Iconography auxiliary analysis method for endometriosis

Abstract

The invention relates to the technical field of image data processing, in particular to an imaging auxiliary analysis method for endometriosis. According to the method, edge detection is carried out on an endometriosis ultrasonic image, lesion indexes of an endometriosis part are determined, lesion characteristics are accurately extracted, and the size and trend of a lesion area are quantified; in order to provide a type basis for marking, determining a focus type corresponding to each first image based on an endometriosis part focus index; determining a deterioration degree judgment coefficient corresponding to the first image according to the lesion index, the lesion type and an analysis model, thereby quantifying the severity of the lesion; and finally, marking the endometriosis ultrasonic image based on the deterioration degree judgment coefficient and the lesion type to obtain an ultrasonic image comprising classification labels of the lesion type and the deterioration degree, so that the classification labels of the lesion type and the deterioration degree obtained through accurate extraction and quantitative analysis can be provided, and the accuracy of the classification labels is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of image data processing, and particularly relates to an imaging-assisted analysis method for endometriosis. Background Art

[0002] Endometriosis is a common gynecological disease. Under normal circumstances, the endometrial tissue only exists in the uterine cavity. However, under abnormal circumstances, the endometrial tissue appears outside the uterus, such as in the ovaries, fallopian tubes, pelvic cavity and other parts, thus forming pelvic endometriotic foci, cervical endometriotic cysts and abdominal wall scar endometriotic cysts, etc. Such diseases may cause problems such as pain, irregular menstruation and infertility, and the condition may deteriorate over time. Non-invasive ultrasound technology can collect color Doppler ultrasound images of the endometrial tissue, process and analyze the images, and finally obtain a classification result of the degree of endometriosis deterioration through classification. This classification result can be used to assist doctors in subsequent diagnoses. Doctors conduct comprehensive analysis by combining other physical parameters and physical conditions of the patient to obtain the final diagnosis result.

[0003] Related technologies usually use deep learning methods to first process and label several ultrasound images of the endometrium, and then classify and label the images to be labeled according to the labeled ultrasound images of the endometrium and neural networks, so as to assign labels to all ultrasound images of the endometrium.

[0004] However, the processing and labeling in related technologies often only focus on the surface information of endometriosis, lacking precise extraction and quantitative analysis of the lesion characteristics of endometriosis, resulting in the labeling results not being labeled according to grades and accurately classified, and further resulting in deviations in the classification and labeling results of neural networks. Summary of the Invention

[0005] In view of this, the present invention provides an imaging-assisted analysis method for endometriosis, which can provide classification labels of lesion types and degrees of deterioration obtained through precise extraction and quantitative analysis, and improve the accuracy of the classification labels.

[0006] The purpose of the present invention is to provide an imaging-assisted analysis method for endometriosis, and the specific technical solution adopted is as follows: Obtain sample endometriosis ultrasound images, wherein the sample endometriosis ultrasound images contain lesion information of sample pelvic endometriotic foci, sample cervical endometriotic cysts and abdominal wall scar endometriotic cysts; Preprocess the sample endometriosis ultrasound images to obtain a first image; Perform edge detection on the first image to determine the lesion index of the endometriosis site corresponding to each first image; Determine the lesion type corresponding to each first image based on the lesion indicators of the endometriosis site; Determine the deterioration degree determination coefficient corresponding to the first image according to the lesion indicators, lesion type and analysis model of the endometriosis site corresponding to the first image; Label the sample endometriosis ultrasound image based on the deterioration degree determination coefficient and lesion type corresponding to the first image to obtain a sample labeled endometriosis ultrasound image, wherein the sample labeled endometriosis ultrasound image includes classification labels of the lesion type and deterioration degree.

[0007] In some embodiments, the preprocessing of the sample endometriosis ultrasound image includes: performing histogram equalization processing on the sample endometriosis ultrasound image.

[0008] In some embodiments, the edge detection of the first image to determine the lesion indicators of the endometriosis site corresponding to each first image includes: Perform edge detection on the first image to obtain an edge detection result, where the edge detection result includes a connected lesion area, lesion location, and ultrasonic feature information; Determine a first index and a second index according to the area and contour shape features of the connected lesion area, where the first index is the lesion indicator of cervical endometriosis cyst, and the second index is the lesion indicator of abdominal wall scar endometriosis cyst and other types of cysts; Determine the lesion indicators of the endometriosis site based on the first index and the second index.

[0009] In some embodiments, determine the first index according to the area and contour shape features of the connected lesion area: wherein, represents the lesion indicator of cervical endometriosis cyst, represents the area of the connected lesion area, i represents the intersection number, represents the Euclidean distance from the geometric center of the connected lesion area to the i-th intersection, represents the Euclidean distance from the geometric center of the connected lesion area to the (i + 1)-th intersection point, where the intersection point and the intersection point serial number i satisfy: a ray is made from the geometric center of the connected lesion area along the horizontal direction towards the contour of the connected lesion area, the ray intersects the contour at the first intersection point, the intersection point serial number i = 1 is recorded, at this time the included angle between the ray and the horizontal line is 0°, the ray is rotated counterclockwise, and one intersection point of the ray and the contour is obtained every 30° of counterclockwise rotation. After the ray completes one full rotation, a total of twelve intersection points are obtained, and they are numbered in the order of acquisition to obtain the serial number i.

[0010] In some embodiments, according to the area and contour shape characteristics of the connected lesion area, a second index is determined: In the formula, represents the lesion index of abdominal wall scar endometriosis cyst and other types of cysts, represents the area of the connected lesion area, j represents the intersection point serial number, represents the difference between the maximum Euclidean distance and the minimum Euclidean distance from the geometric center of the connected lesion area to the intersection point, represents the Euclidean distance from the geometric center of the connected lesion area to the j-th intersection point, represents the Euclidean distance from the geometric center of the connected lesion area to the (j + 6)-th intersection point, where the intersection point and the intersection point serial number j satisfy: a ray is made from the geometric center of the connected lesion area along the horizontal direction towards the contour of the connected lesion area, the ray intersects the contour at the first intersection point, the intersection point serial number j = 1 is recorded, at this time the included angle between the ray and the horizontal line is 0°, the ray is rotated counterclockwise, and one intersection point of the ray and the contour is obtained every 30° of counterclockwise rotation. After the ray completes one full rotation, a total of twelve intersection points are obtained, and they are numbered in the order of acquisition to obtain the serial number j.

[0011] In some embodiments, the determining the deterioration degree determination coefficient corresponding to the first image based on the endometriosis site lesion index, lesion type, and analysis model corresponding to the first image includes: Obtain the analysis model and determine the deterioration degree determination coefficient corresponding to the first image; Determine the image with the largest deterioration degree determination coefficient among the first images with the same lesion type, obtain the image with the largest deterioration degree determination coefficient for each lesion type, and use the image with the largest deterioration degree determination coefficient for each lesion type as the reference image for each lesion type; Determine that the deterioration degree of the reference image for each lesion type is the fifth level; Input the reference image, other images to be determined except the reference image in the first image, and the deterioration degree of the reference image into the analysis model to obtain the lesion type corresponding to each of the other images to be determined and the correlation coefficient between the reference image and the other image to be determined corresponding to the lesion type of each of the other images to be determined.

[0012] Based on the correlation coefficient and the lesion index, determine the deterioration degree determination coefficient corresponding to the first image.

[0013] In some embodiments, based on the first index and the second index, determine the lesion index of the endometriosis site: wherein, represents the lesion index of the endometriosis site, represents the sign function, represents the lesion index of the cervical endometriosis cyst, represents the lesion index of the abdominal wall scar endometriosis cyst and other types of cysts.

[0014] In some embodiments, based on the deterioration degree determination coefficient corresponding to the first image, determine the deterioration degree of the sample-labeled endometriosis ultrasound image, including: In response to the deterioration degree determination coefficient corresponding to the first image being within the first threshold range, the deterioration degree of the sample-labeled endometriosis ultrasound image is the first grade; In response to the deterioration degree determination coefficient corresponding to the first image being within the second threshold range, the deterioration degree of the sample-labeled endometriosis ultrasound image is the second grade; In response to the deterioration degree determination coefficient corresponding to the first image being within the third threshold range, the deterioration degree of the sample-labeled endometriosis ultrasound image is the third grade; In response to the deterioration degree determination coefficient corresponding to the first image being within the fourth threshold range, the deterioration degree of the sample-labeled endometriosis ultrasound image is the fourth grade; In response to the deterioration degree determination coefficient corresponding to the first image being within the fifth threshold range, the deterioration degree of the sample-labeled endometriosis ultrasound image is the fifth grade.

[0015] In some embodiments, based on the correlation coefficient and the lesion index, determine the deterioration degree determination coefficient corresponding to the first image: wherein, represents the deterioration degree determination coefficient, represents the exponential function with the natural constant as the base, Indicates the lesion index of cervical endometriotic cysts Indicates the lesion index of abdominal wall scar endometriotic cysts and other types of cysts Represents the correlation coefficient calculation symbol, a represents the reference image corresponding to the lesion type of each of the other images to be determined, and b represents the other image to be determined Represents the correlation coefficient between the reference image corresponding to the lesion type of each of the other images to be determined and the other image to be determined

[0016] In some embodiments, the analysis model is a template matching model

[0017] The present invention has the following beneficial effects An imaging-assisted analysis method for endometriosis provided by the present invention first performs edge detection on the preprocessed sample endometriosis ultrasound images to determine the lesion index of the endometriosis site, thereby accurately extracting the lesion characteristics and quantifying the size and trend of the lesion area; then, based on the lesion index of the endometriosis site, accurately determines the lesion type corresponding to each first image, providing a type basis for annotation; then, according to the lesion index, lesion type and analysis model corresponding to the first image, determines the deterioration degree determination coefficient corresponding to the first image, thereby quantifying the severity of the lesion; finally, based on the deterioration degree determination coefficient and lesion type corresponding to the first image, annotates the sample endometriosis ultrasound images to obtain the sample annotated endometriosis ultrasound images including the classification labels of the lesion type and deterioration degree, improving the accuracy of the classification labels BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts

[0019] Figure 1 It is a method flow chart of an imaging-assisted analysis method for endometriosis provided by an embodiment of the present invention DETAILED DESCRIPTION OF THE INVENTION

[0020] To further elaborate on the technical means and effects adopted by the present invention to achieve the intended invention purpose, the following specifically describes, in conjunction with the accompanying drawings and preferred embodiments, a method for imaging-assisted analysis of endometriosis according to the present invention, including its specific implementation manner, structure, features, and effects. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. In addition, the specific features, structures, or characteristics in one or more embodiments can be combined in any suitable form.

[0021] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the technical field to which this invention belongs.

[0022] The following specifically describes the specific solution of a method for imaging-assisted analysis of endometriosis provided by the present invention in conjunction with the accompanying drawings.

[0023] Please refer to Figure 1 , which shows a flowchart of a method for imaging-assisted analysis of endometriosis provided by an embodiment of the present invention. The method includes: Step 101, obtaining a sample endometriosis ultrasound image, where the sample endometriosis ultrasound image contains lesion information of sample pelvic endometriosis lesions, sample cervical endometriosis cysts, and abdominal wall scar endometriosis cysts.

[0024] In some embodiments, the sample endometriosis ultrasound image includes, but is not limited to, lesion information of sample pelvic endometriosis lesions, sample cervical endometriosis cysts, and abdominal wall scar endometriosis cysts, and may also include ultrasound features and bleeding conditions, etc.

[0025] Step 102, preprocessing the sample endometriosis ultrasound image to obtain a first image.

[0026] In some embodiments, the preprocessing in step 102 can be achieved in the following manner: performing histogram equalization processing on the sample endometriosis ultrasound image to ensure the observability and contrast of the image.

[0027] Step 103, performing edge detection on the first image to determine the lesion index of the endometriosis site corresponding to each first image.

[0028] Edge detection can accurately extract lesion features, obtain lesion ultrasound features and bleeding conditions, etc. in the first image, determine the lesion index of the endometriosis site, and thus quantify the size and trend of the lesion area.

[0029] It should be noted that endometriosis lesions with a diameter of more than 2 cm can be detected by ultrasound. They have various manifestations according to different growth sites, and different growth sites correspond to different lesion positions, so the specific types are also different. Cervical endometriosis cyst: It appears as a round or oval cloud-like hypoechoic area within the cervical tissue, with a relatively clear boundary and a rough inner wall. Its cyst wall is composed of cervical tissue; Abdominal wall scar endometriosis cyst: It can occur in each layer of the abdominal wall scar, with local abdominal wall thickening. The lesion is fusiform or oval, and the boundary is relatively blurred. Therefore, based on its specific distribution characteristics, the corresponding lesion position, lesion type, lesion ultrasound characteristics, bleeding conditions, etc. can be analyzed and determined. The closer the edge detection result is to the lesion characteristics of a certain position above, the greater the probability of it being that ectopia, and then the lesion indicators of the ectopic site are closer to the indicators of this type of lesion.

[0030] In some embodiments, the edge detection in step 3 can be Canny edge detection. The pixel values of the detection result are either 0 or 1, which can intuitively reflect the contour shape characteristics and distribution range of the connected lesion area. The distribution range affects the area of the connected area, that is, the size of the lesion.

[0031] Since the contours of some connected lesion areas in the edge detection result may not be closed and have gaps, in some embodiments, the edge detection result can be dilated by a morphological dilation algorithm, so that the originally unconnected edge contours can be closed, thereby dividing the connected lesion area.

[0032] In some embodiments, step 103 includes: Step 1031, perform edge detection on the first image to obtain an edge detection result, which includes a connected lesion area, a lesion position, and ultrasonic feature information, so as to quantify the size and trend of the lesion area.

[0033] Step 1032, determine a first index and a second index according to the area and contour shape characteristics of the connected lesion area. The first index is the lesion index of the cervical endometriosis cyst, and the second index is the lesion index of the abdominal wall scar endometriosis cyst and other types of cysts.

[0034] The first index and the second index are lesion indexes of different lesion types, so as to obtain the possibility degree of different lesion types within the connected lesion area.

[0035] In some embodiments, according to the area and contour shape characteristics of the connected lesion area, determine the first index: In the formula, represents the lesion index of the cervical endometriosis cyst, that is, the first index, represents the area of the connected lesion region, and i represents the intersection point number. represents the Euclidean distance from the geometric center of the connected lesion region to the i-th intersection point. represents the Euclidean distance from the geometric center of the connected lesion region to the (i + 1)-th intersection point. Among them, the intersection point and the intersection point number i satisfy: a ray is made from the geometric center of the connected lesion region along the horizontal direction to the contour of the connected lesion region, and the ray intersects the contour at the first intersection point, and the intersection point number i = 1 is recorded. At this time, the angle between the ray and the horizontal line is 0°. The ray is rotated counterclockwise, and a ray intersects the contour at an intersection point every 30° of counterclockwise rotation. After the ray completes a full rotation, a total of twelve intersection points are obtained, and they are numbered in the order of acquisition to obtain the number i.

[0036] represents the lesion index of cervical endometriosis cyst, aiming to quantify the size and tendency of the lesion corresponding to the cervical endometriosis cyst, that is, whether it is endometriosis of this lesion type. Usually, the characteristics of this type of lesion are: a round or oval cloud-like hypoechoic area in the cervical tissue, with a relatively clear boundary and a rough inner wall. Then, the contour shape characteristics of the connected lesion region obtained through edge detection will also show such characteristics.

[0037] The closer the contour shape characteristics of the connected lesion region are to a circle or an oval, and the larger the area of the connected lesion region, the larger the lesion index. The Euclidean distance from the geometric center of the connected lesion region to the i-th intersection point can be used as an important parameter to quantify whether the contour shape of the connected lesion region is a circle or an oval. When the contour shape is closer to a circle, the Euclidean distances from the geometric center of the connected lesion region to each intersection point are closer, and the distances from the geometric center of the connected lesion region to two adjacent intersection points are also closer. Therefore, use to characterize the proximity degree of the distance from the geometric center of the connected lesion region to the intersection point; The smaller it is, the closer the distances from the geometric center of the connected lesion region to two adjacent intersection points are, that is, the closer the contour shape characteristics are to a circle or an oval. The larger it is, the larger the lesion index. Then the summation result is larger; multiplying the summation result by the area of the connected lesion region (the number of pixel points in the connected lesion region) to obtain the lesion index of the cervical endometriosis cyst , the larger this value is, the larger the lesion region is, and the higher the corresponding lesion index is, that is, the greater the possibility that the lesion type is cervical endometriosis cyst.

[0038] In some embodiments, according to the area and contour shape characteristics of the connected lesion region, a second index is determined: In the formula, represents the lesion index of endometriosis cyst and other types of cysts in the abdominal wall scar, that is, the second index. represents the area of the connected lesion region, and j represents the intersection point number. represents the difference between the maximum Euclidean distance and the minimum Euclidean distance from the geometric center of the connected lesion region to the intersection point. represents the Euclidean distance from the geometric center of the connected lesion region to the j-th intersection point. represents the Euclidean distance from the geometric center of the connected lesion region to the (j + 6)-th intersection point. Among them, the intersection point and the intersection point number j satisfy: a ray is made along the horizontal direction from the geometric center of the connected lesion region to the contour of the connected lesion region, and the ray intersects the contour at the first intersection point, and the intersection point number j = 1 is recorded. At this time, the angle between the ray and the horizontal line is 0°. The ray is rotated counterclockwise, and a ray intersects the contour at an intersection point every 30° counterclockwise rotation. After the ray completes one circle of rotation, a total of twelve intersection points are obtained, and they are numbered in the order of acquisition to obtain the number j.

[0039] represents the lesion index of endometriosis cyst and other types of cysts in the abdominal wall scar, aiming to quantify the size and trend of the lesions corresponding to the abdominal wall scar and other types of cysts, that is, whether it is the abdominal wall scar and other types of cysts of this lesion type. The lesion characteristics formed by the abdominal wall scar and other types of cysts do not have a relatively regular geometric shape compared with the cervical endometriosis cyst. Its specific characteristics are: the lesion is fusiform or oval, so the contour shape characteristics of the connected lesion region obtained by edge detection will also be fusiform or oval.

[0040] The closer the contour shape characteristics of the connected lesion region are to fusiform or oval, and the larger the area of the connected lesion region, the larger the lesion index. The Euclidean distance from the geometric center of the connected lesion region to the j-th intersection point can be used as an important parameter to quantify whether the contour shape of the connected lesion region is fusiform or oval. When the contour shape is closer to fusiform or oval, the Euclidean distance from the geometric center of the connected lesion region to the j-th intersection point is closer to the Euclidean distance from the geometric center of the connected lesion region to the (j + 6)-th intersection point. Therefore, represents the degree of closeness between the Euclidean distance from the geometric center of the connected lesion region to the j-th intersection point and the Euclidean distance from the geometric center of the connected lesion region to the (j + 6)-th intersection point; the closer it is to 1, that is, the closer the contour shape characteristics are to fusiform or oval, the closer it is to 1, the larger the lesion index, and then the summation result is larger; the difference between the maximum Euclidean distance and the minimum Euclidean distance from the geometric center of the connected lesion region to the intersection point Indicates the degree of flatness of a spindle or oval shape. The larger this value, the flatter the lesion is in the shape of a spindle or oval. Compare the summation result with the area of the connected lesion region (the number of pixel points in the connected lesion region), Multiply to obtain the lesion index of endometriosis cysts in abdominal wall scars and other types of cysts , the larger this value, the larger the lesion area, and the higher the corresponding lesion index, that is, the greater the possibility that the lesion type is endometriosis cysts in abdominal wall scars and other types of cysts.

[0041] Step 1033: Based on the first index and the second index, determine the lesion index of the endometriosis site.

[0042] The obtained lesion index of the endometriosis site can reflect the size and trend of the entire connected lesion region, and determine whether the connected lesion region is biased towards endometriosis cysts in the cervix or endometriosis cysts in abdominal wall scars and other types of cysts.

[0043] In some embodiments, according to the following formula, based on the first index and the second index, determine the lesion index of the endometriosis site: In the formula, represents the lesion index of the endometriosis site, represents the sign function, represents the lesion index of endometriosis cysts in the cervix, represents the lesion index of endometriosis cysts in abdominal wall scars and other types of cysts.

[0044] Compare the first index and the second index corresponding to the connected lesion region, and judge through the sign function the positivity or negativity. If the value of the first index is large, then is greater than 0, the classification result of is 1, and the lesion type of this lesion region is endometriosis cysts in the cervix. If the value of the second index is large, then is less than 0, the classification result of is -1, endometriosis cysts in abdominal wall scars and other types of cysts. Judge through the sign function

[0045] the positivity or negativity of

[0046] to obtain the classification result of the lesion index, so as to determine the lesion index of the endometriosis site .

[0045] Step 104: Based on the lesion index of the endometriosis site, determine the lesion type corresponding to each first image.

[0046] The lesion indicators at the endometriosis sites can quantify the characteristics such as the size and trend of the lesion areas, thereby determining the lesion types. By whether the lesion indicator is 1 or -1, it is determined whether the lesion type corresponding to each first image is a cervical endometriotic cyst, an abdominal wall scar endometriotic cyst, or other types of cysts, providing an accurate guidance for the label classification of the lesion types. The determination of the lesion types here is to screen out the corresponding lesion types from the ultrasound images, so as to facilitate the subsequent annotation of the sample endometriosis ultrasound images of different lesion types.

[0047] Step 105: Determine the deterioration degree determination coefficient corresponding to the first image according to the endometriosis site lesion indicator, lesion type, and analysis model corresponding to the first image.

[0048] The deterioration degree determination coefficient is used to quantify the severity of the lesion, so as to provide an accurate classification basis for the label classification of the deterioration degree.

[0049] In some embodiments, step 105 includes: Step 1051: Obtain the analysis model and determine the deterioration degree determination coefficient corresponding to the first image.

[0050] The analysis model can perform template matching to quantify the deterioration degree corresponding to the first image into the deterioration degree determination coefficient.

[0051] Step 1052: Determine the image with the largest deterioration degree determination coefficient among the first images with the same lesion type, obtain the image with the largest deterioration degree determination coefficient corresponding to each lesion type, and use the image with the largest deterioration degree determination coefficient corresponding to each lesion type as the reference image for each lesion type.

[0052] The reference image can also provide a reference basis for the determination of the deterioration degree of the first image. Since the deterioration degree determination coefficient of the reference image is the largest, a unified judgment standard can be set for the deterioration degree corresponding to each lesion type, and the deterioration degree is quantified by the deterioration degree determination coefficient, so as to more accurately determine the deterioration degree of each first image subsequently.

[0053] Step 1053: Determine that the deterioration degree of the reference image of each lesion type is the fifth grade.

[0054] Determine that the deterioration degree of the reference image is the most severe lesion degree, use the fifth grade to characterize the deterioration degree of the reference image, set a unified standard for the analysis model, and facilitate the quantification and classification annotation of the deterioration degree of other images.

[0055] Step 1054: Input the reference image, the other images to be determined in the first image excluding the reference image, and the degree of deterioration of the reference image into the analysis model to obtain the lesion type corresponding to each other image to be determined and the correlation coefficient between the reference image corresponding to the lesion type of each other image to be determined and the other image to be determined.

[0056] In some embodiments, the analysis model is a template matching model to find the image similar to the reference image in other images to be determined according to the matching degree.

[0057] The other images to be determined in the first image excluding the reference image need to be determined by the analysis model based on the deterioration degree determination coefficient and the degree of deterioration in the reference image, so as to obtain the correlation coefficient between the image and the reference image of the same lesion type. This correlation coefficient represents the degree of closeness between the degree of deterioration of the image and the reference image of the same lesion type (the degree of deterioration is the fifth level). The correlation coefficient is intended to analyze the difference between the reference image and the first image. The larger the correlation coefficient, the closer the lesion type, lesion size and degree of deterioration of the first image are to the reference image, that is, its cyst area, the size corresponding to the cyst, etc. are highly similar.

[0058] Step 1055: Determine the deterioration degree determination coefficient corresponding to the first image based on the correlation coefficient and the lesion index.

[0059] The larger the correlation coefficient, the relatively larger the deterioration degree determination coefficient; the smaller the correlation coefficient, the relatively smaller the deterioration degree determination coefficient. Adjust the correlation coefficient through the lesion index to obtain the deterioration degree determination coefficient, so as to classify the degree of deterioration more accurately.

[0060] In some embodiments, according to the following formula, step 1055 is implemented to determine the deterioration degree determination coefficient corresponding to the first image based on the correlation coefficient and the lesion index: In the formula, represents the deterioration degree determination coefficient, represents the exponential function with the natural constant as the base, exp[-] is used for negative correlation mapping and normalization processing, represents the lesion index of cervical endometriosis cyst, represents the lesion index of abdominal wall scar endometriosis cyst and other types of cysts, represents the correlation coefficient calculation symbol, a represents the reference image corresponding to the lesion type of each other image to be determined, b represents the other image to be determined, represents the correlation coefficient between the reference image corresponding to the lesion type of each other image to be determined and the other image to be determined.

[0061] Since the lesion index affects the deterioration degree coefficient, that is, the deterioration degrees at different positions of the lesion are different. Specifically, the ratio of the first index and the second index is used to adjust the magnitude of the correlation coefficient, so that the deterioration degree determination coefficient incorporates the lesion type information to obtain the deterioration degree determination coefficient, thereby more accurately classifying the deterioration degree. The index ratio result before the correlation coefficient Quantify the proximity between the first index and the second index. The closer the two indexes are, the closer the lesion types are. Then, when participating in the calculation of the deterioration degree determination coefficient, its weight value is greater.

[0062] The correlation coefficient aims to analyze the difference between the reference image and the first image. When the deterioration degrees of the reference image and the first image are highly consistent, the normalized value of the correlation coefficient is closer to 1. After subtracting 1 from it and performing inverse normalization on the result is closer to 1, and the corresponding deterioration degree determination coefficient is higher; conversely, when there are significant differences in their deterioration degrees, for example, there are significant differences in the lesion size (i.e., the area of the connected lesion region) and the contour shape of the connected lesion region, that is, there are significant differences in the lesion characteristics of endometriosis, then there are significant differences in their deterioration degrees. At this time, the normalized correlation coefficient is closer to 0, and the inverse normalization result is less than 1, and the corresponding deterioration degree determination coefficient is lower.

[0063] In some embodiments, based on the deterioration degree determination coefficient corresponding to the first image, determining the deterioration degree of the sample-labeled endometriosis ultrasound image includes: (1) In response to the deterioration degree determination coefficient corresponding to the first image being within the first threshold range, the deterioration degree of the sample-labeled endometriosis ultrasound image is the first grade; (2) In response to the deterioration degree determination coefficient corresponding to the first image being within the second threshold range, the deterioration degree of the sample-labeled endometriosis ultrasound image is the second grade; (3) In response to the deterioration degree determination coefficient corresponding to the first image being within the third threshold range, the deterioration degree of the sample-labeled endometriosis ultrasound image is the third grade; (4) In response to the deterioration degree determination coefficient corresponding to the first image being within the fourth threshold range, the deterioration degree of the sample-labeled endometriosis ultrasound image is the fourth grade; (5) In response to the deterioration degree determination coefficient corresponding to the first image being within the fifth threshold range, the deterioration degree of the sample-labeled endometriosis ultrasound image is the fifth grade. Among them, the levels from the first grade to the fifth grade increase in sequence, and the deterioration degree determination coefficients also increase in sequence.

[0064] The deterioration degree is divided into five grades as the grading standard for quantifying the deterioration degree. By judging the threshold range where the deterioration degree determination coefficient is located, the grade of the deterioration degree corresponding to the image is determined.

[0065] In some embodiments, the first threshold range may be , and the second threshold range may be , and the third threshold range may be , and the fourth threshold range may be , and the fifth threshold range may be .

[0066] Exemplarily, when the deterioration degree determination coefficient corresponding to the first image is within the range, the deterioration degree of the sample-labeled endometriosis ultrasound image is rated as grade one; when the deterioration degree determination coefficient corresponding to the first image is within the range, the deterioration degree of the sample-labeled endometriosis ultrasound image is rated as grade two; when the deterioration degree determination coefficient corresponding to the first image is within the range, the deterioration degree of the sample-labeled endometriosis ultrasound image is rated as grade three; when the deterioration degree determination coefficient corresponding to the first image is within the range, the deterioration degree of the sample-labeled endometriosis ultrasound image is rated as grade four; when the deterioration degree determination coefficient corresponding to the first image is within the range, the deterioration degree of the sample-labeled endometriosis ultrasound image is rated as grade five.

[0067] Step 106: Based on the deterioration degree determination coefficient and the lesion type corresponding to the first image, label the sample endometriosis ultrasound image to obtain a sample-labeled endometriosis ultrasound image, where the sample-labeled endometriosis ultrasound image includes classification labels for the lesion type and the deterioration degree.

[0068] The sample-labeled endometriosis ultrasound image includes classification labels for the lesion type and the deterioration degree. This classification label can assign a recommended classification result of the lesion type and the deterioration degree to each endometriosis ultrasound image, thereby providing an effective auxiliary reference basis for doctors' evaluation and determination of the lesion type and the deterioration degree, and helping to improve doctors' trust and acceptance of ultrasound technology.

[0069] It should be noted that the classification result of the deterioration degree is only a recommended result, and specifically, professional physicians need to evaluate and determine it according to the actual situation and medical professional knowledge.

[0070] In some embodiments, the sample-labeled endometriosis ultrasound image with classification labels can be obtained by training a CNN classification network. The loss function of the CNN classification network uses the cross-entropy function, and the cross-entropy function can measure the amount of information required to eliminate uncertainty and improve the parameter update speed.

[0071] In summary, an imaging-assisted analysis method for endometriosis provided by the present invention performs edge detection on the preprocessed endometriosis ultrasound images of the samples, determines the lesion indicators at the endometriosis sites, and thus accurately extracts the lesion features and quantifies the size and trend of the lesion areas. To provide a basis for the annotation types, further based on the lesion indicators at the endometriosis sites, the lesion types corresponding to each first image are accurately determined. Then, according to the lesion indicators, lesion types, and analysis model corresponding to the first image, the deterioration degree determination coefficient corresponding to the first image is determined, thereby quantifying the severity of the lesions. Finally, based on the deterioration degree determination coefficient and lesion types corresponding to the first image, the endometriosis ultrasound images of the samples are annotated to obtain the sample-annotated endometriosis ultrasound images including the classification labels of the lesion types and deterioration degrees. This method can provide classification labels of lesion types and deterioration degrees obtained through accurate extraction and quantitative analysis, improving the accuracy of the classification labels.

[0072] It should be noted that the above sequence of the embodiments of the present invention is only for description and does not represent the advantages or disadvantages of the embodiments. The processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0073] Each embodiment in this specification is described in a progressive manner, and the same or similar parts among the embodiments can be referred to each other. Each embodiment focuses on the differences from other embodiments.

Claims

1. An imaging-assisted analysis method for endometriosis, characterized in that: The method comprises: Acquiring a sample endometriosis ultrasound image, wherein the sample endometriosis ultrasound image includes lesion information of a sample pelvic endometriosis focus, a sample cervical endometriosis cyst, and an abdominal wall scar endometriosis cyst; Preprocessing the sample endometriosis ultrasound image to obtain a first image; Performing edge detection on the first image to determine an endometriosis lesion index corresponding to each first image; Based on the endometriosis site lesion index, determining the lesion type corresponding to each first image; Determining a deterioration degree determination coefficient corresponding to the first image according to the endometriosis site lesion index, lesion type and analysis model corresponding to the first image; Based on the deterioration degree determination coefficient and the lesion type corresponding to the first image, the sample endometriosis ultrasound image is labeled to obtain a sample labeled endometriosis ultrasound image, wherein the sample labeled endometriosis ultrasound image includes classification labels of lesion type and deterioration degree.

2. The imaging-assisted analysis method for endometriosis according to claim 1, characterized in that: The preprocessing of the sample endometriosis ultrasound image comprises: The sample endometriosis ultrasound image is subjected to histogram equalization processing.

3. The imaging-assisted analysis method for endometriosis according to claim 1, characterized in that: The performing edge detection on the first image to determine the endometriosis lesion index corresponding to each first image includes: Performing edge detection on the first image to obtain an edge detection result, wherein the edge detection result includes connected lesion areas, lesion locations, and ultrasonic feature information; Determine a first index and a second index according to the area and contour shape characteristics of the connected lesion area, wherein the first index is the lesion index of cervical endometriosis cyst, and the second index is the lesion index of abdominal wall scar endometriosis cyst and other types of cysts; Based on the first index and the second index, an endometriosis site lesion index is determined.

4. The imaging-assisted analysis method for endometriosis according to claim 3, characterized in that: According to the area and contour shape characteristics of the connected lesion area, the first indicator is determined: In the formula, Indicators of lesions of cervical endometriosis cysts, represents the area of ​​the connected lesion area, i represents the intersection number, represents the Euclidean distance from the geometric center of the connected lesion area to the i-th intersection point, Represents the Euclidean distance from the geometric center of the connected lesion area to the i+1th intersection point, wherein the intersection point and the intersection point serial number i satisfy: a ray is made through the geometric center of the connected lesion area along the horizontal direction to the outline of the connected lesion area, the ray intersects with the outline at the first intersection point, and the intersection point serial number i=1 is recorded. At this time, the angle between the ray and the horizontal line is 0°, and the ray is rotated counterclockwise. An intersection point between the ray and the outline is obtained for every 30° counterclockwise rotation. The ray completes one rotation, and a total of twelve intersection points are obtained. The intersection points are labeled in the order in which they are obtained to obtain the serial number i.

5. The imaging-assisted analysis method for endometriosis according to claim 3, characterized in that: The second index is determined based on the area and contour shape characteristics of the connected lesion area: In the formula, Indicates the lesion indicators of abdominal wall scar, endometriosis cyst and other types of cysts. represents the area of ​​the connected lesion area, j represents the intersection number, It represents the difference between the maximum Euclidean distance and the minimum Euclidean distance from the geometric center of the connected lesion area to the intersection point. represents the Euclidean distance from the geometric center of the connected lesion area to the jth intersection point, Represents the Euclidean distance from the geometric center of the connected lesion area to the j+6th intersection point, wherein the intersection point and intersection number j satisfy: a ray is made through the geometric center of the connected lesion area along the horizontal direction to the outline of the connected lesion area, the ray intersects with the outline at the first intersection point, and the intersection number j=1 is recorded. At this time, the angle between the ray and the horizontal line is 0°. The ray is rotated counterclockwise, and an intersection point between the ray and the outline is obtained every 30° counterclockwise rotation. The ray completes one rotation, and a total of twelve intersection points are obtained. The intersection points are labeled in the order in which they are obtained to obtain the number j.

6. The imaging-assisted analysis method for endometriosis according to claim 1, characterized in that: The step of determining the deterioration degree determination coefficient corresponding to the first image according to the endometriosis site lesion index, lesion type and analysis model corresponding to the first image comprises: Acquire an analysis model to determine a deterioration degree determination coefficient corresponding to the first image; Determine the image with the largest deterioration degree determination coefficient among the first images with the same lesion type, obtain the image with the largest deterioration degree determination coefficient corresponding to each lesion type, and use the image with the largest deterioration degree determination coefficient corresponding to each lesion type as the reference image for each lesion type; The deterioration of the reference image for each lesion type was determined as grade 5; Inputting the reference image, other images to be determined in the first image excluding the reference image, and the deterioration degree of the reference image into the analysis model, obtaining the lesion type corresponding to each of the other images to be determined, and the correlation coefficient between the reference image and the other images to be determined corresponding to the lesion type of each of the other images to be determined; Based on the correlation coefficient and the lesion index, a deterioration degree determination coefficient corresponding to the first image is determined.

7. The imaging-assisted analysis method for endometriosis according to claim 3, characterized in that: Based on the first index and the second index, determining the endometriosis lesion index: In the formula, Indicates the endometriosis lesion index. represents the symbolic function, Indicators of lesions of cervical endometriosis cysts, Lesion indicators for abdominal wall scar endometriosis cysts and other types of cysts.

8. The imaging-assisted analysis method for endometriosis according to claim 6, characterized in that: Determining the deterioration degree of the sample labeled endometriosis ultrasound image based on the deterioration degree determination coefficient corresponding to the first image includes: In response to the deterioration degree determination coefficient corresponding to the first image being within a first threshold range, the sample marks the deterioration degree of the endometriosis ultrasound image as the first level; In response to the deterioration degree determination coefficient corresponding to the first image being within a second threshold range, the sample marks the deterioration degree of the endometriosis ultrasound image as the second level; In response to the deterioration degree determination coefficient corresponding to the first image being within a third threshold range, the sample marks the deterioration degree of the endometriosis ultrasound image as the third level; In response to the deterioration degree determination coefficient corresponding to the first image being within a fourth threshold range, the sample marks the deterioration degree of the endometriosis ultrasound image as the fourth level; In response to the deterioration degree determination coefficient corresponding to the first image being within a fifth threshold range, the sample marks the deterioration degree of the endometriosis ultrasound image as the fifth level.

9. The imaging-assisted analysis method for endometriosis according to claim 6, characterized in that: Based on the correlation coefficient and the lesion index, a deterioration degree determination coefficient corresponding to the first image is determined: In the formula, represents the determination coefficient of the degree of deterioration, represents an exponential function with a natural constant as base, Indicators of lesions of cervical endometriosis cysts, Indicates the lesion indicators of abdominal wall scar, endometriosis cyst and other types of cysts. represents the correlation coefficient calculation symbol, a represents the reference image corresponding to the lesion type of each of the other images to be determined, b represents the other images to be determined, The correlation coefficient between the reference image corresponding to the lesion type of each of the other images to be determined and the other images to be determined is represented.

10. The imaging-assisted analysis method for endometriosis according to claim 6, characterized in that: The analysis model is a template matching model.

Images