Ovarian state determination method and device, computer device, and storage medium

Abstract

The application relates to an ovary state determination method and device, computer equipment, a storage medium and a computer program product. The method comprises the following steps: acquiring a target slice image of an ovary staining slice, and at least one target follicle meeting a follicle state analysis condition existing in the target slice image; identifying a first target region where the target follicle is located and a second target region where a follicle membrane layer is located from the target slice image; identifying a third target region where a wall layer granulosa cell layer is located from the first target region; determining the state of the target follicle based on the area size ratio of the second target region and the third target region, and obtaining a target follicle state determination result; and determining the state of the ovary according to the target follicle state determination result, and obtaining an ovary state determination result. The method can accurately evaluate the state of the ovary.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of female health, and in particular to an ovary state determination method and device, a computer device, a storage medium, and a computer program product. BACKGROUND

[0002] With the development of society, people pay more and more attention to their own physical health, and women pay more and more attention to their own health.

[0003] In the traditional technology, the measurement method of the follicle size in the ovary is to measure the longest axis of the follicle and another shortest axis intersecting the longest axis to calculate the diameter of the follicle. By randomly selecting the area of the follicle membrane layer and the wall granulosa cell layer in the follicle, the average thickness of the follicle membrane layer and the wall granulosa cell layer is calculated, so as to realize the determination of the ovary state. However, the result obtained by using the traditional technology has a large error, and it is difficult to realize the accurate evaluation of the ovary state. SUMMARY

[0004] Therefore, it is necessary to provide an ovary state evaluation method, device, computer equipment, computer readable storage medium, and computer program product capable of accurately evaluating the ovary state in view of the above technical problems.

[0005] In a first aspect, the present application provides an ovary state determination method, which comprises:

[0006] obtaining a target slice image of an ovary staining slice, wherein at least one target follicle meeting a follicle state analysis condition exists in the target slice image; the target follicle is surrounded by a follicle membrane layer, and the target follicle comprises a follicle cavity and a wall granulosa cell layer surrounding the follicle cavity;

[0007] From the target slice image, a first target region where the target follicle is located and a second target region where the follicle membrane layer is located are identified;

[0008] From the first target region, a third target region where the wall granulosa cell layer is located is identified;

[0009] Based on the area size ratio of the second target region to the third target region, the state of the target follicle is determined to obtain a target follicle state determination result;

[0010] According to the target follicle state determination result, the state of the ovary is determined to obtain a determination result of the ovary state.

[0011] In one of the embodiments, before the target slice image of the ovary staining slice is obtained, the method further comprises:

[0012] a plurality of continuous ovarian sections, each of the continuous ovarian sections having an equal section thickness;

[0013] a plurality of target sections having an equal number of sections apart are selected from the continuous ovarian sections by equidistant sampling;

[0014] each of the target sections is subjected to a staining process to obtain a plurality of stained ovarian sections;

[0015] the target section image of the ovarian stained section includes:

[0016] each of the ovarian stained sections is subjected to an imaging process to obtain a plurality of target section images corresponding to the respective ovarian stained sections.

[0017] In one embodiment, after identifying the first target region where the target follicle is located and the second target region where the follicle membrane layer is located from the target section image, the method further includes:

[0018] calculating a first area corresponding to the first target region where the target follicle is located;

[0019] calculating a difference between the first area and a total area of the target follicle and the follicle membrane layer surrounding the target follicle to obtain a second area corresponding to the follicle membrane layer;

[0020] determining the area size ratio according to the second area and an area corresponding to the third target region.

[0021] In one embodiment, identifying the third target region where the theca granulosa cell layer is located from the first target region includes:

[0022] obtaining a connection position between the follicle lumen and the theca granulosa cell layer from the first target region where the target follicle is located;

[0023] determining the third target region where the theca granulosa cell layer is located in the first target region according to the connection position;

[0024] After identifying the third target region where the theca granulosa cell layer is located from the first target region, the method further includes:

[0025] calculating an area of the follicle lumen;

[0026] calculating a difference between an area corresponding to the first target region and the area of the follicle lumen to obtain a third area corresponding to the third target region;

[0027] determining the area size ratio according to the third area and an area corresponding to the second target region.

[0028] In one embodiment, there are at least two target follicles in the target slice image that meet the follicle state analysis condition;

[0029] The follicle state determination module is configured to determine the state of the target follicle based on the area size ratio of the second target area to the third target area, to obtain a target follicle state determination result.

[0030] The follicle state determination module is configured to determine the state of the target follicle based on the area size ratio of the second target area to the third target area, to obtain a target follicle state determination result.

[0031] The follicle state determination module is configured to determine the state of the target follicle based on the area size ratio of the second target area to the third target area, to obtain a target follicle state determination result.

[0032] The follicle state determination module is configured to determine the state of the target follicle based on the area size ratio of the second target area to the third target area, to obtain a target follicle state determination result.

[0033] When the maximum area and the average value exceed the critical value of ovarian tissue pathological evaluation, it is determined that the target follicle has a lesion.

[0034] When the maximum area and the average value do not exceed the critical value of ovarian tissue pathological evaluation, it is determined that the target follicle has no lesion.

[0035] In a second aspect, the present application provides an ovarian state determination device, which comprises:

[0036] A target slice image acquisition module is configured to acquire a target slice image of an ovarian dyeing slice, wherein there is at least one target follicle in the target slice image that meets a follicle state analysis condition; the target follicle is surrounded by a theca layer, and the target follicle comprises a follicle cavity and a wall layer granulosa cell layer surrounding the follicle cavity.

[0037] A first region identification module is configured to identify a first target region where the target follicle is located and a second target region where the theca layer is located from the target slice image.

[0038] A second region identification module is configured to identify a third target region where the wall layer granulosa cell layer is located from the first target region.

[0039] A follicle state determination module is configured to determine the state of the target follicle based on the area size ratio of the second target area to the third target area, to obtain a target follicle state determination result.

[0040] An ovary state determination module is configured to determine the state of the ovary according to the target follicle state determination result, and obtain a determination result of the ovary state.

[0041] In a third aspect, the present application provides a computer device, comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the method described above when executing the computer program.

[0042] In a fourth aspect, the present application provides a computer readable storage medium, which stores a computer program, and the computer program implements the steps of the method described above when executed by a processor.

[0043] In a fifth aspect, the present application provides a computer program product, comprising a computer program, and the computer program implements the steps of the method described above when executed by a processor.

[0044] The ovary state determination method, device, computer device, storage medium and computer program product described above can facilitate the observation of the follicle in the ovary slice by obtaining the staining slice image of the ovary, so as to accurately find out the target follicle meeting the follicle state analysis condition. The first target region where the target follicle meeting the follicle state analysis condition is located and the second target region where the follicle membrane layer is located can be identified, so as to facilitate the calculation of the area of the target follicle and the follicle membrane layer surrounding the target follicle. The third target region where the theca granulosa cell layer is located can be identified from the first target region, so as to reduce the measurement error caused by the small target follicle, thereby realizing the accurate identification of the third target region. The health status of the target follicle can be determined by calculating the ratio of the second target region to the third target region, thereby realizing the accurate determination of the ovary state. BRIEF DESCRIPTION OF DRAWINGS

[0045] Figure 1 An application environment diagram of the ovary state determination method in an embodiment;

[0046] Figure 2 A flowchart of the ovary state determination method in an embodiment;

[0047] Figure 3 A flowchart of the ovary state determination method in another embodiment;

[0048] Figure 4 A follicle structure diagram in an embodiment;

[0049] Figure 5 A diagram of the area of each tissue structure in a follicle in an embodiment;

[0050] Figure 6 A structural block diagram of the ovary state determination device in an embodiment;

[0051] Figure 7 Fig. 1 is a schematic diagram of the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0052] For the purpose of making the purpose, technical solutions and advantages of the present application clearer, the present application is further described in detail below in combination with the drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and do not limit the present application.

[0053] The ovary state determination method provided by the embodiments of the present application can be applied to an application environment as shown in Figure 1 . The terminal 102 communicates with the server 104 through a network. The data storage system can store data required to be processed by the server 104. The data storage system can be integrated on the server 104, or placed on a cloud or other network server. The server 104 first obtains a target slice image of an ovary staining slice, and observes the target slice image. In the obtained target slice image, at least one follicle that can be analyzed for follicle state exists. The server 104 finds, according to the observation of the target slice image, that the follicle is surrounded by a theca layer, and the follicle includes a follicle cavity and a wall layer granulosa cell layer surrounding the follicle cavity. The server 104 identifies, from the obtained target slice image, a first target region where the target follicle is located, and a second target region where the theca layer surrounding the target follicle is located. The server 104 identifies, from the first target region where the target follicle is located, a third target region where the wall layer granulosa cell layer of the target follicle is located. The server 104 determines the state of the target follicle according to the area size ratio of the second target region and the third target region of the target follicle, and determines the state of the ovary according to the state determination result of the target follicle, to finally obtain a determination result of the state of the ovary. The terminal 102 can be, but is not limited to, various personal computers, notebook computers, smart phones, tablet computers, Internet of Things devices and portable wearable devices. The Internet of Things device can be a smart speaker, a smart television, a smart air conditioner, a smart vehicle device, etc. The portable wearable device can be a smart watch, a smart bracelet, a head-mounted device, etc. The server 104 can be implemented by an independent server or a server cluster composed of multiple servers.

[0054] In one embodiment, as shown in Figure 2 , an ovary state determination method is provided. Taking the server 104 in Figure 1 as an example, the method includes:

[0055] Step 202, obtaining a target slice image of the ovary staining slice, and at least one target follicle meeting the follicle state analysis condition exists in the target slice image. The target follicle is surrounded by the follicle membrane layer, and the target follicle includes the follicle cavity and the wall granulosa cell layer surrounding the follicle cavity.

[0056] The target slice image of the ovary staining slice is an image obtained after a part of the slice selected from all the ovary slices is subjected to staining treatment and imaging. The target follicle meeting the follicle state analysis condition is the follicle with the largest cross-sectional area obtained by observing the target slice image. For example, in the target slice image, follicles A and B are the follicles with the largest area in the image, and follicles A and B are the target follicles meeting the follicle state analysis condition.

[0057] The follicle membrane layer is a layer of tissue structure surrounding the follicle, which is formed by the spindle-shaped cells of the connective tissue around the follicle. The follicle cavity is a half-moon-shaped cavity formed by the combination of some irregular intercellular spaces in the process of continuous development of the follicle cells, and the follicle cells increase to 6 to 12 layers. The follicle cavity is surrounded by the wall granulosa cell layer, which is differentiated from the follicle cells distributed around the follicle cavity. Specifically, the server obtains a target slice image of the ovary slice after staining treatment and imaging, and at least one target follicle meeting the follicle state analysis condition exists in the target slice image. Each follicle is composed of a follicle cavity and a wall granulosa cell layer surrounding the follicle cavity, and each follicle is surrounded by a follicle membrane layer.

[0058] Step 204, identifying the first target area where the target follicle is located and the second target area where the follicle membrane layer is located from the target slice image.

[0059] The first target area is where the target follicle exists, including the follicle cavity and the wall granulosa cell layer. The second target area represents where the follicle membrane layer exists. After the first target area where the target follicle is located and the second target area where the follicle membrane layer is located are framed, area calculation software can be used to calculate the areas of the first target area and the second target area.

[0060] Step 206, identifying the third target area where the wall granulosa cell layer is located from the first target area.

[0061] The third target area represents where the wall granulosa cell layer and the oocyte and cumulus cells closely connected to the wall granulosa cell layer are located. After the third target area where the wall granulosa cell layer is located is framed, area calculation software can be used to calculate the area of the third target area.

[0062] At step 208, the state of the target follicle is determined based on the area size ratio of the second target region to the third target region, and a target follicle state determination result is obtained.

[0063] The follicle state determination result refers to the health state of the target follicle, and the health state of the ovary where the target follicle is located can be determined according to the health state of the target follicle. For example, when the state determination result of the target follicle shows that it is unhealthy, it indicates that the ovary where the target follicle is located may have a lesion, and further detection and analysis of the ovary are required. When the state determination result of the target follicle shows that it is healthy, it indicates that the ovary where the target follicle is located is in a healthy state, and further detection and analysis of the ovary is not required.

[0064] At step 210, the state of the ovary is determined according to the target follicle state determination result, and an ovary state determination result is obtained.

[0065] The ovary state determination result is determined by analyzing the state determination result of the follicle after determining the state of the follicle in the ovary, so as to accurately determine the state of the ovary. In actual application, relevant personnel can analyze the ovary state determination result obtained by means of a computer device, and further analyze and determine whether the ovary has a lesion.

[0066] Specifically, the server determines the health state of the target follicle according to the area size ratio of the second target region where the follicle membrane layer is located to the third target region where the theca granulosa cell layer is located, and then determines the health state of the ovary where the target follicle is located according to the health state of the target follicle, to obtain the ovary state determination result.

[0067] In the above ovary state determination method, the staining section image of the ovary is obtained, which can facilitate the observation of the follicle in the ovary section, so as to accurately find the target follicle meeting the follicle state analysis condition. The first target region where the target follicle meeting the follicle state analysis condition is located and the second target region where the follicle membrane layer is located are identified, which can facilitate the calculation of the area of the target follicle and the follicle membrane layer surrounding the target follicle. The third target region where the theca granulosa cell layer is located is identified from the first target region, which can reduce the measurement error caused by the small size of the target follicle, so as to accurately identify the third target region. The health state of the target follicle is determined by calculating the ratio of the second target region to the third target region, so as to accurately determine the state of the ovary.

[0068] In one embodiment, as shown in FIG. 2, the method further includes the following steps before obtaining the target section image of the ovary staining section: Figure 3

[0069] At step 302, a plurality of continuous ovary sections are obtained, and the section thickness of each continuous ovary section is equal.​

[0070] The slice is a thin slice of tissue for observation by optical microscopy or electron microscopy, and belongs to one of the glass slide specimens. According to the actual situation, the slice can be manually sliced by using a blade, or the slice can be sliced by using a slicer. The continuous ovary slice indicates that all the slices are arranged in a continuous slice according to the order of slicing. The slice thickness indicates the thickness of the slice, and the thickness of the slice can be 5 μm.

[0071] In step 304, a plurality of target slices with equal interval sampling are selected from the continuous ovary slices.

[0072] In the equal interval sampling, each unit in the population is arranged and numbered in a certain order, and then an interval is set, and the unit individuals to be investigated are selected based on the interval. For example, there are 50 units in the population, numbered 1, 2, …, 50, and the interval for selecting unit individuals is set to 10. The first randomly selected unit individual is numbered 10, and the subsequent selected unit individuals are numbered 20, 30, 40, and 50. The units numbered 10, 20, 30, 40, and 50 are the unit individuals to be investigated.

[0073] In step 306, each target slice is subjected to dyeing treatment to obtain a plurality of dyed ovary slices.

[0074] In the dyeing treatment, a small amount of dyeing substance is added to the obtained target slice to color part of the substance on the slice, so as to facilitate observation. For example, the hematoxylin-eosin staining method can make the chromatin in the cell nucleus and the nucleic acid in the cytoplasm present purple blue color, and the components in the cytoplasm and extracellular matrix present red color, thereby facilitating the observation of cells.

[0075] The target slice image of the ovary dyeing slice is obtained, including:

[0076] In step 308, each ovary dyeing slice is subjected to imaging processing to obtain a plurality of target slice images corresponding to each ovary dyeing slice.

[0077] In the imaging processing, the target slice is placed under a microscope or other device with magnification function, and the follicle in the target slice is subjected to image magnification processing by the lenses of the device.

[0078] In this embodiment, the server can make the observer better recognize the morphology of each tissue structure in the cell by dyeing the obtained target slice.

[0079] In one embodiment, after identifying the first target region where the target follicle is located and the second target region where the follicle membrane layer is located from the target slice image, the method further includes:

[0080] calculating a first area corresponding to the first target region where the target follicle is located.

[0081] calculating a difference between the first area and a total area of the target follicle and a follicle membrane layer surrounding the target follicle, to obtain a second area corresponding to the follicle membrane layer.

[0082] determining an area size ratio according to the second area and an area corresponding to the third target region.

[0083] The first area is an area of the target follicle, which is obtained by using an image processing software such as CaseViewer to frame along a side where the granulosa cell layer of the theca layer contacts the follicle membrane layer, and then automatically calculating the framed part by the software. The follicle membrane layer is close to the theca layer, and there is a basement membrane between the follicle membrane layer and the theca layer. Because of the existence of the basement membrane, the boundary between the follicle membrane layer and the theca layer is very clear.

[0084] The total area represents a sum of the area of the follicle membrane layer and the area of the target follicle, which is obtained by using an image processing software such as CaseViewer to frame along a non-contact side of the follicle membrane layer and the target follicle, and then automatically calculating the framed part by the software.

[0085] Specifically, the server identifies the first area corresponding to the target follicle, the total area of the target follicle and the follicle membrane layer surrounding the target follicle, and then obtains the area of the follicle membrane layer by calculating the difference between the total area and the first area. Finally, the area of the follicle membrane layer and the area corresponding to the third target region where the theca layer is located are calculated by ratio, so that the area size ratio of the follicle membrane layer and the theca layer can be determined.

[0086] In a specific application, the server identifies that the first area corresponding to the target follicle is 60751 μm 2 , the total area of the target follicle and the follicle membrane layer surrounding the target follicle is 71162 μm 2 , and then the area of the follicle membrane layer is 10411 μm 2 obtained by calculating the difference between the total area and the first area. Finally, the area of the follicle membrane layer and the area corresponding to the third target region where the theca layer is located are calculated by ratio, so that the area size ratio of the follicle membrane layer and the theca layer can be determined.

[0087] In this embodiment, the area of the follicle membrane layer is obtained by calculating the difference between the first area and the total area, which can reduce the measurement error caused by the uneven thickness of the follicle membrane layer, so that a more accurate area of the follicle membrane layer can be obtained.

[0088] In one of the embodiments, the third target region where the theca-granulosa cell layer is located is identified from the first target region, comprising:

[0089] The position where the follicle lumen and the theca-granulosa cell layer meet is obtained from the first target region where the target follicle is located.

[0090] The third target region where the theca-granulosa cell layer is located in the first target region is determined according to the position where the follicle lumen and the theca-granulosa cell layer meet.

[0091] After the third target region where the theca-granulosa cell layer is located is identified from the first target region, the method further comprises:

[0092] The area of the follicle lumen is calculated.

[0093] The difference between the area corresponding to the first target region and the area of the follicle lumen is calculated to obtain a third area corresponding to the third target region.

[0094] The area size ratio is determined according to the third area and the area corresponding to the second target region.

[0095] The position where the follicle lumen and the theca-granulosa cell layer meet refers to the position where the follicle lumen and the theca-granulosa cell layer meet. The area of the follicle lumen is obtained by using CaseViewer or other image processing software to frame the side where the theca-granulosa cell layer and the follicle lumen meet, and then using the software to automatically calculate the framed part.

[0096] The third area is the area of the theca-granulosa cell layer, which is obtained by using CaseViewer or other image processing software to frame the side where the theca-granulosa cell layer and the follicle membrane meet, and then using the software to automatically calculate the framed part of the target follicle. Then, the area of the target follicle is calculated, and the difference between the area of the target follicle and the area of the follicle lumen is calculated to obtain the area of the theca-granulosa cell layer.

[0097] Specifically, the server first determines the position of the follicle, and then obtains the position where the follicle lumen and the theca-granulosa cell layer surrounding the follicle lumen meet. According to the position where they meet, the region where the theca-granulosa cell layer surrounding the follicle lumen is located in the follicle can be determined. After the region where the theca-granulosa cell layer is located is determined, the area of the follicle lumen is obtained by using CaseViewer or other image processing software to frame the side where the theca-granulosa cell layer and the follicle lumen meet, and then using the software to automatically calculate the framed part. Then, the area of the target follicle is calculated by using CaseViewer or other image processing software to frame the side where the theca-granulosa cell layer and the follicle membrane meet, and then using the software to automatically calculate the framed part. Then, the difference between the area of the target follicle and the area of the follicle lumen is calculated to obtain the area of the region where the theca-granulosa cell layer is located. Finally, the area ratio of the follicle membrane and the theca-granulosa cell layer is determined according to the calculated area value.

[0098] In this embodiment, the area of the granulosa cell layer is obtained by calculating the difference between the area corresponding to the first target region and the follicle cavity area, which can reduce the measurement error caused by the small area of the granulosa cell layer, thereby obtaining a more accurate area of the granulosa cell layer.

[0099] In one of the embodiments, there are at least two target follicles in the target slice image that meet the follicle state analysis condition.

[0100] Based on the area size ratio of the second target region and the third target region, the state of the target follicle is determined to obtain a target follicle state determination result, including:

[0101] The average value of the area size ratio of the second area corresponding to the second target region and the third area corresponding to the third target region of each target follicle is calculated, and the maximum area in the first area is obtained.

[0102] In addition to directly obtaining the maximum area according to the value of the first area, the average value of the first areas of multiple target follicles can also be calculated to obtain the maximum area, and the method of obtaining the maximum area can be applied to each stage of follicular development. For example, when three target follicles are detected with very close and large areas, the average value of the first areas of the three target follicles is calculated to obtain the maximum area in the first area.

[0103] According to the average value and the maximum area, the state of the target follicle is determined to obtain a target follicle state determination result.

[0104] Specifically, the server obtains at least two follicles with the largest cross section from the target slice image, calculates the area size ratio of the theca layer and the granulosa cell layer in each follicle, calculates the average value of each area size ratio, and obtains the area value of the follicle with the largest cross section. The server determines the state of the follicle according to the calculated average value of each area size ratio and the area value of the follicle with the largest cross section.

[0105] In one of the embodiments, according to the average value and the maximum area, the state of the target follicle is determined to obtain a target follicle state determination result, including:

[0106] When the maximum area and the average value exceed the critical value of the ovarian histopathological evaluation, it is determined that the target follicle has a lesion. When the maximum area and the average value do not exceed the critical value of the ovarian histopathological evaluation, it is determined that the target follicle has no lesion.

[0107] The maximum area and the average value can also be used as a comparison control for the follicle size. For example, a group of normal follicles is selected, the maximum area and the average value of the area size ratio of the follicle membrane layer to the granulosa cell layer of the wall layer are measured, another group of follicles that have been treated is selected, the maximum area and the average value of the area size ratio of the follicle membrane layer to the granulosa cell layer of the wall layer are measured, and the maximum area and the average value of each group of follicles are compared to analyze the effect of the treatment on the follicles.

[0108] Specifically, the server uses the maximum area of the follicle and the average value of the area size ratio of the follicle membrane layer to the granulosa cell layer of the wall layer to make a pathological evaluation of the ovary tissue where the follicle is located, to determine whether the state of the follicle is normal.

[0109] In this embodiment, the state of the follicle can be determined by the average value of the area size ratio of the follicle membrane layer to the granulosa cell layer of the wall layer and the maximum area of the follicle, so that the state of the ovary where the follicle is located can be accurately determined.

[0110] The application also provides an application scenario that applies the ovary state determination method described above. Specifically, the ovary state determination method is applied in the following way in the application scenario: when performing pathological structure evaluation of ovary tissue, the server uses continuous sections of the ovary tissue for observation, and the follicle cavity structure is as shown in FIG. 1. Figure 4 The thickness of each section obtained by sectioning is 5 μm. Using the equidistant sampling method, every 10 tissue sections are taken, 1 section is taken as a target section, and all the target sections taken are dyed and analyzed using hematoxylin-eosin.

[0111] The server selects two target follicles with the largest follicle sections for analysis according to the size of the follicles in the continuous sections from the hematoxylin-eosin-stained continuous tissue sections, and uses image processing software such as CaseViewer to frame the area where the follicle cavity is located along the inner layer of theca granulosa cells, and uses the automatic area calculation tool of the software to obtain the area of the follicle cavity. The server frames the area where the follicle cavity and the theca granulosa cell layer are located along the junction of the theca granulosa cell layer and the follicle membrane layer, and uses the automatic area calculation tool of the software to obtain the area of the target follicle. The server frames the area where the target follicle and the follicle membrane layer surrounding the target follicle are located along the outside of the follicle membrane layer, and uses the automatic area calculation tool of the software to obtain the total area of the target follicle and the follicle membrane layer surrounding the target follicle. After obtaining the area of the target follicle, the area of the follicle cavity, and the total area of the target follicle and the follicle membrane layer surrounding the target follicle, the server obtains the area of the theca granulosa cell layer of the target follicle by calculating the difference between the area of the target follicle and the area of the follicle cavity, and obtains the area of the follicle membrane layer by calculating the difference between the total area of the target follicle and the follicle membrane layer surrounding the target follicle and the area of the target follicle. The areas of various tissue structures are as shown in Table 1. Figure 5 The server then calculates the area ratio of the follicle membrane layer and the theca granulosa layer of the two target follicles, respectively, and obtains the average of the two area ratios. Finally, the server realizes the determination of the ovarian histopathology through the largest follicle area of the two target follicles and the average of the area ratio of the follicle membrane layer and the theca granulosa cell layer.

[0112] It should be understood that although each step in the flowchart involved in each of the above-described embodiments is shown in sequence according to the direction of the arrow, these steps are not necessarily executed in sequence according to the direction of the arrow. Unless otherwise specified herein, the execution of these steps is not strictly limited in sequence, and these steps can be executed in other sequences. Moreover, at least part of the steps in the flowchart involved in each of the above-described embodiments can include multiple steps or stages, which are not necessarily executed at the same time, but can be executed at different times, and the execution sequence of these steps or stages is not necessarily sequential, but can be executed in rotation or alternation with at least part of other steps or stages in other steps.

[0113] Based on the same inventive concept, the embodiments of the present application also provide an ovarian state determination device for implementing the ovarian state determination method described above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme described in the above method, and therefore the specific limitations in one or more ovarian state determination device embodiments provided below can refer to the limitations of the ovarian state determination method described above, which will not be described here again.

[0114] In one embodiment, as shown in Figure 6 An ovarian state determination apparatus is provided, comprising:

[0115] A target slice image acquisition module 602 is configured to acquire a target slice image of an ovarian staining slice, wherein the target slice image contains at least one target follicle meeting a follicle state analysis condition. The target follicle is surrounded by a theca layer, and the target follicle includes a follicle cavity and a wall granulosa cell layer surrounding the follicle cavity.

[0116] A first region identification module 604 is configured to identify, from the target slice image, a first target region where the target follicle is located, and a second target region where the theca layer is located.

[0117] A second region identification module 606 is configured to identify, from the first target region, a third target region where the wall granulosa cell layer is located.

[0118] A follicle state determination module 608 is configured to determine a state of the target follicle based on an area size ratio of the second target region to the third target region, and obtain a target follicle state determination result.

[0119] An ovarian state determination module 610 is configured to determine a state of the ovary based on the target follicle state determination result, and obtain a determination result of the ovarian state.

[0120] In one embodiment, the target slice image acquisition module further comprises:

[0121] A slice acquisition unit is configured to acquire a plurality of continuous ovarian slices, and the slice thickness of each continuous ovarian slice is equal.

[0122] An equidistant sampling unit is configured to filter a plurality of target slices with equal interval slice numbers from the continuous ovarian slices by using an equidistant sampling manner.

[0123] A slice staining unit is configured to perform staining processing on each target slice respectively, and obtain a plurality of stained ovarian slices.

[0124] An imaging unit is configured to perform imaging processing on each ovarian staining slice respectively, and obtain a target slice image corresponding to each of the plurality of ovarian staining slices.

[0125] In one embodiment, the first region identification module further comprises:

[0126] A first area calculation unit is configured to calculate a first area corresponding to the first target region where the target follicle is located.

[0127] A second area calculation unit is configured to calculate a difference between the first area and a total area of the target follicle and the theca layer surrounding the target follicle, and obtain a second area corresponding to the theca layer.

[0128] The first ratio determining unit is configured to determine an area size ratio according to the second area and an area corresponding to the third target region.

[0129] In one of the embodiments, the first region identifying module further comprises:

[0130] The junction determining unit is configured to obtain a junction position of the follicle lumen and the theca granulosa cell layer from the first target region where the target follicle is located.

[0131] The third target region determining unit is configured to determine a third target region where the theca granulosa cell layer is located in the first target region according to the junction position.

[0132] The follicle lumen area calculating unit is configured to calculate an area of the follicle lumen.

[0133] The third area calculating unit is configured to calculate a difference between the area corresponding to the first target region and the area of the follicle lumen to obtain a third area corresponding to the third target region.

[0134] The second ratio determining unit is configured to determine an area size ratio according to the third area and an area corresponding to the second target region.

[0135] In one of the embodiments, the follicle state determining module further comprises:

[0136] The average value determining unit is configured to calculate an average value of the area size ratio of the second area corresponding to the second target region and the third area corresponding to the third target region of each target follicle, and obtain a maximum area in the first area.

[0137] The determination result determining unit is configured to determine the state of the target follicle according to the average value and the maximum area to obtain a target follicle state determination result.

[0138] In one of the embodiments, the determination result determining unit further comprises:

[0139] The normal determination sub-unit is configured to determine that the target follicle has a lesion when the maximum area and the average value exceed a critical value of the ovarian tissue pathological evaluation.

[0140] The abnormal determination sub-unit is configured to determine that the target follicle has no lesion when the maximum area and the average value do not exceed the critical value of the ovarian tissue pathological evaluation.

[0141] The above-mentioned modules in the ovarian state determination device can be realized by software, hardware and combinations thereof in whole or in part. The above-mentioned modules can be embedded in or independent of the processor in the computer device in hardware form, or can be stored in the memory in the computer device in software form, so as to be called and executed by the processor to perform the operations corresponding to the above-mentioned modules.

[0142] In one embodiment, a computer device is provided, which can be a server, and an internal structure diagram of the computer device can be as shown in Figure 7 The computer device includes a processor, a memory, an input / output interface (I / O), and a communication interface. The processor, the memory, and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. The processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for running the operating system and the computer program in the non-volatile storage medium. The database of the computer device is configured to store respective target slice images of ovary staining slices, target follicles in the target slice images that meet follicle state analysis conditions, slice thickness, a first area corresponding to a first target region where the target follicle is located, a second area corresponding to a follicle membrane layer, a total area of the target follicle and the follicle membrane layer surrounding the target follicle, a difference between the first area and the total area of the target follicle and the follicle membrane layer surrounding the target follicle, an area size ratio, a third area corresponding to a third target region where a theca granulosa layer is located, an average value, an area of the largest follicle, and all determination result data. The input / output interface of the computer device is configured to exchange information between the processor and external devices. The communication interface of the computer device is configured to communicate with terminals outside through network connection. The computer program is executed by the processor to implement an ovary state determination method.

[0143] Those skilled in the art can understand that Figure 7 The structure shown in the above embodiment is only a block diagram of part of the structure related to the scheme of the present application, and does not constitute a limitation on the computer device to which the scheme of the present application is applied. The specific computer device can include more or fewer components than those shown in the diagram, or combine certain components, or have a different arrangement of components.

[0144] In one embodiment, a computer device is provided, which includes a memory and a processor, and the memory stores a computer program. The processor executes the computer program to implement the following steps:

[0145] An ovary staining section image is acquired, and at least one target follicle meeting a follicle state analysis condition exists in the target section image; the target follicle is surrounded by a follicle membrane layer, and the target follicle includes a follicle cavity and a wall granulosa cell layer surrounding the follicle cavity; a first target region where the target follicle is located and a second target region where the follicle membrane layer is located are identified from the target section image; a third target region where the wall granulosa cell layer is located is identified from the first target region; a target follicle state is determined based on an area size ratio of the second target region to the third target region, and a target follicle state determination result is obtained; and a state of the ovary is determined according to the target follicle state determination result, and a determination result of the ovary state is obtained.

[0146] In one embodiment, the processor, when executing the computer program, also implements the following steps:

[0147] A plurality of continuous ovary sections are acquired, and the section thickness of each continuous ovary section is equal; a plurality of target sections with equal interval sampling are screened from the continuous ovary sections; each target section is subjected to staining treatment to obtain a plurality of stained ovary sections; and each ovary staining section is subjected to imaging processing to obtain a target section image corresponding to each ovary staining section.

[0148] In one embodiment, the processor, when executing the computer program, also implements the following steps:

[0149] A first area corresponding to the first target region where the target follicle is located is calculated; a difference between the first area and a total area of the target follicle and the follicle membrane layer surrounding the target follicle is calculated to obtain a second area corresponding to the follicle membrane layer; and an area size ratio is determined according to the second area and an area corresponding to the third target region.

[0150] In one embodiment, the processor, when executing the computer program, also implements the following steps:

[0151] A connection position of the follicle cavity and the wall granulosa cell layer in the first target region where the target follicle is located is acquired; the third target region where the wall granulosa cell layer is located in the first target region is determined according to the connection position; an area of the follicle cavity is calculated; a difference between an area corresponding to the first target region and the area of the follicle cavity is calculated to obtain a third area corresponding to the third target region; and an area size ratio is determined according to the third area and an area corresponding to the second target region.

[0152] In one embodiment, the processor, when executing the computer program, also implements the following steps:

[0153] There are at least two target follicles meeting the follicle state analysis condition in the target slice image; an average value of area size ratios of the second area corresponding to each target follicle to the third area is calculated, and a maximum area in the first area is obtained; according to the average value and the maximum area, the target follicle is determined to obtain a target follicle state determination result.

[0154] In one embodiment, the processor further implements the following steps when executing the computer program:

[0155] When the maximum area and the average value exceed the critical value of the ovarian histopathological evaluation, it is determined that the target follicle has a lesion; when the maximum area and the average value do not exceed the critical value of the ovarian histopathological evaluation, it is determined that the target follicle has no lesion.

[0156] In one embodiment, a computer readable storage medium is provided, and the computer readable storage medium stores a computer program, and the computer program is executed by a processor to implement the following steps:

[0157] A target slice image of an ovarian staining slice is obtained, and there is at least one target follicle meeting the follicle state analysis condition in the target slice image; the target follicle is surrounded by a theca layer, and the target follicle includes a follicle cavity and a wall granulosa cell layer surrounding the follicle cavity; from the target slice image, a first target area where the target follicle is located and a second target area where the theca layer is located are identified; from the first target area, a third target area where the wall granulosa cell layer is located is identified; based on the area size ratio of the second target area to the third target area, the state of the target follicle is determined to obtain a target follicle state determination result; according to the target follicle state determination result, the state of the ovary is determined to obtain an ovary state determination result.

[0158] In one embodiment, the computer program is executed by the processor to further implement the following steps:

[0159] A plurality of continuous ovarian slices are obtained, and the slice thickness of each continuous ovarian slice is equal; a plurality of target slices are selected from the continuous ovarian slices by using equidistant sampling, and the number of slices between the target slices is equal; each target slice is subjected to staining treatment to obtain a plurality of stained ovarian slices; each ovarian staining slice is subjected to imaging processing to obtain a target slice image corresponding to each of the plurality of ovarian staining slices.

[0160] In one embodiment, the computer program is executed by the processor to further implement the following steps:

[0161] The first area corresponding to the first target region where the target follicle is located is calculated, and the second area corresponding to the follicle membrane layer is obtained by calculating the difference between the first area and the total area of the target follicle and the follicle membrane layer surrounding the target follicle. The area size ratio is determined according to the second area and the area corresponding to the third target region.

[0162] In one embodiment, the computer program, when executed by the processor, further implements the following steps:

[0163] The connection position of the follicle cavity and the theca granulosa cell layer in the first target region where the target follicle is located is obtained, the third target region where the theca granulosa cell layer is located in the first target region is determined according to the connection position, the area of the follicle cavity is calculated, the difference between the area corresponding to the first target region and the area of the follicle cavity is calculated to obtain the third area corresponding to the third target region, and the area size ratio is determined according to the third area and the area corresponding to the second target region.

[0164] In one embodiment, the computer program, when executed by the processor, further implements the following steps:

[0165] There are at least two target follicles in the target slice image that meet the follicle state analysis condition, the average value of the area size ratio of the second area corresponding to the second target region and the third area corresponding to the third target region of each target follicle is calculated, and the maximum area in the first area is obtained, the state of the target follicle is determined according to the average value and the maximum area, and the target follicle state determination result is obtained.

[0166] In one embodiment, the computer program, when executed by the processor, further implements the following steps:

[0167] When the maximum area and the average value exceed the critical value of the ovarian histopathological evaluation, it is determined that the target follicle has a lesion; when the maximum area and the average value do not exceed the critical value of the ovarian histopathological evaluation, it is determined that the target follicle has no lesion.

[0168] In one embodiment, a computer program product is provided, comprising a computer program which, when executed by the processor, implements the following steps:

[0169] An ovary staining section image is acquired, and at least one target follicle meeting a follicle state analysis condition exists in the target section image; the target follicle is surrounded by a follicle membrane layer, and the target follicle includes a follicle cavity and a wall granulosa cell layer surrounding the follicle cavity; a first target region where the target follicle is located and a second target region where the follicle membrane layer is located are identified from the target section image; a third target region where the wall granulosa cell layer is located is identified from the first target region; a target follicle state is determined based on an area size ratio of the second target region to the third target region, and a target follicle state determination result is obtained; and a state of the ovary is determined according to the target follicle state determination result, and a determination result of the ovary state is obtained.

[0170] In one embodiment, the computer program, when executed by the processor, further implements the following steps:

[0171] A plurality of continuous ovary sections are acquired, and the section thickness of each continuous ovary section is equal; a plurality of target sections with equal interval sampling are screened from the continuous ovary sections; each target section is subjected to staining treatment to obtain a plurality of stained ovary sections; and each ovary staining section is subjected to imaging processing to obtain a target section image corresponding to each ovary staining section.

[0172] In one embodiment, the computer program, when executed by the processor, further implements the following steps:

[0173] A first area corresponding to the first target region where the target follicle is located is calculated; a difference between the first area and a total area of the target follicle and the follicle membrane layer surrounding the target follicle is calculated to obtain a second area corresponding to the follicle membrane layer; and an area size ratio is determined according to the second area and an area corresponding to the third target region.

[0174] In one embodiment, the computer program, when executed by the processor, further implements the following steps:

[0175] A connection position of the follicle cavity and the wall granulosa cell layer is acquired from the first target region where the target follicle is located; a third target region where the wall granulosa cell layer is located in the first target region is determined according to the connection position; an area of the follicle cavity is calculated; a difference between an area corresponding to the first target region and the area of the follicle cavity is calculated to obtain a third area corresponding to the third target region; and an area size ratio is determined according to the third area and an area corresponding to the second target region.

[0176] In one embodiment, the computer program, when executed by the processor, further implements the following steps:

[0177] At least two target follicles meeting the follicle state analysis condition exist in the target slice image; an average value of area size ratios of a second area corresponding to each target follicle to a third area corresponding to a third target area is calculated, and a maximum area in the first area is obtained; according to the average value and the maximum area, the target follicle is determined to obtain a target follicle state determination result.

[0178] In one embodiment, the computer program, when executed by the processor, further implements the following steps:

[0179] When the maximum area and the average value exceed the critical value of the ovarian histopathological evaluation, it is determined that the target follicle has a lesion; when the maximum area and the average value do not exceed the critical value of the ovarian histopathological evaluation, it is determined that the target follicle has no lesion.

[0180] It should be noted that the user information (including but not limited to user equipment information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in the present application are all information and data authorized by the user or authorized by all parties, and the collection, use and processing of related data need to comply with relevant laws, regulations and standards of relevant countries and regions.

[0181] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer readable storage medium, and when the computer program is executed, the processes of the above-mentioned embodiments of the methods can be included. Any reference to memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (Read-Only Memory, ROM), magnetic tape, floppy disk, flash memory, optical storage, high-density embedded non-volatile memory, resistive memory (ReRAM), magnetoresistive random access memory (Magnetoresistive Random Access Memory, MRAM), ferroelectric memory (Ferroelectric Random Access Memory, FRAM), phase change memory (Phase Change Memory, PCM), graphene memory, etc. Volatile memory can include random access memory (Random Access Memory, RAM) or external cache memory, etc. As an illustration but not limitation, RAM can be in various forms, such as static random access memory (Static Random Access Memory, SRAM) or dynamic random access memory (Dynamic Random Access Memory, DRAM), etc. The database involved in the embodiments provided in the present application can include at least one of a relational database and a non-relational database. The non-relational database can include a distributed database based on a block chain, etc., without being limited thereto. The processor involved in the embodiments provided in the present application can be a general-purpose processor, a central processing unit, a graphics processing unit, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., without being limited thereto.

[0182] Any combination of the technical features of the above embodiments can be made. In order to make the description simple, all possible combinations of the technical features in the above embodiments are not described, however, as long as the combination of the technical features does not exist contradictory, it should be considered as the scope of the present application.

[0183] The above embodiments only express several implementation manners of the present application, and the description is more specific and detailed, but it should not be understood as a limitation on the scope of the patent of the present application. It should be pointed out that for ordinary skilled in the art, without departing from the concept of the present application, a number of modifications and improvements can be made, which are within the scope of protection of the present application. Therefore, the protection scope of the present application should be subject to the appended claims.

Claims

1. A method for determining ovarian status, characterized in that, The method comprises: obtaining a target slice image of an ovary stained slice, at least one target follicle in the target slice image meeting a follicle state analysis condition; the target follicle is surrounded by a follicle membrane layer, and the target follicle comprises a follicle cavity and a wall layer granulosa cell layer surrounding the follicle cavity; from the target slice image, a first target region where the target follicle is located and a second target region where the follicle membrane layer is located are identified; from the first target region, a third target region where the wall layer granulosa cell layer is located is identified; based on the area size ratio of the second target region to the third target region, the state of the target follicle is determined, and a target follicle state determination result is obtained; according to the target follicle state determination result, the state of the ovary is determined, and a determination result of the ovary state is obtained.

2. The method of claim 1, wherein, Before the target slice image of the ovary stained slice is obtained, the method further comprises: obtaining a plurality of continuous ovary slices, and the slice thickness of each continuous ovary slice is equal; using equidistant sampling, a plurality of target slices with equal interval slice numbers are selected from the continuous ovary slices; each target slice is subjected to staining treatment to obtain a plurality of stained ovary slices; the target slice image of the ovary stained slice is obtained by: each ovary stained slice is subjected to imaging processing to obtain a target slice image corresponding to each ovary stained slice.

3. The method of claim 1, wherein, After the first target region where the target follicle is located and the second target region where the follicle membrane layer is located are identified from the target slice image, the method further comprises: calculating a first area corresponding to the first target region where the target follicle is located; calculating a difference between the first area and a total area of the target follicle and the follicle membrane layer surrounding the target follicle to obtain a second area corresponding to the follicle membrane layer; determining the area size ratio according to the second area and an area corresponding to the third target region.

4. The method of claim 1, wherein, The third target region where the wall layer granulosa cell layer is located is identified from the first target region, comprising: obtaining a connection position of the follicle cavity and the wall layer granulosa cell layer from the first target region where the target follicle is located; determining the third target region where the wall layer granulosa cell layer is located in the first target region according to the connection position; After the third target region where the wall layer granulosa cell layer is located is identified from the first target region, the method further comprises: calculating an area of the follicle cavity; calculating a difference between an area corresponding to the first target region and the area of the follicle cavity to obtain a third area corresponding to the third target region; determining the area size ratio according to the third area and an area corresponding to the second target region.

5. The method of claim 3, wherein, There are at least two target follicles in the target slice image, which meet the follicle state analysis condition; the target follicle state determination result is obtained by determining the state of the target follicle based on the area size ratio of the second target region to the third target region, comprising: An average of area size ratios of a second area corresponding to a second target region of each of the target follicles to a third area corresponding to a third target region is calculated, and a maximum area in the first area is obtained; According to the average and the maximum area, a state of the target follicle is determined to obtain a target follicle state determination result.

6. The method of claim 5, wherein, The state of the target follicle is determined according to the average and the maximum area to obtain a target follicle state determination result, including: When the maximum area and the average exceed a critical value of ovarian histopathological evaluation, it is determined that the target follicle has a lesion; When the maximum area and the average do not exceed the critical value of ovarian histopathological evaluation, it is determined that the target follicle has no lesion.

7. An ovary state determination device characterized by comprising: The device includes: A target slice image acquisition module is configured to acquire a target slice image of an ovarian staining slice, wherein at least one target follicle meeting a follicle state analysis condition exists in the target slice image, the target follicle is surrounded by a follicle membrane layer, and the target follicle includes a follicle cavity and a wall layer granulosa cell layer surrounding the follicle cavity; A first region identification module is configured to identify, from the target slice image, a first target region where the target follicle is located and a second target region where the follicle membrane layer is located; A second region identification module is configured to identify, from the first target region, a third target region where the wall layer granulosa cell layer is located; A follicle state determination module is configured to determine a state of the target follicle based on an area size ratio of the second target region to the third target region to obtain a target follicle state determination result; An ovarian state determination module is configured to determine a state of an ovary based on the target follicle state determination result to obtain an ovarian state determination result.

8. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that, The processor executes the computer program to implement the steps of the method of any one of claims 1 to 6.

9. A computer readable storage medium having stored thereon a computer program, characterized in that, The computer program is executed by the processor to implement the steps of the method of any one of claims 1 to 6.

10. A computer program product comprising a computer program, characterized in that, The computer program is executed by the processor to implement the steps of the method of any one of claims 1 to 6.

Images