Method and system for detecting the therapeutic effect of electroacupuncture in patients with premature ovarian failure based on medical imaging

Abstract

The present invention relates to the field of image processing technology, and in particular to a method and system for detecting the efficacy of electroacupuncture in patients with premature ovarian failure based on medical images. The method obtains the suspected follicle degree and suspected ovarian matrix degree of each pixel point based on the local grayscale change of each pixel point in the grayscale image of the ovarian medical image; obtains suspected follicle areas, suspected ovarian matrix areas and other areas based on the suspected follicle degree and suspected ovarian matrix degree of each pixel point, and obtains the credibility of each area based on the local characteristics of each area; obtains the adaptive h parameter of each pixel point in the NLM algorithm based on the gradient direction distribution within the local range of each pixel point and the credibility of the area where each pixel point is located, and then uses the NLM algorithm to denoise the grayscale image. The electroacupuncture efficacy of patients with premature ovarian failure is detected based on the denoised grayscale image, thereby improving the accuracy of detecting the electroacupuncture efficacy of patients with premature ovarian failure.

Description

Technical Field

[0001] The present invention relates to the technical field of image processing, and in particular to a method and system for detecting the efficacy of electroacupuncture in patients with premature ovarian failure based on medical images. Background Art

[0002] Premature ovarian failure is a disease that seriously affects women's reproductive health and physical and mental health. Premature ovarian failure not only leads to decreased female fertility, but also triggers a series of endocrine disorders, seriously affecting the patient's quality of life. In recent years, electroacupuncture treatment for premature ovarian failure has gradually gained attention. Electroacupuncture applies weak electric currents to specific acupuncture points to stimulate nerve afferent fibers, regulate the neuroendocrine system, and improve ovarian function. Ovarian B-ultrasound medical images can be used to display the number of follicles and ovarian morphology to evaluate the efficacy of electroacupuncture treatment for premature ovarian failure. However, in undenoised B-ultrasound medical images, noise may mask changes in ovarian morphology and interfere with the detection of follicle count, causing the efficacy evaluation results to deviate from the actual results. Therefore, before analyzing the B-ultrasound medical images of the ovaries, the B-ultrasound medical images of the ovaries need to be denoised.

[0003] Traditionally, the non-local means denoising algorithm (NLM algorithm) is used to denoise B-ultrasound medical images. However, when using the NLM algorithm to denoise B-ultrasound medical images, the Gaussian function smoothing parameter (h parameter) of each pixel point is usually set based on an empirical value. A larger h parameter has lower similarity requirements, and more pixel blocks will be included in the weighted average calculation, resulting in a stronger denoising effect but causing loss of image details. Conversely, a smaller h parameter has higher similarity requirements and can retain more image details, but will weaken the denoising effect.

[0004] Therefore, how to adaptively obtain the h parameter of each pixel to improve the denoising effect of ovarian B-ultrasound medical images and thereby improve the accuracy of detecting the efficacy of electroacupuncture in patients with premature ovarian failure has become an urgent problem to be solved. Summary of the Invention

[0005] In view of this, an embodiment of the present invention provides a method and system for detecting the efficacy of electroacupuncture in patients with premature ovarian failure based on medical images, so as to solve the problem of how to adaptively obtain the h parameter of each pixel point to improve the denoising effect of ovarian B-ultrasound medical images, thereby improving the accuracy of detecting the efficacy of electroacupuncture in patients with premature ovarian failure.

[0006] In a first aspect, an embodiment of the present invention provides a method for detecting the efficacy of electroacupuncture in patients with premature ovarian failure based on medical imaging, the method comprising the following steps:

[0007] Obtaining a grayscale image of the ovary of a patient with premature ovarian failure, and obtaining the suspected follicle degree and suspected ovarian stroma degree of each pixel based on the grayscale value distribution of each pixel within a local range of the grayscale image;

[0008] According to the suspected follicle degree and suspected ovarian stroma degree of each pixel point, the grayscale image is divided into suspected follicle area, suspected ovarian stroma area and other areas. The credibility of each suspected follicle area is obtained based on the gradient of the boundary pixels of each suspected follicle area and the shape regularity of each suspected follicle area. The credibility of each suspected ovarian stroma area is obtained based on the credibility of the adjacent areas of each suspected ovarian stroma area.

[0009] Based on the distribution of the gradient direction of each pixel within the local range of each pixel in the grayscale image, the credibility of the suspected follicle area, the credibility of the suspected ovarian stroma area, and the preset credibility of other areas, the adaptive h parameter of each pixel in the NLM algorithm is obtained. Based on the adaptive h parameter of each pixel, the grayscale image is denoised using the NLM algorithm to obtain a denoised grayscale image. The denoised grayscale image is used to detect the efficacy of electroacupuncture in patients with premature ovarian failure.

[0010] Preferably, obtaining the suspected follicle degree and suspected ovarian stroma degree of each pixel point according to the grayscale value distribution of the pixel points within the local range of each pixel point in the grayscale image includes:

[0011] For any pixel point in the grayscale image, a preset number of windows of different scales are constructed with the any pixel point as the center, the grayscale value mean and grayscale value standard deviation of all pixels in each window are calculated, the product of the reciprocal of the grayscale value mean and the reciprocal of the grayscale value standard deviation corresponding to each window is calculated, and the follicle characteristic value of each window is obtained. The mean of the follicle characteristic values ​​of all windows is linearly normalized to obtain the suspected follicle degree of any pixel point.

[0012] Preferably, the step of obtaining the suspected follicle degree and suspected ovarian stroma degree of each pixel point based on the grayscale value distribution of the pixel points within the local range of each pixel point in the grayscale image further includes:

[0013] Calculate the product between the reciprocal of the grayscale value mean corresponding to each window of any pixel and the grayscale value standard deviation to obtain the ovarian stroma characteristic value of each window, and linearly normalize the mean of the ovarian stroma characteristic values ​​of all windows to obtain the suspected ovarian stroma degree of any pixel.

[0014] Preferably, the grayscale image is divided into suspected follicle areas, suspected ovarian stroma areas and other areas according to the suspected follicle level and suspected ovarian stroma level of each pixel, including:

[0015] Clustering is performed according to the suspected follicle degree of each pixel point in the grayscale image to obtain at least one suspected follicle cluster, and the mean of the suspected follicle degree of all pixels corresponding to each suspected follicle cluster is calculated and recorded as the suspected follicle degree mean; if the suspected follicle degree mean of any suspected follicle cluster is greater than or equal to a preset suspected follicle degree threshold, the area formed by all pixels in any suspected follicle cluster in the grayscale image is recorded as the suspected follicle area;

[0016] Clustering is performed according to the suspected ovarian stroma degree of each pixel point in the grayscale image to obtain at least one suspected ovarian stroma cluster, and the mean of the suspected ovarian stroma degree of all pixels corresponding to each of the suspected ovarian stroma clusters is calculated and recorded as the suspected ovarian stroma degree mean; if the suspected ovarian stroma degree mean of any suspected ovarian stroma cluster is greater than or equal to a preset suspected ovarian stroma degree threshold, then the area formed by all pixels in any suspected ovarian stroma cluster in the grayscale image is recorded as the suspected ovarian stroma area;

[0017] The areas other than the suspected follicle area and the suspected ovarian stroma area in the grayscale image are recorded as other areas.

[0018] Preferably, obtaining the credibility of each suspected follicle region according to the gradient of the boundary pixel points of each suspected follicle region and the shape regularity of each suspected follicle region includes:

[0019] For any suspected follicle region, calculate the difference between the constant 1 and the circularity of the suspected follicle region, calculate the inverse of the sum of the difference and a preset constant, and obtain the circularity of the suspected follicle region;

[0020] Obtain the boundary pixel points of any suspected follicle area, and in the grayscale image, calculate the mean of the grayscale values ​​of a preset number of pixels on the right side of the normal direction of any boundary pixel point to obtain the right grayscale mean, calculate the mean of the grayscale values ​​of a preset number of pixels on the left side of the normal direction of any boundary pixel point to obtain the left grayscale mean, calculate the absolute value of the difference between the right grayscale mean and the left grayscale mean, calculate the product between the gradient value of any boundary pixel point and the absolute value of the difference, and obtain the clarity of any boundary pixel point;

[0021] The clarity mean of all boundary pixels of any suspected follicle region is calculated, and the product of the clarity mean and the circularity is used as the credibility of any suspected follicle region.

[0022] Preferably, obtaining the credibility of each suspected ovarian stroma region according to the credibility of adjacent regions of each suspected ovarian stroma region includes:

[0023] For any suspected ovarian stroma region, in the grayscale image, obtain at least one pixel point adjacent to a boundary pixel point of the any suspected ovarian stroma region, record it as a target pixel point, and eliminate the any suspected ovarian stroma region in the area where all target pixels are located to obtain at least one adjacent area of ​​the any suspected ovarian stroma region;

[0024] For any adjacent region, the credibility of the adjacent region is obtained based on the gradient of the boundary pixels of the adjacent region and the shape regularity of the adjacent region, which is recorded as the follicle credibility. The product of the mean of the suspected follicle degree of all pixels in the adjacent region and the follicle credibility of the adjacent region is calculated to obtain the follicle possibility degree of the adjacent region.

[0025] The follicle possibility degree of each of the adjacent areas of the any suspected ovarian stroma area is obtained, and the maximum value among the follicle possibility degrees of all the adjacent areas is selected as the credibility of the any suspected ovarian stroma area.

[0026] Preferably, the step of obtaining the adaptive h parameter of each pixel in the NLM algorithm based on the distribution of the gradient direction of the pixel within the local range of each pixel in the grayscale image, the credibility of the suspected follicle area, the credibility of the suspected ovarian stroma area, and the preset credibility of other areas includes:

[0027] For any pixel point in the grayscale image, if the pixel point belongs to a suspected follicle area, the product of the suspected follicle degree of the pixel point and the credibility of the suspected follicle area where the pixel point is located is calculated to obtain the criticality of the pixel point;

[0028] If any of the pixels belongs to a suspected ovarian stroma area, the product of the suspected ovarian stroma degree of the pixel and the credibility of the suspected ovarian stroma area where the pixel is located is calculated to obtain the criticality of the pixel;

[0029] If any pixel point belongs to both the suspected ovarian stroma area and the suspected follicle area, the maximum value of the suspected follicle degree and the suspected ovarian stroma degree of any pixel point is obtained; if the maximum value is the suspected follicle degree, the product of the suspected follicle degree and the credibility of the suspected follicle area where the any pixel point is located is calculated to obtain the criticality of the any pixel point; if the maximum value is the suspected ovarian stroma degree, the product of the suspected ovarian stroma degree and the credibility of the suspected ovarian stroma area where the any pixel point is located is calculated to obtain the criticality of the any pixel point;

[0030] If any of the pixels belongs to other areas, the preset credibility of the other areas is used as the criticality of any of the pixels;

[0031] According to the criticality of any pixel point and the distribution of gradient directions of pixels within a local range of any pixel point, an adaptive h parameter of any pixel point in the NLM algorithm is obtained.

[0032] Preferably, obtaining the adaptive h parameter of any pixel in the NLM algorithm based on the criticality of any pixel and the distribution of the gradient direction of pixels within the local range of any pixel includes:

[0033] In the grayscale image, a target window of a preset size is constructed with any pixel as the center, and the gradient direction entropy is obtained according to the gradient directions of all pixels in the target window. The product of the gradient value of any pixel and the inverse of the gradient direction entropy is linearly normalized to obtain the edge degree of any pixel;

[0034] Performing a weighted summation on the edge degree and the critical degree of any pixel point to obtain a weighted summation result, calculating the difference between a preset maximum h parameter and a preset minimum h parameter to obtain a preset h parameter range difference, and calculating the product between the preset h parameter range difference and the weighted summation result to obtain an h parameter adjustment coefficient for any pixel point;

[0035] The difference between the preset maximum h parameter and the h parameter adjustment coefficient of any pixel point is calculated to obtain the adaptive h parameter of any pixel point in the NLM algorithm.

[0036] Preferably, the preset credibility of the other areas is set to 0.

[0037] In a second aspect, an embodiment of the present invention further provides a system for detecting the efficacy of electroacupuncture in patients with premature ovarian failure based on medical imaging, comprising a memory, a processor, and a computer program stored in the memory and running on the processor. When the processor executes the computer program, it implements a method for detecting the efficacy of electroacupuncture in patients with premature ovarian failure based on medical imaging as described in the first aspect.

[0038] Compared with the prior art, the embodiments of the present invention have the following beneficial effects:

[0039] The present invention obtains a grayscale image of an ovarian medical image of a patient with premature ovarian failure, obtains a suspected follicle degree and a suspected ovarian matrix degree of each pixel point based on a grayscale value distribution of pixels within a local range of each pixel point in the grayscale image; divides the grayscale image into a suspected follicle region, a suspected ovarian matrix region, and other regions based on the suspected follicle degree and suspected ovarian matrix degree of each pixel point; obtains the credibility of each suspected follicle region based on the gradient of boundary pixels of each suspected follicle region and the shape regularity of each suspected follicle region; obtains the credibility of each suspected ovarian matrix region based on the credibility of adjacent regions of each suspected ovarian matrix region; obtains an adaptive h parameter of each pixel point in an NLM algorithm based on a distribution of gradient directions of pixels within a local range of each pixel point in the grayscale image, the credibility of the suspected follicle region, the credibility of the suspected ovarian matrix region, and preset credibility of other regions; denoises the grayscale image using the NLM algorithm based on the adaptive h parameter of each pixel point to obtain a denoised grayscale image; and detects the therapeutic effect of electroacupuncture on patients with premature ovarian failure based on the denoised grayscale image. Among them, according to the local characteristics of each pixel point in the grayscale image (the suspected follicle degree and the suspected ovarian stroma degree), the suspected follicle area and the suspected ovarian stroma area are obtained. According to the characteristics of each suspected follicle area and the suspected ovarian stroma area, the credibility of each suspected follicle area and the suspected ovarian stroma area is obtained to eliminate the interference of the noise area; according to the credibility of the area where each pixel point is located and the local characteristics of each pixel point, the adaptive h parameter of each pixel point in the NLM algorithm is obtained, and then according to the adaptive h parameter of each pixel point, the grayscale image is denoised using the NLM algorithm. While denoising, the characteristics of the key areas (follicle area and ovarian stroma area) are retained, thereby improving the denoising effect of ovarian B-ultrasound medical images, and thus improving the accuracy of detecting the efficacy of electroacupuncture in patients with premature ovarian failure. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. 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 any creative work.

[0041] Figure 1 This is a flow chart of a method for detecting the efficacy of electroacupuncture for patients with premature ovarian failure based on medical imaging, provided in Example 1 of the present invention. DETAILED DESCRIPTION

[0042] The following describes in detail embodiments of the present disclosure, examples of which are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present disclosure, and should not be construed as limiting the present disclosure.

[0043] It should be noted that the terms "first," "second," and the like in the specification of the present disclosure and the accompanying drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or precedence. It should be understood that the terms used in this manner are interchangeable where appropriate, so that the embodiments of the present disclosure described herein can be implemented in an order other than those illustrated or described herein. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present disclosure. Instead, they are merely examples of devices and methods consistent with some aspects of the present disclosure.

[0044] In order to illustrate the technical solution of the present invention, specific embodiments are provided below.

[0045] See also Figure 1 , is a flow chart of a method for detecting the efficacy of electroacupuncture in patients with premature ovarian failure based on medical imaging, provided in Example 1 of the present invention. Figure 1 As shown, the method may include:

[0046] Step S101, obtaining a grayscale image of the ovary medical imaging of a patient with premature ovarian failure, and obtaining the suspected follicle degree and suspected ovarian stroma degree of each pixel point based on the grayscale value distribution of the pixel points within the local range of each pixel point in the grayscale image.

[0047] Ovarian medical images of patients with premature ovarian failure after electroacupuncture treatment are obtained using a B-ultrasound machine. Since the efficacy of electroacupuncture treatment for patients with premature ovarian failure needs to be detected in combination with the number of follicles and ovarian morphology in the ovarian medical images, and there may be noise in the ovarian medical images, the noise may mask the changes in ovarian morphology and interfere with the detection of the number of follicles, thereby causing the efficacy test results to deviate from the actual results, the ovarian medical images need to be denoised before analysis.

[0048] Traditionally, the NLM algorithm is used to denoise ovarian medical images. However, the Gaussian function smoothing parameter (h parameter) for each pixel in ovarian medical images is usually set based on empirical values. A larger h parameter has lower similarity requirements, and more pixel blocks will be included in the weighted average calculation, resulting in a stronger denoising effect but causing loss of details. Conversely, a smaller h parameter has higher similarity requirements and can retain more details, but will weaken the denoising effect.

[0049] Therefore, in an embodiment of the present invention, the ovarian medical image is first grayscaled using OpenCV to obtain a grayscale image of the ovarian medical image of a patient with premature ovarian failure. Then, the local change characteristics of each pixel in the grayscale image are analyzed to obtain the adaptive h parameter of each pixel in the NLM algorithm, thereby improving the denoising effect of the ovarian B-ultrasound medical image, and further improving the accuracy of detecting the efficacy of electroacupuncture treatment for premature ovarian failure in patients. Among them, the use of OpenCV to grayscale the ovarian medical image is a prior art and will not be repeated here.

[0050] Since the efficacy of electroacupuncture treatment for patients with premature ovarian failure needs to be detected in combination with the number of follicles and ovarian morphology in ovarian medical images, it is first necessary to determine the follicle area and ovarian stroma area in the grayscale image. For the pixels at the edges of the follicle area and ovarian stroma area, a smaller h parameter should be assigned to them to preserve the edge details; for the pixels inside the follicle area and ovarian stroma area, a larger h parameter should be assigned to them to preserve the morphological characteristics within the area while appropriately denoising and eliminating noise interference.

[0051] Considering that follicles typically appear as dark areas, the grayscale value of the follicle region is low in grayscale images, and the grayscale values ​​of the pixels within the region are evenly distributed. The ovarian stroma is composed of the cortex and medulla. The cortex contains follicles and dense connective tissue, while the medulla contains loose connective tissue and abundant blood vessels, nerves, lymphatic vessels, and smooth muscle fibers. Different tissue components reflect and absorb ultrasound differently, resulting in the ovarian stroma region appearing as hypoechoic overall. In grayscale images, the grayscale value of the ovarian stroma region is low, and the grayscale values ​​of the pixels within the region are unevenly distributed. Furthermore, considering that ovarian medical images contain not only follicle and ovarian stroma regions, but also other tissue regions that exhibit high echoes or noise interference, which appear as higher grayscale values ​​in grayscale images, in embodiments of the present invention, the suspected follicle and suspected ovarian stroma levels of each pixel are obtained based on the local grayscale features of each pixel in the grayscale image. This is used to preliminarily determine the likelihood that each pixel belongs to the follicle and ovarian regions while reducing interference from other tissue regions or noise interference, thereby determining the follicle and ovarian stroma regions in the grayscale image.

[0052] Taking the i-th pixel in the grayscale image as an example, the specific method for obtaining the suspected follicle degree of the i-th pixel is:

[0053] Three windows of different scales are constructed with the i-th pixel as the center. In the embodiment of the present invention, the scales of the three windows are set to 5×5, 7×7 and 9×9 respectively. There is no restriction here. The implementer can set the number of windows and the window scale according to the specific scenario, calculate the gray value mean and gray value standard deviation of all pixels in each window, calculate the product between the reciprocal of the gray value mean and the reciprocal of the gray value standard deviation corresponding to each window, and obtain the follicle characteristic value of each window. The mean of the follicle characteristic values ​​of all windows is linearly normalized to obtain the suspected follicle degree of any pixel point. The linear normalization is a prior art and will not be repeated here.

[0054] In one embodiment, the calculation formula for the suspected follicle degree of the i-th pixel is:

[0055]

[0056] in, Indicates the suspected follicle degree of the i-th pixel, represents the number of all windows corresponding to the i-th pixel (in this embodiment of the present invention, N=3), Represents the number of all pixels in a window of size n, Indicates the grayscale value of the jth pixel in the window of size n at the i-th pixel. It represents the standard deviation of the grayscale values ​​of all pixels in the window with a scale of n at the i-th pixel point, and norm() represents the linear normalization function.

[0057] It should be noted that The smaller it is, the more the i-th pixel point conforms to the dark area characteristics, that is, the more the i-th pixel point conforms to the characteristics of the follicle area, and thus The larger it is, the greater the possibility that the i-th pixel is a pixel in the follicle area; The smaller it is, the more evenly the grayscale value of the pixel is distributed in the window corresponding to the i-th pixel. The larger the value is, the greater the possibility that the i-th pixel is a pixel in the follicle area.

[0058] Furthermore, the suspected ovarian stroma degree of the i-th pixel is obtained, specifically:

[0059] The product of the reciprocal of the grayscale value mean and the grayscale value standard deviation corresponding to each window of the i-th pixel point is calculated to obtain the ovarian stroma characteristic value of each window, and the mean of the ovarian stroma characteristic values ​​of all windows is linearly normalized to obtain the suspected ovarian stroma degree of the i-th pixel point.

[0060] In one embodiment, the calculation formula for the suspected ovarian stroma level of the i-th pixel is:

[0061]

[0062] in, Indicates the suspected ovarian stroma degree of the i-th pixel, represents the number of all windows corresponding to the i-th pixel (in this embodiment of the present invention, N=3), Represents the number of all pixels in a window of size n, Indicates the grayscale value of the jth pixel in the window of size n at the i-th pixel. It represents the standard deviation of the grayscale values ​​of all pixels in the window with a scale of n at the i-th pixel point, and norm() represents the linear normalization function.

[0063] It should be noted that The smaller the value, the more consistent the i-th pixel point is with the low echo characteristics of the ovarian stroma area. The larger it is, the greater the possibility that the i-th pixel is a pixel in the ovarian stroma area; The larger the value, the more uneven the grayscale value distribution of the pixel points in the window corresponding to the i-th pixel point. The larger the value is, the greater the possibility that the i-th pixel is a pixel in the ovarian stroma area.

[0064] At this point, the suspected follicle degree and suspected ovarian matrix degree of the i-th pixel point are obtained. Similarly, the suspected follicle degree and suspected ovarian matrix degree of each pixel point in the grayscale image are obtained for subsequent determination of the follicle area and ovarian matrix area in the grayscale image.

[0065] Step S102: Divide the grayscale image into suspected follicle areas, suspected ovarian stroma areas, and other areas based on the suspected follicle degree and suspected ovarian stroma degree of each pixel point. Obtain the credibility of each suspected follicle area based on the gradient of the boundary pixels of each suspected follicle area and the shape regularity of each suspected follicle area. Obtain the credibility of each suspected ovarian stroma area based on the credibility of the adjacent areas of each suspected ovarian stroma area.

[0066] After obtaining the suspected follicle degree and suspected ovarian stroma degree of each pixel in the grayscale image in step S101, the suspected follicle area and suspected ovarian stroma area in the grayscale image are preliminarily determined. Specifically:

[0067] Utilize the mean shift clustering algorithm to cluster according to the suspected follicle degree of each pixel in the grayscale image to obtain at least one suspected follicle cluster. There is no restriction here. The implementer can select the clustering algorithm according to the specific scenario, and calculate the mean of the suspected follicle degree of all pixels corresponding to each of the suspected follicle clusters, which is recorded as the suspected follicle degree mean. According to experimental statistics, in an embodiment of the present invention, the preset suspected follicle degree threshold is set to 0.8. There is no restriction here. The implementer can set it according to the specific scenario. If the suspected follicle degree mean of any suspected follicle cluster is greater than or equal to 0.8, the area composed of all pixels in any suspected follicle cluster in the grayscale image is recorded as the suspected follicle area.

[0068] Using the mean shift clustering algorithm, clustering is performed according to the suspected ovarian stroma degree of each pixel in the grayscale image to obtain at least one suspected ovarian stroma cluster, and the mean of the suspected ovarian stroma degree of all pixels corresponding to each of the suspected ovarian stroma clusters is calculated, and recorded as the suspected ovarian stroma degree mean. According to experimental statistics, in an embodiment of the present invention, a preset suspected ovarian stroma degree threshold is set to 0.8, which is not limited here. The implementer can set it according to the specific scenario. If the suspected ovarian stroma degree mean of any suspected ovarian stroma cluster is greater than or equal to 0.8, the area composed of all pixels in any suspected ovarian stroma cluster in the grayscale image is recorded as the suspected ovarian stroma area;

[0069] The areas other than the suspected follicle area and the suspected ovarian stroma area in the grayscale image are recorded as other areas. The mean shift clustering algorithm is an existing technology and will not be described here in detail.

[0070] Since there may be interference areas with features similar to those of the follicle area or the ovarian stroma area in the B-ultrasound medical image of the ovary, in an embodiment of the present invention, the local features of the suspected follicle area and the suspected ovarian stroma area in the grayscale image are combined to obtain the credibility of the suspected follicle area and the suspected ovarian stroma area, respectively, to improve the accuracy of the judgment of the follicle area or the ovarian stroma area.

[0071] Considering that the follicle region is quasi-circular with clear boundaries, and the ovarian stroma region and the follicle region belong to the same ovarian region, the ovarian stroma region and the follicle region are adjacent to each other, while the interference region generally has an irregular shape and a fuzzy boundary. Based on the above characteristics, in the embodiment of the present invention, the credibility of each suspected follicle region is first obtained based on the gradient of the boundary pixel points of each suspected follicle region and the shape regularity of each suspected follicle region. Specifically:

[0072] For any suspected follicle region, calculate the difference between the constant 1 and the circularity of the suspected follicle region, calculate the inverse of the sum of the difference and a preset constant, and obtain the circularity of the suspected follicle region;

[0073] Binarize any suspected follicle area, and use the findContours function to extract the outermost pixel points of any suspected follicle area, that is, the boundary pixel points of any suspected follicle area. In the grayscale image, use the Sobel operator to obtain the normal direction of any boundary pixel point, calculate the mean of the grayscale values ​​of a preset number of pixel points on the right side of the normal direction of any boundary pixel point, and obtain the right grayscale mean. Calculate the mean of the grayscale values ​​of a preset number of pixel points on the left side of the normal direction of any boundary pixel point to obtain the left grayscale mean. Calculate the absolute value of the difference between the right grayscale mean and the left grayscale mean, calculate the product between the gradient value of any boundary pixel point and the absolute value of the difference, and obtain the clarity of any boundary pixel point. The preset number is set to 3, which is not limited here. The implementer can set it according to the specific scenario. Binarization, findContours function, and Sobel operator to obtain the normal direction of pixel points are existing technologies and will not be repeated here.

[0074] The clarity mean of all boundary pixels of any suspected follicle region is calculated, and the product of the clarity mean and the circularity is used as the credibility of any suspected follicle region.

[0075] In one embodiment, taking the fth suspected follicle region as an example, the calculation formula for the reliability of the fth suspected follicle region is:

[0076]

[0077] in, represents the reliability of the fth suspected follicle area, represents the circularity of the fth suspected follicle area, Represents a preset constant, used to prevent the denominator from being 0. In the embodiment of the present invention, ,There is no restriction here, and the implementer can set it according to the specific scenario. represents the gradient value of the bth boundary pixel point in the fth suspected follicle area, represents the mean of the grayscale values ​​of a preset number (in the embodiment of the present invention, the preset number is 3) of pixels on the left side of the normal direction of the b boundary pixels, that is, the left grayscale mean, represents the average of the grayscale values ​​of a preset number (in the embodiment of the present invention, the preset number is 3) of pixels on the right side of the normal direction of the b boundary pixels, that is, the right grayscale mean, represents the number of all boundary pixels of the fth suspected follicle area, Indicates the absolute value symbol.

[0078] It should be noted that The larger the value is, the closer the fth suspected follicle area is to a circle. The larger it is, the higher the probability that the fth suspected follicle region belongs to the follicle region; The bigger, and The larger the value is, the clearer the boundary of the fth suspected follicle area is. The larger it is, the higher the possibility that the fth suspected follicle region belongs to the follicle region.

[0079] Similarly, the credibility of all suspected follicle regions in the grayscale image is obtained.

[0080] Furthermore, the credibility of all suspected ovarian stroma regions in the grayscale image is obtained. Taking the hth suspected ovarian stroma region as an example, since the ovarian stroma region and the follicle region both belong to the ovarian region and are adjacent to the follicle region, in an embodiment of the present invention, according to the method for obtaining the credibility of the suspected follicle region, the follicle possibility degree of each adjacent region of the hth suspected ovarian stroma region in the grayscale image is obtained, and then the credibility of the hth suspected ovarian stroma region is obtained based on the follicle possibility degree of each adjacent region. Specifically:

[0081] Binarize the hth suspected ovarian matrix region, and use the findContours function to extract the outermost pixel points of the hth suspected ovarian matrix region, that is, the boundary pixel points of the hth suspected ovarian matrix region. In the grayscale image, obtain at least one pixel point adjacent to the boundary pixel point of the hth suspected ovarian matrix region, record it as the target pixel point, and eliminate the hth suspected ovarian matrix region in the area where all target pixels are located to obtain at least one adjacent area of ​​the hth suspected ovarian matrix region;

[0082] For any adjacent area, according to the above-mentioned method for obtaining the credibility of the suspected follicle area, the credibility of any adjacent area is obtained according to the gradient of the boundary pixel points of any adjacent area and the shape regularity of any adjacent area, which is recorded as the follicle credibility. The product of the mean of the suspected follicle degree of all pixels in any adjacent area and the follicle credibility of any adjacent area is calculated to obtain the possible follicle degree of any adjacent area.

[0083] In one embodiment, taking the xth adjacent region of the hth suspected ovarian stroma region as an example, the calculation formula for the follicle possibility of the xth adjacent region is:

[0084]

[0085] in, Indicates the follicle possibility of the xth adjacent area of ​​the hth suspected ovarian stroma area, represents the mean value of the suspected follicle degree of all pixels in the xth adjacent area of ​​the hth suspected ovarian stroma area, It represents the reliability of the follicle in the xth adjacent area of ​​the hth suspected ovarian stroma area.

[0086] It should be noted that The larger the value is, the more the xth adjacent area conforms to the characteristics of the pixels in the follicle area. The larger it is, the more likely that the xth adjacent region is the follicle region, and the higher the probability that the hth suspected ovarian stroma region belongs to the suspected ovarian stroma region; The larger the value is, the greater the circular similarity of the xth adjacent area is, and the clearer the boundary is, the more consistent it is with the characteristics of the follicle area. The larger the value is, the greater the possibility that the xth adjacent region is the follicle region, and the higher the possibility that the hth suspected ovarian stroma region belongs to the suspected ovarian stroma region.

[0087] Similarly, the follicle probability of each adjacent area of ​​the h-th suspected ovarian matrix area is obtained, and the maximum value of the follicle probability of all adjacent areas is selected as the credibility of the h-th suspected ovarian matrix area, which is recorded as .

[0088] Similarly, the credibility of each suspected ovarian stroma region in the grayscale image is obtained.

[0089] Step S103: Based on the distribution of the gradient direction of each pixel within the local range of each pixel in the grayscale image, the credibility of the suspected follicle area, the credibility of the suspected ovarian stroma area, and the preset credibility of other areas, the adaptive h parameter of each pixel in the NLM algorithm is obtained. Based on the adaptive h parameter of each pixel, the grayscale image is denoised using the NLM algorithm to obtain a denoised grayscale image. The denoised grayscale image is used to detect the efficacy of electroacupuncture in patients with premature ovarian failure.

[0090] After obtaining the credibility of each suspected follicle region and each suspected ovarian stroma region in the grayscale image according to step S102, the criticality of each pixel is obtained according to the suspected follicle degree and suspected ovarian stroma degree of each pixel in the grayscale image and the credibility of the region where each pixel is located. Then, the adaptive h parameter of each pixel in the NLM algorithm is obtained according to the criticality of each pixel. Specifically:

[0091] For the i-th pixel in the grayscale image, if the i-th pixel belongs to the suspected follicle area, the product of the suspected follicle degree of the i-th pixel and the credibility of the suspected follicle area where the i-th pixel is located is calculated to obtain the criticality of the i-th pixel, which is recorded as ,Right now ,in, Indicates the suspected follicle degree of the i-th pixel, Indicates the credibility of the suspected follicle area where the i-th pixel is located. The greater the suspected follicle degree of the i-th pixel and the greater the credibility of the suspected follicle area where the i-th pixel is located, the greater the possibility that the i-th pixel belongs to the follicle area;

[0092] If the i-th pixel belongs to the suspected ovarian stroma area, the product of the suspected ovarian stroma degree of the i-th pixel and the credibility of the suspected ovarian stroma area where the i-th pixel is located is calculated to obtain the criticality of the i-th pixel, which is recorded as ,Right now ,in, Indicates the suspected ovarian stroma degree of the i-th pixel, Indicates the credibility of the suspected ovarian stroma region where the i-th pixel is located. The greater the degree of suspected ovarian stroma of the i-th pixel and the greater the credibility of the suspected ovarian stroma region where the i-th pixel is located, the greater the possibility that the i-th pixel belongs to the ovarian stroma region;

[0093] Since the suspected ovarian matrix area and the suspected follicle area are clustered according to the suspected ovarian matrix degree and the suspected follicle degree of each pixel, it is possible that a certain pixel belongs to both the suspected ovarian matrix area and the suspected follicle area. If the i-th pixel belongs to both the suspected ovarian matrix area and the suspected follicle area, the maximum value of the suspected follicle degree and the suspected ovarian matrix degree of the i-th pixel is obtained. If the maximum value is the suspected follicle degree, the product of the suspected follicle degree and the credibility of the suspected follicle area where the i-th pixel is located is calculated to obtain the criticality of the i-th pixel, that is, If the maximum value is the suspected ovarian stroma degree, then the product of the suspected ovarian stroma degree and the credibility of the suspected ovarian stroma area where the i-th pixel point is located is calculated to obtain the criticality of the i-th pixel point, that is, ;

[0094] Since the efficacy of electroacupuncture in patients with premature ovarian failure is detected based on the number of follicles and ovarian morphology, and other areas are irrelevant to the detection of the efficacy of electroacupuncture in patients with premature ovarian failure, if the i-th pixel point belongs to other areas, the preset credibility of other areas is used as the criticality of the i-th pixel point. In the present invention, the preset credibility of other areas is set to 0, that is, if the i-th pixel point belongs to other areas, the criticality of the i-th pixel point is There is no restriction here, and implementers can set it according to specific scenarios.

[0095] At this point, the criticality of the i-th pixel point is obtained. The higher the criticality of the i-th pixel point, the higher the possibility that it belongs to the follicle area or the ovarian stroma area. Since the efficacy of electroacupuncture in patients with premature ovarian failure is detected based on the number of follicles and the morphology of the ovaries, it is also necessary to retain the detailed features of the suspected follicle area and the suspected ovarian stroma area in the grayscale image. If the i-th pixel point is an edge pixel point of the suspected follicle area or the suspected ovarian stroma area, it should be given a smaller h parameter to retain the edge details. Since the edges of the follicle area and the ovarian stroma area are relatively smooth, in an embodiment of the present invention, the edge degree of the i-th pixel point is obtained based on the distribution of the gradient direction of the i-th pixel point within its local range. Specifically:

[0096] In the grayscale image, a 5×5 target window is constructed with the i-th pixel as the center. There is no restriction here. The implementer can set the size of the target window according to the specific scenario. The gradient direction entropy is obtained according to the gradient direction of all pixels in the target window. The product of the gradient value of the i-th pixel and the inverse of the gradient direction entropy is linearly normalized to obtain the edge degree of the i-th pixel.

[0097] In one embodiment, the calculation formula for the edge degree of the i-th pixel is:

[0098]

[0099] in, Indicates the edge degree of the i-th pixel, Represents the gradient value of the i-th pixel, It represents the gradient directional entropy of all pixels in the target window of the i-th pixel, and norm() is a linear normalization function.

[0100] It should be noted that The smaller it is, the more consistent the distribution of the gradient direction of the pixels in the target window is. The larger it is, the greater the possibility that the i-th pixel is an edge pixel of the suspected follicle area or the suspected ovarian stroma area; The larger the value, the more dramatic the change of the gray value of the i-th pixel in the local range of the i-th pixel, and the greater the edge feature of the i-th pixel. The larger the value is, the greater the possibility that the i-th pixel is an edge pixel of the suspected follicle area or the suspected ovarian stroma area.

[0101] Furthermore, according to the edge degree and criticality of the i-th pixel, the adaptive h parameter of the i-th pixel in the NLM algorithm is obtained. Specifically:

[0102] Performing a weighted summation on the edge degree and the critical degree of the i-th pixel to obtain a weighted summation result, calculating the difference between a preset maximum h parameter and a preset minimum h parameter to obtain a preset h parameter range difference, and calculating the product of the preset h parameter range difference and the weighted summation result to obtain an h parameter adjustment coefficient for the i-th pixel;

[0103] The difference between the preset maximum h parameter and the h parameter adjustment coefficient of the i-th pixel point is calculated to obtain the adaptive h parameter of the i-th pixel point in the NLM algorithm.

[0104] In one embodiment, the calculation formula of the adaptive h parameter of the i-th pixel point is:

[0105]

[0106] in, represents the adaptive h parameter of the i-th pixel, Indicates the preset maximum h parameter, Indicates the preset minimum h parameter, represents the weight, Indicates the edge degree of the i-th pixel, Indicates the criticality of the i-th pixel.

[0107] It should be noted that, according to experimental statistics, in the embodiment of the present invention, setting , There is no restriction here, and implementers can set it according to specific scenarios. The weight used to represent the edge degree, The weight of the criticality is represented by the adaptive h parameter of the i-th pixel in the NLM algorithm, which is mainly based on its criticality. Therefore, in the embodiment of the present invention, ,Right now , there is no restriction here, and the implementer can set it according to the specific scenario. The greater the criticality of the i-th pixel and the greater the edge degree, the greater the possibility that the i-th pixel is an edge pixel of the suspected follicle area or the suspected ovarian stroma area, and it should be given a smaller h parameter to retain edge details, thereby The smaller it is, the smaller the adaptive h parameter of the i-th pixel is.

[0108] Similarly, the adaptive h parameter for all pixels in the grayscale image is obtained. Based on the adaptive h parameter for each pixel, the grayscale image is denoised using the NLM algorithm to obtain a denoised grayscale image. Within this denoised grayscale image, the efficacy of electroacupuncture in patients with premature ovarian failure is assessed based on the number of follicles and the morphology of the ovarian stroma. Detecting the efficacy of electroacupuncture in patients with premature ovarian failure based on the number of follicles and the morphology of the ovarian stroma is a prior art technique and will not be further elaborated here.

[0109] In summary, the present invention obtains a grayscale image of an ovarian medical image of a patient with premature ovarian failure, obtains the suspected follicle degree and suspected ovarian matrix degree of each pixel point based on the grayscale value distribution of the pixel points within the local range of each pixel point in the grayscale image; divides the grayscale image into a suspected follicle area, a suspected ovarian matrix area, and other areas based on the suspected follicle degree and suspected ovarian matrix degree of each pixel point; obtains the credibility of each suspected follicle area based on the gradient of the boundary pixels of each suspected follicle area and the shape regularity of each suspected follicle area; obtains the credibility of each suspected ovarian matrix area based on the credibility of the adjacent areas of each suspected ovarian matrix area; obtains the adaptive h parameter of each pixel point in the NLM algorithm based on the distribution of the gradient direction of the pixel points within the local range of each pixel point in the grayscale image, the credibility of the suspected follicle area, the credibility of the suspected ovarian matrix area, and the preset credibility of other areas; denoises the grayscale image using the NLM algorithm based on the adaptive h parameter of each pixel point to obtain a denoised grayscale image; and detects the efficacy of electroacupuncture in patients with premature ovarian failure based on the denoised grayscale image. Among them, according to the local characteristics of each pixel point in the grayscale image (the suspected follicle degree and the suspected ovarian stroma degree), the suspected follicle area and the suspected ovarian stroma area are obtained. According to the characteristics of each suspected follicle area and the suspected ovarian stroma area, the credibility of each suspected follicle area and the suspected ovarian stroma area is obtained to eliminate the interference of the noise area; according to the credibility of the area where each pixel point is located and the local characteristics of each pixel point, the adaptive h parameter of each pixel point in the NLM algorithm is obtained, and then according to the adaptive h parameter of each pixel point, the grayscale image is denoised using the NLM algorithm. While denoising, the characteristics of the key areas (follicle area and ovarian stroma area) are retained, thereby improving the denoising effect of ovarian B-ultrasound medical images, and thus improving the accuracy of detecting the efficacy of electroacupuncture in patients with premature ovarian failure.

[0110] Based on the same inventive concept as the above method, an embodiment of the present invention also provides a medical imaging-based electroacupuncture efficacy detection system for patients with premature ovarian failure, comprising a memory, a processor, and a computer program stored in the memory and running on the processor. When the processor executes the computer program, the steps of any one of the above-mentioned medical imaging-based electroacupuncture efficacy detection methods for patients with premature ovarian failure are implemented.

[0111] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention, and should all be included in the scope of protection of the present invention.

Claims

1. A method for detecting the efficacy of electroacupuncture in patients with premature ovarian failure based on medical imaging, characterized in that: The method for detecting the efficacy of electroacupuncture in patients with premature ovarian failure based on medical imaging includes: Obtaining a grayscale image of the ovary of a patient with premature ovarian failure, and obtaining the suspected follicle degree and suspected ovarian stroma degree of each pixel based on the grayscale value distribution of each pixel within a local range of the grayscale image; According to the suspected follicle degree and suspected ovarian stroma degree of each pixel point, the grayscale image is divided into suspected follicle area, suspected ovarian stroma area and other areas. The credibility of each suspected follicle area is obtained based on the gradient of the boundary pixels of each suspected follicle area and the shape regularity of each suspected follicle area. The credibility of each suspected ovarian stroma area is obtained based on the credibility of the adjacent areas of each suspected ovarian stroma area. Based on the distribution of the gradient direction of each pixel within the local range of each pixel in the grayscale image, the credibility of the suspected follicle area, the credibility of the suspected ovarian stroma area, and the preset credibility of other areas, the adaptive h parameter of each pixel in the NLM algorithm is obtained. Based on the adaptive h parameter of each pixel, the grayscale image is denoised using the NLM algorithm to obtain a denoised grayscale image. The denoised grayscale image is used to detect the efficacy of electroacupuncture in patients with premature ovarian failure.

2. The method for detecting the efficacy of electroacupuncture in patients with premature ovarian failure based on medical imaging according to claim 1, characterized in that: The step of obtaining the suspected follicle degree and the suspected ovarian matrix degree of each pixel point according to the grayscale value distribution of the pixel points within the local range of each pixel point in the grayscale image includes: For any pixel point in the grayscale image, a preset number of windows of different scales are constructed with the any pixel point as the center, the grayscale value mean and grayscale value standard deviation of all pixels in each window are calculated, the product of the reciprocal of the grayscale value mean and the reciprocal of the grayscale value standard deviation corresponding to each window is calculated, and the follicle characteristic value of each window is obtained. The mean of the follicle characteristic values ​​of all windows is linearly normalized to obtain the suspected follicle degree of any pixel point.

3. The method for detecting the efficacy of electroacupuncture in patients with premature ovarian failure based on medical imaging according to claim 2, characterized in that: The step of obtaining the suspected follicle degree and the suspected ovarian matrix degree of each pixel point according to the grayscale value distribution of the pixel points within the local range of each pixel point in the grayscale image further includes: Calculate the product between the reciprocal of the grayscale value mean corresponding to each window of any pixel and the grayscale value standard deviation to obtain the ovarian stroma characteristic value of each window, and linearly normalize the mean of the ovarian stroma characteristic values ​​of all windows to obtain the suspected ovarian stroma degree of any pixel.

4. The method for detecting the efficacy of electroacupuncture in patients with premature ovarian failure based on medical imaging according to claim 1, characterized in that: The grayscale image is divided into suspected follicle areas, suspected ovarian stroma areas, and other areas according to the suspected follicle level and suspected ovarian stroma level of each pixel, including: Clustering is performed according to the suspected follicle degree of each pixel point in the grayscale image to obtain at least one suspected follicle cluster, and the mean of the suspected follicle degree of all pixels corresponding to each suspected follicle cluster is calculated and recorded as the suspected follicle degree mean; if the suspected follicle degree mean of any suspected follicle cluster is greater than or equal to a preset suspected follicle degree threshold, the area formed by all pixels in any suspected follicle cluster in the grayscale image is recorded as the suspected follicle area; Clustering is performed according to the suspected ovarian stroma degree of each pixel point in the grayscale image to obtain at least one suspected ovarian stroma cluster, and the mean of the suspected ovarian stroma degree of all pixels corresponding to each of the suspected ovarian stroma clusters is calculated and recorded as the suspected ovarian stroma degree mean; if the suspected ovarian stroma degree mean of any suspected ovarian stroma cluster is greater than or equal to a preset suspected ovarian stroma degree threshold, then the area formed by all pixels in any suspected ovarian stroma cluster in the grayscale image is recorded as the suspected ovarian stroma area; The areas other than the suspected follicle area and the suspected ovarian stroma area in the grayscale image are recorded as other areas.

5. The method for detecting the efficacy of electroacupuncture in patients with premature ovarian failure based on medical imaging according to claim 1, characterized in that: The step of obtaining the credibility of each suspected follicle region according to the gradient of the boundary pixel points of each suspected follicle region and the shape regularity of each suspected follicle region includes: For any suspected follicle region, calculate the difference between the constant 1 and the circularity of the suspected follicle region, calculate the inverse of the sum of the difference and a preset constant, and obtain the circularity of the suspected follicle region; Obtain the boundary pixel points of any suspected follicle area, and in the grayscale image, calculate the mean of the grayscale values ​​of a preset number of pixels on the right side of the normal direction of any boundary pixel point to obtain the right grayscale mean, calculate the mean of the grayscale values ​​of a preset number of pixels on the left side of the normal direction of any boundary pixel point to obtain the left grayscale mean, calculate the absolute value of the difference between the right grayscale mean and the left grayscale mean, calculate the product between the gradient value of any boundary pixel point and the absolute value of the difference, and obtain the clarity of any boundary pixel point; The clarity mean of all boundary pixels of any suspected follicle region is calculated, and the product of the clarity mean and the circularity is used as the credibility of any suspected follicle region.

6. The method for detecting the efficacy of electroacupuncture in patients with premature ovarian failure based on medical imaging according to claim 5, characterized in that: The step of obtaining the credibility of each suspected ovarian stroma region according to the credibility of the adjacent regions of each suspected ovarian stroma region includes: For any suspected ovarian stroma region, in the grayscale image, obtain at least one pixel point adjacent to a boundary pixel point of the any suspected ovarian stroma region, record it as a target pixel point, and eliminate the any suspected ovarian stroma region in the area where all target pixels are located to obtain at least one adjacent area of ​​the any suspected ovarian stroma region; For any adjacent region, the credibility of the adjacent region is obtained based on the gradient of the boundary pixels of the adjacent region and the shape regularity of the adjacent region, which is recorded as the follicle credibility. The product of the mean of the suspected follicle degree of all pixels in the adjacent region and the follicle credibility of the adjacent region is calculated to obtain the follicle possibility degree of the adjacent region. The follicle possibility degree of each of the adjacent areas of the any suspected ovarian stroma area is obtained, and the maximum value among the follicle possibility degrees of all the adjacent areas is selected as the credibility of the any suspected ovarian stroma area.

7. The method for detecting the efficacy of electroacupuncture in patients with premature ovarian failure based on medical imaging according to claim 1, characterized in that: The method of obtaining the adaptive h parameter of each pixel in the NLM algorithm based on the distribution of the gradient direction of the pixel within the local range of each pixel in the grayscale image, the credibility of the suspected follicle area, the credibility of the suspected ovarian stroma area, and the preset credibility of other areas includes: For any pixel point in the grayscale image, if the pixel point belongs to a suspected follicle area, the product of the suspected follicle degree of the pixel point and the credibility of the suspected follicle area where the pixel point is located is calculated to obtain the criticality of the pixel point; If any of the pixels belongs to a suspected ovarian stroma area, the product of the suspected ovarian stroma degree of the pixel and the credibility of the suspected ovarian stroma area where the pixel is located is calculated to obtain the criticality of the pixel; If any pixel point belongs to both the suspected ovarian stroma area and the suspected follicle area, the maximum value of the suspected follicle degree and the suspected ovarian stroma degree of any pixel point is obtained; if the maximum value is the suspected follicle degree, the product of the suspected follicle degree and the credibility of the suspected follicle area where the any pixel point is located is calculated to obtain the criticality of the any pixel point; if the maximum value is the suspected ovarian stroma degree, the product of the suspected ovarian stroma degree and the credibility of the suspected ovarian stroma area where the any pixel point is located is calculated to obtain the criticality of the any pixel point; If any of the pixels belongs to other areas, the preset credibility of the other areas is used as the criticality of any of the pixels; According to the criticality of any pixel point and the distribution of gradient directions of pixels within a local range of any pixel point, an adaptive h parameter of any pixel point in the NLM algorithm is obtained.

8. The method for detecting the efficacy of electroacupuncture in patients with premature ovarian failure based on medical imaging according to claim 7, characterized in that: The step of obtaining the adaptive h parameter of any pixel point in the NLM algorithm according to the criticality of any pixel point and the distribution of the gradient directions of pixels within a local range of any pixel point includes: In the grayscale image, a target window of a preset size is constructed with any pixel as the center, and the gradient direction entropy is obtained according to the gradient directions of all pixels in the target window. The product of the gradient value of any pixel and the inverse of the gradient direction entropy is linearly normalized to obtain the edge degree of any pixel; Performing a weighted summation on the edge degree and the critical degree of any pixel point to obtain a weighted summation result, calculating the difference between a preset maximum h parameter and a preset minimum h parameter to obtain a preset h parameter range difference, and calculating the product between the preset h parameter range difference and the weighted summation result to obtain an h parameter adjustment coefficient for any pixel point; The difference between the preset maximum h parameter and the h parameter adjustment coefficient of any pixel point is calculated to obtain the adaptive h parameter of any pixel point in the NLM algorithm.

9. The method for detecting the efficacy of electroacupuncture in patients with premature ovarian failure based on medical imaging according to claim 7, characterized in that: The preset credibility of the other areas is set to 0.

10. A medical imaging-based electroacupuncture efficacy detection system for patients with premature ovarian failure, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that: When the processor executes the computer program, the steps of the method for detecting the efficacy of electroacupuncture in patients with premature ovarian failure based on medical imaging are implemented as described in any one of claims 1 to 9.

Images