An adaptive display method and browser for medical images

Abstract

The application relates to a kind of adaptive display method and browser of medical image, the display method includes: S10, for the medical image to be displayed, the medical image is parsed, and the label information of the medical image is obtained;S20, according to the label information, the standardized uptake value SUV pixel value of pixel point in the specified range in the medical image is acquired;S30, according to the SUV pixel value of pixel point in the specified range, the window parameter for displaying medical image is acquired, and the medical image is adaptively displayed based on the window parameter, and the optimally displayed image is obtained.The display method of the application realizes the function of automatically calculating the window width and window level parameter value of the suitable display of PET image, makes the gray value transition of the adaptively displayed PET image smooth, gray is uniform, detail is clear, reaches more ideal display effect, so that the operation of user is more convenient and efficient.

Description

Technical Field

[0001] This invention relates to the field of digital medical image processing technology, and in particular to an adaptive display method and browser for medical images. Background Technology

[0002] In existing technologies, the storage, parsing, and transmission of digital medical images all utilize the DICOM (Digital Imaging and Communication of Medicine) standard format. The data length of each pixel value is typically 8-16 bits, and these images are displayed as grayscale images. Most commonly used computer monitors support 8-bit grayscale display. Therefore, when the data length of a digital medical image's pixel value exceeds 8 bits, direct display on a computer will result in the loss of some image information. Consequently, the display of digital medical images typically employs window width and window level techniques, selecting a portion of the original digital medical image's numerical range and mapping it to the grayscale range that the monitor can display. This selected range of pixel values ​​is called the window, the difference between the upper and lower limits of this range is called the window width, and the pixel value at the center of the range is called the window level. When displaying a digital medical image, the window width and window level values ​​must be specified for the image to be displayed correctly.

[0003] Mainstream digital medical imaging types typically include CT (Computed Tomography) images, MR (Magnetic Resonance Imaging) images, and PET (Positron Emission Computed Tomography) images. Among these, CT and MR images usually have fixed window width and level parameters. Taking CT images as an example, the imaging principle is based on the different absorption and transmittance of X-rays by different tissues in the human body. Highly sensitive instruments are used to measure the absorption of X-rays by the human body, resulting in a corresponding CT image. The CT value of each pixel in the CT image reflects the density of different parts of the body. Since the density of different tissues in the human body has a definite range, when displaying the details of a particular tissue, the corresponding window width and level values ​​can be set by referring to the density of that tissue. However, PET images cannot use fixed window width and level parameters. The imaging principle of PET images is based on the injection of radiopharmaceuticals into the human body. The accumulation of these radiopharmaceuticals during the body's metabolic process reflects the state of metabolic activities. Therefore, the pixel values ​​in PET images are greatly affected by human metabolic activities. Factors such as the dosage and timing of radiopharmaceutical injections, the patient's condition, the acquisition equipment, and the surrounding environment all directly impact the range of pixel values ​​in PET images. Even images acquired by the same equipment at the same time from the same tissue site will show significantly different grayscale effects depending on the patient. For these reasons, after opening a PET image, users often need to manually adjust the window width and level parameters repeatedly to achieve a satisfactory display for subsequent analysis, which is quite inconvenient. Summary of the Invention

[0004] (a) Technical problems to be solved

[0005] In view of the above-mentioned shortcomings and deficiencies of the prior art, the present invention provides an adaptive display method and browser for medical images, which solves the technical problem that in the prior art, users need to repeatedly manually adjust the window width and window level values ​​of PET images in order to achieve a more ideal display effect.

[0006] (II) Technical Solution

[0007] To achieve the above objectives, the main technical solutions adopted by the present invention include:

[0008] In a first aspect, embodiments of the present invention provide an adaptive display method for medical images, comprising:

[0009] S10. For the medical image to be displayed, parse the medical image to obtain the label information of the medical image;

[0010] S20. Based on the label information, obtain the standardized uptake value (SUV) pixel value of pixels within a specified range in the medical image;

[0011] S30. Based on the SUV pixel values ​​of the pixels within the specified range, obtain the window parameters for displaying the medical image, and adaptively display the medical image based on the window parameters to obtain the optimal displayed image.

[0012] Optionally, the medical image is a PET image, and the tag information includes: patient weight, half-life of the radiopharmaceutical, dosage of the radiopharmaceutical, administration time of the radiopharmaceutical, and acquisition time of the PET image.

[0013] Optionally, S20 includes:

[0014] Based on the label information, the pixel values ​​of pixels within a specified range in the PET image are transformed using SUV transformation according to formula (1) to obtain SUV pixel values; the formula (1) is:

[0015]

[0016] In formula (1), pixelPET represents the pixel value of a pixel in a PET image, pixelSUV represents the SUV pixel value obtained after SUV transformation of the pixel value of a pixel in a PET image, weight represents the patient's weight, RTD represents the dose of the radiopharmaceutical, and RHL represents the decay rate of the radioactive element. RHL is calculated based on the half-life of the radiopharmaceutical, the administration time, and the acquisition time of the PET image.

[0017] Optionally, the window parameters include window width and window level, and S30 includes:

[0018] S301. Statistically analyze the probability distribution of the pixel values ​​of the SUV;

[0019] S302. Based on the probability distribution of the SUV pixel values, perform an inverse SUV transformation on the first SUV pixel values ​​corresponding to the first preset value with a cumulative probability, and obtain the first SUV pixel values ​​mapped to the first PET pixel values ​​in the PET image, which are used as the optimal window position of the PET image.

[0020] S303. Based on the probability distribution of the SUV pixel values, perform curve fitting to obtain the corresponding curve equation; based on the curvature of the curve equation, determine the optimal left boundary of the window width of the PET image; based on the optimal window position and the optimal left boundary, determine the optimal window width;

[0021] S304. Using the optimal window position and optimal window width as window parameters, the PET image is adaptively displayed based on these window parameters to obtain the optimally displayed PET image.

[0022] Optionally, S301 includes:

[0023] Based on the pre-defined distribution range of SUV pixel values, divide the area into M equally spaced unit intervals, where M is a positive integer;

[0024] The probability distribution S(i) = N of the SUV pixel values ​​is obtained by counting the number of pixels whose pixel values ​​fall within each unit interval. i / N;

[0025] Where i is a positive integer not greater than M, and N i This represents the number of pixels whose SUV pixel value falls within the i-th unit interval, and N represents the total number of pixels in the PET image.

[0026] Optionally, S302 includes:

[0027] S302-1. Based on the probability distribution S(i) of the SUV pixel values, calculate the cumulative probability of S(i).

[0028] S302-2. Determine whether the cumulative probability Sum(i) is not less than a first preset value.

[0029] If not, increment the value of i by 1 and jump to S302-1;

[0030] If so, proceed to S302-3;

[0031] S302-3. Randomly select a value from the unit interval corresponding to the current i value as the first SUV pixel value;

[0032] S302-4. Based on the label information, perform an inverse SUV transformation on the first pixel value according to formula (2) to obtain the first SUV pixel value mapped to the first PET pixel value in the PET image, and use the first PET pixel value as the optimal window position of the PET image;

[0033] Formula (2) is as follows:

[0034]

[0035] Optionally, the range of the first preset value is [0.786, 0.841].

[0036] Optionally, S303 includes:

[0037] S303-1. Based on the probability distribution S(i), perform curve fitting to obtain the curve equation f(S(i));

[0038] S303-2. Calculate the i value corresponding to the maximum curvature point on the curve equation f(S(i)), multiply the i value by the second preset value and round it to obtain a new i value, and randomly select a value from the unit interval corresponding to the new i value as the second SUV pixel value.

[0039] S303-3. Based on the label information, perform an inverse SUV transformation on the second SUV pixel value according to the formula (2) to obtain the second SUV pixel value mapped to the second PET pixel value in the PET image, and use the second PET pixel value as the optimal left boundary of the window width of the PET image;

[0040] S303-4. Based on the optimal window position and optimal left boundary, the optimal window width of the PET image is calculated according to formula (3); wherein, formula (3) is:

[0041] WW=abs(pixelPET1-pixelPET2)×2 (3)

[0042] In formula (3), WW represents the optimal window width of the PET image, abs() represents the absolute value operation, pixelPET1 represents the first PET pixel value, and pixelPET2 represents the second PET pixel value.

[0043] Optionally, the range of the second preset value is [0.425, 0.534].

[0044] Secondly, embodiments of the present invention provide a browser, including an adaptive display device, the adaptive display device comprising:

[0045] The image parsing module is used to parse the medical image to be displayed and obtain the label information of the medical image;

[0046] The SUV transformation module is used to obtain the standardized uptake value (SUV pixel value) of pixels within a specified range in the medical image based on the label information.

[0047] The adaptive display module is used to obtain window parameters for displaying medical images based on the SUV pixel values ​​of pixels within the specified range, and to adaptively display the medical images based on the window parameters to obtain the optimal display image.

[0048] (III) Beneficial Effects

[0049] The adaptive display method and browser proposed in this invention first introduce the SUV index to standardize the pixel values ​​of the PET image, converting the pixel values ​​of the target PET image into SUV pixel values. Next, the probability distribution of the SUV pixel values ​​is statistically analyzed. Based on this probability distribution, the optimal window position is determined according to the cumulative probability of the SUV pixel values. Then, the optimal left boundary is determined according to the fitting function of the probability distribution, and the pixel values ​​of the optimal window position and optimal left boundary are remapped back to the target PET image. Finally, the optimal window width is determined based on the optimal window position and optimal left boundary, obtaining window parameters for displaying medical images, which are used for adaptive display of the target PET image data. The adaptive display method and browser provided in this invention automatically calculate the appropriate window width and window position parameter values ​​for displaying PET images, resulting in smooth transitions in grayscale values ​​of the adaptively displayed PET images and achieving a more ideal display effect, thus making user operation more convenient and efficient.

[0050] Furthermore, compared to users manually adjusting the window width and window level parameters through trial and error based on experience, the window width and window level parameters obtained by this invention based on the SUV pixel value distribution law of PET images are more consistent with the statistical characteristics of the target PET image, thereby enabling the displayed PET image to have uniform grayscale, clear details, and better display effect. Attached Figure Description

[0051] Figure 1 This is a flowchart illustrating an adaptive display method for medical images provided in this embodiment;

[0052] Figure 2 The original PET image provided in the embodiment;

[0053] Figure 3 This is a PET image that is adaptively displayed based on the window parameters obtained by the display method of the present invention in the embodiment.

[0054] Figure 4 This is a schematic diagram of the structure of a browser provided in the embodiment. Detailed Implementation

[0055] To better explain and facilitate understanding of the present invention, the present invention will be described in detail below with reference to the accompanying drawings and specific embodiments.

[0056] To better understand the above technical solutions, exemplary embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. Although exemplary embodiments of the present invention are shown in the drawings, it should be understood that the present invention can be implemented in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that the present invention can be understood more clearly and thoroughly, and that the scope of the present invention can be fully conveyed to those skilled in the art.

[0057] Example 1

[0058] This embodiment provides an adaptive display method for medical images, used for adaptive display of medical images. This method can be implemented on any electronic device. Figure 1 As shown, the display method includes:

[0059] S10. For the medical image to be displayed, parse the medical image to obtain the label information of the medical image.

[0060] Specifically, the medical image may be a CT image, an MR image, or a PET image.

[0061] When the medical image is a PET image, the tag information includes: patient weight, half-life of the radiopharmaceutical, dosage of the radiopharmaceutical, administration time of the radiopharmaceutical, and acquisition time of the PET image.

[0062] More specifically, to accommodate PET images with different preprocessing levels, the label information of the PET image may further include adjusted intercept, adjusted slope, and attenuation correction markings. In step S10, after obtaining the above-mentioned label information of the PET image, the following steps are also included:

[0063] S100-1. Based on the adjusted intercept and adjusted slope contained in the label information, the original values ​​of the pixels in the PET image are converted into actual captured values ​​according to formula (4), and the actual captured values ​​are used as the pixel values ​​of the pixels in the PET image. The formula (4) is:

[0064] actualPET=originalPET*RS+RI (4)

[0065] In formula (4), actualPET represents the actual captured value of the pixel in the PET image, originalPET represents the original value of the pixel in the PET image, RS represents the adjustment slope, and RI represents the adjustment intercept.

[0066] S100-2. Based on the attenuation correction flag, determine whether the PET image has undergone attenuation correction. If yes, set the decay rate RHL of the radioactive element parameter to 1. If no, calculate RHL according to formula (5) based on the attribute information associated with the target PET image, and use it for calculation in subsequent steps S20-S30. The formula (5) is:

[0067]

[0068] In formula (5), T represents the acquisition time of the PET image, T0 represents the administration time of the radiopharmaceutical, and T... 1 / 2 This indicates the half-life of a radiopharmaceutical.

[0069] S20. Based on the label information, obtain the standardized uptake value (SUV pixel value) of pixels within a specified range in the medical image.

[0070] The pixels within a specified range in the medical image can be an image area selected by the user through keyboard and mouse operation, a default image area, or an image area corresponding to the entire medical image.

[0071] In a preferred embodiment of this example, step S20 includes: performing an SUV transformation on the pixel values ​​of pixels within a specified range in the PET image based on the label information and formula (1) to obtain SUV pixel values; the formula (1) is:

[0072]

[0073] In formula (1), pixelPET represents the pixel value of a pixel in a PET image, pixelSUV represents the SUV pixel value obtained after SUV transformation of the pixel value of a pixel in a PET image, weight represents the patient's weight, RTD represents the dose of the radiopharmaceutical, and RHL represents the decay rate of the radioactive element. RHL can be calculated by step S100-2.

[0074] S30. Based on the SUV pixel values ​​of the pixels within the specified range, obtain the window parameters for displaying the medical image, and adaptively display the medical image based on the window parameters to obtain the optimal displayed image.

[0075] The adaptive display method and browser proposed in this embodiment introduce the SUV index to standardize the pixel values ​​of PET images, converting the pixel values ​​of the target PET image into SUV pixel values. Based on the SUV pixel values ​​of pixels within a specified range, window parameters for displaying medical images are obtained, and the medical image is adaptively displayed based on these window parameters. The adaptive display method provided in this embodiment automatically calculates the appropriate window parameters for displaying PET images, resulting in smooth grayscale transitions and a more ideal display effect, thus making user operation more convenient and efficient. Compared to the original method of users manually adjusting and trial-and-error based on experience and judging image display effects by eye, the window width and window level parameters obtained by this invention based on the SUV pixel values ​​of PET images better match the statistical characteristics of the target PET image, thereby enabling the displayed PET image to have uniform grayscale, clear details, and a superior display effect.

[0076] It should be noted that the SUV index in existing technologies is used to describe the amount of radioactive uptake in lesions. In commonly used 18F-FDG PET imaging, the SUV index typically provides a reference for differentiating between benign and malignant lesions. Because many factors influence the SUV value, when using the SUV index to differentiate between benign and malignant lesions, users need to consider the location, shape, size, number, and radioactive distribution within the lesions, as well as the patient's medical history and other imaging and objective examination results for comprehensive analysis to obtain the final analysis result. However, this invention creatively uses the SUV index for the standardization of PET image pixel values, making the pixel value distribution pattern of PET images clearer and providing a more reliable data foundation for subsequent calculations of optimal window level and width, thereby improving the display effect of PET images.

[0077] Example 2

[0078] To better understand step S30 in Embodiment 1, this embodiment will be described in detail with reference to specific steps.

[0079] This embodiment provides an adaptive display method for medical images, which automatically calculates the optimal window position and optimal window width for adaptive display based on DICOM format PET images. The execution subject of the display method can be a computer device, an image processing device, or a computer program for browsing PET images.

[0080] The adaptive display method includes:

[0081] S10. For the PET image to be displayed, parse the PET medical image to obtain the label information of the PET image.

[0082] The tag information includes: patient weight, half-life of the radiopharmaceutical, dosage of the radiopharmaceutical, time of administration of the radiopharmaceutical, and time of PET image acquisition.

[0083] S20. Based on the label information, obtain the standardized ingestion value (SUV pixel value) of pixels within a specified range in the PET image.

[0084] S30. Based on the SUV pixel values ​​of the pixels within the specified range, obtain the window parameters for displaying the medical image, and adaptively display the medical image based on the window parameters to obtain the optimal displayed image.

[0085] S30 includes the following sub-steps:

[0086] S301. Statistically analyze the probability distribution of the pixel values ​​of the SUV.

[0087] Specifically, step S301 includes the following sub-steps:

[0088] Based on a pre-defined SUV pixel value distribution range, divide the area into M equally spaced unit intervals, where M is a positive integer; count the number of pixels whose SUV pixel values ​​fall within each unit interval to obtain the probability distribution S(i) = N for the SUV pixel values. i / N.

[0089] Where i is a positive integer not greater than M, and N i This represents the number of pixels whose SUV pixel value falls within the i-th unit interval, and N represents the total number of pixels in the PET image.

[0090] In a preferred embodiment of this example, the distribution range of SUV pixel values ​​is pre-defined as [0, 90]. Based on this distribution range, 900 equally spaced unit intervals are formed. Each unit interval has a length of 0.1, the value range of the first unit interval is [0, 0.1], the value range of the i-th unit interval is (0.1i-0.1, 0.1i], and the value range of the 900th unit interval is (89.9, 90). Here, i is a positive integer not greater than 900.

[0091] S302. Based on the probability distribution of the SUV pixel values, perform an inverse SUV transformation on the first SUV pixel values ​​corresponding to the first preset value with a cumulative probability, and obtain the first PET pixel values ​​mapped from the first SUV pixel values ​​to the PET image, which are used as the optimal window position of the PET image.

[0092] Specifically, step S302 includes the following sub-steps:

[0093] S302-1. Set the initial value of i to 1, and calculate the cumulative probability of S(i) based on the probability distribution S(i) of the SUV pixel values.

[0094] S302-2. Determine whether the cumulative probability Sum(i) is not less than a first preset value.

[0095] If not, increment the value of i by 1 and jump to S302-1;

[0096] If so, proceed to S302-3.

[0097] The aforementioned first preset value is used to locate the center position of the area where the pixel values ​​of the SUV are relatively concentrated, so as to determine the optimal window position of the PET image in subsequent steps. Preferably, the value range of the aforementioned first preset value is [0.786, 0.841], and more preferably, the first preset value is 0.8.

[0098] S302-3. Randomly select a value from the unit interval corresponding to the current i value as the first SUV pixel value. Preferably, the value of the first SUV pixel value can be the right endpoint value or the middle value of the corresponding unit interval.

[0099] S302-4. Based on the label information, perform an inverse SUV transformation on the first pixel value according to formula (2) to obtain the first SUV pixel value mapped to the first PET pixel value in the PET image, and use the first PET pixel value as the optimal window position of the PET image.

[0100] Formula (2) is as follows:

[0101]

[0102] The above-mentioned S302-1~S302-2 cyclic process is equivalent to increasing the value of i sequentially based on the probability distribution of the SUV pixel value and calculating the corresponding cumulative probabilities Sum(1), Sum(2), ... Sum(i) until the first unit interval with a cumulative probability greater than the first preset value is found, and then the first SUV pixel value is selected from the unit interval.

[0103] S303. Based on the probability distribution of the SUV pixel values, perform curve fitting to obtain the corresponding curve equation; based on the curvature of the curve equation, determine the optimal left boundary of the window width of the PET image; based on the optimal window position and the optimal left boundary, determine the optimal window width.

[0104] In a preferred embodiment of this invention, step S303 includes the following sub-steps:

[0105] S303-1. Based on the probability distribution S(i), the B-spline curve fitting method is used to perform curve fitting to obtain the curve equation f(S(i)).

[0106] S303-2. Calculate the i value corresponding to the maximum curvature point on the curve equation f(S(i)), multiply the i value by the second preset value and round it to obtain a new i value, and randomly select a value from the unit interval corresponding to the new i value as the second SUV pixel value.

[0107] Specifically, f(S(i)) can be substituted into formula (6) to calculate the i value corresponding to the maximum value of K, and the i value is taken as the i value corresponding to the maximum curvature point on the curve equation f(S(i)); the i value is multiplied by the second preset value and rounded to obtain a new i value, and a value is randomly selected from the unit interval corresponding to the new i value as the second SUV pixel value.

[0108] Formula (6) is as follows:

[0109]

[0110] In formula (6), f(S(i))′ represents the first derivative of f(S(i)), f(S(i))″ represents the second derivative of f(S(i)), and K represents the curvature of f(S(i)).

[0111] Preferably, the value of the second SUV pixel can be the right endpoint value or the middle value of the corresponding unit interval.

[0112] The aforementioned second preset value is used to locate the left boundary of the region where the SUV pixel values ​​are relatively concentrated, based on the i value corresponding to the maximum curvature point on the curve equation f(S(i)), so as to determine the optimal left boundary of the PET image window width in subsequent steps. Preferably, the value range of the second preset value is [0.425, 0.534], and more preferably, the value of the second preset value is 0.5.

[0113] S303-3. Based on the label information, perform an inverse SUV transformation on the second SUV pixel value according to the formula (2) to obtain the second SUV pixel value mapped to the second PET pixel value in the PET image, and use the second PET pixel value as the optimal left boundary of the PET image window width.

[0114] S303-4. Based on the optimal window position and optimal left boundary, the optimal window width of the PET image is calculated according to formula (3). Formula (3) is:

[0115] WW=abs(pixelPET1-pixelPET2)×2 (3)

[0116] In formula (3), WW represents the optimal window width of the PET image, abs() represents the absolute value operation, pixelPET1 represents the first PET pixel value, and pixelPET2 represents the second PET pixel value.

[0117] S304. Using the optimal window position and optimal window width as window parameters, the PET image is adaptively displayed based on these window parameters to obtain the optimally displayed PET image.

[0118] like Figure 2-3 As shown, this embodiment also provides a comparison between the PET image and the original PET image, which are adaptively displayed based on the optimal window position and optimal window width obtained by the above display method. Among them, Figure 2 The original PET image, Figure 3 This is a PET image adaptively displayed based on the optimal window position and width obtained using the above display method. (Comparison) Figure 2 and Figure 3 It can be seen that, compared with the original PET image, the PET image displayed with the optimal window position and optimal window width obtained based on the above display method has a more uniform grayscale distribution and higher contrast, thus making the details of the target PET image clearer and the overall display effect better.

[0119] The adaptive display method proposed in this invention first introduces the SUV index to standardize the pixel values ​​of the PET image, converting the pixel values ​​of the target PET image into SUV pixel values. Next, the probability distribution of the SUV pixel values ​​is statistically analyzed. Based on this probability distribution, the optimal window level is determined according to the cumulative probability of the SUV pixel values. Then, the optimal left boundary is determined based on the fitting function of the probability distribution, and the pixel values ​​of the optimal window level and optimal left boundary are remapped back to the target PET image. Finally, the optimal window width is determined based on the optimal window level and optimal left boundary, resulting in window parameters for displaying medical images, used for adaptive display of the target PET image data. Compared to users manually adjusting window width and window level parameters through trial and error, the window width and window level parameters obtained by this invention based on the SUV pixel value distribution of the PET image better match the statistical characteristics of the target PET image, thereby enabling the displayed PET image to have uniform grayscale, clear details, and superior display effect.

[0120] Example 3

[0121] like Figure 4 As shown, this embodiment provides a browser, which is a browser for doctors to display medical images, or a browser for the operating console in a PET detection system. The browser includes an adaptive display device, which comprises: an image parsing module, an SUV transformation module, and an adaptive display module, as detailed below:

[0122] The image parsing module is used to parse the medical image to be displayed and obtain the label information of the medical image.

[0123] The SUV transformation module is used to obtain the standardized uptake value (SUV pixel value) of pixels within a specified range in the medical image based on the label information.

[0124] The adaptive display module is used to obtain window parameters for displaying medical images based on the SUV pixel values ​​of pixels within the specified range, and to adaptively display the medical images based on the window parameters to obtain the optimal displayed image.

[0125] In a preferred embodiment of this invention, the adaptive display module further includes: a probability distribution statistics module, a window parameter calculation module, an SUV inverse transform module, and a display module, as detailed below:

[0126] The probability distribution statistics module is used to statistically analyze the probability distribution of the SUV pixel values.

[0127] The window parameter calculation module is used to calculate the first SUV pixel value corresponding to the first preset value based on the probability distribution of the SUV pixel value, and call the SUV inverse transform module to calculate the first PET pixel value corresponding to the first SUV pixel value, as the optimal window position of the target PET image data.

[0128] The window parameter calculation module is also used to perform curve fitting based on the probability distribution of the SUV pixel values ​​to obtain the corresponding curve equation; determine the second SUV pixel value based on the maximum curvature point of the curve equation, and call the SUV inverse transform module to calculate the second PET pixel value corresponding to the second SUV pixel value, which is used as the optimal left boundary of the PET image window width, and determine the optimal window width based on the optimal window position and the optimal left boundary.

[0129] The SUV inverse transformation module is used to receive the call from the window parameter calculation module, perform SUV inverse transformation on the first SUV pixel value or the first SUV pixel value to obtain the corresponding first PET pixel value or second PET pixel value, and return it to the window parameter calculation module.

[0130] The display module is used to adaptively display the medical image by using the optimal window level and optimal window width as window parameters, so as to obtain the optimally displayed image.

[0131] Since the systems / devices described in the above embodiments of the present invention are systems / devices used to implement the methods of the above embodiments of the present invention, those skilled in the art can understand the specific structure and modifications of the systems / devices based on the methods described in the above embodiments of the present invention, and therefore will not be repeated here. All systems / devices used in the methods of the above embodiments of the present invention fall within the scope of protection of the present invention.

[0132] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0133] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, as well as combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions.

[0134] It should be noted that any reference numerals placed between parentheses in the claims should not be construed as limiting the claims. The word "comprising" does not exclude the presence of components or steps not listed in the claims. The word "a" or "an" preceding a component does not exclude the presence of a plurality of such components. The invention can be implemented by means of hardware comprising several different components and by means of a suitably programmed computer. In claims that enumerate several means, several of these means may be embodied by the same hardware. The use of the terms first, second, third, etc., is merely for convenience of expression and does not indicate any order. These terms can be understood as part of the component names.

[0135] Furthermore, it should be noted that in the description of this specification, the terms "one embodiment," "some embodiments," "embodiment," "example," "specific example," or "some examples," etc., refer to specific features, structures, materials, or characteristics described in connection with that embodiment or example, which are included in at least one embodiment or example of the present invention. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Furthermore, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0136] Although preferred embodiments of the invention have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the claims should be interpreted to include both the preferred embodiments and all changes and modifications falling within the scope of the invention.

[0137] Obviously, those skilled in the art can make various modifications and variations to this invention without departing from its spirit and scope. Therefore, if these modifications and variations fall within the scope of the claims of this invention and their equivalents, then this invention should also include these modifications and variations.

Claims

1. An adaptive display method for medical images, characterized in that, include: S10. For the medical image to be displayed, parse the medical image to obtain the label information of the medical image; The medical image is a PET image, and the tag information includes: patient weight, half-life of the radiopharmaceutical, dosage of the radiopharmaceutical, administration time of the radiopharmaceutical, and acquisition time of the PET image. S20. Based on the label information, obtain the standardized uptake value (SUV) pixel value of pixels within a specified range in the medical image; wherein, based on the label information, perform SUV transformation on the pixel values ​​of pixels within a specified range in the PET image according to formula (1) to obtain the SUV pixel value; the formula (1) is: （1） In formula (1), pixelPET represents the pixel value of a pixel in a PET image, pixelSUV represents the SUV pixel value obtained after SUV transformation of the pixel value of a pixel in a PET image, weight represents the patient's weight, RTD represents the dose of the radiopharmaceutical, and RHL represents the decay rate of the radioactive element. RHL is calculated based on the half-life of the radiopharmaceutical, the administration time, and the acquisition time of the PET image. S30. Based on the SUV pixel values ​​of the pixels within the specified range, obtain window parameters for displaying the medical image, and adaptively display the medical image based on the window parameters to obtain the optimal displayed image; wherein, the window parameters for displaying the medical image are obtained based on the distribution law of SUV pixel values ​​of PET images, and the window parameters include window width and window level; S30 includes: S301. Statistically analyze the probability distribution of the pixel values ​​of the SUV; S302. Based on the probability distribution of the SUV pixel values, perform an inverse SUV transformation on the first SUV pixel values ​​corresponding to the first preset value with a cumulative probability, and obtain the first SUV pixel values ​​mapped to the first PET pixel values ​​in the PET image, which are used as the optimal window position of the PET image. S303. Based on the probability distribution of the SUV pixel values, perform curve fitting to obtain the corresponding curve equation; based on the curvature of the curve equation, determine the optimal left boundary of the window width of the PET image; based on the optimal window position and the optimal left boundary, determine the optimal window width; S304. Using the optimal window position and optimal window width as window parameters, the PET image is adaptively displayed based on these window parameters to obtain the optimally displayed PET image.

2. The display method according to claim 1, characterized in that, S301 includes: Based on the pre-defined distribution range of SUV pixel values, divide the area into M equally spaced unit intervals, where M is a positive integer; The probability distribution S(i) = N of the SUV pixel values ​​is obtained by counting the number of pixels whose pixel values ​​fall within each unit interval. i / N; Where i is a positive integer not greater than M, and N i This represents the number of pixels whose SUV pixel value falls within the i-th unit interval, and N represents the total number of pixels in the PET image.

3. The display method according to claim 2, characterized in that, S302 includes: S302-1. Based on the probability distribution S(i) of the SUV pixel values, calculate the cumulative probability of S(i). ; S302-2. Determine whether the cumulative probability Sum(i) is not less than a first preset value. If not, increment the value of i by 1 and jump to S302-1; If so, proceed to S302-3; S302-3. Randomly select a value from the unit interval corresponding to the current i value as the first SUV pixel value; S302-4. Based on the label information, perform an inverse SUV transformation on the first pixel value according to formula (2) to obtain the first SUV pixel value mapped to the first PET pixel value in the PET image, and use the first PET pixel value as the optimal window position of the PET image. Formula (2) is as follows: （2）。 4. The display method according to claim 3, characterized in that, The range of the first preset value is [0.786, 0.841].

5. The display method according to claim 3, characterized in that, S303 includes: S303-1. Based on the probability distribution S(i), perform curve fitting to obtain the curve equation f(S(i)); S303-2. Calculate the i value corresponding to the maximum curvature point on the curve equation f(S(i)), multiply the i value by the second preset value and round it to obtain a new i value, and randomly select a value from the unit interval corresponding to the new i value as the second SUV pixel value. S303-3. Based on the label information, perform an inverse SUV transformation on the second SUV pixel value according to the formula (2) to obtain the second SUV pixel value mapped to the second PET pixel value in the PET image, and use the second PET pixel value as the optimal left boundary of the window width of the PET image; S303-4. Based on the optimal window position and optimal left boundary, the optimal window width of the PET image is calculated according to formula (3); wherein, formula (3) is: （3） In formula (3), WW represents the optimal window width of the PET image, abs() represents the absolute value operation, pixelPET1 represents the first PET pixel value, and pixelPET2 represents the second PET pixel value.

6. The display method according to claim 5, characterized in that, The second preset value ranges from [0.425, 0.534].

7. A browser, characterized in that, Includes an adaptive display device, the adaptive display device comprising: The image parsing module is used to parse the medical image to be displayed and obtain the label information of the medical image; the medical image is a PET image, and the label information includes: patient weight, half-life of radiopharmaceutical, dosage of radiopharmaceutical, administration time of radiopharmaceutical, and acquisition time of PET image; The SUV transformation module is used to obtain the standardized uptake value (SUV) pixel value of pixels within a specified range in the medical image based on the label information; it is also used to perform SUV transformation on the pixel values ​​of pixels within a specified range in the PET image based on the label information and formula (1) to obtain the SUV pixel value; the formula (1) is: （1） In formula (1), pixelPET represents the pixel value of a pixel in a PET image, pixelSUV represents the SUV pixel value obtained after SUV transformation of the pixel value of a pixel in a PET image, weight represents the patient's weight, RTD represents the dose of the radiopharmaceutical, and RHL represents the decay rate of the radioactive element. RHL is calculated based on the half-life of the radiopharmaceutical, the administration time, and the acquisition time of the PET image. An adaptive display module is configured to: obtain window parameters for displaying medical images based on the SUV pixel values ​​of pixels within a specified range; adaptively display the medical images based on these window parameters to obtain the optimally displayed image; obtain the window parameters for displaying medical images based on the distribution pattern of SUV pixel values ​​in PET images, wherein the window parameters include window width and window level; statistically analyze the probability distribution of the SUV pixel values; perform an inverse SUV transformation on the first SUV pixel values ​​corresponding to a first preset probability value based on the probability distribution of the SUV pixel values ​​to obtain the first PET pixel values ​​mapped from the first SUV pixel values ​​to the first PET pixel values ​​in the PET images, which serve as the optimal window level of the PET images; perform curve fitting based on the probability distribution of the SUV pixel values ​​to obtain the corresponding curve equation; determine the optimal left boundary of the window width of the PET images based on the curvature of the curve equation; determine the optimal window width based on the optimal window level and optimal left boundary; use the optimal window level and optimal window width as window parameters; and adaptively display the PET images based on these window parameters to obtain the optimally displayed PET images.

Images