A method and system for measuring radioactive drug concentration
By calculating the relative density of grayscale and drug influence of pixel points, clustering and blocking processing, combined with histogram equalization method, local image enhancement is performed on SPECT imaging, which solves the problem of poor image enhancement effect in the prior art. Improve the accuracy of radiopharmaceutical concentration measurement.
Patent Information
- Application Number
- CN202411246014.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-06
- Publication Date
- 2024-11-12
- Estimated Expiration
- 2044-09-06
AI Technical Summary
When the prior art uses histogram equalization method to enhance the image of SPECT imaging, it is difficult to take into account the area of local radiopharmaceutical concentration changes, resulting in poor image enhancement effect, which in turn affects the accuracy of radiopharmaceutical concentration measurement.
By obtaining the relative gray density of pixel points and drug influence, the drug distribution possibility is calculated, and the image to be enhanced is clustered based on the region growth algorithm, the image enhancement is enhanced in block areas, and local image enhancement is enhanced by using the histogram equalization method. .
It improves the image enhancement effect, more accurately reflects the distribution of radioactive drug concentration, and improves the accuracy of drug concentration calculation.
Smart Images

Figure CN118781038B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of image enhancement, and in particular to a method and system for measuring the concentration of radioactive drugs. Background Art
[0002] Radioactive drugs are often used to diagnose diseases and observe physiological processes in the human body. By measuring the concentration of drugs in specific tissues or organs, doctors can determine abnormal physiological processes or disease states and formulate or adjust treatment plans and monitor the progress of treatment. SPECT technology (Single-Photon Emission Computed Tomography) is a nuclear medicine imaging technology. SPECT images collected by SPECT equipment can reflect the concentration distribution information of radioactive drugs. In order to improve the contrast and clarity of radioactive drug concentration in SPECT images, image enhancement processing is usually required.
[0003] Histogram equalization is a widely used technology in the field of image enhancement. Histogram equalization redistributes the pixel values of the image to make the brightness distribution of the image more uniform, thereby enhancing the image. However, in the process of using histogram equalization to enhance SPECT imaging, since histogram equalization is based on the overall image, and the expression of the local radioactive drug concentration change area is weak, the histogram equalization method is difficult to take into account the local radioactive drug concentration change area, resulting in poor image enhancement effect, and the enhanced image is difficult to accurately reflect the distribution of radioactive drug concentration, which leads to inaccurate measurement of radioactive drug concentration. Summary of the invention
[0004] In order to solve the technical problem that the image enhancement effect of the drug concentration image to be enhanced is poor in the prior art, the purpose of the present invention is to provide a method and system for measuring the concentration of radioactive drugs. The technical solution adopted is as follows:
[0005] A method for measuring radioactive drug concentration, the method comprising:
[0006] Acquiring a drug concentration image to be enhanced;
[0007] In the drug concentration image to be enhanced, the grayscale relative density of the pixel is obtained according to the similarity of the grayscale value of the pixel and the local surrounding space area; the drug influence of the pixel is obtained according to the inconsistency of the grayscale value of the local surrounding space area of the pixel; the drug distribution possibility of the pixel is obtained according to the grayscale value of the pixel, the grayscale relative density and the drug influence; according to the drug distribution possibility, all the pixels in the drug concentration image to be enhanced are clustered to obtain each drug block area;
[0008] Image enhancement is performed on each of the drug block regions in the drug concentration image to be enhanced to obtain a drug concentration enhanced image.
[0009] Furthermore, the grayscale relative density acquisition method includes:
[0010] Get all surrounding points of the pixel in the preset surrounding space area;
[0011] According to the gray value difference between each surrounding point and the pixel point, the surrounding gray value difference index of each surrounding point is obtained;
[0012] According to the spatial distance between each surrounding point and the pixel point, the distribution distance index of each surrounding point is obtained;
[0013] The surrounding grayscale difference index and the distribution distance index of all surrounding points are combined to obtain the grayscale relative density of the pixel point; the surrounding grayscale difference index and the distribution distance index are both negatively correlated with the grayscale relative density.
[0014] Furthermore, the method for obtaining the drug influence degree includes:
[0015] Obtaining neighborhood points of the pixel point in a preset neighborhood area; dividing a preset number of preset local areas from the preset neighborhood area;
[0016] According to the grayscale value differences of all neighboring points in the preset local area of the pixel point, the grayscale feature value of the preset local area of the pixel point is obtained;
[0017] The drug influence degree of the pixel point is obtained according to the inconsistency of the grayscale characteristic values of all the preset local areas of the pixel point.
[0018] Furthermore, the method for obtaining the preset local area includes:
[0019] A preset number of preset directions of the pixel points are constructed, and an area formed by all the neighborhood points that each preset direction passes through in the preset neighborhood area is used as a preset local area of each pixel point.
[0020] Furthermore, the grayscale characteristic value acquisition method includes:
[0021] In a preset local area of the pixel point, according to the difference in grayscale values between each neighborhood point and the neighboring points adjacent to it in a preset direction, a grayscale difference characteristic value of each neighborhood point is obtained;
[0022] According to the overall distribution of the grayscale difference characteristic values of all neighborhood points, the overall grayscale difference value of the direction of the preset local area of the pixel point is obtained;
[0023] According to the fluctuation of the grayscale difference characteristic values of all neighborhood points, the directional grayscale unevenness value of the preset local area of the pixel point is obtained;
[0024] The grayscale characteristic value of the preset local area of the pixel point is obtained by combining the overall grayscale difference value of the direction and the grayscale unevenness value of the direction; the overall grayscale difference value of the direction and the grayscale unevenness value of the direction are both positively correlated with the grayscale characteristic value.
[0025] Furthermore, the method for obtaining the drug influence degree of a pixel point according to the inconsistency of the grayscale characteristic values of all the preset local areas of the pixel point includes:
[0026] The variance of the grayscale eigenvalues of the pixel points in all preset local areas is calculated to obtain the drug influence of the pixel points.
[0027] Furthermore, the method for obtaining the drug distribution possibility includes:
[0028] The grayscale value of the pixel point is proportionally normalized to obtain the high concentration weight; the difference between 1 and the high concentration weight is calculated to obtain the low concentration weight; the product of the high concentration weight and the drug influence is calculated to obtain the first product value; the product of the low concentration weight and the grayscale relative density is calculated to obtain the second product value; the sum of the first product value and the second product value is calculated to obtain the drug distribution possibility of the pixel point.
[0029] Furthermore, the method for obtaining the drug block area includes:
[0030] Based on the region growing algorithm, all the pixels in the drug concentration image to be enhanced are clustered according to the drug distribution possibility of all the pixels, and each drug block region is obtained.
[0031] Furthermore, the method for acquiring the drug concentration enhanced image includes:
[0032] By using a histogram equalization method, image enhancement is performed on each of the drug block regions in the drug concentration image to be enhanced to obtain a drug concentration enhanced image.
[0033] The present invention proposes a radioactive drug concentration calculation system, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the processor implements any one of the steps of the radioactive drug concentration calculation method.
[0034] The present invention has the following beneficial effects:
[0035] In the drug concentration image to be enhanced, due to the differences in physiological activities of different tissues and organs, different concentrations of radioactive drugs will be caused. The larger the gray value of the pixel, the higher the concentration of radioactive drugs in the area where the pixel is located. In order to cluster the distribution areas of each radioactive drug in the drug concentration image to be enhanced, it is necessary to first analyze the performance of the drug. Considering that when the concentration of radioactive drugs is low, the performance of radioactive drugs is low gray value and the distribution is relatively uniform; when the concentration of radioactive drugs is high, affected by factors such as pathological state and dynamic flow of blood flow, the local grayscale characteristics of radioactive drugs are inconsistent. The drug distribution possibility is obtained. The larger the drug distribution possibility, the more likely the area where the pixel is located is the radioactive drug distribution area. Then, the drug concentration image to be enhanced is clustered to obtain drug block areas that better reflect the distribution areas of each radioactive drug. By performing image enhancement on each drug block area in the drug concentration image to be enhanced, the image enhancement fully considers the needs of the drug block area, better takes into account the needs of the local radioactive drug concentration area, improves the image enhancement effect, and makes the drug concentration enhanced image more accurately reflect the distribution of radioactive drug concentration. BRIEF DESCRIPTION OF THE DRAWINGS
[0036] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.
[0037] Figure 1 A flow chart of a method for calculating the concentration of a radioactive drug provided by one embodiment of the present invention;
[0038] Figure 2 A flow chart of a method for obtaining grayscale relative density provided by an embodiment of the present invention;
[0039] Figure 3 A flow chart of a method for obtaining drug influence provided by an embodiment of the present invention;
[0040] Figure 4 A structural diagram of a radioactive drug concentration measurement system provided by one embodiment of the present invention. DETAILED DESCRIPTION
[0041] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the following is a detailed description of a radiopharmaceutical concentration measurement method and system proposed by the present invention, its specific implementation, structure, features and effects, in conjunction with the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" does not necessarily refer to the same embodiment. In addition, specific features, structures or characteristics in one or more embodiments may be combined in any suitable form.
[0042] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
[0043] The specific scheme of a radioactive drug concentration measurement method and system provided by the present invention is described in detail below with reference to the accompanying drawings.
[0044] The present invention provides a method and system for measuring the concentration of radioactive drugs. Figure 1 , which shows a flow chart of a method for calculating the concentration of a radioactive drug provided by an embodiment of the present invention, the method comprising the following steps:
[0045] Step S1: Acquire the drug concentration image to be enhanced.
[0046] In order to assist doctors in diagnosing the patient's condition, it is necessary to obtain an image of the drug concentration to be enhanced.
[0047] Since radioactive drugs are usually designed to be absorbed by specific tissues or organs and release radiation in the body that can be detected by SPECT equipment, patients need to wait for a period of time after taking the drugs so that the drugs can be fully distributed in the target tissues or organs, and then the radiation emitted by the radioactive drugs in the patient's body can be detected by the SPECT equipment to generate SPECT images. SPECT imaging can show the absorption of radioactive drugs by the patient's internal tissues and organs, reflect the physiological functions and metabolism of the patient's internal tissues and organs, and can assist doctors in diagnosing the patient's condition.
[0048] Specifically, the patient's SPECT image is obtained from the medical detection system. The specific process of collecting the patient's SPECT image includes: the patient takes the radioactive drug according to the doctor's instructions, and after waiting for the time required by the doctor, the doctor uses the SPECT device to collect images of the patient, obtains the SPECT image, and uploads the SPECT image to the medical system. Due to the influence of the equipment itself and other external factors, the directly collected SPECT image will have noise, which affects the subsequent analysis. The SPECT image needs to be denoised to obtain a denoised image. The denoised image is grayed to obtain an image of the drug concentration to be enhanced.
[0049] It should be noted that in the embodiment of the present invention, a weighted average grayscale algorithm is selected for grayscale processing, and a Gaussian filter is used for denoising. The specific methods are not introduced here, and they are all technical means well known to those skilled in the art. In other embodiments of the present invention, bilateral filtering can also be used for denoising, and a component method grayscale algorithm can be used for grayscale processing. Bilateral filtering and component method grayscale are technical means well known to those skilled in the art, and are not limited here. It should be noted that, in order to facilitate calculations, all indicator data involved in the calculations in the embodiments of the present invention are subjected to data preprocessing to eliminate the influence of dimensions. The specific means of eliminating the influence of dimensions are technical means well known to those skilled in the art, and are not limited here.
[0050] In order to improve the contrast and clarity of the radioactive drug concentration in the drug concentration image to be enhanced, it is necessary to perform image enhancement on the drug concentration image to be enhanced. Considering that the histogram equalization method is used to enhance the entire drug concentration image to be enhanced, although it can improve the overall contrast, it may not fully take into account the needs of the local area, resulting in poor image enhancement effects in the local area, so it is necessary to perform regional enhancement on the drug concentration image to be enhanced. Due to the differences in physiological activities of different tissues and organs, different absorption or metabolic rates of radioactive drugs will occur, especially the perfusion of the heart, the metabolism of the tumor, etc. will affect the distribution of radioactive drugs. Therefore, the present invention clusters the various drug block areas in the drug concentration image to be enhanced through the different performance conditions of the radioactive drugs in the drug concentration image to be enhanced, and then performs image enhancement.
[0051] Step S2: In the drug concentration image to be enhanced, the grayscale relative density of the pixel is obtained according to the similarity of the grayscale value of the pixel and the local surrounding space area; the drug influence of the pixel is obtained according to the inconsistency of the grayscale value of the local surrounding space area of the pixel; the drug distribution possibility of the pixel is obtained according to the grayscale value, grayscale relative density and drug influence of the pixel; according to the drug distribution possibility of all pixels, all pixels in the drug concentration image to be enhanced are clustered to obtain each drug block area.
[0052] In the drug concentration image to be enhanced, the differences in physiological activities of different tissues and organs will lead to different concentrations of radioactive drugs. The larger the gray value of the pixel, the higher the concentration of radioactive drugs in the area where the pixel is located. In order to cluster the distribution areas of each radioactive drug in the drug concentration image to be enhanced, it is necessary to first analyze the performance of the drug. Considering that when the concentration of radioactive drugs is low, the performance of radioactive drugs is low gray value and the distribution is relatively uniform; when the concentration of radioactive drugs is high, affected by factors such as pathological conditions and blood flow dynamics, the local grayscale characteristics of radioactive drugs are inconsistent. Based on this, the drug distribution possibility can be obtained. The larger the drug distribution possibility, the more likely the area where the pixel is located is the radioactive drug distribution area, and then the drug concentration image to be enhanced is clustered to obtain drug block areas that better reflect the distribution areas of each radioactive drug.
[0053] Considering that radiopharmaceutical concentrations cause radiopharmaceuticals to have different behaviors, when the radiopharmaceutical concentration is low, the radiopharmaceuticals will have low grayscale values and a relatively uniform distribution. For example, if the low grayscale value of a pixel is surrounded by low grayscale values, this may indicate a relatively uniform low-concentration radiopharmaceutical area; and if the grayscale value around the pixel suddenly increases, it often indicates that the pixel is an edge or boundary of the drug distribution. The relative grayscale density of a pixel reflects the proximity of the grayscale values of the pixel and the surrounding pixels. See Figure 2 , which shows a flow chart of a method for obtaining grayscale relative density in one embodiment of the present invention. Preferably, in one embodiment of the present invention, the method for obtaining grayscale relative density includes:
[0054] Step S201: Acquire all surrounding points of a pixel point in a preset surrounding space area.
[0055] In order to subsequently analyze the difference between the pixel point and surrounding pixels, all surrounding points of the pixel point in a preset surrounding space area are obtained.
[0056] In one embodiment of the present invention, for any pixel in the drug concentration image to be enhanced, the pixel is taken as the central pixel to construct a preset surrounding space region of size 10*10, and the center of the preset surrounding space region is the central pixel. In the present invention, all pixels in the preset surrounding space region except the central pixel are taken as surrounding points.
[0057] Step S202: Obtain a surrounding grayscale difference index of each surrounding point according to the grayscale value difference between each surrounding point and the pixel point.
[0058] The larger the surrounding grayscale difference index is, the greater the grayscale value difference between the surrounding points and the pixel point is.
[0059] In one embodiment of the present invention, in a preset surrounding space area of a pixel point, the absolute value of the difference between the grayscale value of each surrounding point and the pixel point is calculated to obtain a surrounding grayscale difference index of each surrounding point.
[0060] Step S203: Obtain the distribution distance index of each surrounding point according to the spatial distance between each surrounding point and the pixel point.
[0061] The larger the distribution distance index is, the greater the spatial distance between the surrounding points and the pixel point is.
[0062] In one embodiment of the present invention, in a preset surrounding space area of a pixel point, the Euclidean distance between each surrounding point and the pixel point is used as a distribution distance indicator of each surrounding point. It should be noted that the Euclidean distance is a prior art well known to those skilled in the art and will not be described in detail here.
[0063] Step S204: The surrounding grayscale difference index and distribution distance index of all surrounding points are integrated to obtain the grayscale relative density of the pixel point; the surrounding grayscale difference index and the distribution distance index are both negatively correlated with the grayscale relative density.
[0064] The greater the relative grayscale density, the closer the grayscale value of the surrounding area is to the pixel, which means that the grayscale value distribution around the pixel is closer to the pixel, the more uniform the grayscale distribution around the pixel is, and the pixel is more consistent with the performance characteristics of low-concentration radioactive drugs.
[0065] In one embodiment of the present invention, in a preset surrounding spatial area of a pixel point, the product of the surrounding grayscale difference index and the distribution distance index of the surrounding points is calculated to obtain the grayscale density index of the surrounding points; the cumulative value of the grayscale density index of all surrounding points is calculated, and the cumulative value is negatively correlated mapped to obtain the grayscale relative density of the pixel point. In one embodiment of the present invention, the method of negative correlation mapping is: the opposite number of the cumulative value is used as the power of an exponential function with a natural constant as the base to obtain a negative correlation mapping result. It should be noted that in other embodiments of the present invention, other negative correlation mapping methods such as opposite numbers and reciprocals may also be selected, which are all technical means well known to those skilled in the art and will not be elaborated or limited here.
[0066] Considering that radioactive drug concentrations lead to different performances of radioactive drugs, when the concentration of radioactive drugs is high, the distribution of radioactive drugs is more random due to the influence of factors such as pathological conditions and blood flow dynamics. The grayscale characteristics of high-concentration radioactive drugs in the local area are inconsistent. The drug distribution probability is obtained. The greater the drug distribution probability, the more random characteristics of radioactive drug distribution, and the area where the pixel is located is more likely to be a high-concentration radioactive drug distribution area. Please refer to Figure 3, which shows a flow chart of a method for obtaining a drug influence degree in one embodiment of the present invention. Preferably, in one embodiment of the present invention, the method for obtaining a drug influence degree includes:
[0067] Step S211: obtaining neighborhood points of a pixel point in a preset neighborhood area; and dividing a preset number of preset local areas from the preset neighborhood area.
[0068] In order to subsequently analyze the difference between the pixel point and the surrounding pixels, all neighborhood points of the pixel point in the preset neighborhood area and all preset local areas are obtained.
[0069] In order to reflect the surrounding range of the pixel point, in one embodiment of the present invention, the method for obtaining all neighboring points of the pixel point in the preset neighborhood area includes: taking the pixel point as the central pixel point, constructing a preset neighborhood area of size 9*9, and the center of the preset neighborhood area is the central pixel point. In the present invention, all pixels except the central pixel point in the preset neighborhood area are regarded as neighborhood points.
[0070] In order to analyze the local grayscale features of the pixel points, a preset number of preset local areas are divided from the preset neighborhood area. In one embodiment of the present invention, the method for obtaining the preset local areas includes:
[0071] A preset number of preset directions of the pixel points are constructed, and an area formed by all neighborhood points passed by each preset direction in the preset neighborhood area is used as a preset local area of each pixel point.
[0072] In one embodiment of the present invention, the preset number of preset directions passing through the pixel point are: the eight neighborhood directions of the pixel point, that is, all directions starting from the pixel point and pointing to the eight neighboring pixel points immediately surrounding, wherein the preset number is 8, and the area formed by all the neighborhood points passed by each preset direction in the preset neighborhood area is used as the preset local area of each pixel point. In other embodiments of the present invention, the method for obtaining the preset local area includes: based on the image coordinate system, in the preset neighborhood area of the pixel point, a straight line to be rotated is constructed by the pixel point in a direction parallel to the X-axis, and the straight line to be rotated is respectively rotated clockwise by each preset angle to obtain each preset straight line of the pixel point; each preset straight line only in the preset neighborhood area of the pixel point is used as a preset area line segment; the pixel point of the preset neighborhood area is used as a dividing point, and all the preset area line segments are divided to obtain all the preset segmented line segments of the pixel point, that is, a preset number of preset segmented line segments. All the neighborhood points passed by each preset segmented line segment are used as each preset local area, that is, a preset number of preset local areas are obtained. It should be noted that the image coordinate system is a technical means well known to those skilled in the art, and will not be described in detail here. In other embodiments of the present invention, based on the image coordinate system, in the preset neighborhood area of the pixel point, a straight line to be rotated is constructed through the pixel point in a direction parallel to the X-axis, and the straight line to be rotated is respectively rotated clockwise by various preset angles to obtain various preset straight lines of the pixel point, and all preset straight lines divide the preset neighborhood area equally into a preset number of preset local areas. In one embodiment of the present invention, the preset angles are 0 degrees, 45 degrees, 90 degrees and 135 degrees, and the preset number is 8.
[0073] Step S212: Obtaining the grayscale feature value of the preset local area of the pixel point according to the grayscale value difference of all neighborhood points in the preset local area of the pixel point.
[0074] In order to analyze the inconsistency of the grayscale features of the local area around the pixel, the grayscale feature value of the preset local area is first obtained. The larger the grayscale feature value, the greater the grayscale value difference feature between the pixel and all neighboring points in the preset local area.
[0075] In one embodiment of the present invention, a method for obtaining grayscale eigenvalues includes: obtaining the grayscale difference eigenvalue of each neighborhood point in a preset local area of the pixel point based on the difference in grayscale values between each neighborhood point and the neighboring points adjacent to it in a preset direction; obtaining the directional overall grayscale difference value of the preset local area of the pixel point based on the overall distribution of the grayscale difference eigenvalues of all neighborhood points; obtaining the directional grayscale unevenness value of the preset local area of the pixel point based on the fluctuation of the grayscale difference eigenvalues of all neighborhood points; obtaining the grayscale eigenvalue of the preset local area of the pixel point by combining the directional overall grayscale difference value and the directional grayscale unevenness value; the directional overall grayscale difference value and the directional grayscale unevenness value are both positively correlated with the grayscale eigenvalue.
[0076] The grayscale difference eigenvalue reflects the difference in grayscale values between adjacent neighborhood points. The larger the value, the greater the difference. The directional overall grayscale difference value reflects the grayscale difference eigenvalue of all neighborhood points in the preset local area. The larger the value, the greater the overall grayscale difference eigenvalue. The directional grayscale unevenness value reflects the fluctuation of the grayscale difference eigenvalue of all neighborhood points. The larger the value, the greater the fluctuation. The grayscale difference between the whole and the pixel in the preset local area, as well as the grayscale difference fluctuation, are combined to obtain the grayscale eigenvalue of the preset local area of the pixel. The larger the grayscale eigenvalue, the more obvious the difference in grayscale values of all neighborhood points in the preset local area of the pixel.
[0077] For the above steps, specifically, in the preset local area of the pixel point, in the preset local area of the pixel point, all the neighborhood points are sorted according to the preset direction, and the absolute value of the difference in grayscale values between each neighborhood point and its previous neighborhood point is calculated to obtain the grayscale difference characteristic value of each neighborhood point; in the preset local area of the pixel point, the mean of the grayscale difference characteristic values of all the neighborhood points is calculated to obtain the overall grayscale difference value of the direction of the preset local area of the pixel point; in the preset local area of the pixel point, the variance of the grayscale difference characteristic values of all the neighborhood points is calculated to obtain the directional grayscale unevenness of the preset local area of the pixel point; the product of the directional overall grayscale difference value and the directional grayscale unevenness is calculated to obtain the grayscale characteristic value of the preset local area of the pixel point. In other embodiments of the present invention, the method for obtaining the grayscale difference characteristic value includes: in the preset local area of the pixel point, all the neighborhood points are sorted according to the preset segment line segment derived direction, and the absolute value of the difference in grayscale values between each neighborhood point and its previous neighborhood point is calculated to obtain the grayscale difference characteristic value of each neighborhood point.
[0078] In other embodiments of the present invention, the method for obtaining grayscale eigenvalues also includes: calculating the mean of the absolute values of the grayscale value differences between each neighborhood point and its eight neighborhood pixel points in a preset local area of the pixel point to obtain the grayscale difference eigenvalue of each neighborhood point; calculating the mean of the grayscale difference eigenvalues of all neighborhood points in a preset local area of the pixel point to obtain the directional overall grayscale difference value of the preset local area of the pixel point; calculating the variance of the grayscale difference eigenvalues of all neighborhood points in a preset local area of the pixel point to obtain the directional grayscale unevenness of the preset local area of the pixel point; calculating the product of the directional overall grayscale difference value and the directional grayscale unevenness to obtain the grayscale eigenvalue of the preset local area of the pixel point. It should be noted that the eight-neighborhood pixel points are prior art well known to those skilled in the art and will not be elaborated on here.
[0079] Step S213: Obtain the drug influence degree of the pixel point according to the inconsistency of the grayscale feature values of all preset local areas of the pixel point.
[0080] Taking into account that when the concentration of radioactive drugs is high, it is affected by factors such as pathological conditions and dynamic blood flow, and its corresponding grayscale eigenvalues are inconsistent locally. The possibility of drug distribution is obtained. The greater the possibility of drug distribution, the more likely the area where the pixel is located is to be a high-concentration radioactive drug distribution area.
[0081] In one embodiment of the present invention, the variance of the grayscale feature values of the pixel points in all preset local areas is calculated to obtain the drug influence of the pixel points; the inconsistency is reflected by the variance, and the inconsistency is reflected by the variance.
[0082] In order to more accurately cluster the radioactive drug distribution area, it is considered that when clustering directly using grayscale values, the radioactive drug distribution characteristics may be ignored due to the singleness of grayscale values. By analyzing the performance characteristics of high-concentration radioactive drugs and low-concentration radioactive drugs, the drug distribution possibility is constructed for subsequent clustering to better capture the radioactive drug distribution characteristics in the drug concentration image to be enhanced, thereby improving the accuracy of clustering. In one embodiment of the present invention, the method for obtaining the drug distribution possibility includes:
[0083] Normalize the grayscale value of the pixel point proportionally to obtain the high concentration weight; calculate the difference between 1 and the high concentration weight to obtain the low concentration weight; calculate the product of the high concentration weight and the drug influence to obtain the first product value; calculate the product of the low concentration weight and the grayscale relative density to obtain the second product value; calculate the sum of the first product value and the second product value to obtain the drug distribution possibility of the pixel point. In one embodiment of the present invention, the proportional normalization method is: use a linear normalization function for normalization to limit the value range to between 0 and 1. The specific formula includes:
[0084] ;in, For the Possibility of drug distribution at each pixel; To adjust the parameters; For the The gray value of each pixel; is the standard normalization function; For the Drug influence of each pixel; For the The relative grayscale density of each pixel; For the High concentration weight of each pixel; For the In one embodiment of the present invention, the adjustment parameter The value of is 8, which is used to adjust the weight distribution of drug influence and grayscale relative density.
[0085] In the formula, Reflects the concentration of radioactive drugs in the area where the pixel is located. The larger the value, the greater the concentration, and the more the judgment center is inclined to the drug influence; otherwise, the judgment center is more inclined to the grayscale relative density. The weights of drug influence and grayscale relative density are adjusted so that the drug distribution possibility can more accurately reflect the performance characteristics of the radioactive drug distribution area.
[0086] At this point, the drug distribution probability is obtained.
[0087] Considering that the drug distribution possibility can more accurately reflect the performance characteristics of the radioactive drug distribution area, all pixels in the enhanced drug concentration image are clustered according to the drug distribution possibility of all pixels to obtain each drug block area.
[0088] In one embodiment of the present invention, a method for obtaining a drug block region includes:
[0089] Based on the region growing algorithm, all pixels in the enhanced drug concentration image are clustered according to the drug distribution probability of all pixels, and pixels with similar drug distribution probability are divided into a block area, so that each drug block area can be obtained.
[0090] It should be noted that the region growing algorithm is a technical means well known to those skilled in the art, and here we only briefly describe the steps of obtaining each drug block region using the region growing algorithm:
[0091] (1) Set each seed point in the drug concentration image to be enhanced, and use each seed point as the initial growth area; (2) Each growth area performs regional growth according to the preset growth criterion to form each updated growth area; (3) Repeat (2) until the growth area meets the preset iteration termination condition; (4) until all growth areas meet the iteration termination condition, use each final growth area as the drug block area, and output each drug block area. In one embodiment of the present invention, the preset growth criterion includes: taking the pixel point on the edge of the growth area as the edge pixel point of the growth area, if the absolute value of the difference in drug distribution possibility between the edge pixel point of the growth area and its adjacent pixel point is less than the preset difference value, the adjacent pixel point is added to the growth area. The preset iteration termination condition includes: if the absolute value of the difference in gradient value between the edge pixel point of the growth area and all its adjacent pixel points is not less than the preset difference value. In one embodiment of the present invention, the preset difference value is 0.1, and the implementer can set it according to the implementation scenario.
[0092] Step S3: performing image enhancement on each drug block region in the drug concentration image to be enhanced to obtain a drug concentration enhanced image.
[0093] The above steps are used to determine the drug block areas that better reflect the distribution areas of each radioactive drug. By performing image enhancement on each drug block area in the drug concentration image to be enhanced, the image enhancement fully considers the needs of the drug block area, better takes into account the needs of the local radioactive drug concentration area, improves the image enhancement effect, and makes the drug concentration enhanced image more accurately reflect the distribution of the radioactive drug concentration.
[0094] In one embodiment of the present invention, a method for acquiring a drug concentration enhanced image includes:
[0095] By using the histogram equalization method, each drug block area in the drug concentration image to be enhanced is enhanced to obtain a drug concentration enhanced image. In other embodiments of the present invention, an adaptive histogram equalization method can also be used to enhance the image of each drug block area in the drug concentration image to be enhanced to obtain a drug concentration enhanced image. It should be noted that the histogram equalization method and the adaptive histogram equalization method are technical means well known to those skilled in the art and will not be described in detail here.
[0096] Specifically, drug concentration enhanced image quantitative analysis is used to measure the concentration of radioactive drugs in different areas, so as to improve the accuracy of the measurement and assist doctors in treatment.
[0097] The present invention also proposes a radioactive drug concentration measurement system, see Figure 4 , which shows a structure diagram of a radioactive drug concentration measurement system provided by an embodiment of the present invention. The system includes: an image acquisition module 101, a clustering module 102, and an image enhancement module 103.
[0098] The image acquisition module 101 is used to acquire an image of drug concentration to be enhanced.
[0099] The clustering module 102 is used to obtain the grayscale relative density of the pixel point in the drug concentration image to be enhanced according to the similarity of the grayscale value of the pixel point and the local surrounding space area; obtain the drug influence of the pixel point according to the inconsistency of the grayscale value of the local surrounding space area of the pixel point; obtain the drug distribution possibility of the pixel point according to the grayscale value, grayscale relative density and drug influence of the pixel point; cluster all the pixels in the drug concentration image to be enhanced according to the drug distribution possibility of all the pixels to obtain each drug block area.
[0100] The image enhancement module 103 is used to perform image enhancement on each drug block region in the drug concentration image to be enhanced to obtain a drug concentration enhanced image.
[0101] It should be noted that: the system provided in the above embodiment is only illustrated by the above functional modules. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the computer device is divided into different functional modules to complete all or part of the functions described above. In addition, the radiopharmaceutical concentration measurement system and the radiopharmaceutical concentration measurement method embodiment provided in the above embodiment belong to the same concept. The specific implementation process is detailed in the method embodiment and will not be repeated here.
[0102] In summary, the embodiment of the present invention provides a method and system for measuring the concentration of radioactive drugs. First, the grayscale relative density of the pixel is obtained according to the similarity of the grayscale value of the pixel and the local surrounding space area; the drug influence of the pixel is obtained according to the inconsistency of the grayscale value of the local surrounding space area of the pixel; the drug distribution possibility of the pixel is obtained according to the grayscale value, grayscale relative density and drug influence of the pixel; according to the drug distribution possibility of all pixels, all pixels in the enhanced drug concentration image are clustered to obtain each drug block area; each drug block area in the enhanced drug concentration image is enhanced to obtain a drug concentration enhanced image. In the embodiment of the present invention, the needs of the local radioactive drug concentration area are fully considered to improve the image enhancement effect, so that the drug concentration enhanced image more accurately reflects the distribution of the radioactive drug concentration.
[0103] It should be noted that the sequence of the above embodiments of the present invention is only for description and does not represent the advantages and disadvantages of the embodiments. The processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.
[0104] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referenced to each other, and each embodiment focuses on the differences from other embodiments.
Claims
1. A method for measuring the concentration of radioactive drugs, It is characterized in that The method comprises: Acquiring a drug concentration image to be enhanced; In the drug concentration image to be enhanced, the grayscale relative density of the pixel is obtained according to the similarity of the grayscale value of the pixel and the local surrounding space area; the drug influence of the pixel is obtained according to the inconsistency of the grayscale value of the local surrounding space area of the pixel; the drug distribution possibility of the pixel is obtained according to the grayscale value of the pixel, the grayscale relative density and the drug influence; according to the drug distribution possibility, all the pixels in the drug concentration image to be enhanced are clustered to obtain each drug block area; Performing image enhancement on each of the drug block regions in the drug concentration image to be enhanced to obtain a drug concentration enhanced image; The method for obtaining the grayscale relative density includes: Get all surrounding points of the pixel in the preset surrounding space area; According to the gray value difference between each surrounding point and the pixel point, the surrounding gray value difference index of each surrounding point is obtained; According to the spatial distance between each surrounding point and the pixel point, the distribution distance index of each surrounding point is obtained; The grayscale relative density of the pixel point is obtained by combining the surrounding grayscale difference index and the distribution distance index of all surrounding points; the surrounding grayscale difference index and the distribution distance index are both negatively correlated with the grayscale relative density; The method for obtaining the surrounding grayscale difference index of the surrounding points includes: calculating the absolute value of the difference between the grayscale values of each surrounding point and the pixel point in a preset surrounding space area of the pixel point to obtain the surrounding grayscale difference index of each surrounding point; The method for obtaining the drug influence degree includes: Obtaining neighborhood points of the pixel point in a preset neighborhood area; dividing a preset number of preset local areas from the preset neighborhood area; According to the grayscale value differences of all neighboring points in the preset local area of the pixel point, the grayscale feature value of the preset local area of the pixel point is obtained; Obtaining the drug influence degree of the pixel point according to the inconsistency of the grayscale characteristic values of all the preset local areas of the pixel point; The method for obtaining the drug distribution possibility comprises: The grayscale value of the pixel point is proportionally normalized to obtain the high concentration weight; the difference between 1 and the high concentration weight is calculated to obtain the low concentration weight; the product of the high concentration weight and the drug influence is calculated to obtain the first product value; the product of the low concentration weight and the grayscale relative density is calculated to obtain the second product value; the sum of the first product value and the second product value is calculated to obtain the drug distribution possibility of the pixel point.
2. A method for calculating the concentration of a radioactive drug according to claim 1, It is characterized in that The method for obtaining the preset local area includes: A preset number of preset directions of the pixel points are constructed, and an area formed by all the neighborhood points that each preset direction passes through in the preset neighborhood area is used as a preset local area of each pixel point.
3. A method for calculating the concentration of a radioactive drug according to claim 2, It is characterized in that The method for obtaining the grayscale characteristic value comprises: In a preset local area of the pixel point, according to the difference in grayscale values between each neighborhood point and the neighboring points adjacent to it in a preset direction, a grayscale difference characteristic value of each neighborhood point is obtained; According to the overall distribution of the grayscale difference characteristic values of all neighborhood points, the overall grayscale difference value of the direction of the preset local area of the pixel point is obtained; According to the fluctuation of the grayscale difference characteristic values of all neighborhood points, the directional grayscale unevenness value of the preset local area of the pixel point is obtained; The grayscale characteristic value of the preset local area of the pixel point is obtained by combining the overall grayscale difference value of the direction and the grayscale unevenness value of the direction; the overall grayscale difference value of the direction and the grayscale unevenness value of the direction are both positively correlated with the grayscale characteristic value.
4. A method for calculating the concentration of a radioactive drug according to claim 1, It is characterized in that The method for obtaining the drug influence degree of a pixel point according to the inconsistency of the grayscale characteristic values of all the preset local areas of the pixel point includes: The variance of the grayscale eigenvalues of the pixel points in all preset local areas is calculated to obtain the drug influence of the pixel points.
5. A method for calculating the concentration of a radioactive drug according to claim 1, It is characterized in that The method for obtaining the drug block area comprises: Based on the region growing algorithm, all the pixels in the drug concentration image to be enhanced are clustered according to the drug distribution possibility of all the pixels, and each drug block region is obtained.
6. A method for calculating the concentration of a radioactive drug according to claim 1, It is characterized in that The method for acquiring the drug concentration enhanced image comprises: By using a histogram equalization method, image enhancement is performed on each of the drug block regions in the drug concentration image to be enhanced to obtain a drug concentration enhanced image.
7. A radiopharmaceutical concentration calculation system, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, It is characterized in that When the processor executes the computer program, the steps of a method for measuring the concentration of a radioactive drug as described in any one of claims 1 to 6 are implemented.
