process of steps S61 and S62 until the entire image is processed and an X-ray WV three-dimensional image is established.

[0064] Optionally, the WVHSV colored three-dimensional image converted in step S7 is:

[0065] Step S71: Acquire image data of X-ray WV three-dimensional image;

[0066] Step S72: Calculate the optimized color value of the red channel, green channel and blue channel of each pixel in the X-ray WV three-dimensional image, and combine them to form the optimized color value of the pixel;

[0067] Step S73: Improve image quality and increase image details through exponential function filtering and detail image enhancement, combine the optimized color values ​​of all pixels, and output X-ray WV colored three-dimensional high-definition image.

[0068] Beneficial effects of the present invention:

[0069] 1. In the present invention, by radiating the reflected vibration of the object, a photoelectric wave vibration layer with short wave, dense wave and small wave is formed, which is continuously calculated, and the image is repeatedly compared and discarded to obtain a clear image to the maximum extent. The data can be moved forward, and the factors that will form the image can be extracted and mined as much as possible to achieve the highest possible clarity of the image;

[0070] 2. In the present invention, it is possible to automatically calculate in real time to obtain the best feedback radiation signal for processing, to more accurately capture the quality characteristics of the identification and differentiation analysis signal, to dynamically adjust its processing parameters according to the signal characteristics to optimize the signal screening process, to quickly identify high-quality signals in the feedback signal, to effectively resist noise interference, to improve the signal-to-noise ratio, and to maintain high performance under various adverse conditions such as signal distortion and noise interference, showing good robustness;

[0071] 3. In the present invention, the two-dimensional signal can be transformed and processed into simulated three-dimensional signals and colored signals, providing more comprehensive and accurate signal analysis. By screening out high-quality signals, it can help optimize the rapid allocation of resources, reduce time and storage space requirements, and can be applicable to a variety of different types of equipment and application scenarios. BRIEF DESCRIPTION OF THE DRAWINGS

[0072] Figure 1 The figure is a logic flow chart of the present invention.

[0073] Figure 2 This is a before and after comparison diagram of an X-ray WVYM image produced by the present invention.

[0074] Figure 3 This is an X-ray high-definition colored three-dimensional image of the present invention. DETAILED DESCRIPTION

[0075] In order to more clearly illustrate the embodiments of the invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0076] like Figure 1 , 2 As shown in , 3, a wave vibration algorithm for improving the quality level of X-ray machine images includes the following contents:

[0077] (I) Steps of the program

[0078] An innovative WVA technology solution and steps to improve the image quality of digital X-ray machines:

[0079] Step 1: Preliminary WVA calculation: Take the parameter information of the X-ray machine radiating the patient's body, design multiple targeted WVA function formulas, form mathematical combinations, and perform calculations. Make the radiation parameter information form the WV initial grayscale source image of the patient's body.

[0080] Step 2: In order to improve the quality of the step-by-step image, a combination of relevant WVA function formulas is designed to perform WVA operations on the WV initial grayscale source image, and the WV initial grayscale source image is converted into a WVPP image with clear texture and high image quality.

[0081] Step 3: Mid-term WVA operation: Design several WVA function formulas to form a combination, and convert the WVPP image into a WVRH image. This conversion process is essentially a selective enhancement operation of the image frequency components, and its purpose is to highlight the edge and detail information of the image. After the WVA function formula combination processing of the WVPP image, the edge and detail of the WVRH image will become clearer and more prominent, and the two-dimensional image can also be changed into a simulated three-dimensional image.

[0082] Step 4: After the designed WVA function formula is combined and operated, the WVRH image is converted into a WVHSV color image, the color of the X-ray image is analyzed and enhanced, and the mechanism of color analysis and feature enhancement of the X-ray image is further improved. After the operation, the image of the prominent lesion area is converted into a WVHSV color image, making the color of the lesion area image more prominent and clear, which is convenient for doctors to observe and analyze.

[0083] Step 5, post-WVA operation: Use the combination of WVA function formulas to perform the final WVYM image optimization and modification on the WVHSV color image. The image processed by WVYM optimization and modification can accurately extract the target object of a specific color from the image; it helps to remove irrelevant background information and make the body of the patient under test more prominent; the optimized WVYM image can be used to enhance the visual effect of the patient's body under test, and enhance its color and contrast for better analysis and identification; in the subsequent WVYM image processing, analysis and calculation, it can also reduce the amount of data processing, improve processing speed and efficiency; remove interference caused by factors such as uneven lighting and color noise, and improve image quality; it can provide an accurate basis for applications such as image stitching and multimodal image (CT, MRI) fusion; according to different application scenarios and needs, flexibly adjust the optimization parameters and operation strategies to meet various specific image processing tasks. Finally, a high-quality, high-definition X-ray WV image is formed.

[0084] 2. Design calculation method

[0085] By using the WVA function formula to combine the advantages, the radiation of the X-ray machine is reduced, the clarity and accuracy of the image taken is improved, and the patient is served quickly and accurately, the imaging ability of the X-ray machine is effectively improved and the technical deficiencies are overcome, so that the X-ray imaging system can truly form a colored three-dimensional high-definition X-ray image of the patient's body, and strive to reach the quality level of the high-definition image of the CT machine. The method is as follows:

[0086] 1. Formula combination scheme for constructing X-ray WV initial grayscale source image from X-ray machine radiation

[0087] (1) First, use an X-ray machine to irradiate the patient's body and obtain relevant information parameters of the patient's body. From the radiation probe of the patient's body, we can know the different density thicknesses of X-rays penetrating the patient's body and the different attenuation levels of X-rays. By using this X-ray density thickness attenuation difference conversion and the corresponding node pixel image parameters of each level, the WVA function formula is calculated, and the initial grayscale value of the constructed image and the grayscale value in the WV initial grayscale source image are measured, analyzed and quantified, presenting the visualization of the internal structure of the patient's body, thereby realizing the design of the X-ray WV initial grayscale source image WVA function formula combination. The specific method of designing the operation is:

[0088] X-ray image WV radiation expression:

[0089] Radiation(x,y)=D*p(-E*Absorption_Coefficient(x,y) * Thickness(x, y) *Wvxs,

[0090] Where: D is the WV radiation intensity or reference intensity of the digital X-ray machine to the patient's body. E is the information coefficient related to the patient's body, which is related to the characteristics of the interaction between the radiation and the patient's body.

[0091] Absorption_Coefficient(x,y) is the radiation absorption coefficient of the patient's body at the coordinate (x,y) for X-rays. It varies with the type, properties and position of the patient's body and can be obtained by looking up the absorption coefficient table of related substances or experimental measurement. Calculate the coefficient of absorption of relevant information that different patient's bodies may have different X-ray radiation capabilities at different positions. Thickness(x,y) is the thickness of the patient's body that the X-ray passes through at the positioning coordinate (x,y). It needs to be determined by actual measurement or based on the known structure of the patient's body. Radiation(x,y) is the intensity of X-ray radiation at the coordinate (x,y). By collecting data, collect data on the radiation absorption coefficient and thickness of the patient's body related to the coordinate point (x,y), and determine the appropriate values ​​of D and E. Wvxs is a specific WV parameter or variable, depending on the specific application and context.

[0092] Specific algorithm: First, the meaning of each variable is clear: Radiation (x, y): the amount of radiation at the coordinate (x, y). D: a constant coefficient, representing the proportional factor of the initial radiation intensity and the radiation. Its specific meaning depends on the specific physical situation and is related to the attenuation characteristics of the radiation.

[0093] Absorption_Coefficient(x,y) * Thickness(x, y) This part: represents the absorption coefficient of the material to radiation at this coordinate. The larger the absorption coefficient, the stronger the material's ability to absorb radiation. Thickness(x,y) is the thickness of the material at this coordinate. Absorption_Coefficient(x,y): The material absorption coefficient at coordinate (x,y), which represents the material's ability to absorb radiation. Thickness(x,y): The thickness of the material at coordinate (x,y). The product of the two represents the total absorption effect caused by the absorption characteristics of the material when the radiation passes through the material of this thickness.

[0094] -E*Absorption_Coefficient(x,y) * Thickness(x, y): E is a coefficient that adjusts the strength of the absorption effect. Multiplying by -1 makes this value gradually decrease as the absorption effect increases. Then p(-E*Absorption_Coefficient(x,y) * Thickness(x, y)): p is a function,

[0095] Perform some specific operation on the value of -E*Absorption_Coefficient(x,y) * Thickness(x, y). Depending on the definition of the function p, it may involve various mathematical operations such as exponentials, logarithms, etc. The final result is D*p(-E*Absorption_Coefficient(x,y) * Thickness(x, y)) *Wvxs: D is another coefficient that can adjust the proportion of the overall radiation amount. Wvxs is a specific parameter coefficient that also affects the final radiation amount. By calculating Absorption_Coefficient(x,y) * Thickness(x, y), we get a value related to the absorption degree of the material at the coordinate (x,y). Then multiply it by the constant E, that is, E*Absorption_Coefficient(x,y) * Thickness(x, y). Take the negative value of this product and get -E*Absorption_Coefficient(x,y) * Thickness(x, y). This negative value is used as the input of function p, that is, p(-E*Absorption_Coefficient(x,y) * Thickness(x, y)). Finally, this result is multiplied by D and Wvxs, that is, D*p(-E*Absorption_Coefficient(x,y) * Thickness(x, y)) *Wvxs, to obtain the radiation Radiation(x,y) at the coordinate (x,y).

[0096] The radiation at the coordinate (x, y) is calculated by combining the absorption coefficient, material thickness, coefficient E, function p, coefficient D and parameter Wvxs. The specific values ​​and calculation results will vary depending on the specific values ​​of these parameters and the definition of function p.

[0097] It should be noted that: 1). The values ​​of D and E should be determined based on WVA theory and radiation data, and the measurement of absorption coefficient and thickness should be as accurate as possible to ensure the reliability of the calculation results. 2). During the calculation process, ensure that the units of all parameters match each other to avoid calculation errors due to inconsistent units. 3). Determine the values ​​of constants D and E. These values ​​should be determined based on X-ray radiation conditions and equipment characteristics. 4). Calculate the radiation intensity after passing through a medium of a certain thickness, indicating that the radiation intensity decays exponentially with the product of the absorption coefficient and thickness of the medium. With the increase of absorption coefficient or thickness, the radiation intensity will decrease according to the exponential law. 5). In practical applications, it is used to predict and control the characteristic changes when irradiating different materials, laying a data foundation for the initial grayscale source image of WV.

[0098] (2) Converting X-ray WV radiation data into an initial grayscale source image can more intuitively display and understand the distribution of X-rays at different locations and the changes in intensity, thickness, and characteristics. The difference in image grayscale values ​​can clearly show the differences in radiation intensity, thickness, and characteristics. Excluding the influence of various factors, such as equipment differences, exposure time, patient body thickness, etc., these may cause uneven distribution of image grayscale values. Generating grayscale source images facilitates the comparison and detection of X-ray radiation conditions of different samples, different states, or different times. By comparing the differences in grayscale images, abnormal areas, lesions, or defects in materials can be found. Grayscale value images are the basic input of many image processing algorithms and techniques. Subsequently, the initial grayscale source image can be filtered, enhanced, denoised, contrast enhanced, edge detected, and other analytical processing operations to form a high-definition X-ray WV image. The method is to use the WVA function formula combination analysis.

[0099] The conversion of X-ray WV radiation grayscale value into X-ray WV initial grayscale source image helps to understand and analyze the information data carried by X-rays more intuitively and accurately, and uses WVA function formula combination design. The specific method of design operation is:

[0100] The initial grayscale source image expression of X-ray image WV is:

[0101] Gray_Value = (A*sin(ω*t + φ)+B)* Radiation(x,y)* Wvxs,

[0102] Among them: A, controls the amplitude of the wave vibration, which determines the magnitude of the grayscale value change. ω, represents the angular frequency, which determines the period and frequency of WV. x, is the position coordinate in the image. φ, the initial phase, affects the starting position of WV. B, controls the overall grayscale offset so that the grayscale value is within a reasonable range. Radiation(x, y), this part represents a position-dependent radiation intensity function, which is related to the light intensity or other factors at each point in the image. The value of this function will affect the final grayscale value. The values ​​of these parameters are calculated according to the specific X-ray image WV radiation requirements and image characteristics to obtain the X-ray WV initial grayscale source image. Gray_Value is a quantity related to the variable x. It consists of three parts, the first is the product of the coefficient A and the sine function sin(ω*x + φ), and then the constant B is added. Among them, A determines the amplitude of the sine function value. The larger the value of A, the greater the fluctuation amplitude of the sine curve; ω is the angular frequency, which determines the period of the sine function. The larger the ω, the shorter the period and the faster the function changes; t is a spatial variable, which can represent the spatial position or other physical quantities; φ is the initial phase, which determines the initial position of the sine function; B is a constant, which translates the entire sine function upward (B is a positive number) or downward (B is a negative number), thereby affecting the overall value level of Gray_Value. Wvxs is a WV parameter variable, which depends on the specific application and background.

[0103] The relationship between the change of image gray value (Gray_Value) position (x) is the linear transformation of the sine function.

[0104] Gray_Value: refers to the grayscale value of each pixel in the image, usually in the range of 0 to 255. For 8-bit images, it represents the brightness or color depth of the image at that point.

[0105] A is an amplitude coefficient that determines the maximum amplitude of the sine wave, that is, the range of grayscale value change.

[0106] If A is a positive value, the grayscale value will fluctuate above and below B; if A is a negative value, the grayscale value will fluctuate in the opposite direction. The larger the absolute value of A, the wider the range of grayscale value variation. sin, this is the sine function, which is a periodic mathematical function whose value varies between -1 and 1. The sine function is used to generate a curve with a wavy shape. ω (omega), this is the angular frequency coefficient, which determines the speed of the periodic change of the sine wave. The larger the ω value, the shorter the period of the sine wave, that is, the smaller the distance between the peaks, and the faster the grayscale value changes. x, this is the position coordinate of the pixel point in the image, which determines the position of the sine wave on the image.

[0107] φ (phi), this is the phase shift coefficient, which determines the starting position of the sine wave on the x-axis. Different values ​​of φ will cause the sine wave to be translated along the x-axis without changing its shape and period. B, this is a vertical shift coefficient, which determines the position of the center line of the sine wave (i.e. the average value of the grayscale value) on the y-axis. The value of B moves the entire sine wave up or down, but does not change its amplitude or period.

[0108] Specific calculation: When calculating the gray value Gray_Value: first look at the part in the brackets: Asin(ωt+ φ)+B: A is the amplitude coefficient, which determines the amplitude of the sine function. The larger the amplitude, the greater the range of variation of the value of this part between the maximum and minimum values. sin (ω*t + φ) is the expression of the sine function, where ω is the angular frequency, which determines the periodic characteristics of the sine function. x is usually a variable related to position or a certain parameter. φ is the initial phase, which determines the state of the sine function at the initial moment. B is an offset that causes the entire sine function to translate up and down in the vertical direction. Then consider Radiation (x,y): This represents the amount of radiation at the coordinate point (x,y). The amount of radiation depends on the specific physical scene and related parameters, such as absorption coefficient, material thickness, etc. Finally, Wvxs: Wvxs is a specific weight coefficient and parameter. The entire calculation result will be further adjusted. Calculate the sine function value in the brackets plus the offset, and then multiply the result with the radiation at the coordinate point (x, y) and Wvxs to get the final gray value Gray_Value. This gray value can be used to represent the brightness, intensity or other related physical quantities of the image at a specific coordinate point. The entire combination of the periodic changes of the sine function, the radiation and the influence of specific parameters jointly determine the size of the gray value.

[0109] Gray_Value = (A*sin(ω*t + φ)+B) * Radiation (x,y)* Wvxs, is an expression used in image processing to simulate the wave (WV) phenomenon: A*sin(ω* t+φ) is used to simulate waves, such as water waves, sound waves, light waves, electromagnetic waves and other physical phenomena. Here A is the amplitude, ω is the angular frequency, t is the spatial variable, and φ is the phase, which together determine the shape and position of the wave (WV). Finally, multiply it by the WV coefficient Wvxs to form the WV calculation formula.

[0110] The purpose of the design is to simulate the fluctuation (WV) phenomenon in the image or model to make it closer to the physical behavior in the real world. B is the baseline for adjusting the gray value, which can make the value after the fluctuation (WV) adapt to a specific gray range. The constant B is added to ensure that the gray value after the fluctuation (WV) does not exceed the range required for image processing, and it can also adjust the brightness of the image. Consider the influence of lighting: Radiation (x, y) represents the intensity of light or radiation at a specific position (x, y), which ultimately affects the gray value. So it defines a gray value, a function that changes with position, and uses a sine function to simulate the fluctuation (WV) of the gray value in the image. The amplitude coefficient A determines the range of grayscale value change, the angular frequency coefficient ω determines the frequency of grayscale value change, the phase offset coefficient φ determines the starting position of grayscale value change, and the vertical offset coefficient B determines the average grayscale value. Finally, multiply it by Radiation (x, y), the parameters of X-ray WV radiation to get the image grayscale value. In order to consider the influence of light or radiation in image processing, the grayscale value can reflect the lighting conditions on the surface of the object. It can be used for image enhancement to improve the contrast of the image or highlight certain features by adjusting the grayscale value. By combining the fluctuation (WV) mode and the radiation function, the visual effect of the image is enhanced to make it clearer or highlight specific details, and the X-ray WV initial grayscale source image is constructed.

[0111] 2. Formula combination design scheme for transforming initial grayscale source image into X-ray WV spectrum image

[0112] Converting the X-ray WV initial grayscale source image into an X-ray WVPP image is an important part of improving the quality of X-ray images. It can reveal the distribution of different frequency components in the image, make it easier to extract and analyze these features, and help discover the patterns and laws hidden in the initial grayscale source image. It can process noise more specifically, thereby improving the quality and clarity of X-ray PP images.

[0113] By analyzing and processing X-ray WVPP, more efficient image compression and encoding can be achieved, reducing the cost of data storage and transmission. X-ray WVPP features are more discriminative than initial grayscale features. After converting the WV initial grayscale source image to an X-ray WVPP image, more effective features can be extracted for classification and recognition, improving the accuracy and performance of the system. The method to achieve the transformation from X-ray WV grayscale source image to X-ray WVPP image is to use the WVA function formula combination analysis:

[0114] (1) WVA itself has excellent WVDZ resolution signal analysis capabilities. In the X-ray WV grayscale source image, the size, shape and texture feature signals of different structures vary greatly. Traditional transformations have limited effect in processing such non-stationary signals. WVA analyzes and processes the X-ray WV grayscale source image with X-ray WVDZ resolution data. According to the X-ray WV propagation characteristics and spatial fluctuations, it decomposes different sub-WV frequencies and analyzes and processes each level of X-ray WV signals one by one. It can effectively capture the edge and texture signals of the lesion area and the specific features of the image, and effectively process them, which exceeds the traditional transformation processing. Through the formula operation of the X-ray WV grayscale source image and the X-ray image WVDZ resolution, the WVA function formula is formed to design the prefix of the X-ray WVPP image. The specific method of designing the operation is:

[0115] X-ray image WVDZ resolution expression:

[0116] Resolution = C*(λ / d) f*(x,y)*Gray_Value*Wvxs,

[0117] Where: Resolution represents resolution. C is a constant that adjusts and calibrates the ratio of the entire formula to ensure that the calculation result is within a reasonable range. λ is the wavelength of the X-ray. d is the spacing of the detector or the related physical size. This ratio reflects to some extent the impact of the basic physical characteristics of X-ray propagation and detection on the WV resolution. f(x,y) is a function related to the image position (x,y), which means that the WVDZ resolution may vary at different positions in the image. It takes into account the impact of spatial position factors on the WVDZ resolution. Gray_Value represents the gray value of the image. It is closely related to the WVDZ resolution and can reflect the impact of image characteristics such as brightness and contrast on the resolution. The entire formula shows that the final resolution is determined by a constant C, the ratio of the wavelength of the X-ray to the spacing of the detector, the position-related function f(x,y) and the image gray value Gray_Value. Wvxs is a WV parameter variable, and its specific meaning depends on the specific application and background.

[0118] How to calculate the DZ resolution of an X-ray image. The resolution is affected by a combination of factors. The X-ray wavelength (λ) and the distance parameter (d) determine the basic characteristics of X-ray propagation and imaging. The constant C is used to adjust the overall proportional relationship. The function f(x,y) takes into account the specific properties of different positions in the image, so that the resolution can be adjusted according to the change in spatial position. Gray value (Gray_Value) reflects the brightness information of the image and also contributes to the resolution. Wvxs represents specific factors related to the X-ray WV, which further affects the calculation results of DZ resolution.

[0119] Specific algorithm: Determine the specific values ​​or expressions of each parameter and variable: Determine the value of constant C. Measure the value of the wavelength λ and distance or size parameter d of the given X-ray. Determine the specific form and calculation method of the function f(x,y). Obtain the gray value Gray_Value of the corresponding position in the image. Determine the value of Wvxs.

[0120] Calculate the value of λ / d. Calculate the value of the function f(x,y) at the given coordinates (x,y). Multiply the values ​​of C, λ / d, f(x,y), Gray_Value, and Wvxs to get the value of Resolution.

[0121] That is: Resolution = C×(λ / d)×f(x,y)×Gray_Value× Wvxs. Make sure the units of λ and d match to get the correct λ / d value. Function calculation accuracy: For the calculation of f(x,y), it is necessary to accurately calculate according to its definition and the given coordinates. Reasonableness of parameter values: The values ​​of each given parameter must be consistent with the actual physical meaning and the background of the problem. Through the above calculation method, the value of resolution Resolution is calculated according to the given parameters and variables. Substitute the formula to calculate the resolution: Substitute all the determined parameters and variables into the formula to calculate the value of WVDZ resolution. Analysis and optimization: According to the calculation results, analyze which factors have a greater impact on the resolution, so as to take corresponding measures to optimize the imaging system or image processing method to improve the DZ resolution.

[0122] In medical X-ray imaging, the image WVDZ resolution is optimized by adjusting the wavelength (λ) of the X-ray and the distance from the detector to the patient (d) to convert it into WVPP to extract different frequency features in the image. This helps to gain a deeper understanding of the details, textures, and structural information in the image, providing more targeted features for subsequent WVPP image analysis and processing, and better providing high-definition, clear, and detailed images for image processing, analysis, diagnosis, and research.

[0123] A variety of factors are considered to describe the WVDZ resolution of X-ray images, so as to more accurately describe the changes in X-ray image resolutions from multiple angles and form an X-ray WVPP image building framework.

[0124] (2) Transforming the X-ray WVDZ resolution into the X-ray WVPP can reveal the X-ray frequency characteristics and energy distribution in more depth. It helps to understand the intensity and variation of X-rays at different frequencies and the X-ray absorption and scattering characteristics of different substances. Transforming into WVPP images also helps to more accurately analyze the pixels, structure and properties of the patient's body image, remove noise, enhance useful information, and thus improve the quality level and clarity of the X-ray image.

[0125] The X-ray WV initial grayscale source image is transformed into an X-ray WVPP image. After the X-ray WVDZ resolution is processed, the X-ray WVPP image transformation processing operation is performed more efficiently in the frequency domain than in the spatial domain, forming the ability to efficiently process X-ray WVPP images. The specific design method is:

[0126] X-ray WVPP image transformation expression:

[0127] Spectral_Image(f) = ∫∫[Resolution +…

[0128] +Resolution (x,y)exp(−2πifx)]dxdy*Wvxs,

[0129] Where Resolution + ... +Resolution (x,y) represents the summation of all N WV resolution functions. These functions are evaluated at their respective (x,y) locations and multiplied by the WV transform kernel. ∫∫ represents a double integration over the entire image space (x and y directions). This means that the WVDZ resolution information (after the WV transform) at each point in the image is accumulated to obtain a representation of the WVPP image at a specific frequency f. This contains multiple WVDZ resolution contributions, and both x and y need to be transformed, depending on the dimensionality of the image being processed and the type of transform required. The WVDZ resolution is usually related to the clarity and detail of the image. Spectral_Image(f ) represents the WVPP image at frequency f. This result describes the distribution of the image in the frequency domain, reflecting the frequency content of the image. exp(−2πifx), which is a complex exponential function, is used to convert spatial information into frequency information. Here f is the frequency and x is the spatial coordinate. The function of this term is to modulate the signal in the spatial domain so that the information of a specific frequency can be extracted by integration. dxdy, which represents the double integration of the spatial coordinates x and y, is used to calculate the frequency components in the entire image area. ∫∫, represents the double integration of the entire image space (x and y directions). This means that the WVDZ resolution information of each point in the image is accumulated to obtain the representation of the WVPP image at a specific frequency f.

[0130] The WVPP image is a representation of image data in the frequency domain. It reveals the distribution of different frequency components in the image (such as color, texture, edge, etc.). WVPP image analysis allows the frequency components in the image, which is very useful for understanding the characteristics of the image such as texture, edge, color, etc.

[0131] Different WVDZ resolution functions can more accurately describe the clarity of X-ray images in different areas or conditions. Combining these WVDZ resolution functions with WVPP, these WVPP characteristics can be analyzed in the frequency domain. By summing and integrating, all WVDZ resolution information (representation in the frequency domain) in the image is combined to form a WVPP image. This method facilitates comparison and verification: WVPP images with WVDZ resolution can be compared and verified with each other, increasing the reliability and stability of the results, providing an overall view of the WV image at different WV frequencies, and presenting a high-definition X-ray WVPP image.

[0132] Specific algorithm: Determine the expression or value related to resolution. Clarify the value of frequency f. Determine the range of integration, that is, the range of values ​​of x and y. For each pair of (x,y) coordinates within the integration range: calculate the value of Resolution (x,y)exp(−2πifx). If there are multiple Resolution terms, add them together. For each calculated value, multiply it by the corresponding small area dxdy. Accumulate all these products over the entire integration range to get the result of the integration. Multiply the integration result by Wvxs to get the final value of Spectral_Image(f ).

[0133] Select appropriate numerical integration methods (such as rectangular method, trapezoidal method, etc.) according to the specific situation for accurate symbolic integration. When calculating the exponential function, pay attention to the stability of the numerical value to avoid numerical overflow or loss of precision. Parameter accuracy: Make sure that the input frequency f, resolution-related parameters, and integration range are accurate. Through the above calculation method scheme, the value of the WVPP image Spectral_Image(f) at a given frequency f can be calculated step by step.

[0134] 3. Function formula combination design scheme for X-ray WVRH image conversion

[0135] Converting X-ray WVPP images into WVRH images can more clearly display detailed information such as fine structures, lesion edges and bone textures in X-ray images; enhance details and edge information to reduce uncertainty and the possibility of misjudgment in diagnosis; increase image contrast to make the differences between different tissues and structures more obvious; reduce X-ray image blurring caused by various factors to a certain extent, making X-ray images more clear and truly reflecting the detected situation, facilitating observation and interpretation of images, reducing visual fatigue and improving diagnostic efficiency.

[0136] Using the WVA function formula to convert X-ray WVPP images into X-ray WVRH images can also help improve the quality and effectiveness of medical diagnosis and provide a more accurate basis for patient treatment. The method to achieve the conversion is to use the WVA function formula combination analysis:

[0137] (1) Through the X-ray WVNX engineering function formula operation, the X-ray WVPP image is converted and reconstructed into the WVRH image in the spatial domain, so that the color image can be better produced in the next step. When the relevant data is input into the WVNX engineering in the X-ray WV frequency domain, it depends on the specific X-ray application scenario and the parameters of the X-ray WVPP image to operate in the WVA function formula to form a waveform data that matches the spatial domain and frequency domain, so as to achieve the purpose of converting the X-ray WVPP image into the X-ray WVRH image, so as to obtain the best X-ray WVRH image effect. The specific method of designing the operation is:

[0138] X-ray image WVNX engineering expression:

[0139] Reconstructed_Image(x,y) =Inverse_Trans form [Fourier_Spectrum_Image(x,y)]+

[0140] Regularization_Term*Spectral_Image(f )*Wvxs,

[0141] Where: Reconstructed_Image(x, y) is the value of the X-ray image reconstructed by the WVNX project at the coordinate (x, y), and the reconstructed WVRH image.

[0142] Inverse_Transform[Fourier_Spectrum_Image(x, y)] represents the result of the inverse transform operation on the X-ray WVPP image. Spectral_Image(f) represents the WVPP image at frequency f. Wvxs is the WV coefficient. Regularization_Term is the regularization term used to control the reconstruction process. It is a constant parameter related to the image. Spectral_Image(f) is the WVPP image related to frequency f, which represents a certain feature of the image in the frequency domain. Wvxs is a WV coefficient, variable or function, and its specific meaning depends on the application scenario.

[0143] Specific algorithm: First, obtain or calculate the following Fourier_Spectrum_Image(x,y):

[0144] Fourier_Spectrum_Image(x,y): The original transformed WVPP image data, obtained by transforming the original image. Determine the value of Regularization_Term, constants or parameters determined by the optimization algorithm. Obtain Spectral_Image(f), and obtain the WVPP image and characteristic image associated with frequency f. Clarify the value of Wvxs and the calculation method.

[0145] Execute the WVNX project: Use the algorithm function to inverse transform Fourier_Spectrum_Image(x,y) to get Inverse_Transform [Fourier_Spectrum_Image(x,y)]. Calculate the product term: Multiply Regularization_Term, Spectral_Image(f) and Wvxs to get Regularization_Term *Spectral_Image(f) * Wvxs.

[0146] Sum to get the reconstructed image: Add the result of the inverse transform to the above product term, that is, Reconstructed_Image(x,y)=Inverse_Transform[Fourier_Spectrum_Image(x,y)] + Regularization_Term *Spectral_Image(f ) * Wvxs, to get the reconstructed image value at the coordinate (x,y). Data type and precision: During the calculation process, pay attention to the type of data (such as floating point precision) to avoid precision loss or calculation errors. Computational efficiency: Inverse transform and multiplication operations are computationally intensive. Choose efficient algorithms and tools to perform calculations to improve computational efficiency.

[0147] Parameter adjustment: The value of Regularization_Term is adjusted through experiments or based on specific optimization goals to obtain the best reconstruction effect. Understanding of frequency and WVPP: Understanding and correct use of Spectral_Image(f), and understanding the relationship between its frequency characteristics and the reconstructed image. Through the above calculation method, the WVPP image can be gradually calculated according to the given X-ray image WVNX engineering formula to obtain the reconstructed X-ray WVRH image effect.

[0148] (2) After the X-ray WVPP image is converted to the X-ray WVRH image through the WVNX project, the image details and edge information are restored. This makes the details that may not be clear become more obvious, which helps to better observe and analyze the subtle features in the image. Improve the image clarity, reduce or eliminate the blurriness of the image, and make the X-ray WVRH image look clearer and sharper, thereby improving the quality and readability of the image. Highlight and enhance the physical features of the patient being examined by X-ray, making them easier to detect and identify. Increase the contrast between different areas in the image, making the differences between different parts more significant, compensating for the defects of the imaging system, and restoring or enhancing the original features of the image.

[0149] Controlling the intensity of the WVRH image effect, when the WVPP image is converted to the WVRH image through the WVNX project, the operation and processing control of the intensity of the WVRH image effect is an important factor in X-ray image processing. It directly affects the quality and usability of the image. Adjust the WVRH parameters, increase the WVRH intensity, and balance WVRH with noise reduction: effectively control the intensity of the WVRH image effect to achieve the best visual effect and meet specific application requirements. The specific method of designing the operation is:

[0150] X-ray WVRH image effect intensity expression:

[0151] Sharpening_Intensity = k*(Max_Edge_Gradient - Min_Edge_Gradient)

[0152] *Reconstructed_Image(x,y)*Wvxs,

[0153] Where: Sharpening_Intensity represents the intensity of the effect in the WVRH image. k is a proportional constant used to adjust the measurement scale of the intensity. Max_Edge_Gradient is the maximum value of the edge gradient in the WVRH image. Min_Edge_Gradient is the minimum value of the edge gradient in the WVRH image.

[0154] Sharpening_Intensity, represents the effect intensity of the X-ray WVRH image. K, is a proportional coefficient used to adjust the intensity scaling. Max_Edge_Gradient, represents the maximum value of the edge gradient in the WVRH image, reflecting the part of the image with the most dramatic edge changes. Min_Edge_Gradient, represents the minimum value of the edge gradient in the WVRH image, and together with the maximum value, reflects the range of the edge gradient.

[0155] (Max_Edge_Gradient -Min_Edge_Gradient), this part calculates the range of edge gradients, reflecting the magnitude of edge changes in the image. Reconstructed_Image(x,y), is the value of the reconstructed X-ray image at coordinates (x,y), which participates in the calculation to consider the entire WVRH image information. Wvxs, is a parameter related to WV weights, coefficients and WVRH, and its meaning depends on the specific application.

[0156] The meaning of the whole formula is to comprehensively measure the effect intensity of the X-ray WVRH image by calculating the range of edge gradients, multiplying it by the value of the reconstructed image at a specific coordinate and the WV parameter Wvxs, and then multiplying it by the scale factor k. This means that the WVRH intensity depends not only on the range of edge gradient changes, but also on the local information and specific parameters of the reconstructed image.

[0157] Specific algorithm; determine the values ​​of related parameters and variables: determine the value of the proportional coefficient k, which is set based on experience, experiment or specific algorithm rules. Calculate or obtain the values ​​of Max_Edge_Gradient and Min_Edge_Gradient, which need to be obtained by edge detection and gradient calculation of the sharpened image. Know or calculate the value of the reconstructed X-ray image at the coordinate (x, y) Reconstructed_Image(x, y). Clear the value of Wvxs, which is the WV parameter.

[0158] Calculate the range of the edge gradient: calculate Max_Edge_Gradient - Min_Edge_Gradient. Calculate the intermediate product: multiply the result of step 1 by k to get k * (Max_Edge_Gradient - Min_Edge_Gradient). Calculate the final product: multiply the result of step 2 by Reconstructed_Image(x,y) and Wvxs, that is, Sharpening_Intensity = k* (Max_Edge_Gradient - Min_Edge_Gradient) * Reconstructed_Image(x,y) * Wvxs.

[0159] During the calculation process, pay attention to the data type and precision of each parameter and variable to avoid the influence of precision error on the result. Unit consistency: Make sure that the units of edge gradient, image value and other parameters are consistent in the calculation, or perform necessary unit conversion. When selecting the appropriate k value and determining the value of Wvxs, it is necessary to find the optimal value through experimentation and adjustment based on the expected and actual needs of the image sharpening effect. Through the above calculation methods and schemes, the intensity Sharpening_Intensity of the X-ray WVRH image can be calculated according to the given parameters and variables.

[0160] Through the combined analytical operation of the WVA function formula, the X-ray WVPP image is converted into the X-ray WVRH image, so that the X-ray image achieves the best visual effect.

[0161] 4. Function formula combination design scheme for constructing X-ray WV three-dimensional images

[0162] The use of WVA can enhance the imaging capability of the soft tissues of the patient's body being irradiated, and construct the X-ray WV three-dimensional image based on the X-ray WVRH two-dimensional image. General X-ray machines are mainly suitable for imaging the patient's bones and other high-density tissue structures, and usually produce two-dimensional images. The detection and resolution imaging capabilities of the patient's soft tissues such as muscles and internal organs are relatively weak. In order to obtain more comprehensive diagnostic information, other types of imaging examinations have to be used, such as ultrasound, CT scans or MRI.

[0163] With WVA, the image quality can be improved by simulating the propagation of light waves in the medium. It is particularly suitable for the enhanced processing of soft tissue imaging of patients by X-ray machines, reducing the blur and scattering of images, making the details of patients' soft tissues clearer. Therefore, this algorithm can make the boundaries between different soft tissues of patients more prominent, and is more helpful to accurately identify and distinguish the stereoscopic images of various soft tissues of patients, forming X-ray WV three-dimensional images. The calculation method is to use the WVA function formula combination analysis:

[0164] (1) In the detection and imaging of patient soft tissues, X-ray scattering is a common problem. WVA simulates the scattering process and corrects it by designing a function formula, using a more accurate mathematical model to construct an X-ray WV three-dimensional image, and optimizes the accuracy of patient soft tissue imaging. It also customizes the optimization parameters according to the characteristics of different types of patient soft tissues, and provides personalized solutions for different imaging needs. This further improves the three-dimensional effect of detection imaging. It better identifies and evaluates patient soft tissue lesions, such as tumors, inflammation, etc., so as to make a more accurate diagnosis. The specific method of designing the operation is:

[0165] X-ray WV soft tissue imaging intensity expression:

[0166] I(x,y) = S * t * exp(-∫μ(x,y)ds) +F[Wv_Signal(x,y)] +

[0167] (Noise_Component)*Sharpening_Intensity *Wvxs,

[0168] Among them, ∫μ(x,y)ds represents the integration of the attenuation coefficient along the path of the X-ray passing through the tissue. F is a function related to the WV transformation, and Wv_Signal(x,y) is the X-ray wave signal.

[0169] Noise_Component is the noise component to be considered. I(x,y) is the final imaging intensity of the X-ray WV soft tissue imaging at the coordinate (x,y). It is related to the wavelength λ of the X-ray, the attenuation coefficient of the tissue -∫μ(x,y), the exposure time t, and the sensitivity S of the detector. S is the sensitivity of the detector, which indicates the detector's ability to respond to X-rays. Sharpening_Intensity is the intensity of the X-ray WVRH image, which is used to adjust the clarity and details of the image. S is the sensitivity of the detector, which indicates the detector's ability to respond to X-rays. t is the exposure time, that is, the duration of X-ray irradiation. exp(-∫μ(x,y)ds): This part is related to the attenuation of X-rays by tissues. μ(x,y) is the attenuation coefficient of the tissue at the coordinate (x,y). It is integrated along the path of the X-ray passing through the tissue, and then the negative value of the exponent is taken, which reflects the attenuation of the X-ray after passing through the tissue.

[0170] F[Wv_Signal(x,y)]: is the result of a function operation on the X-ray WV signal wv_Signal(x,y), which may be used to extract or process features related to vibration. Noise_Component: represents the noise component, which may come from the imaging system, environment, etc. Wvxs: is a specific coefficient, weight or parameter.

[0171] The entire formula takes into account the characteristics of the detector (S and t), tissue attenuation (exp(-∫μ(x,y)ds), WV signal processing (F[Wv_Signal(x,y)]), the impact of noise (Noise_Component), WVRH image effect (Sharpening_Intensity) and specific parameters Wvxs to calculate the intensity of X-ray WV soft tissue imaging at a specific coordinate (x,y).

[0172] Specific calculation method: Determine the values ​​of various parameters and variables: Clarify the specific values ​​of the detector sensitivity S and the exposure time t. Calculate the attenuation coefficient μ(x,y) of the tissue at the coordinate (x,y) and perform the path integral ∫μ(x,y)ds. The vibration signal Wv_Signal(x,y) is known or calculated. Determine the values ​​of the noise component Noise_Component, the WVRH intensity Sharpening_Intensity and the parameter Wvxs. Determine the specific form of the function F. Calculate the exponential term: Calculate exp(-∫μ(x,y)ds). Calculate the first term: Multiply S, t and the exponential term obtained in step 1, that is, S * t * exp(-∫μ(x,y)ds). Calculate the function term: Apply function F to the WV signal Wv_Signal(x,y) to obtain F[Wv_Signal(x,y)]. Calculate the product term: Multiply Noise_Component, Sharpening_Intensity, and Wvxs to get (Noise_Component) *Sharpening_Intensity * Wvxs. Calculate the final result: Add the result from step 2, the result from step 3, and the result from step 4, that is, I(x,y) = S * t * exp(-∫μ(x,y)ds)+F[WV_Signal(x,y)]+(Noise_Component)* Sharpening_Intensity * Wvxs.

[0173] In the calculation process, especially when exponential and integral operations are involved, attention should be paid to numerical precision to avoid the accumulation of rounding errors. Function calculation accuracy: Ensure that the calculation of function F is accurate and consistent with its definition and expected behavior. Parameter rationality: The values ​​of the given parameters should be within a reasonable physical and mathematical range to ensure the validity and rationality of the calculation results.

[0174] Through the above calculation steps, the X-ray WV soft tissue imaging intensity I(x,y) at the coordinate (x,y) can be calculated according to the given parameters and variables. The optimal stereo value can be found through experiments and adjustments. Through the above calculation methods and schemes, the X-ray WV three-dimensional image can be calculated according to the given parameters and variables.

[0175] (2) X-ray WV three-dimensional imaging is to obtain X-ray radiation images from multiple different angles, and then use WVA to process and reconstruct these images to generate a WV three-dimensional model of the patient's body. It can provide detailed information on the three-dimensional structure of the soft tissue inside the patient's body in the WV three-dimensional space, and can accurately observe and diagnose the shape, size, position and relationship of the lesion site with surrounding tissues from different angles and three-dimensional sections, which helps to diagnose the disease more accurately. The specific method of designing the operation is:

[0176] X-ray WV three-dimensional image expression:

[0177] I(x, y, z) = S*t*exp (-∫∫∫ μ(x, y, z, k)*Δl) dxdydz+

[0178] F (W v) G [∫∫∫Wv_Signal(x, y, z) dxdydz]*I(x,y)*Wvxs,

[0179] Where: (x, y,z,k) is a discrete point in three-dimensional space. Δl is a small length increment along the X-ray propagation path. G is a specific function. This transformation is a linear transformation operation in image or signal processing, which converts the integrated result into another form of output. The integrated WV_Signal is enhanced, filtered, compressed, etc. to obtain a specific output result, which is used to process the integral result of the vibration signal and the attenuation coefficient. I(x,y) is the WV soft tissue imaging intensity. I(x, y, z) is the intensity of three-dimensional imaging, which is related to the wavelength λ of the X-ray, the attenuation coefficient μ (x, y,z, k) of the object in three-dimensional space, the exposure time t, the sensitivity S of the detector, and the final intensity of the WV imaging of the X-ray. S is the sensitivity of the detector, which reflects the detector's response characteristics to X-rays. t is the exposure time, that is, the duration of X-ray irradiation. exp (-∫∫∫ μ(x, y, z, k) * Δl) dxdydz, which involves the attenuation coefficient of the object at different positions (x, y, z) in three-dimensional space, μ is the integration along the X-ray propagation path. The exponential form represents the attenuation of the X-ray after passing through the object. F (W v) is a function operation related to wavelet variation. G [∫∫∫WV_Signal(x, y, z)dxdydz] is the result of integrating the wavelet signal of the X-ray in three-dimensional space and processing it through the function G. I(x,y) is the imaging intensity on the two-dimensional plane (x and y directions). Wvxs is a specific WV coefficient.

[0180] The entire formula takes into account factors such as detector characteristics, exposure time, object attenuation, wave vibration correlation processing, and two-dimensional imaging intensity to calculate the final intensity of X-ray WV imaging at the three-dimensional coordinates (x, y, z).

[0181] Specific calculation method: clarify the meaning and specific values ​​of various parameters and variables: determine the specific values ​​of detector sensitivity S and exposure time t. Understand the expression or numerical distribution of the attenuation coefficient μ(x, y, z, k), and determine the small length increment Δl. Clarify the specific form and calculation method of functions F (W v) and G. The values ​​of the two-dimensional imaging intensity I(x,y) and parameter Wvxs are known or calculated. Calculate the integral term: calculate ∫∫∫ μ(x, y, z, k) * Δl dxdydz, which requires the use of numerical integration methods. Calculate the exponential term: calculate exp (-∫∫∫ μ(x, y, z, k) * Δl dxdydz). Calculate the first term: multiply S, t and the exponential term obtained in step 2 to obtain S* t *exp (-∫∫∫ μ(x, y, z, k) * Δl dxdydz). Calculate the integral of the wave signal: Calculate step 3 ∫∫∫WV_Signal(x, y, z) dxdydz. Calculate the intermediate terms: Apply the function G to the result of step 4 to obtain G [∫∫∫WV_Signal(x, y, z) dxdydz]. Step 5 Multiply it with F (W v) to obtain F (W v) G [∫∫∫WV_Signal(x, y, z) dxdydz]. Calculate the product term: Step 6 Multiply I(x,y) and Wvxs to obtain I(x,y) * Wvxs. Calculate the final result: Add the result from step 3, the result from step 5, and the result from step 6 to obtain I(x, y, z) = S * t * exp (-∫∫∫ μ(x, y, z, k) * Δl dxdydz) + F(W v) G [∫∫∫WV_Signal(x, y, z) dxdydz]*I(x,y)*Wvxs.

[0182] When performing numerical calculations, especially integration and exponential operations, it is important to control numerical precision and avoid cumulative errors. Ensure that the implementation of functions F (W v) and G is correct and consistent with their definitions and expected functions. Integration method selection: Select appropriate numerical integration methods based on the characteristics of the problem and computing resources to ensure computational efficiency and accuracy. Data rationality: Check whether the input parameters and data are within a reasonable range to avoid unreasonable data leading to incorrect calculation results.

[0183] Through the above calculation method, the effect of obtaining a WV three-dimensional image by transforming the X-ray WV soft tissue imaging intensity is achieved.

[0184] Through the combined analytical operation of the WVA function formula, the X-ray WV soft tissue imaging intensity is iteratively reconstructed and transformed into an X-ray WV three-dimensional image based on the WVRH image, and the best three-dimensional effect is achieved.

[0185] 5. Function formula combination design scheme for producing X-ray WVHSV colored three-dimensional images

[0186] WVA can be used to convert X-ray WV three-dimensional images into WVHSV colored images, enhancing the specific analysis and visualization effects of the images. The following effects can be achieved by using the WVA function formula calculation:

[0187] A. Enhanced visualization: WVHSV color 3D space can convert X-ray WVRH 3D images into WVHSV color 3D images, helping radiologists to more easily distinguish different tissues and structures. B. Improved contrast: By adjusting WVHSV saturation and brightness, the contrast of the image can be enhanced, making subtle differences more obvious. C. Feature extraction: In WVHSV color 3D space, specific features can be identified and extracted based on hue and saturation to distinguish different types of tissues or lesions. D. Image segmentation: Converting X-ray WVMN 3D images into WVHSV color 3D images helps to automatically or semi-automatically segment the image and identify areas of interest. E. Robustness to illumination changes: Although not common in X-ray images, the robustness of WVHSV color 3D space to illumination changes can form consistent colors under different imaging conditions. F. Development of image processing and analysis algorithms: The characteristics of WVHSV color space can make WV image processing more effective.

[0188] (1) The production of WVHSV colored three-dimensional models can more intuitively distinguish different black and white levels, converting the black and white information of X-rays into color information that is easier for the human eye to recognize, and introducing an additional color information dimension. Color can be used to represent different physical properties (such as density, thickness, etc.) or different tissue types, providing more clues for image interpretation, thereby enhancing the visualization of the image, making it easier to observe and understand the structure and details in the image, and enhancing the visualization of X-ray WVHSV colored three-dimensional images. The specific method of designing the operation is:

[0189] X-ray WVHSV colored three-dimensional image expression:

[0190] HSV(x, y, z) = ((N - 1)*(360 / N) + (Wave_Value(x, y, z) - (N - 1)*W / N)*(360 / N)*I(x,y,z)*Wvxs,

[0191] abs(Wave_Value(x,y,z)-0.5*W) / M*I(x,y,z)*Wvxs,

[0192] Wave_Value(x, y, z) / W*I(x, y, z)*Wvxs),

[0193] After splitting, it becomes:

[0194] HSV(x) = (N - 1)*(360 / N) + (Wave_Value(x) - (N - 1)*W / N)*(360 / N)*I(x)*Wvxs,

[0195] HSV(y) = abs(Wave_Value(y)-0.5*W) / M*I(y)*Wvxs,

[0196] HSV(z)= Wave_Value(z) / W*I(z)*Wvxs。

[0197] Among them: HSV (x, y, z) is a three-dimensional vector, which represents the hue H, saturation S, and brightness V at the coordinates (x, y, z). Wave_Value (x, y, z) represents the X-ray wave vibration value at the coordinates (x, y, z). W is a constant, representing the maximum value of the X-ray wave vibration value, and is a specific value used for normalization. W is a specific value related to the X-ray WV, the maximum value, average value, etc. of WV. 0.5*W is half of W. First calculate the difference between Wave_Value (x, y, z) - 0.5*W, and then take its absolute value abs ( Wave_Value (x, y, z) - 0.5*W ) to get a non-negative value, which represents the deviation between the WV value and 0.5*W. M is another specific value that is a constant related to WV. Finally, divide the above deviation value by M, and the result is the saturation at the coordinate. The larger the value, the higher the saturation; the smaller the value, the lower the saturation. N is a parameter that determines the HSV (hue, saturation, brightness) value at the coordinate (x, y, z) through the interaction with other parameters (such as W, M) and the wave value (Wave_Value), the influence factor I (x, y, z) and the WV coefficient Wvxs. (Wave_Value (x, y, z) - (N - 1)*W / N) This part calculates the difference between the wave value (Wave_Value) and the value related to N and another parameter W. This difference is multiplied by (360 / N), then multiplied by the influence factor I (x, y, z) and the WV coefficient Wvxs, and finally added to the base value to get the hue value. Here N participates in determining the degree of influence of the wave value on the hue. Different N values ​​will result in different ranges and distributions of hue. Wvxs: It is a WV coefficient and variable function. Its specific meaning depends on the application scenario.

[0198] Specific calculation method: Calculate the hue H(x, y, z): First calculate (N - 1)*(360 / N). Then calculate (Wave_Value(x, y, z) - (N - 1)*W / N). Multiply the above result by (360 / N). Multiply it by I(x,y,z) and Wvxs. Finally, add the result of the first step to the above product to get the hue H(x, y, z). Calculate the saturation S(x, y,z): Calculate Wave_Value(x,y,z) - 0.5*W. Take its absolute value Abs (Wave_Value(x,y,z) - 0.5*W). Divide the absolute value by M. Multiply it by I(x,y,z) and Wvxs to get the saturation S(x, y, z). Calculate the lightness V(x, y, z): Calculate Wave_Value(x, y, z) / W. Multiply I(x, y, z) and Wvxs to get the lightness V(x, y, z). In the calculation process, you need to first determine the specific values ​​of the parameters N, W, M, I(x,y,z) and Wvxs. Then follow the above steps to calculate the values ​​of hue, saturation, and lightness, and finally get the HSV colored three-dimensional model value at the coordinate (x, y, z).

[0199] In the calculation process, it is necessary to determine the specific values ​​or calculation methods of W, M, N, I(x, y, z) and Wvxs in advance. At the same time, attention should be paid to the calculation accuracy and numerical range to ensure the accuracy and rationality of the results.

[0200] The result obtained by dividing the WV value at the coordinate (x, y, z) by W, M, N is used to represent the brightness, saturation, and hue of the location in the range of 0 to 1. The larger the ratio, the higher the value; the smaller the ratio, the lower the value. This calculation method converts the original X-ray WV value into a relative value for subsequent color processing and representation in the HSV color model.

[0201] After the combined analytical calculation of the WVA function formula, the X-ray WV three-dimensional image production and processing color component adjustment and the synthesis of multiple color images are formed to form a high-definition X-ray WVHSV colored three-dimensional image.

[0202] 6. Analysis of the function formula combination design for optimizing the production of X-ray WVYM colored three-dimensional images

[0203] WVYMM color 3D image optimization is the last important function formula to improve the quality of X-ray images. The WVYM color 3D image production optimization function formula with specific production is placed in the X-ray WVHSV color 3D image to form relevant codes, and then the real X-ray image is optimized and calculated from these codes. This technology breaks the sampling form of the corresponding scene and image in traditional imaging, and shifts the focus of imaging technology from hardware to algorithm.

[0204] The production optimization of X-ray WVYM colored three-dimensional images based on X-ray WVHSV colored three-dimensional images is the final image production of X-ray radiation imaging. It is a re-optimized image that realizes the complex amplitude of the radiation light wave field, and it is the frequency-scaling complexity of X-ray system imaging. When WVYM colored three-dimensional images are optimized to synthesize X-ray high-definition colored three-dimensional images, feature information at different scales is extracted to realize operations such as analysis, repair, enhancement, optimization or compression of the synthesized image. WV is decomposed into sub-bands of different frequencies, and the synthesized WVYM is reprocessed at different FB rates. When optimizing the processing of X-ray WVYM colored three-dimensional images, feature information such as details, edges, and textures in the synthesized X-ray high-definition colored three-dimensional images is further identified to realize the synthesis of X-ray high-definition colored three-dimensional images, making the X-ray images more perfect, clearer, and easier to diagnose.

[0205] (1) In X-ray digital imaging technology, the WVYM optimization calculation of X-ray WVHSV colored three-dimensional images is the final function formula to significantly improve image quality. Only by forming high-definition X-ray images can we ensure the clarity and accuracy of patient detection, diagnosis and evaluation results, so as to catch up with the detection and imaging level of CT. In general, the production of WVYM colored three-dimensional images based on X-ray WVHSV colored three-dimensional images is the final application of WVA X-ray imaging. It not only further improves the image quality, but also provides a guarantee for simplifying the design of the imaging system, which is of certain significance for promoting the development of X-ray digital imaging technology. The specific method of designing the operation is:

[0206] X-ray WVYM colored three-dimensional image production expression:

[0207] Color(x,y,z)=(k1*Wave_Value(x,y,z)*Mask_Value(x,y,z)+b1*V(x,y,z)*Wvxs,

[0208] k2*Wave_Value(x,y,z)*Mask_Value(x,y,z)+b2*V(x,y,z)*Wvxs,

[0209] k3*Wave_Value(x,y,z)*Mask_Value(x,y,z) + b3*V(x, y, z)*Wvxs),

[0210] In this combined formula, Color(x,y,z) is a three-dimensional vector representing the color at coordinates (x,y,z), whose three components correspond to the values ​​of the red, green, and blue channels, respectively.

[0211] Among them, k1, k2, k3 are scale factors, b1, b2, b3 are offsets used to adjust the range and brightness of the color channel. The WV value at the three-dimensional coordinate (x, y, z) is Wave_Value(x, y, z). The YM value is Mask_Value(x, y, z). The red, green, and blue channels of the image are represented by R (x, y, z), G (x, y, z), and B (x, y, z), respectively. H(x, y, z), S(x, y, z), and V(x, y, z)HSV are the three-dimensional values ​​of X-ray WVHSV color.

[0212] Wvxs: is the WV coefficient, variable function, which depends on the application scenario. It is used to calculate the color Color(x,y,z) at the three-dimensional coordinate (x,y,z). The color is represented as a triple, corresponding to the values ​​of the red, green and blue channels respectively. For the red channel: k1 is a coefficient related to the red channel. Wave_Value(x,y,z) is the WV value at this coordinate. Mask_Value(x,y,z) is the YM value at this coordinate. Their product Wave_Value(x,y,z)*Mask_Value(x,y,z) is adjusted by the coefficient k1. V(x,y,z) is some value at this coordinate (it may be brightness or other related values). Then K1*Wave_Value(x,y,z)*Mask_Value(x,y,z) is added to b1*V(x,y,z)*Wvxs to get the value of the red channel. For the green channel: similar to the red channel, except that the coefficients become k2 and b2. For the blue channel: the coefficients are k3 and b3. In summary, this formula calculates the red, green, and blue channel values ​​of the color at the three-dimensional coordinates (x, y, z) through the WV value, the YM value, a value V(x, y, z) related to the coordinates, and the coefficients and parameters.

[0213] Specific calculation method: First, we need to clarify the meaning of each variable and the given value: Wave_Value(x,y,z): WV value at coordinate (x,y,z). Mask_Value(x,y,z): YM value at coordinate (x,y,z). V(x,y,z): A certain value at coordinate (x,y,z). Wvxs: parameter coefficient. k1, k2, k3: Coefficients used to adjust the product of WV value and YM value in red, green, and blue channels, respectively. b1, b2, b3: Coefficients used to adjust the parts of red, green, and blue channels related to V(x,y,z).

[0214] Calculate the value of the red channel: k1*Wave_Value(x,y,z)*Mask_Value(x,y,z), which is the product of the WV value and the YM value adjusted by k1. Calculate b1*V(x,y,z)*Wvxs. Add the above two results to get the value of the red channel k1*Wave_Value(x,y,z)*Mask_Value(x,y,z) + b1*V(x,y,z)*Wvxs.

[0215] Calculate the value of the green channel: Just like the red channel, first calculate k2*Wave_Value(x,y,z)*Mask_Value(x,y,z). Calculate b2*V(x,y,z)*Wvxs. Add them together to get the value of the green channel k2*Wave_Value(x,y,z)*Mask_Value(x,y,z) + b2*V(x,y,z)*Wvxs.

[0216] Calculate the value of the blue channel: calculate k3*Wave_Value(x,y,z)*Mask_Value(x,y,z).

[0217] Calculate b3*V(x,y,z)*Wvxs. Add them together to get the value of the blue channel k3*Wave_Value(x,y,z)*Mask_Value(x,y,z) + b3*V(x,y,z)*Wvxs.

[0218] Finally, the calculated red, green, and blue channel values ​​are combined to form the color Color(x,y,z) at the coordinates (x,y,z).

[0219] (2) The optimization of X-ray WVYM colored three-dimensional images aims to improve the quality of X-ray images and perform specific image analysis. During the optimization process, the original light source is adjusted according to the optimal light source position information to obtain a pre-optimized light source, and a specific light intensity value is assigned to the light source point within a specific range in the pupil. During the optimization image enhancement process, exponential function filtering and detail image enhancement are used to optimize the WVYM colored three-dimensional image into an X-ray colored three-dimensional high-definition image, which greatly improves the quality of the X-ray image.

[0220] X-ray WVYM image optimization expression:

[0221] Opt_Color(x,y,z)=(a1*Wave_R(x,y,z)*Mask_R(x,y,z)+b1*(Wave_R(x,y,z)+Mask_R(x,y,z))+c1*Wave_R(x,y,z)^2+d1*Mask_R(x,y,z)^2+e1,

[0222] a2*Wave_G(x,y,z) *Mask_G(x, y, z)+b2*(Wave_G(x,y,z)+Mask_G(x,y,z))+c2*Wave_G(x,y,z)^2+d2* Mask_G(x,y,z)^2+e2,

[0223] a3*Wave_B(x,y,z)*Mask_B(x,y,z)+b3*(Wave_B(x,y,z)+ Mask_B(x,y,z))+c3*Wave_B(x, y, z)^2+d3*Mask_B(x,y,z)^2+e3),

[0224] Calculates the WVYM optimized color value Opt_Color at the three-dimensional coordinate (x, y, z).

[0225] The color value consists of three channels: red (R), green (G), and blue (B).

[0226] For the red channel Opt_R: a1*Wave_R(x,y,z)*Mask_R(x,y,z) means the product of the red channel value Wave_R of the X-ray WV image and the red channel value Mask_R of the WVYM image multiplied by the coefficient a1.

[0227] b1*(Wave_R(x,y,z) + Mask_R(x,y,z)) means the sum of Wave_R and Mask_R multiplied by the coefficient b1.

[0228] c1*Wave_R(x,y,z)^2 means Wave_R squared multiplied by the coefficient c1.

[0229] d1*Mask_R(x,y,z)^2 means the square of Mask_R multiplied by the coefficient d1. Finally, add the constant e1.

[0230] For the green channel Opt_G, the calculation method is similar to that of the red channel, except that the coefficients are a2, b2, c2, d2, and the constant is e2. For the blue channel Opt_B, the calculation method is similar to the first two channels, with coefficients a3, b3, c3, d3, and the constant is e3. Combining the calculation results of the three channels, the color value Opt_Color optimized by WVYN is obtained at the coordinate (x, y, z).

[0231] Specific calculation method: First, clarify the input variables: Wave_R(x,y,z): the red channel value of the X-ray WV image at the coordinate (x,y,z). Mask_R(x,y,z): the red channel value of the YM image at the coordinate (x,y,z). Wave_G(x,y,z) and Mask_G(x,y,z) are the values ​​of the green channel, Wave_B(x,y,z) and Mask_B(x,y,z) are the values ​​of the blue channel. Calculate the optimized red channel value of WVYM Opt_R(x,y,z): Calculate a1*Wave_R(x,y,z)*Mask_R(x,y,z), which is the product of the WV red channel value and the YM red channel value multiplied by the coefficient a1. Calculate b1*(Wave_R(x,y,z)+Mask_R(x,y,z)), which is the sum of the WV red channel value and the YM red channel value multiplied by the coefficient b1. Calculate c1*Wave_R(x,y,z)^2, which is the square of the red channel value of WV multiplied by the coefficient c1. Calculate d1*Mask_R(x,y,z)^2, which is the square of the red channel value of YM multiplied by the coefficient d1. Add the above four calculation results, plus the constant e1, to get Opt_R(x,y,z).

[0232] Calculate the green channel value Opt_G(x,y,z) after WVYM optimization: In a similar way to the red channel, calculate a2*Wave_G(x,y,z)*Mask_G(x,y,z), b2*(Wave_G(x,y,z)+Mask_G(x,y,z)), c2*Wave_G(x,y,z)^2, and D2*Mask_G(x,y,z)^2 respectively.

[0233] Add these four results, plus the constant e2, to get Opt_G(x,y,z). Calculate the optimized blue channel value Opt_B(x,y,z): Follow similar steps to calculate a3*Wave_B(x,y,z)*Mask_B(x,y,z), b3*(Wave_B(x,y,z)+Mask_B(x,y,z)), c3*Wave_B(x,y,z)^2, d3*Mask_B(x,y,z)^2. Add these four results, plus the constant e3, to get Opt_B(x,y,z). Finally, combine the calculated Opt_R(x,y,z), Opt_G(x,y,z), and Opt_B(x,y,z) to form the optimized color Opt_Color(x,y,z) of the X-ray WVYM colored three-dimensional image.

[0234] The above combined analytical calculations of the WVA function formula realize the optimization of the WVYM colored three-dimensional image, and play an important role in forming the high-definition of the entire X-ray image.

[0235] Finally, after the combined operation of the WVA function formula, the production optimization of the X-ray WV colored three-dimensional high-definition image is completed, making it close to and reach the imaging level of the CT machine.

[0236] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modification, equivalent substitution or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A wave vibration algorithm for improving the quality level of X-ray machine images, characterized in that: The following steps are involved: Step S1: preliminary WVA calculation, based on the parameter information of the X-ray machine irradiating the patient's body, using the WVA function formula to construct the WV initial grayscale source image of the X-ray machine irradiating the patient's body; Step S2: Preliminary image quality processing: using a combination of related WVA function formulas to perform WVA operations on the WV initial grayscale source image, and converting the WV initial grayscale source image into a WVPP image; Step S3: mid-term WVA operation, designing the first WVA function formula to form a combination, processing the WVPP image, and changing the two-dimensional image into a simulated three-dimensional image, converting the WVPP image into a WVRH image, and highlighting the edge and detail information of the image; Step S4: image color analysis and enhancement, using a combination of WVA function formulas to process the WVRH image and convert it into a WVHSV color image, making the color of the region significant and clear, and improving image color analysis and feature enhancement; Step S5: Post-WVA operation, using the second WVA function formula combination, performs subsequent WVYM image optimization and modification processing on the WVHSV color image to form an X-ray WV image; Step S6: forming an X-ray WV three-dimensional image, by acquiring X-ray radiation images from multiple angles, processing the images using a combination of WVA function formulas, and performing stereoscopic reconstruction of the X-ray WV three-dimensional image; Step S7: Create a WVHSV colored three-dimensional image, use a WVA function formula combination to process the X-ray WV three-dimensional image, and convert it into a WVHSV colored three-dimensional image.

2. The wave vibration algorithm for improving the image quality level of an X-ray machine according to claim 1, characterized in that: The construction of the WV initial grayscale source image of the X-ray machine irradiating the patient's body in step S1 is achieved by: Step S11: Establishing a radiation expression, based on the X-ray radiation principle, establishing an X-ray image WV radiation expression; Step S12: measurement and calculation, according to the material properties of the patient's body, measure or query the absorption coefficient of each point, determine the material thickness of each point through the measured value or known structure, and determine the initial radiation intensity or reference intensity and information parameters related to the patient's body according to the WVA theory and radiation data; Step S13: Calculate the radiation amount of each coordinate point according to the radiation expression established in step S11; Step S14: converting the calculated radiation amount into a grayscale value in the image.

3. The wave vibration algorithm for improving the image quality level of an X-ray machine according to claim 2, characterized in that: The radiation expression in step S11 is: Radiation(x,y)=D*p(-E*Absorption_Coefficient(x,y) * Thickness(x, y)) *Wvxs, Where: Radiation(x,y) is the X-ray radiation intensity at the coordinate (x,y), D is the WV radiation intensity or reference intensity of the digital X-ray machine to the patient's body, E is the information coefficient related to the patient's body, Absorption_Coefficient(x,y) is the radiation absorption coefficient of the patient's body to X-ray at the coordinate (x,y), Thickness(x,y) is the thickness of the X-ray passing through the patient's body at the positioning coordinate (x,y), Wvxs is the WV parameter or variable, p is the specific physical process of radiation, signal propagation or image processing operation function; The conversion formula in step S14 is: Gray_Value = (A*sin(ω*t + φ)+B)* Radiation(x,y)* Wvxs, Where Gray_Value is the gray value, A is the amplitude coefficient, B is the gray offset, Radiation(x, y) is the radiation intensity function, Wvxs is the WV parameter or variable, t is the spatial variable, ω is the angular frequency, and φ is the initial phase.

4. The wave vibration algorithm for improving the image quality level of an X-ray machine according to claim 1, characterized in that: The preliminary image quality processing in step S2 is achieved by: Step S21: Based on the physical characteristics of the X-ray image, establish the WVDZ resolution expression of the X-ray image: Resolution = C*(λ / d) f*(x,y)*Gray_Value*Wvxs, Where C is a constant, λ is the wavelength of X-rays, d is the spacing of the detectors or related physical dimensions, f(x,y) is the image position function, Gray_Value is the gray value of the image, and Wvxs is the WV parameter or variable; Step S22: Calculate the WVDZ resolution, determine the constant C, the X-ray wavelength λ and the detector spacing d, and obtain the gray value of each pixel from the X-ray WV initial gray source image, and use the formula in step S21 to calculate the WVDZ resolution of each coordinate point; Step S23: Convert the WVDZ resolution into a WVPP image.

5. The wave vibration algorithm for improving the image quality level of an X-ray machine according to claim 4, characterized in that: The conversion formula in step S23 is: Spectral_Image(f) = ∫∫[Resolution +…+Resolution (x,y)exp(−2πifx)]dxdy*Wvxs, where Spectral_Image(f ) is the WVPP image at frequency f, Resolution + ... +Resolution (x,y) represents the sum of all N WV resolution functions, exp(−2πifx) is the function that converts spatial information into frequency information, ∫∫ is the double integration of the entire image space, dxdy is the tiny area, and Wvxs is the WV parameter or variable.

6. The wave vibration algorithm for improving the image quality level of an X-ray machine according to claim 1, characterized in that: The mid-term WVA calculation in step S3 is implemented in the following manner: Step S31: Based on the physical characteristics of the X-ray image and the WVNX project, establish the X-ray image WVNX project expression: Reconstructed_Image(x,y) =Inverse_Trans form [Fourier_Spectrum_Image(x,y)]+Regularization_Term*Spectral_Image(f )*Wvxs, Where Reconstructed_Image(x, y) is the value of the X-ray image reconstructed by the WVNX project at the coordinate (x, y), and the reconstructed WVRH image; Inverse_Transform[Fourier_Spectrum_Image(x, y)] is the result of the inverse transform operation on the X-ray WVPP image, Regularization_Term is the regularization term, which is an image parameter, Spectral_Image(f) is the WVPP image at frequency f, and Wvxs is the WV parameter or variable; Step S32: obtaining input data, executing the WVNX project, inputting data, performing an inverse transformation operation, calculating a product term, and then adding the inverse transformation result and the product term to obtain reconstructed image data; Step S33: Calculate the WVRH image effect strength, and perform image processing and optimization to highlight the edge and detail information of the image.

7. The wave vibration algorithm for improving the image quality level of an X-ray machine according to claim 1, characterized in that: The conversion of the WVRH image into a WVHSV color image in step S4 is achieved by: Step S41: Based on the physical characteristics of the X-ray image, establish an X-ray WV soft tissue imaging intensity expression. I(x,y) = S * t * exp(-∫μ(x,y)ds) +F[Wv_Signal(x,y)]+(Noise_Component)*Sharpening_Intensity *Wvxs, Where: S is the sensitivity of the detector, t is the exposure time, ∫μ(x,y)ds is the integration of the attenuation coefficient along the path of the X-ray passing through the tissue, F is the WV transformation function, Wv_Signal(x,y) is the X-ray wave vibration signal, Noise_Component is the noise component, Sharpening_Intensity is the intensity of the X-ray WVRH image, and Wvxs is a WV parameter or variable; Step S42: By acquiring X-ray radiation images from multiple different angles, the X-ray WV three-dimensional image expression is: I(x, y, z) = S*t*exp (-∫∫∫ μ(x, y, z, k)*Δl) dxdydz+ F (W v) G [∫∫∫Wv_Signal(x, y, z) dxdydz]*I(x,y)*Wvxs; Where S is the sensitivity of the detector, t is the exposure time, (x, y, z, k) is a discrete point in three-dimensional space, Δl is a small length increment along the X-ray propagation path, F (Wv) is the wave function, G is the transformation function of the signal after integrating WV_Signal(x, y, z) in three-dimensional space, ∫∫∫WV_Signal(x, y, z)dxdydz is the integration of the X-ray wave signal in three-dimensional space, and Wvxs is the WV parameter or variable.

8. The wave vibration algorithm for improving the image quality level of an X-ray machine according to claim 7, characterized in that: The subsequent WVYM image optimization and modification processing of the WVHSV color image in step S5 is as follows: The new dimension of color is introduced to enhance the X-ray WVHSV colored three-dimensional image. The expression of X-ray WVHSV colored three-dimensional image is: HSV(x, y, z) = ((N - 1)*(360 / N) + (Wave_Value(x, y, z) - (N - 1)*W / N)*(360 / N)*I(x,y,z)*Wvxs,abs(Wave_Value(x,y,z)-0.5*W) / M*I(x,y, z)*Wvxs,Wave_Value(x, y, z) / W*I(x, y, z)*Wvxs), Where N is the number of tone segments, Wave_Value(x, y, z) is the X-ray wave value at the coordinate (x, y, z), I(x, y, z) is the intensity of three-dimensional imaging, W is the maximum value of the X-ray wave value, abs is the absolute value, and Wvxs is the WV parameter or variable.

9. The wave vibration algorithm for improving the image quality level of an X-ray machine according to claim 8, characterized in that: The stereoscopic reconstruction of the X-ray WV three-dimensional image in step S6 is: Step S61: Calculate each channel value, respectively calculate the red channel value, the green channel value and the blue channel value; Step S62: combining color values, combining the calculated red channel value, green channel value and blue channel value to form the color at the coordinate (x, y, z); Step S63: Repeat the calculation and processing for each pixel in the image, and repeat the process of steps S61 and S62 until the entire image is processed and an X-ray WV three-dimensional image is established.

10. The wave vibration algorithm for improving the image quality level of an X-ray machine according to claim 9, characterized in that: The colored three-dimensional image converted into WVHSV in step S7 is: Step S71: Acquire image data of X-ray WV three-dimensional image; Step S72: Calculate the optimized color value of the red channel, green channel and blue channel of each pixel in the X-ray WV three-dimensional image, and combine them to form the optimized color value of the pixel; Step S73: Improve image quality and increase image details through exponential function filtering and detail image enhancement, combine the optimized color values ​​of all pixels, and output X-ray WV colored three-dimensional high-definition image.

Images