Ovarian function assessment system based on AMH detection and image analysis

Abstract

The invention relates to the technical field of biomedical engineering, and specifically discloses an ovarian function evaluation system based on AMH detection and image analysis. The system comprises a data receiving module, a sample analysis module, an image analysis module, a data evaluation module, a result feedback terminal and a medical database. The system receives blood test samples and ovarian ultrasound images of a person to be detected, respectively analyzes the blood test samples and ovarian ultrasound images of the person to be detected, and finally performs a comprehensive score on the ovarian function of the person to be detected. The system can help doctors understand the fertility status of patients more comprehensively, can not only help doctors understand the health status of the female reproductive system, but also provide important information to prevent and treat various gynecological problems, maintain a healthy lifestyle, and improve self-care awareness, so as to ensure the health of the female reproductive system and promote overall health and a happy life.

Description

Technical Field

[0001] The invention relates to the technical field of biomedical engineering analysis, and in particular to an ovarian function evaluation system based on AMH detection and image analysis. Background Art

[0002] With the development of society, people are paying more and more attention to health, and women are also paying more attention to reproductive health. Women's ovaries have both reproductive functions and the role of maintaining endocrine homeostasis, which not only affects their own life safety and physical health, but also affects the physique and health of the next generation. Pay attention to the ovaries, manage health in advance, explore effective and safe methods and strategies to intervene in ovarian aging and diseases, and maintain the health of women's endocrine system throughout their life cycle.

[0003] Ovarian function assessment is an important part of women's reproductive health. Traditional assessment methods mainly rely on basal hormone level detection and ultrasound image analysis. Anti-Mullerian hormone (AMH), as a marker of ovarian reserve, has been widely used in ovarian function assessment in recent years. However, existing technologies have not fully integrated AMH detection and image analysis methods, making it difficult to achieve comprehensive and accurate ovarian function assessment. Summary of the invention

[0004] 1. Technical issues to be resolved

[0005] Anti-Müllerian hormone (AMH) is a protein secreted by granulosa cells in the ovaries, and its concentration is closely related to the ovarian reserve function of women. Traditional AMH detection methods mainly rely on biochemical analysis of blood samples, but this method cannot provide structural information of the ovaries, and the detection process is time-consuming. In view of the shortcomings of the prior art, the present invention provides an ovarian function evaluation system based on AMH detection and image analysis, which can provide a more comprehensive and rapid ovarian function evaluation.

[0006] (II) Technical solution

[0007] The present invention solves the above technical problems through the following technical means:

[0008] An ovarian function evaluation system based on AMH detection and image analysis, including a data receiving module, a sample analysis module, an image analysis module, a data evaluation module, a result feedback terminal and a medical database;

[0009] The data receiving module is used to receive the blood test sample and ovarian ultrasound image of the person to be tested;

[0010] The sample analysis module is used to analyze the blood test samples of the person to be tested based on the blood test samples of the person to be tested;

[0011] The image analysis module is used to analyze the ovarian ultrasound image of the person to be tested based on the ovarian ultrasound image of the person to be tested;

[0012] The data evaluation module is used to combine the blood test sample analysis results of the person to be tested with the ovarian ultrasound image analysis results, and then to make a comprehensive score for the ovarian function of the person to be tested;

[0013] The result feedback terminal is used to feed back the comprehensive score of the ovarian function of the person to be tested to the system interface of the attending physician of the person to be tested;

[0014] The medical database is used to store a data table of AMH reference concentrations corresponding to optical density readings, to store the resolution of ultrasound equipment and normal ovarian volume ranges, and to store score values ​​corresponding to each evaluation coefficient range.

[0015] Exemplarily, the sample analysis module also includes performing experimental operations on the blood test samples of the test personnel, and the specific experimental operation process is as follows;

[0016] Step 1: Place the blood test sample of the person to be tested in a microplate containing specific anti-AMH antibodies;

[0017] Step 2: washing the blood sample of the person to be tested to remove unbound substances;

[0018] Step 3: adding a substrate to the blood test sample of the person to be tested, so that the substrate reacts with the enzyme-labeled antibody in the blood test sample of the person to be tested to produce a color change;

[0019] Step 4: Use enzyme-labeled antibodies to detect AMH in the blood test sample of the person to be tested, and produce color changes according to the degree of reaction;

[0020] Step 5: Use an ELISA reader to read the optical density of each microwell in the microplate corresponding to the blood test sample of the person to be tested , c represents the number of each microwell in the microwell plate, c=1,2,...m.

[0021] Exemplarily, the blood test sample analysis of the person to be tested is carried out in the following specific analysis process:

[0022] Extract the values ​​of each AMH reference concentration and the values ​​of the optical density readings corresponding to each AMH reference concentration from the data table of optical density readings corresponding to the AMH reference concentration stored in the medical database, substitute them into the linear regression equation of OD=a×AMH+b, solve the values ​​of the slope a and the intercept b in the linear regression equation, and mark the values ​​of the slope a and the intercept b in the linear regression equation as a=a1 and b=b1 respectively;

[0023] And filter out the optical density reading value corresponding to the maximum AMH reference concentration value from the data table of AMH reference concentration corresponding to optical density readings And the optical density reading corresponding to the minimum AMH reference concentration value ;

[0024] Import the optical density of each microwell in the microplate corresponding to the blood test sample of the person to be tested into the regression model In this way, the AMH concentration value of the optical density of each microwell in the microplate corresponding to the blood test sample of the person to be tested is obtained. ;

[0025] and through , the AMH concentration value of the blood test sample of the person to be tested is calculated, and m represents the total number of microwells in the microwell plate.

[0026] Exemplarily, the image analysis module obtains ovarian data of the person to be tested based on the ovarian ultrasound image of the person to be tested;

[0027] The ovarian data of the person to be tested specifically include ovarian volume, ovarian cortex volume, ovarian area, ovarian cortex area, and the number of follicles and the size of each follicle.

[0028] Exemplarily, the ovarian area and ovarian volume of the person to be tested are obtained, and the specific acquisition process is:

[0029] S51, performing a preprocessing operation on the ovarian ultrasound image of the person to be detected, and using a Canny edge detector to detect and obtain the ovarian edge line of the person to be detected, thereby obtaining the ovarian region of the person to be detected based on the Canny edge detector, and at the same time using a threshold segmentation method to separate the ovarian region of the person to be detected from the ovarian ultrasound image of the person to be detected, to obtain the ovarian region image of the person to be detected;

[0030] S52, enlarging the image of the ovarian region of the person to be tested until each pixel grid is displayed, and obtaining the area of ​​the pixel grid in the ovarian region of the person to be tested , and obtain the resolution of the ultrasound device from the medical database, taking it as the actual length represented by the unit pixel grid, according to the calculation formula , calculate the ovarian area of ​​the person to be tested , Indicates the actual length represented by the unit pixel grid;

[0031] S53, marking the longest straight line from the transverse and longitudinal ultrasound images of the ovaries of the person to be tested, and recording the longest straight line in the transverse and longitudinal ultrasound images of the ovaries of the person to be tested as the maximum length L, and drawing each vertical line perpendicular to the longest straight line, and obtaining the length of each vertical line perpendicular to the longest straight line, selecting the vertical line with the maximum length as the reference vertical line, and synchronously obtaining the length of the reference vertical line, and recording it as the maximum width W;

[0032] Marking the longest straight line from the longitudinal section ultrasound image of the ovary of the person to be tested, and recording the longest straight line in the longitudinal section ultrasound image of the ovary of the person to be tested as the maximum height H;

[0033] S54. Obtain the ovarian volume of the person to be tested by comprehensive calculation using the ellipsoid formula .

[0034] Exemplarily, the ovarian cortex area and ovarian cortex volume of the person to be tested are obtained, and the specific acquisition process is as follows:

[0035] S61, obtaining different regions in the ovarian ultrasound image corresponding to the person to be tested according to the Canny edge detector, and graying the ovarian ultrasound image of the person to be tested to obtain the gray value of each pixel in each different region corresponding to the ovarian ultrasound image of the person to be tested;

[0036] S62, synchronously taking the grayscale value of each pixel in each other area corresponding to the ovarian ultrasound image of the person to be tested as the echo intensity of each pixel in each other area corresponding to the ovarian ultrasound image of the person to be tested , j represents the number of each pixel grid, j=1,2,...i, p represents the number of each other area, p=1,2,...n; further calculation is performed to obtain the average echo intensity of each other area corresponding to the ovarian ultrasound image of the person to be tested , i represents the total number of pixel grids;

[0037] S63, importing the grayscale value of each pixel in each other area corresponding to the ovarian ultrasound image of the person to be tested into the set gray level co-occurrence matrix, thereby obtaining the pixel features of each pixel in each other area corresponding to the ovarian ultrasound image of the person to be tested , where the element feature is specifically represented by the pixel grid with gray value j and in a certain direction The number of times the pixel grid with gray value g at distance d appears together;

[0038] S64, calculating and obtaining the image grayscale distribution contrast of each other area of ​​the ovarian ultrasound image of the person to be tested ;

[0039] Calculate the image texture uniformity of each other area of ​​the ovarian ultrasound image of the person to be tested ;

[0040] Calculate the image texture roughness of each other area of ​​the ovarian ultrasound image of the person to be tested ;

[0041] The mean and standard deviation of the row and column of the j-th pixel grid and the g-th pixel grid are calculated from the gray level co-occurrence matrix, and the correlation between the pixels in each other area of ​​the ovarian ultrasound image of the person to be tested and the surrounding pixels is calculated. , Respectively represent the standard deviation of the row and column of the j-th pixel grid and the g-th pixel grid, Respectively represent the average values ​​of the rows and columns where the j-th pixel grid and the g-th pixel grid are located;

[0042] S65, thereby further obtaining the feature vectors of each other region of the ovarian ultrasound image of the person to be tested , comparing it with the reference feature vector interval value of the set ovarian cortex area, and then obtaining the ovarian cortex area of ​​the ovarian ultrasound image of the person to be tested;

[0043] S66. Based on the calculation method of the ovarian area and ovarian volume of the person to be tested, the ovarian cortical area and ovarian cortical volume of the person to be tested are calculated in the same way based on the ovarian cortical area of ​​the ovarian ultrasound image of the person to be tested.

[0044] Exemplarily, the number of follicles and the size of each follicle of the person to be tested are obtained, and the specific acquisition process is:

[0045] S71, using the Otsu method to automatically determine the threshold, performing image binarization processing on the grayscale image of the ovarian ultrasound image of the person to be detected, separating the follicle area from the background area, and applying a contour detection algorithm to obtain the contours of each graphic in the binarized image of the ovarian ultrasound image of the person to be detected;

[0046] S72, and obtaining the contour area and shape features of each figure in the binary image of the ovarian ultrasound image of the person to be tested, and based on them, identifying each follicle in the ovarian ultrasound image of the person to be tested, thereby obtaining the number of follicles of the person to be tested and the size of each follicle.

[0047] Exemplarily, the ovarian ultrasound image analysis of the person to be tested is performed in the following specific analysis process:

[0048] Obtain the ovarian volume, ovarian cortical volume, ovarian area, ovarian cortical area and the size of each follicle of the person to be tested;

[0049] Obtaining the normal ovarian volume range from the medical database , analyze the normal evaluation coefficient of the ovarian volume of the person to be tested in They represent the maximum and minimum interval values ​​of the normal ovarian volume range respectively;

[0050] According to the calculation method of the normal evaluation coefficient of the ovarian volume of the person to be tested, the normal evaluation coefficient of the ovarian area, the normal evaluation coefficient of the ovarian cortex volume, the normal evaluation coefficient of the ovarian cortex area and the normal evaluation coefficient of each follicle size of the person to be tested are calculated in the same way;

[0051] The normal evaluation coefficients of the follicle sizes of the persons to be tested are summed and averaged to calculate the normal evaluation coefficients of the follicle sizes of the persons to be tested.

[0052] Exemplarily, the ovarian function of the person to be tested is comprehensively scored, and the specific scoring process is:

[0053] Compare the normal evaluation coefficient of the ovarian volume of the person to be tested with the score values ​​corresponding to each evaluation coefficient interval stored in the medical database to obtain the score value of the ovarian volume corresponding to the person to be tested;

[0054] Similarly, the scoring values ​​of the ovarian area, ovarian cortical volume, ovarian cortical area and follicle size, and AMH concentration of the person to be tested are obtained, and the sum of the scores is calculated by dividing the sum by 6 to obtain the ovarian function score of the person to be tested.

[0055] An ovarian function assessment device based on AMH detection and image analysis, comprising a processor, a memory and a communication bus;

[0056] The memory stores a computer-readable program executable by the processor;

[0057] The communication bus realizes the connection and communication between the processor and the memory;

[0058] When the processor executes the computer-readable program, it is implemented to implement the above-mentioned ovarian function assessment system based on AMH detection and image analysis.

[0059] A computer-readable storage medium, characterized in that: the computer-readable storage medium stores one or more programs, and the one or more programs can be executed by one or more processors to implement the above-mentioned ovarian function assessment system based on AMH detection and image analysis.

[0060] Beneficial effects of the present invention:

[0061] (1) The ovarian function evaluation system based on AMH detection and image analysis provided by the present invention receives blood test samples and ovarian ultrasound images of the person to be tested, and then analyzes the blood test samples and ovarian ultrasound images of the person to be tested respectively, and finally performs a comprehensive score on the ovarian function of the person to be tested. It mainly analyzes the ovarian area, ovarian volume, ovarian cortical volume, ovarian cortical area, follicle size and other indicators of the person to be tested, combined with biomarkers such as AMH concentration, to comprehensively evaluate the ovarian function status. Firstly, it can detect and diagnose abnormal conditions of the female reproductive system early, and if problems are found, corresponding intervention measures can be taken to improve the treatment effect and avoid the impact of disease progression on fertility. Secondly, ovarian function evaluation helps to evaluate women's reproductive potential and childbearing age, and can more accurately understand women's reproductive potential, providing a scientific basis for family planning;

[0062] Secondly, the ovarian cortical area is the surface area of ​​the ovarian cortex, which is the main area for follicle formation. Its size can reflect the ovarian reserve and fertility potential. The evaluation of these indicators can help doctors determine an individual's fertility and predict ovulation, providing more accurate diagnosis and treatment options for infertile patients.

[0063] (2) The comprehensive evaluation method shown in the embodiment of the present invention can help doctors understand the patient's reproductive status more comprehensively. It can not only help doctors understand the health status of the female reproductive system, but also provide important information to prevent and treat various gynecological problems, maintain a healthy lifestyle, and improve self-care awareness to ensure the health of the female reproductive system and promote overall health and a happy life. BRIEF DESCRIPTION OF THE DRAWINGS

[0064] Figure 1 It is a schematic diagram of the system module connection structure of the present invention.

[0065] Figure 2 This is an example table of data showing the corresponding optical density readings of AMH reference concentrations shown in the present invention.

[0066] Figure 3 It is a schematic diagram of the structure of the device shown in the present invention. DETAILED DESCRIPTION

[0067] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0068] Example 1

[0069] See also Figure 1 As shown, the ovarian function evaluation system based on AMH detection and image analysis includes a data receiving module, a sample analysis module, an image analysis module, a data evaluation module, a result feedback terminal and a medical database;

[0070] The sample analysis module and the image analysis module are connected to the data receiving module respectively, the data evaluation module is also connected to the sample analysis module and the image analysis module respectively, the result feedback terminal is connected to the data evaluation module, and the medical database is connected to the sample analysis module and the image analysis module respectively.

[0071] The data receiving module is used to receive the blood test sample and ovarian ultrasound image of the person to be tested;

[0072] The sample analysis module is used to analyze the blood test samples of the person to be tested based on the blood test samples of the person to be tested;

[0073] It should be noted that the sample analysis module also includes experimental operations on the blood test samples of the test personnel. The specific experimental operation process is as follows:

[0074] Step 1: Place the blood test sample of the person to be tested in a microplate containing specific anti-AMH antibodies;

[0075] Step 2: washing the blood sample of the person to be tested to remove unbound substances;

[0076] Step 3: adding a substrate to the blood test sample of the person to be tested, so that the substrate reacts with the enzyme-labeled antibody in the blood test sample of the person to be tested to produce a color change;

[0077] Step 4: Use enzyme-labeled antibodies to detect AMH in the blood test sample of the person to be tested, and produce color changes according to the degree of reaction;

[0078] Step 5: Use an ELISA reader to read the optical density of each microwell in the microplate corresponding to the blood test sample of the person to be tested , c represents the number of each microwell in the microwell plate, c=1,2,...m.

[0079] It should be noted that the specific analysis process of the blood sample analysis of the person to be tested is as follows:

[0080] See also Figure 2As shown, from the data table of AMH reference concentrations corresponding to optical density readings stored in the medical database, the values ​​of each AMH reference concentration and the values ​​of the optical density readings corresponding to each AMH reference concentration are extracted, and they are respectively substituted into the linear regression equation of OD=a×AMH+b, and the values ​​of the slope a and the intercept b in the linear regression equation are solved, and the values ​​of the slope a and the intercept b in the linear regression equation are marked as a=a1, b=b1 respectively;

[0081] And filter out the optical density reading value corresponding to the maximum AMH reference concentration value from the data table of AMH reference concentration corresponding to optical density readings And the optical density reading corresponding to the minimum AMH reference concentration value ;

[0082] It should be added that the optical density reading value corresponding to the maximum AMH reference concentration value is specifically expressed as the maximum OD when the concentration tends to infinity, and the optical density reading value corresponding to the minimum AMH reference concentration value is specifically expressed as the minimum OD when the concentration tends to zero.

[0083] Import the optical density of each microwell in the microplate corresponding to the blood test sample of the person to be tested into the regression model In this way, the AMH concentration value of the optical density of each microwell in the microplate corresponding to the blood test sample of the person to be tested is obtained. ; In the regression model The value calculated by this formula is the half-maximum effect concentration value;

[0084] and through , the AMH concentration value of the blood test sample of the person to be tested is calculated, and m represents the total number of microwells in the microwell plate.

[0085] The image analysis module is used to analyze the ovarian ultrasound image of the person to be tested based on the ovarian ultrasound image of the person to be tested;

[0086] It should be noted that the image analysis module obtains the ovarian data of the person to be tested based on the ovarian ultrasound image of the person to be tested;

[0087] The ovarian data of the person to be tested specifically include ovarian volume, ovarian cortex volume, ovarian area, ovarian cortex area, and the number of follicles and the size of each follicle.

[0088] It should be noted that the specific process of obtaining the ovarian area and ovarian volume of the person to be tested is as follows:

[0089] S51, performing a preprocessing operation on the ovarian ultrasound image of the person to be detected, and using a Canny edge detector to detect and obtain the ovarian edge line of the person to be detected, thereby obtaining the ovarian region of the person to be detected based on the Canny edge detector, and at the same time using a threshold segmentation method to separate the ovarian region of the person to be detected from the ovarian ultrasound image of the person to be detected, to obtain the ovarian region image of the person to be detected;

[0090] S52, enlarging the image of the ovarian region of the person to be tested until each pixel grid is displayed, and obtaining the area of ​​the pixel grid in the ovarian region of the person to be tested , and obtain the resolution of the ultrasound device from the medical database, taking it as the actual length represented by the unit pixel grid, according to the calculation formula , calculate the ovarian area of ​​the person to be tested , Indicates the actual length represented by the unit pixel grid;

[0091] S53, marking the longest straight line from the transverse and longitudinal ultrasound images of the ovaries of the person to be tested, and recording the longest straight line in the transverse and longitudinal ultrasound images of the ovaries of the person to be tested as the maximum length L, and drawing each vertical line perpendicular to the longest straight line, and obtaining the length of each vertical line perpendicular to the longest straight line, selecting the vertical line with the maximum length as the reference vertical line, and synchronously obtaining the length of the reference vertical line, and recording it as the maximum width W;

[0092] Marking the longest straight line from the longitudinal section ultrasound image of the ovary of the person to be tested, and recording the longest straight line in the longitudinal section ultrasound image of the ovary of the person to be tested as the maximum height H;

[0093] S54. Obtain the ovarian volume of the person to be tested by comprehensive calculation using the ellipsoid formula .

[0094] It should be noted that the ovarian cortex area and ovarian cortex volume of the person to be tested are obtained in the following specific process:

[0095] S61, obtaining different regions in the ovarian ultrasound image corresponding to the person to be tested according to the Canny edge detector, and graying the ovarian ultrasound image of the person to be tested to obtain the gray value of each pixel in each different region corresponding to the ovarian ultrasound image of the person to be tested;

[0096] S62, synchronously taking the grayscale value of each pixel in each other area corresponding to the ovarian ultrasound image of the person to be tested as the echo intensity of each pixel in each other area corresponding to the ovarian ultrasound image of the person to be tested , j represents the number of each pixel grid, j=1,2,...i, p represents the number of each other area, p=1,2,...n; further calculation is performed to obtain the average echo intensity of each other area corresponding to the ovarian ultrasound image of the person to be tested , i represents the total number of pixel grids;

[0097] S63, importing the grayscale value of each pixel in each other area corresponding to the ovarian ultrasound image of the person to be tested into the set gray level co-occurrence matrix, thereby obtaining the pixel features of each pixel in each other area corresponding to the ovarian ultrasound image of the person to be tested , where the element feature is specifically represented by the pixel grid with gray value j and in a certain direction The number of times the pixel grid with gray value g at distance d appears together;

[0098] S64, calculating and obtaining the image grayscale distribution contrast of each other area of ​​the ovarian ultrasound image of the person to be tested ;

[0099] Calculate the image texture uniformity of each other area of ​​the ovarian ultrasound image of the person to be tested ;

[0100] Calculate the image texture roughness of each other area of ​​the ovarian ultrasound image of the person to be tested ;

[0101] The mean and standard deviation of the row and column of the j-th pixel grid and the g-th pixel grid are calculated from the gray level co-occurrence matrix, and the correlation between the pixels in each other area of ​​the ovarian ultrasound image of the person to be tested and the surrounding pixels is calculated. , Respectively represent the standard deviation of the row and column of the j-th pixel grid and the g-th pixel grid, Respectively represent the average values ​​of the rows and columns where the j-th pixel grid and the g-th pixel grid are located;

[0102] S65, thereby further obtaining the feature vectors of each other region of the ovarian ultrasound image of the person to be tested , comparing it with the reference feature vector interval value of the set ovarian cortex area, and then obtaining the ovarian cortex area of ​​the ovarian ultrasound image of the person to be tested;

[0103] S66. Based on the calculation method of the ovarian area and ovarian volume of the person to be tested, the ovarian cortical area and ovarian cortical volume of the person to be tested are calculated in the same way based on the ovarian cortical area of ​​the ovarian ultrasound image of the person to be tested.

[0104] It should be noted that the specific process of obtaining the number of follicles and the size of each follicle of the person to be tested is as follows:

[0105] S71, using the Otsu method to automatically determine the threshold, performing image binarization processing on the grayscale image of the ovarian ultrasound image of the person to be detected, separating the follicle area from the background area, and applying a contour detection algorithm to obtain the contours of each graphic in the binarized image of the ovarian ultrasound image of the person to be detected;

[0106] S72, and obtaining the contour area and shape features of each figure in the binary image of the ovarian ultrasound image of the person to be tested, and based on them, identifying each follicle in the ovarian ultrasound image of the person to be tested, thereby obtaining the number of follicles of the person to be tested and the size of each follicle.

[0107] It should be added that the specific identification algorithm for identifying each follicle in the ovarian ultrasound image of the person to be tested is as follows:

[0108] # Filter the outlines that may be follicles

[0109] follicle_contours = []

[0110] for contour in contours:

[0111] area = cv2.contourArea(contour)

[0112] # Calculate the perimeter of the contour

[0113] perimeter = cv2.arcLength(contour, True)

[0114] # Calculate roundness

[0115] circularity = 4 * np.pi * (area / (perimeter * perimeter))

[0116] # Set thresholds based on area and circularity

[0117] if area > 100 and 0.7 < circularity < 1.2:

[0118] follicle_contours.append(contour)

[0119] It should be noted that the specific analysis process of the ovarian ultrasound image analysis of the person to be tested is as follows:

[0120] Obtain the ovarian volume, ovarian cortical volume, ovarian area, ovarian cortical area and the size of each follicle of the person to be tested;

[0121] Obtaining the normal ovarian volume range from the medical database , analyze the normal evaluation coefficient of the ovarian volume of the person to be tested in They represent the maximum and minimum interval values ​​of the normal ovarian volume range respectively;

[0122] According to the calculation method of the normal evaluation coefficient of the ovarian volume of the person to be tested, the normal evaluation coefficient of the ovarian area, the normal evaluation coefficient of the ovarian cortex volume, the normal evaluation coefficient of the ovarian cortex area and the normal evaluation coefficient of each follicle size of the person to be tested are calculated in the same way;

[0123] The normal evaluation coefficients of the follicle sizes of the persons to be tested are summed and averaged to calculate the normal evaluation coefficients of the follicle sizes of the persons to be tested.

[0124] The data evaluation module is used to combine the blood test sample analysis results of the person to be tested with the ovarian ultrasound image analysis results, and then to make a comprehensive score for the ovarian function of the person to be tested;

[0125] It should be noted that the comprehensive scoring of the ovarian function of the test subject is carried out as follows:

[0126] Compare the normal evaluation coefficient of the ovarian volume of the person to be tested with the score values ​​corresponding to each evaluation coefficient interval stored in the medical database to obtain the score value of the ovarian volume corresponding to the person to be tested;

[0127] Similarly, the scoring values ​​of the ovarian area, ovarian cortical volume, ovarian cortical area and follicle size, and AMH concentration of the person to be tested are obtained, and the sum of the scores is calculated by dividing the sum by 6 to obtain the ovarian function score of the person to be tested.

[0128] The result feedback terminal is used to feed back the comprehensive score of the ovarian function of the person to be tested to the system interface of the attending physician of the person to be tested;

[0129] The medical database is used to store a data table of AMH reference concentrations corresponding to optical density readings, to store the resolution of ultrasound equipment and normal ovarian volume ranges, and to store score values ​​corresponding to each evaluation coefficient range.

[0130] Example 2

[0131] See also Figure 3 As shown, an ovarian function assessment device based on AMH detection and image analysis includes a processor, a memory and a communication bus;

[0132] The memory stores a computer-readable program executable by the processor;

[0133] The communication bus realizes the connection and communication between the processor and the memory;

[0134] When the processor executes the computer-readable program, it is implemented to implement the above-mentioned ovarian function assessment system based on AMH detection and image analysis.

[0135] Example 3

[0136] A computer-readable storage medium, characterized in that: the computer-readable storage medium stores one or more programs, and the one or more programs can be executed by one or more processors to implement the above-mentioned ovarian function assessment system based on AMH detection and image analysis.

[0137] The above contents are merely examples and explanations of the structure of the present invention. The technicians in this technical field may make various modifications or additions to the specific embodiments described or replace them in a similar manner. As long as they do not deviate from the structure of the invention or exceed the scope defined by the claims, they should all fall within the protection scope of the present invention.

[0138] In the description of this specification, the description with reference to the terms "one embodiment", "example", "specific example", etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner.

[0139] The preferred embodiments of the present invention disclosed above are only used to help explain the present invention. The preferred embodiments do not describe all the details in detail, nor do they limit the invention to only specific implementation methods. Obviously, many modifications and changes can be made according to the content of this specification. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the present invention, so that those skilled in the art can understand and use the present invention well. The present invention is limited only by the claims and their full scope and equivalents.

Claims

1. An ovarian function assessment system based on AMH detection and image analysis, characterized in that: The system includes: A data receiving module, used for receiving blood test samples and ovarian ultrasound images of the person to be tested; A sample analysis module, used for analyzing the blood test samples of the person to be tested based on the blood test samples of the person to be tested; An image analysis module, used for analyzing the ovarian ultrasound image of the person to be tested based on the ovarian ultrasound image of the person to be tested; The image analysis module obtains ovarian data of the person to be tested based on the ovarian ultrasound image of the person to be tested, wherein the ovarian ultrasound image of the person to be tested includes an ovarian transverse and longitudinal ultrasound image and an ovarian longitudinal section ultrasound image; The ovarian data of the person to be tested specifically include ovarian volume, ovarian cortical volume, ovarian area, ovarian cortical area, and the number of follicles and the size of each follicle; The ovarian area and ovarian volume of the person to be tested are obtained. The specific acquisition process is: S51, performing a preprocessing operation on the ovarian ultrasound image of the person to be detected, and using a Canny edge detector to detect and obtain the ovarian edge line of the person to be detected, thereby obtaining the ovarian region of the person to be detected based on the Canny edge detector, and at the same time using a threshold segmentation method to separate the ovarian region of the person to be detected from the ovarian ultrasound image of the person to be detected, to obtain the ovarian region image of the person to be detected; S52, enlarging the image of the ovarian region of the person to be tested until each pixel grid is displayed, and obtaining the area of ​​the pixel grid in the ovarian region of the person to be tested , and obtain the resolution of the ultrasound device from the medical database, taking it as the actual length represented by the unit pixel grid, according to the calculation formula , calculate the ovarian area of ​​the person to be tested , Indicates the actual length represented by the unit pixel grid; S53, marking the longest straight line from the transverse and longitudinal ultrasound images of the ovaries of the person to be tested, and recording the longest straight line in the transverse and longitudinal ultrasound images of the ovaries of the person to be tested as the maximum length L, and drawing each vertical line perpendicular to the longest straight line, and obtaining the length of each vertical line perpendicular to the longest straight line, selecting the vertical line with the maximum length as the reference vertical line, and synchronously obtaining the length of the reference vertical line, and recording it as the maximum width W; Marking the longest straight line from the longitudinal section ultrasound image of the ovary of the person to be tested, and recording the longest straight line in the longitudinal section ultrasound image of the ovary of the person to be tested as the maximum height H; S54. Obtain the ovarian volume of the person to be tested by comprehensive calculation using the ellipsoid formula ; The ovarian cortex area and ovarian cortex volume of the person to be tested are obtained. The specific acquisition process is as follows: S61, obtaining different regions in the ovarian ultrasound image corresponding to the person to be tested according to the Canny edge detector, and graying the ovarian ultrasound image of the person to be tested to obtain the gray value of each pixel in each different region corresponding to the ovarian ultrasound image of the person to be tested; S62, synchronously taking the grayscale value of each pixel in each other area corresponding to the ovarian ultrasound image of the person to be tested as the echo intensity of each pixel in each other area corresponding to the ovarian ultrasound image of the person to be tested , j represents the number of each pixel grid, j=1,2,...i, p represents the number of each other area, p=1,2,...n; further calculation is performed to obtain the average echo intensity of each other area corresponding to the ovarian ultrasound image of the person to be tested , i represents the total number of pixel grids; S63, importing the grayscale value of each pixel in each other area corresponding to the ovarian ultrasound image of the person to be tested into the set gray level co-occurrence matrix, thereby obtaining the pixel features of each pixel in each other area corresponding to the ovarian ultrasound image of the person to be tested , where the element feature is specifically represented by the pixel grid with gray value j and in a certain direction The number of times the pixel grid with gray value g at distance d appears together; S64, calculating and obtaining the image grayscale distribution contrast of each other area of ​​the ovarian ultrasound image of the person to be tested ; Calculate the image texture uniformity of each other area of ​​the ovarian ultrasound image of the person to be tested ; Calculate the image texture roughness of each other area of ​​the ovarian ultrasound image of the person to be tested ; The mean and standard deviation of the row and column of the j-th pixel grid and the g-th pixel grid are calculated from the gray level co-occurrence matrix, and the correlation between the pixels in each other area of ​​the ovarian ultrasound image of the person to be tested and the surrounding pixels is calculated. , Respectively represent the standard deviation of the row and column of the j-th pixel grid and the g-th pixel grid, Respectively represent the average values ​​of the rows and columns where the j-th pixel grid and the g-th pixel grid are located; S65, thereby further obtaining the feature vectors of each other region of the ovarian ultrasound image of the person to be tested , comparing it with the reference feature vector interval value of the set ovarian cortex area, and then obtaining the ovarian cortex area of ​​the ovarian ultrasound image of the person to be tested; S66, according to the calculation method of the ovarian area and ovarian volume of the person to be tested, the ovarian cortex area and ovarian cortex volume of the person to be tested are calculated in the same way according to the ovarian cortex area of ​​the ovarian ultrasound image of the person to be tested; The number of follicles and the size of each follicle of the person to be tested are obtained. The specific acquisition process is: S71, using the Otsu method to automatically determine the threshold, performing image binarization processing on the grayscale image of the ovarian ultrasound image of the person to be detected, separating the follicle area from the background area, and applying a contour detection algorithm to obtain the contours of each graphic in the binarized image of the ovarian ultrasound image of the person to be detected; S72, and obtaining the contour area and shape features of each figure in the binary image of the ovarian ultrasound image of the person to be detected, and identifying each follicle in the ovarian ultrasound image of the person to be detected based on the contour area and shape features, thereby obtaining the number of follicles and the size of each follicle of the person to be detected; The specific analysis process of performing ovarian ultrasound image analysis on the person to be tested is as follows: Obtain the ovarian volume, ovarian cortical volume, ovarian area, ovarian cortical area and the size of each follicle of the person to be tested; Obtaining the normal ovarian volume range from the medical database , analyze the normal evaluation coefficient of the ovarian volume of the person to be tested in They represent the maximum and minimum interval values ​​of the normal ovarian volume range respectively; According to the calculation method of the normal evaluation coefficient of the ovarian volume of the person to be tested, the normal evaluation coefficient of the ovarian area, the normal evaluation coefficient of the ovarian cortex volume, the normal evaluation coefficient of the ovarian cortex area and the normal evaluation coefficient of each follicle size of the person to be tested are calculated in the same way; The normal evaluation coefficients of the follicle sizes of the persons to be tested are summed and averaged to calculate the normal evaluation coefficients of the follicle sizes of the persons to be tested; A data evaluation module is used to combine the blood test sample analysis results of the person to be tested with the ovarian ultrasound image analysis results, and then make a comprehensive score for the ovarian function of the person to be tested; The result feedback terminal is used to feed back the comprehensive score of the ovarian function of the person to be tested to the system interface of the attending physician of the person to be tested; The medical database is used to store a data table of AMH reference concentrations corresponding to optical density readings, to store the resolution of ultrasound equipment and the range of normal ovarian volume, and to store the score values ​​corresponding to each evaluation coefficient range.

2. The ovarian function assessment system based on AMH detection and image analysis according to claim 1, characterized in that: The sample analysis module also includes experimental operations on the blood test samples of the test personnel. The specific experimental operation process is as follows; Step 1: Place the blood sample of the person to be tested in a microplate containing specific anti-AMH antibodies; Step 2: washing the blood sample of the person to be tested to remove unbound substances; Step 3: adding a substrate to the blood test sample of the person to be tested, so that the substrate reacts with the enzyme-labeled antibody in the blood test sample of the person to be tested to produce a color change; Step 4: Use enzyme-labeled antibodies to detect AMH in the blood test sample of the person to be tested, and produce color changes according to the degree of reaction; Step 5: Use an ELISA reader to read the optical density of each microwell in the microplate corresponding to the blood test sample of the person to be tested , c represents the number of each microwell in the microwell plate, c=1,2,...m.

3. The ovarian function assessment system based on AMH detection and image analysis according to claim 2, characterized in that: The specific analysis process of the blood sample analysis of the person to be tested is as follows: Extract the values ​​of each AMH reference concentration and the values ​​of the optical density readings corresponding to each AMH reference concentration from the data table of optical density readings corresponding to the AMH reference concentration stored in the medical database, substitute them into the linear regression equation of OD=a×AMH+b, solve the values ​​of the slope a and the intercept b in the linear regression equation, and mark the values ​​of the slope a and the intercept b in the linear regression equation as a=a1 and b=b1 respectively; And filter out the optical density reading value corresponding to the maximum AMH reference concentration value from the data table of AMH reference concentration corresponding to optical density readings And the optical density reading corresponding to the minimum AMH reference concentration value ; Import the optical density of each microwell in the microplate corresponding to the blood test sample of the person to be tested into the regression model In this way, the AMH concentration value of the optical density of each microwell in the microplate corresponding to the blood test sample of the person to be tested is obtained. ; and through , the AMH concentration value of the blood test sample of the person to be tested is calculated, and m represents the total number of microwells in the microwell plate.

4. The ovarian function assessment system based on AMH detection and image analysis according to claim 1, characterized in that: The ovarian function of the person to be tested is comprehensively scored, and the specific scoring process is as follows: Compare the normal evaluation coefficient of the ovarian volume of the person to be tested with the score values ​​corresponding to each evaluation coefficient interval stored in the medical database to obtain the score value of the ovarian volume corresponding to the person to be tested; Similarly, the scoring values ​​of the ovarian area, ovarian cortical volume, ovarian cortical area and follicle size, and AMH concentration of the person to be tested are obtained, and the sum of the scores is calculated by dividing the sum by 6 to obtain the ovarian function score of the person to be tested.

5. An ovarian function assessment device based on AMH detection and image analysis, characterized in that: It is implemented based on the ovarian function assessment system based on AMH detection and image analysis as described in any one of claims 1 to 4, comprising a processor, a memory and a communication bus; The memory stores a computer-readable program executable by the processor; The communication bus realizes the connection and communication between the processor and the memory; When the processor executes the computer-readable program, it is implemented to implement the ovarian function assessment system based on AMH detection and image analysis as described in any one of claims 1-4.

6. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores one or more programs, and the one or more programs can be executed by one or more processors to implement the ovarian function assessment system based on AMH detection and image analysis as described in any one of claims 1-4.

Images