A method, device and computer equipment for detecting microecology of vaginal samples

Abstract

The embodiments of the present application relate to a method, device and computer equipment for microecological detection of vaginal samples, the computer equipment including a processor, and the method executed by the processor, including: obtaining a sample image corresponding to the target vaginal sample; identifying one or more microbial groups contained in the sample image, and determining the image area corresponding to each microbial group; performing feature extraction on the image area corresponding to each microbial group, obtaining the group characteristics corresponding to each microbial group, and determining the number of microorganisms contained in each microbial group; determining the type of microorganism corresponding to each microbial group according to the group characteristics corresponding to each microbial group; determining the microecological situation corresponding to the target vaginal sample according to the type and number of microorganisms corresponding to each microbial group. The above-mentioned method, device and computer equipment for microecological detection of vaginal samples can improve the detection accuracy of the microecological situation corresponding to the vaginal sample.

Description

Technical Field

[0001] The present application relates to the field of image processing technology, and in particular to a method, device and computer equipment for detecting microecology of vaginal samples. Background Art

[0002] With the in-depth development of medical testing technology and users' high demands for their own health, based on the influence of microorganisms in the microecology, doctors can analyze the microecology corresponding to vaginal samples to learn about the vaginal health of users. Doctors can observe the microorganisms in vaginal samples through a microscope and analyze vaginal samples based on historical experience to determine the microecology corresponding to vaginal samples. Since most of the current analysis equipment still requires doctors to operate manually, there is a problem of inaccurate detection of microecology. Summary of the invention

[0003] The embodiments of the present application disclose a method, device and computer equipment for detecting microecology of vaginal samples, which can improve the detection accuracy of the microecology corresponding to the vaginal samples.

[0004] In a first aspect, an embodiment of the present application discloses a vaginal sample microecological detection method, which is applied to a computer device, wherein the computer device includes a processor, and the processor performs the following steps:

[0005] Acquire a sample image corresponding to a target vaginal sample;

[0006] Identify one or more microbial groups contained in the sample image, and determine the image area corresponding to each of the microbial groups;

[0007] Extracting features from the image regions corresponding to the respective microbial populations to obtain population features corresponding to the respective microbial populations, and determining the number of microorganisms contained in the respective microbial populations;

[0008] Determining the microorganism type corresponding to each of the microorganism groups according to the group characteristics corresponding to each of the microorganism groups;

[0009] According to the microbial types and microbial quantities corresponding to each of the microbial groups, the microecological conditions corresponding to the target vaginal sample are determined.

[0010] As an optional implementation, in the first aspect of the embodiment of the present application, before identifying one or more microbial populations contained in the sample image, the method also includes: extracting features of each microorganism contained in the sample image to obtain image features corresponding to each microorganism; matching the first image features corresponding to the first microorganism with the biological features corresponding to the target microorganism type contained in the standard library; the first microorganism is any microorganism in the sample image; if there is a biological feature corresponding to any target microorganism type in the standard library that successfully matches the first image feature, then the first microorganism is removed from the sample image; identifying one or more microbial populations contained in the sample image and determining the image area corresponding to each microbial population includes: identifying one or more microbial populations contained in a new sample image and determining the image area corresponding to each microbial population; the new sample image is the sample image obtained after removing the microorganisms that successfully match the biological features corresponding to the target microorganism type.

[0011] As an optional implementation, in the first aspect of the embodiments of the present application, before determining the microecological situation corresponding to the target vaginal sample according to the microbial types and microbial quantities corresponding to each of the microbial populations, the method also includes: determining the ratio of the number of microorganisms corresponding to each microbial type to the total amount of microorganisms in the sample image according to the microbial types and microbial quantities corresponding to each of the microbial populations; determining the microecological situation corresponding to the target vaginal sample according to the microbial types and microbial quantities corresponding to each of the microbial populations includes: if the ratios corresponding to the various microbial types are all within the preset proportion range corresponding to the various microbial types, then determining the microecological situation corresponding to the target vaginal sample according to the ratios corresponding to the various microbial types.

[0012] As an optional implementation, in the first aspect of the embodiments of the present application, the method further includes: if there is a ratio corresponding to a first microorganism type that exceeds a preset ratio range corresponding to the first microorganism type, outputting a manual prompt; the manual prompt is used to prompt the manual determination of the microecological situation corresponding to the target vaginal sample; the first microorganism type is any microorganism type in the sample image.

[0013] As an optional implementation, in the first aspect of the embodiment of the present application, determining the microecological conditions corresponding to the target vaginal sample according to the microbial types and microbial quantities corresponding to each of the microbial populations includes:

[0014] Obtain a first size of the oil objective lens and a second size of the sample image, and use the ratio of the first size to the second size as a unit oil objective lens ratio; multiply the number of microbial types contained in the sample image to obtain the type richness corresponding to the target vaginal sample under the unit oil objective lens; multiply the unit oil objective lens ratio by the sum of the number of microorganisms corresponding to each of the microbial groups to obtain the microbial density corresponding to the target vaginal sample under the unit oil objective lens; if it is detected that the microbial density is within a preset density range, and the type richness is within a preset richness range, determine the microecological balance corresponding to the target vaginal sample; if it is detected that the microbial density is not within the preset density range, and / or the type richness is not within the preset richness range, determine the microecological imbalance corresponding to the target vaginal sample.

[0015] As an optional implementation, in the first aspect of the embodiments of the present application, determining the microbial type corresponding to each of the microbial populations based on the population characteristics corresponding to each of the microbial populations includes: matching the first population characteristics corresponding to the first microbial population with the biological characteristics corresponding to each of the microbial types contained in the standard library; the first microbial population is any of the microbial populations; if the first population characteristics successfully match the biological characteristics in the standard library, then the microbial type corresponding to the biological characteristics matching the first population characteristics is used as the microbial type corresponding to the first microbial population.

[0016] As an optional implementation, in the first aspect of the embodiment of the present application, after matching the first population characteristics corresponding to the first microbial population with the biological characteristics corresponding to each microbial type contained in the standard library, the method also includes: if there is a second microbial population in the one or more microbial populations whose population characteristics fail to match the biological characteristics corresponding to each microbial type contained in the standard library, then the microbial type corresponding to the second microbial population is determined to be a special microorganism; determining the microecological situation corresponding to the target vaginal sample based on the microbial type and the number of microorganisms corresponding to each of the microbial populations includes: if a second microbial population containing microbial types of special microorganisms is detected in the one or more microbial populations, and the number of microorganisms contained in the second microbial population is greater than a preset number threshold, then determining that the microecological imbalance corresponding to the target vaginal sample is.

[0017] In a second aspect, the present application discloses a vaginal sample microecological detection device, which is applied to a computer device, and the device includes:

[0018] An image acquisition module, used to acquire a sample image corresponding to a target vaginal sample;

[0019] A microorganism identification module, used to identify one or more microorganism groups contained in the sample image and determine the image area corresponding to each of the microorganism groups;

[0020] A feature extraction module is used to extract features from the image area corresponding to each of the microbial groups, obtain the group features corresponding to each of the microbial groups, and determine the number of microorganisms contained in each of the microbial groups;

[0021] A type determination module, used to determine the microorganism type corresponding to each microorganism group according to the group characteristics corresponding to each microorganism group;

[0022] The microecological determination module is used to determine the microecological conditions corresponding to the target vaginal sample according to the microbial types and microbial quantities corresponding to each of the microbial groups.

[0023] In a third aspect, an embodiment of the present application discloses a computer device, including a memory and a processor, wherein a computer program is stored in the memory, and when the computer program is executed by the processor, the processor implements the method described in any of the above embodiments.

[0024] In a fourth aspect, an embodiment of the present application discloses a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method described in any of the above embodiments is implemented.

[0025] The present application discloses a method, device and computer equipment for detecting the microecology of vaginal samples, obtains a sample image corresponding to the target vaginal sample; identifies one or more microbial groups contained in the sample image, and determines the image area corresponding to each microbial group; extracts features from the image area corresponding to each microbial group, obtains the group features corresponding to each microbial group, and determines the number of microorganisms contained in each microbial group; determines the type of microorganism corresponding to each microbial group according to the group features corresponding to each microbial group; determines the microecological situation corresponding to the target vaginal sample according to the type and number of microorganisms corresponding to each microbial group. In the embodiment of the present application, the processor of the computer equipment automatically identifies one or more microbial groups in the sample image, and uses the feature extraction technology to extract features from the image area corresponding to each microbial group. Based on the feature extraction of the image area corresponding to each microbial group, the microbial group in the vaginal sample can be accurately identified, and the microbial type and number of microorganisms of the microbial group can be quickly determined, so as to accurately determine the microecological situation corresponding to the target vaginal sample. Compared with traditional manual microscopy, it can improve the efficiency of detection, reduce human errors, and improve the detection accuracy of the microecological situation corresponding to the vaginal sample. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0027] Figure 1 This is a diagram of an application scenario of a microecological detection method for vaginal samples in one embodiment;

[0028] Figure 2 is a schematic diagram of a sample image corresponding to a target vaginal sample in an embodiment;

[0029] Figure 3 is a schematic diagram of a sample image corresponding to a target vaginal sample in another embodiment;

[0030] Figure 4 A flowchart of a method for detecting microecology of vaginal samples in one embodiment;

[0031] Figure 5 A flowchart of a method for detecting microecology of vaginal samples in one embodiment;

[0032] Figure 6 This is a flow chart of determining the microecological conditions corresponding to the target vaginal sample according to the microbial types and microbial quantities corresponding to each microbial population in one embodiment;

[0033] Figure 7 A flowchart of a method for detecting microecology of vaginal samples in one embodiment;

[0034] Figure 8 is a block diagram of a vaginal sample microecological detection device in one embodiment;

[0035] Fig. 9 FIG. 4 is a structural block diagram of a computer device in one embodiment. DETAILED DESCRIPTION

[0036] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0037] It should be noted that the terms "including" and "having" and any variations thereof in the embodiments of the present application and the accompanying drawings are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device including a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to these processes, methods, products or devices.

[0038] It is understood that the terms "first", "second", etc. used in this application may be used herein to describe various elements, but these elements are not limited by these terms. These terms are only used to distinguish a first element from another element. For example, without departing from the scope of this application, a first size may be referred to as a second size, and similarly, a second size may be referred to as a first size. Both the first size and the second size contain at least one sub-energy, but they are not the same sub-energy.

[0039] In the related art, vaginal sample testing is mainly used to detect whether the user's vaginal microecology is balanced, so as to determine whether the user has vaginal health problems. Since the vaginal sample is small, the testing doctor needs to observe it through an oil immersion lens, a microscope, etc. In the process of analyzing the vaginal sample, the testing doctor needs to move and search to determine the microorganisms in the entire vaginal sample. Repeating the same operation for a long time is prone to manual fatigue. Therefore, manual analysis and testing of vaginal samples cannot guarantee the accuracy of the detection of the microecological conditions corresponding to the vaginal samples. It is easy to cause errors in microbial judgment or failure to observe all microorganisms due to various subjective or objective factors, resulting in errors in the obtained microecological conditions, which can not only fail to guarantee the accuracy of the detection of the microecological conditions, but also reduce the efficiency of the entire vaginal sample detection.

[0040] The embodiments of the present application disclose a method, device and computer equipment for detecting microecological conditions of vaginal samples, which can improve the detection accuracy of the microecological conditions corresponding to the vaginal samples and improve the detection efficiency.

[0041] Figure 1 FIG. 1 is an application scenario diagram of a microecological detection method for vaginal samples in an embodiment. Figure 1 As shown, the microecological detection method of vaginal samples can be applied to a computer device 110. The computer device 110 includes a processor. The computer device 110 may include but is not limited to various personal computers, smart wearable devices, tablet computers, PCs (Personal Computers), laptop computers, smart phones, and portable wearable devices, etc., which are not limited in the embodiments of the present application.

[0042] The user can choose to perform vaginal sample testing and analysis according to personal needs or doctor's instructions. The user can go to the sample collection agency, and the sampling personnel in the sample collection agency will collect the user's vaginal sample 120, and then transport the collected vaginal sample 120 to the laboratory for staining. The laboratory testing personnel can use the staining instrument 130 to stain each target vaginal sample 120 delivered by the sample collection agency, and collect images of the stained target vaginal samples 120 to obtain sample images corresponding to each stained target vaginal sample 120 (such as Figure 2 , Figure 3 as shown).

[0043] Optionally, different target vaginal samples 120 may use the same or different staining methods according to the actual test items or the operation of the test doctor. The staining reagents used in the staining of different staining test sub-items are not necessarily the same. Specific staining methods include but are not limited to Gram staining, simple staining, negative staining, Gram staining, spore staining, flagella staining, capsule staining, live-dead staining, etc.

[0044] In some embodiments, the computer device 110 can establish a communication connection with the dyeing instrument 130 of the laboratory, so that after the dyeing instrument 130 completes the dyeing process on the target vaginal sample 120, the camera on the dyeing instrument 130 collects the sample image corresponding to the dyed target vaginal sample 120 and sends the sample image to the computer device 110; the computer device 110 can receive the sample image corresponding to the target vaginal sample 120 sent by the dyeing instrument 130. Optionally, the available connection methods include but are not limited to data line connection, Bluetooth connection, NFC (Near Field Communication) connection and other wired or wireless connection methods.

[0045] In some embodiments, the computer device 110 may further include a photographing device for collecting sample images of the vaginal sample. Specifically, the laboratory staff may directly place the dyed target vaginal sample 120 within the photographing range of the photographing device of the computer device 110, and the computer device 110 directly controls the photographing device to collect images of the dyed target vaginal sample 120, thereby obtaining a sample image corresponding to the target vaginal sample 120.

[0046] The computer device 110 obtains a sample image corresponding to the target vaginal sample 120; identifies one or more microbial populations contained in the sample image, and determines the image area corresponding to each microbial population; the computer device 110 extracts features from the image area corresponding to each microbial population, obtains population features corresponding to each microbial population, and determines the number of microorganisms contained in each microbial population; determines the type of microorganism corresponding to each microbial population based on the population features corresponding to each microbial population; the computer device 110 determines the microecological situation corresponding to the target vaginal sample 120 based on the type and number of microorganisms corresponding to each microbial population.

[0047] like Figure 4 As shown, in some embodiments, a vaginal sample microecological detection method is provided, which can be applied to the above-mentioned computer device. The method may include the following steps 410 to 450.

[0048] Step 410, obtaining a sample image corresponding to the target vaginal sample.

[0049] The sample image may include various microorganisms in the target vaginal sample, including but not limited to squamous epithelial cells, columnar epithelial cells, leukocytes, pus cells, erythrocytes, clue cells, Trichomonas, spores, hyphae, Lactobacillus, Gardnerella, Mobiluncus, Gram-positive globules, Gram-negative rods, Trichomonas, spores, hyphae, Gram-negative diplococci, mycoplasma bodies and chlamydia bodies, and other common microorganisms and vaginal-specific microorganisms.

[0050] In some embodiments, after acquiring a sample image corresponding to a target vaginal sample, the computer device may preprocess the target image, including but not limited to denoising, image enhancement, normalization, resizing, histogram equalization, contrast enhancement, color mapping, etc.

[0051] In the field of microbiology, different microorganisms may present different colors after staining. For example, Gram staining can classify bacteria into Gram-positive bacteria (usually stained purple) and Gram-negative bacteria (usually stained red). Therefore, the computer device can perform color enhancement on the sample image so that the computer device can recognize the color difference after staining of different microorganisms through color enhancement, thereby helping to identify different types of microorganisms.

[0052] Step 420 , identifying one or more microbial groups contained in the sample image, and determining the image region corresponding to each microbial group.

[0053] A microbial population refers to a population containing multiple microorganisms. An image region corresponding to a microbial population refers to an image region of the microbial population in a sample image. Image information of an image region corresponding to each microbial population can be obtained. The image information may include image coordinates of the image region (such as the upper left corner and lower right corner coordinates of a bounding box) and image area (or number of pixels).

[0054] In some embodiments, the computer device may first identify each microorganism contained in the sample image, determine the image features of each microorganism, and then divide the sample image according to the image features of each microorganism to obtain one or more microorganism groups contained in the sample image.

[0055] In some embodiments, the computer device may identify each microorganism contained in the sample image through a target detection algorithm, thereby obtaining one or more microorganism groups contained in the sample image. The target detection algorithm may include but is not limited to convolutional neural networks (CNN), support vector machines (SVM), random forests, etc.

[0056] Exemplarily, taking the Faster R-CNN model as an example, the computer device inputs the sample image into the Faster R-CNN model, and extracts the image features of each microorganism in the image through the convolutional layer, pooling layer and fully connected layer in the Faster R-CNN model. Then, in the Region Proposal Network (RPN) of the Faster R-CNN model, a series of candidate regions are generated on the sample image according to the image features of each microorganism, and each candidate region contains a microbial community; the computer device then automatically and accurately adjusts the position and size of the candidate region through graphic fitting to better surround the microbial community; thereby outputting the image region corresponding to one or more microbial communities contained in the sample image.

[0057] In some embodiments, a computer device may train a FasterR-CNN model using training images containing known microbial populations to improve the model's ability to classify microbial populations and obtain more accurate microbial populations.

[0058] In some embodiments, the computer device can directly use the Faster R-CNN model to take the candidate area corresponding to each microbial group as the image area corresponding to each microbial group.

[0059] In some embodiments, after the computer device identifies one or more microbial groups contained in the sample image, it can further identify the edge contours of each microbial group to obtain the image area corresponding to each microbial group, wherein the edge contours are used to clearly define the boundaries of different microbial groups.

[0060] Exemplarily, the computer device can apply various edge detection algorithms to identify the edge contours of the microbial colonies. These algorithms include, but are not limited to, the Sobel operator, the Canny edge detector, the Laplacian of Gaussian (LoG) operator, etc. After edge detection, the computer device further improves the accuracy and integrity of the edge contours through morphological operations (such as corrosion, expansion, opening operation, closing operation, etc.), and the morphological operations can be used to smooth edges, remove noise, fill holes, or separate adherent microbial colonies. Through edge detection and morphological processing, the computer device can connect the detected edge pixels into continuous curves or polygons to form a complete contour to obtain the image area corresponding to each microbial colony.

[0061] Step 430 , extracting features from the image regions corresponding to the respective microbial groups, obtaining group features corresponding to the respective microbial groups, and determining the number of microorganisms contained in the respective microbial groups.

[0062] The population characteristics corresponding to the microbial population refer to the biological characteristics shared by multiple microorganisms contained in the microbial population, such as morphological characteristics (size, shape, edge contour, etc. of each microorganism contained in the microbial population), texture characteristics (roughness, directionality, contrast, etc. of the surface of each microorganism contained in the microbial population), color characteristics, etc.

[0063] In some embodiments, the computer device can extract the texture features corresponding to each microbial population by methods including gray level co-occurrence matrix, local binary pattern, Tamura texture features, etc. The computer device can also extract the color features corresponding to each microbial population by methods such as color histogram and color moment.

[0064] In some embodiments, the computer device may determine the number of microorganisms contained in each microbial population through image processing technology and statistical methods. Specifically, the computer device may first segment the microbial population from the sample image through threshold segmentation, region growing, level set method and other technologies to obtain the regional image or outline of each microbial population; then, by traversing the pixels or outlines of each microorganism in each regional image and using a connected component labeling algorithm (such as a union-find-based algorithm), the microorganisms in each regional image are counted to obtain the number of microorganisms contained in each microbial population.

[0065] Step 440 , determining the microorganism type corresponding to each microorganism group according to the group characteristics corresponding to each microorganism group.

[0066] The types of microorganisms may include, but are not limited to, squamous epithelial cells, columnar epithelial cells, leukocytes, pus cells, erythrocytes, clue cells, Trichomonas, spores, hyphae, Lactobacillus, Gardnerella, Mobiluncus, Gram-positive globules, Gram-negative rods, Trichomonas, spores, hyphae, Gram-negative diplococci, Mycoplasma bodies, and Chlamydia bodies, etc.

[0067] In some embodiments, the computer device may determine the microorganism type of the first group characteristic corresponding to each microorganism group according to the correspondence between the preset group characteristics and the microorganism type. Among them, the computer device may determine the correspondence between the preset group characteristics and the microorganism type based on historical detection experience and the known biological characteristics of various microorganism types. For example, if the group characteristics corresponding to a microorganism group include: a diameter of about 1 micron, spherical or approximately spherical (bean-shaped, kidney-shaped, spear-shaped, etc.), and Gram-positive staining; then the microorganism type corresponding to the microorganism group is Gram-positive sphere. If the group characteristics corresponding to a microorganism group include: a long rod-shaped morphology, a length of about 4-8 microns, usually without flagella, a few have flagella, and Gram-positive staining; then the microorganism type corresponding to the microorganism group is Lactobacillus.

[0068] Step 450, determining the microecological conditions corresponding to the target vaginal sample according to the microbial types and microbial quantities corresponding to each microbial group.

[0069] Microecology is an important indicator for assessing vaginal health. It mainly involves the balance of vaginal microbial communities, whether there is dysbacteriosis, and the risk of potential infection. The balance refers to a relatively stable symbiotic relationship between various microorganisms in the vagina, which helps maintain the vagina's self-cleaning function and defense mechanism. Dysbacteriosis refers to the disruption of the balance of vaginal microbial communities, resulting in the overgrowth or disappearance of certain flora.

[0070] For example, under normal circumstances, when the vaginal microecology is in a balanced state, the dominant flora in the vagina (such as Lactobacillus) can produce acidic substances such as lactic acid to maintain the acidic environment of the vagina (pH between 3.8 and 4.8), thereby inhibiting the growth of harmful bacteria.

[0071] Under normal circumstances, the microorganisms contained in the vagina of women of different age groups have a relatively fixed range of quantity and type, and the types of microorganisms contained in different age groups may be different. For example, the number of microorganisms corresponding to microorganism type A contained in the vaginal sample of a certain age group will be greater than the number of microorganisms corresponding to microorganism type A contained in the vaginal sample of another age group under normal circumstances. Therefore, the computer device can determine the microecological situation corresponding to the target vaginal sample based on the age of the target user corresponding to the target vaginal sample, the type of microorganisms corresponding to each microbial group, and the number of microorganisms.

[0072] In some embodiments, the computer device may first determine the target age group of the target user corresponding to the target vaginal sample; based on the target age group, determine the normal microecological range of women corresponding to the age group (including various normal microbial types and corresponding normal microbial numbers); and then judge the microecological situation of the target vaginal sample based on the microbial types and microbial numbers in the target vaginal sample, for example, whether it is in a balanced state, whether there is dysbiosis or potential infection, etc.

[0073] In some embodiments, the computer device may further include a display device. After determining the microecological conditions corresponding to the target vaginal sample, the computer device may output the evaluation results (including the microbial types and microbial quantities corresponding to each microbial population, the location information of each microbial population in the sample image, and the microecological conditions corresponding to the target vaginal sample, etc.) to an electronic display device, so that laboratory testers can intuitively determine the microecological conditions of the target vaginal sample.

[0074] In an embodiment of the present application, the processor of the computer device automatically identifies one or more microbial communities in the sample image, and uses feature extraction technology to extract features from the image areas corresponding to each microbial community. Based on the feature extraction of the image areas corresponding to each microbial community, the microbial community in the vaginal sample can be accurately identified, and the microbial type and number of microorganisms in the microbial community can be quickly determined, thereby accurately determining the microecological conditions corresponding to the target vaginal sample. Compared with traditional manual microscopy, the detection efficiency can be improved, human errors can be reduced, and the detection accuracy of the microecological conditions corresponding to the vaginal sample can be improved.

[0075] like Figure 5 As shown, in some embodiments, a vaginal sample microecological detection method is provided, which can be applied to the above-mentioned computer device. The method may include the following steps 502 to 524.

[0076] Step 502: Acquire a sample image corresponding to the target vaginal sample.

[0077] For the description of step 502, reference may be made to the description of step 410 in the above embodiment, which will not be repeated here.

[0078] Step 504 , extracting features of each microorganism contained in the sample image to obtain image features corresponding to each microorganism.

[0079] For the description of extracting features from each microorganism in step 504, reference may be made to the description of extracting features from image regions corresponding to each microorganism group in step 430 in the above embodiment, which will not be described in detail here.

[0080] Step 506 : Match the first image feature corresponding to the first microorganism with the biological features corresponding to the target microorganism type contained in the standard library.

[0081] The first microorganism is any microorganism in the sample image.

[0082] The standard library contains a variety of microbial types, biological features corresponding to various microbial types, and whether various microbial types belong to target microbial types. Target microbial types refer to the microbial types of normal microorganisms that are beneficial to health or normally exist in the female vagina under normal circumstances. These normal microorganisms constitute the microecology of the female vagina and play an important role in maintaining the balance of the microecology and preventing the invasion of harmful microorganisms. For example, in the female vagina, lactobacilli are generally considered to be one of the target microbial types because they help maintain the acidic environment of the vagina, thereby inhibiting the growth of harmful bacteria.

[0083] Specifically, if the computer device detects microorganism type a corresponding to microorganism A, and microorganism type a does not belong to the target microorganism type, it means that microorganism A is an abnormal microorganism that should not appear in the female vagina under normal circumstances.

[0084] Optionally, all microorganism types included in the standard library are all microorganism types that may be present in vaginal samples.

[0085] Biological characteristics may also include morphological characteristics, which refer to the morphology of microorganisms at various stages of their life cycle. For example, spores, as a type of microorganism, may have morphological characteristics including size, shape (such as spherical, elliptical, rod-shaped, etc.), surface structure (such as smooth, rough, thorny, etc.), and arrangement of spores, etc., and these characteristics may vary at different stages of the life cycle, especially at key stages such as spore formation, release, and germination.

[0086] In some embodiments, the computer device may respectively calculate the first similarity between the first image feature and the biological feature corresponding to the target microorganism type in the standard library, and complete the matching of the first image feature corresponding to the first microorganism with the biological feature corresponding to the target microorganism type contained in the standard library through the first similarity. The computer device may use methods to calculate the first similarity, including but not limited to: machine learning algorithms (such as support vector machines, neural networks, etc.), distance calculations in feature vector space (such as Euclidean distance, cosine similarity, Pearson correlation coefficient, etc.), etc.

[0087] Step 508 , determining whether there is any biological feature corresponding to the target microorganism type in the standard library that successfully matches the first image feature.

[0088] If there is any biological feature corresponding to the target microorganism type in the standard library that successfully matches the first image feature, step 510 is executed.

[0089] If there is no biological feature corresponding to any target microorganism type in the standard library that successfully matches the first image feature, a new first microorganism is determined, and the new first microorganism is any microorganism in the sample image that has not been matched with the standard library. Step 506 is re-executed until there is no new first microorganism, that is, all microorganisms in the sample image are matched with the standard library.

[0090] In some embodiments, the computer device may set a first preset similarity to determine whether there is a biological feature corresponding to any target microorganism type in the standard library that successfully matches the first image feature. In order to ensure the accuracy of the computer device detection, the first preset similarity may be set to a higher value, such as 90%. In other words, if the computer device detects that there is a biological feature corresponding to any target microorganism type in the standard library and the first image feature has a first similarity greater than or equal to 90%, the computer device determines that there is a biological feature corresponding to any target microorganism type in the standard library that successfully matches the first image feature. If the first similarity is less than 90%, the computer device determines that there is no biological feature corresponding to any target microorganism type in the standard library that successfully matches the first image feature.

[0091] Step 510: remove the first microorganism in the sample image.

[0092] The computer device determines that the biological feature corresponding to any target microorganism type in the standard library successfully matches the first image feature, indicating that the biological feature corresponding to any target microorganism type in the standard library is exactly the same as the first image feature, and the first microorganism is the target microorganism type, that is, the first microorganism is a normal microorganism that is beneficial to health or normally exists in the female vagina under normal circumstances. Therefore, in order to reduce the amount of calculation of subsequent computer device grouping, the computer device can remove the first microorganism in the sample image.

[0093] In some embodiments, if there is a biological feature corresponding to any target microorganism type in the standard library that successfully matches the first image feature, the computer device can determine the position information of the first microorganism in the sample image; and remove the first microorganism from the sample image based on the position information.

[0094] Specifically, the computer device may use an image processing algorithm (such as edge detection, template matching, feature point detection, etc.) to determine the location information of the first microorganism in the sample image; the location information may include the location coordinates and image area of ​​the first microorganism in the sample image; the computer device may crop the image area containing the first microorganism based on the location coordinates, and fill the image area with a background color or other appropriate pixel values; or, use surrounding pixels or the average pixel value of the sample image to cover the image area where the first microorganism is located.

[0095] After the computer device removes the first microorganism that has been successfully matched, a new first microorganism may be determined, and the new first microorganism is any microorganism in the sample image that has not been matched with the standard library, and step 506 is re-executed until there is no new first microorganism, that is, all microorganisms in the sample image are matched with the standard library. The computer device traverses all microorganisms in the sample image to remove microorganisms of the target microorganism type in the sample image to reduce the subsequent calculation amount of the computer device, thereby improving the detection efficiency of the microecological conditions corresponding to the vaginal sample.

[0096] Step 512, identifying one or more microbial groups contained in the new sample image, and determining the image area corresponding to each microbial group; the new sample image is the sample image obtained after removing the microorganisms whose biological features are successfully matched with the target microorganism type.

[0097] Step 514 , extracting features from the image regions corresponding to the respective microbial groups, obtaining group features corresponding to the respective microbial groups, and determining the number of microorganisms contained in the respective microbial groups.

[0098] Step 516, determining the microorganism type corresponding to each microorganism group according to the group characteristics corresponding to each microorganism group.

[0099] For the related description of steps 512 to 516, reference may be made to the related description of steps 420 to 440 in the above embodiment, which will not be repeated here.

[0100] Step 518, determining the ratio of the number of microorganisms corresponding to each microorganism type to the total number of microorganisms in the sample image according to the microorganism type and the number of microorganisms corresponding to each microorganism group.

[0101] In some embodiments, the ratio of the number of microorganisms corresponding to each microorganism type to the total number of microorganisms in the sample image may be the number of microorganisms corresponding to each microorganism type divided by the total number of microorganisms in the sample image. Specifically, the computer device may obtain the ratio of the number of microorganisms corresponding to each microorganism type to the total number of microorganisms in the sample image through formula (1).

[0102] Formula (1);

[0103] Among them, i is different microorganism types; It represents the ratio of the number of microorganisms corresponding to microorganism type i to the total number of microorganisms in the sample image; represents the number of microorganisms corresponding to microorganism type i; Represents the ratio of the total amount of microorganisms in the sample image.

[0104] In some embodiments, the computer device can also calculate the number of microorganisms that successfully match the image features with the biological features corresponding to the target microorganism type, and the ratio of the number of microorganisms to the total number of microorganisms, so that the computer device can determine the normal microorganisms in the target vaginal sample.

[0105] Step 520 , determining whether the ratios corresponding to the various microorganism types are all within the preset ratio ranges corresponding to the various microorganism types. If so, executing step 522 ; if not, executing step 524 .

[0106] The preset ratio range corresponding to each microorganism type is an extreme value, that is, if the ratio corresponding to a certain microorganism type is within the corresponding preset ratio range, it means that the microorganism type may be in a normal state, but if the ratio corresponding to the microorganism type is not within the corresponding preset ratio range, it means that the microorganism type is definitely not in a normal state. For example, the preset ratio range (maximum value) corresponding to microorganism type C is 70%. If the computer device detects that the ratio corresponding to microorganism type C is 60%<70%, then microorganism type C may be in a normal state in the target vaginal sample.

[0107] Step 522, determining the microecological conditions corresponding to the target vaginal sample according to the ratios corresponding to the various microorganism types.

[0108] In some embodiments, if the computer device detects that the ratios corresponding to each microbial type are all within the preset ratio range corresponding to each microbial type, it means that the computer device determines that each microbial type in the target vaginal sample may be in a normal state, and the computer device can further determine the microecological condition corresponding to the target vaginal sample based on the ratios corresponding to each microbial type.

[0109] Step 524, outputting a manual prompt; the manual prompt is used to prompt the manual determination of the microecological conditions corresponding to the target vaginal sample.

[0110] In some embodiments, if the computer device detects that the ratio corresponding to the existence of a first microorganism type exceeds the preset ratio range corresponding to the first microorganism type, and the first microorganism type is any microorganism type in the sample image, it means that the existing microorganism type is definitely not in a normal situation. Therefore, the computer device can output an artificial prompt to prompt the manual determination of the microecological situation corresponding to the target vaginal sample.

[0111] In some embodiments, manual prompts can also be used to remind the tester that the vagina of the target user corresponding to the target vaginal sample may be abnormal and requires re-sampling and testing, or further experimental testing.

[0112] In the embodiment of the present application, the computer device performs subsequent grouping and type determination only after removing the microorganisms that successfully match the target microorganism type, and the computer device preliminarily determines whether the various microorganism types in the vaginal sample are likely to be normal by judging whether the ratios corresponding to the various microorganism types are within the preset ratio range corresponding to the various microorganism types. Only when they are all likely to be normal, the specific microecological situation is further determined, which can reduce the amount of data that the computer device needs to process, reduce the computational complexity and computational time, and improve the overall detection efficiency. In addition, when the computer device detects that there are microorganism types that exceed the preset ratio range, it can output a manual prompt to remind the detection personnel to make further manual judgments or re-sample the test to ensure the reliability and accuracy of the microecological situation of the vaginal sample.

[0113] like Figure 6 As shown, in some embodiments, the step of determining the microecological conditions corresponding to the target vaginal sample according to the microbial types and microbial quantities corresponding to each microbial population may also include the following steps 602 to 612.

[0114] Step 602 , obtaining a first size of the oil objective lens and a second size of the sample image, and taking a ratio of the first size to the second size as a unit oil objective lens ratio.

[0115] In order to combine computer detection with artificial historical experience, the computer equipment can calculate the types and numbers of microorganisms under the unit oil immersion lens, and compare them with the types and numbers of microorganisms under the unit oil immersion lens obtained by artificial historical experience, so that the computer can more accurately reflect the actual observed microbial situation when processing images.

[0116] In some embodiments, the first size may refer to the field of view area covered by the oil objective during observation; the second size refers to the image area of ​​the sample image corresponding to the target vaginal sample; the unit oil objective ratio of the first size and the second size is the ratio between the field of view area of ​​the oil objective and the image area of ​​the sample image.

[0117] Specifically, the computer device can obtain the unit oil mirror ratio M of the first size and the second size through formula (2).

[0118] Formula (2);

[0119] Wherein, A represents the field of view area covered by the oil objective during observation; B represents the image area of ​​the sample image corresponding to the target vaginal sample.

[0120] Step 604 , multiplying the unit oil immersion ratio by the number of microorganism types contained in the sample image to obtain the type richness corresponding to the target vaginal sample under the unit oil immersion.

[0121] In some embodiments, the computer device can determine the number of different microbial types contained in the target vaginal sample, and multiply it by the unit oil immersion ratio to obtain the type richness corresponding to the target vaginal sample under the unit oil immersion. The type richness can be used to represent the diversity of microbial types in the target vaginal sample.

[0122] In some embodiments, the type richness corresponding to the target vaginal sample can be represented by a symbol. The symbol can be represented by Arabic numerals, English characters, etc. For example, the computer device can use the symbol "+" to represent the type richness, wherein the more "+" there are, the higher the type richness, that is, the more types of microorganisms are contained in the target vaginal sample. Specifically, if the computer device detects that there are x types of microorganisms in the target vaginal sample under a unit oil immersion lens, the type richness corresponding to the target vaginal sample is y, wherein the corresponding relationship between x and y can be shown in Table 1.

[0123] Table 1. Correspondence between the number of microbial types x and type richness y under oil immersion

[0124]

[0125] Step 606 , multiplying the unit oil immersion ratio by the sum of the number of microorganisms corresponding to each microbial group to obtain the microbial density corresponding to the target vaginal sample under the unit oil immersion.

[0126] For the description of determining the microbial density corresponding to the target vaginal sample under the unit oil immersion lens in step 606, reference may be made to the description of determining the type richness corresponding to the target vaginal sample under the unit oil immersion lens in step 604 in the above embodiment, which will not be repeated here.

[0127] Specifically, if the computer device detects that there are z microorganisms in the target vaginal sample under the unit oil immersion lens, the microbial density corresponding to the target vaginal sample is m, where the corresponding relationship between z and m can be shown in Table 2.

[0128] Table 2. Corresponding relationship between the number of microorganisms z and the microorganism density m under the unit oil immersion microscope

[0129]

[0130] Step 608, determining whether the density of microorganisms is within a preset density range, and whether the type richness is within a preset richness range.

[0131] If the detected microbial density is within the preset density range and the type richness is within the preset richness range, it means that the microbial community of the target vaginal sample is healthy and the interaction between various microorganisms is harmonious, then step 610 is executed to determine the microecological balance corresponding to the target vaginal sample.

[0132] If it is detected that the microbial density is not within the preset density range, and / or the type richness is not within the preset richness range, step 612 is executed to determine the microecological imbalance corresponding to the target vaginal sample.

[0133] In some embodiments, laboratory personnel may determine a preset density range and a preset richness range based on historical data, industry standards, or expert opinions, and input the preset density range and the preset richness range into a computer device.

[0134] In some embodiments, the computer device may also automatically determine a preset density range and a preset richness range through machine learning or statistical model training.

[0135] In the embodiment of the present application, the computer device calculates the unit oil-immersion ratio (the ratio of the oil-immersion field area to the sample image area), which can more accurately combine the computer detection results with the manual historical experience, and can improve the accuracy and reliability of the detection. By determining whether the microbial density is within the preset density range and whether the type richness is within the preset richness range, a quantitative assessment of the microecological conditions of the target vaginal sample is achieved, further enhancing the reliability and accuracy of the detection results (the microecological conditions corresponding to the target vaginal sample).

[0136] like Figure 7 As shown, in some embodiments, a vaginal sample microecological detection method is provided, which can be applied to the above-mentioned computer device. The method may include the following steps 702 to 716.

[0137] Step 702, obtaining a sample image corresponding to the target vaginal sample.

[0138] Step 704 , identifying one or more microbial groups contained in the sample image, and determining the image region corresponding to each microbial group.

[0139] Step 706 , extracting features from the image regions corresponding to the respective microbial groups, obtaining group features corresponding to the respective microbial groups, and determining the number of microorganisms contained in the respective microbial groups.

[0140] For the description of steps 702 to 706 , reference may be made to the description of steps 410 to 430 in the above embodiment, which will not be repeated here.

[0141] Step 708 , matching the first population feature corresponding to the first microbial population with the biological features corresponding to each microbial type included in the standard library; the first microbial population is any microbial population.

[0142] For the description about matching in step 708, reference may be made to the description about step 306 in the above embodiment, which will not be repeated here.

[0143] In some embodiments, the computer device may calculate a second similarity between the first population feature and the biological feature corresponding to each microorganism type included in the standard library.

[0144] Step 710, determining whether the first group feature matches the biometric feature in the standard library successfully. If the first group feature matches the biometric feature in the standard library successfully, executing step 712; if the first group feature fails to match the biometric feature in the standard library, executing step 714.

[0145] In some embodiments, the computer device may set a second preset similarity to determine whether there is a biometric feature in the standard library that successfully matches the first group feature. The second preset similarity is less than the first preset similarity, for example, the second preset similarity may be 60%. In other words, if the computer device detects that there is a second similarity between any biometric feature and the first group feature in the standard library that is greater than or equal to 60%, the computer device determines that there is a biometric feature in the standard library that successfully matches the first group feature. If the second similarity is less than 60%, the computer device determines that there is no biometric feature in the standard library that successfully matches the first group feature.

[0146] Step 712: The microorganism type corresponding to the biological feature that matches the first group feature is used as the microorganism type corresponding to the first microorganism group.

[0147] Step 714: determine the microorganism type corresponding to the second microorganism group as a special microorganism.

[0148] Optionally, if the computer device detects that there is a second microbial population in one or more microbial populations whose population characteristics do not match the biological characteristics corresponding to each microbial type contained in the standard library, the microbial type corresponding to the second microbial population is determined as a special microorganism.

[0149] Step 716, determining the microecological conditions corresponding to the target vaginal sample according to the microbial types and microbial quantities corresponding to each microbial group.

[0150] For the description of step 716, reference may be made to the description of step 450 in the above embodiment, which will not be repeated here.

[0151] In some specific embodiments, since all microbial types included in the standard library are all microbial types that may exist in female vaginal samples, if the microbial type in the target vaginal sample is not in the standard library, that is, the microbial type corresponding to the microbial population is a special microorganism, it means that the target vaginal sample contains a microbial population that should not exist in female vaginal samples. Therefore, if the computer device includes a second microbial population in one or more microbial populations, and the number of microorganisms included in the second microbial population is greater than a preset number threshold, it is determined that the microecological imbalance corresponding to the target vaginal sample is present.

[0152] In an embodiment of the present application, the computer device can more accurately identify the type of microorganism by matching the population characteristics of the microbial population in the sample image with the biological characteristics in the standard library, thereby reducing the subjectivity of human judgment and improving the accuracy and reliability of detection.

[0153] like Figure 8As shown, in one embodiment, a vaginal sample microecology detection device 800 is provided, which can be applied to the above-mentioned computer device. The vaginal sample microecology detection device 800 may include an image acquisition module 810, a microorganism identification module 820, a feature extraction module 830, a type determination module 840 and a microecology determination module 850.

[0154] The image acquisition module 810 is used to acquire a sample image corresponding to the target vaginal sample.

[0155] The microorganism identification module 820 is used to identify one or more microorganism groups contained in the sample image and determine the image area corresponding to each microorganism group.

[0156] The feature extraction module 830 is used to extract features from the image regions corresponding to each microbial group, obtain the group features corresponding to each microbial group, and determine the number of microorganisms contained in each microbial group.

[0157] The type determination module 840 is used to determine the microorganism type corresponding to each microorganism group according to the group characteristics corresponding to each microorganism group.

[0158] The microecological determination module 850 is used to determine the microecological conditions corresponding to the target vaginal sample according to the microbial types and microbial quantities corresponding to each microbial population.

[0159] In some embodiments, the vaginal sample microecology detection device 800 may further include a microorganism removal module.

[0160] The microorganism removal module is used to extract features of each microorganism contained in the sample image to obtain image features corresponding to each microorganism; match the first image features corresponding to the first microorganism with the biological features corresponding to the target microorganism type contained in the standard library; the first microorganism is any microorganism in the sample image; if the biological features corresponding to any target microorganism type in the standard library successfully match the first image features, the first microorganism is removed from the sample image.

[0161] Optionally, the microorganism identification module 820 is also used to identify one or more microorganism groups contained in the new sample image and determine the image area corresponding to each microorganism group; the new sample image is the sample image obtained after removing the microorganisms that successfully match the biological features corresponding to the target microorganism type.

[0162] In some embodiments, the microecological determination module 850 is further used to determine the ratio of the number of microorganisms corresponding to each microorganism type to the total number of microorganisms in the sample image according to the microorganism type and microorganism number corresponding to each microorganism group. If the ratios corresponding to each microorganism type are within the preset ratio range corresponding to each microorganism type, the microecological situation corresponding to the target vaginal sample is determined according to the ratios corresponding to each microorganism type.

[0163] Optionally, the microecological determination module 850 is also used to output a manual prompt if the ratio corresponding to the first microorganism type exceeds the preset ratio range corresponding to the first microorganism type; the manual prompt is used to prompt the manual determination of the microecological situation corresponding to the target vaginal sample; the first microorganism type is any microorganism type in the sample image.

[0164] In some embodiments, the microecological determination module 850 is also used to obtain a first size of the oil objective and a second size of the sample image, and use the ratio of the first size to the second size as the unit oil objective ratio; multiply the unit oil objective ratio by the number of microbial types contained in the sample image to obtain the type richness corresponding to the target vaginal sample under the unit oil objective; multiply the unit oil objective ratio by the sum of the number of microorganisms corresponding to each microbial population to obtain the microbial density corresponding to the target vaginal sample under the unit oil objective; if the microbial density is detected to be within a preset density range, and the type richness is within a preset richness range, the microecological balance corresponding to the target vaginal sample is determined; if the microbial density is detected to be not within the preset density range, and / or the type richness is not within the preset richness range, the microecological imbalance corresponding to the target vaginal sample is determined.

[0165] Optionally, the type determination module 840 is also used to match the first group feature corresponding to the first microbial group with the biological features corresponding to each microbial type contained in the standard library; the first microbial group is any microbial group; if the first group feature successfully matches the biological feature in the standard library, the microbial type corresponding to the biological feature matching the first group feature is used as the microbial type corresponding to the first microbial group.

[0166] In some embodiments, the type determination module 840 is further used to determine the microorganism type corresponding to the second microorganism population as a special microorganism if there is a second microorganism population in one or more microorganism populations whose population characteristics do not match the biological characteristics corresponding to each microorganism type contained in the standard library.

[0167] Optionally, the microecological determination module 850 is further used to determine that the microecological imbalance corresponding to the target vaginal sample is if a second microbial population is included in one or more microbial populations and the number of microorganisms included in the second microbial population is greater than a preset number threshold.

[0168] In an embodiment of the present application, the processor of the computer device automatically identifies one or more microbial communities in the sample image, and uses feature extraction technology to extract features from the image areas corresponding to each microbial community. Based on the feature extraction of the image areas corresponding to each microbial community, the microbial community in the vaginal sample can be accurately identified, and the microbial type and number of microorganisms in the microbial community can be quickly determined, thereby accurately determining the microecological conditions corresponding to the target vaginal sample. Compared with traditional manual microscopy, the detection efficiency can be improved, human errors can be reduced, and the detection accuracy of the microecological conditions corresponding to the vaginal sample can be improved.

[0169] Fig. 9 FIG. 1 is a block diagram of a computer device in one embodiment. Fig. 9 As shown, the computer device 110 may include one or more of the following components: a processor 910, and a memory 920 coupled to the processor 910, wherein the memory 920 may store one or more computer programs, and the one or more computer programs may be configured to implement the methods described in the above embodiments when executed by one or more processors 910.

[0170] The processor 910 may include one or more processing cores. The processor 910 uses various interfaces and lines to connect various parts of the entire computer device 110, and executes various functions and processes data of the computer device 110 by running or executing instructions, programs, code sets or instruction sets stored in the memory 920, and calling data stored in the memory 920. Optionally, the processor 910 can be implemented in at least one hardware form of digital signal processing (DSP), field-programmable gate array (FPGA), and programmable logic array (PLA). The processor 910 can integrate one or a combination of a central processing unit (CPU), a graphics processing unit (GPU), and a modem. Among them, the CPU mainly processes the operating system, user interface, and application programs; the GPU is responsible for rendering and drawing display content; and the modem is used to process wireless communications. It can be understood that the above-mentioned modem may not be integrated into the processor 910, but may be implemented separately through a communication chip.

[0171] The memory 920 may include a random access memory (RAM) or a read-only memory (ROM). The memory 920 may be used to store instructions, programs, codes, code sets or instruction sets. The memory 920 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for implementing at least one function (such as a touch function, a sound playback function, an image playback function, etc.), instructions for implementing the above-mentioned various method embodiments, etc. The data storage area may also store data created by the computer device 110 during use, etc.

[0172] It is understandable that the computer device 110 may include more or fewer structural elements than those in the above structural block diagram, for example, including a power supply, input buttons, a camera, a speaker, a screen, an RF (Radio Frequency) circuit, a Wi-Fi (Wireless Fidelity) module, a Bluetooth module, a sensor, etc., and is not limited here.

[0173] An embodiment of the present application discloses a computer-readable storage medium storing a computer program, wherein the computer program implements the methods described in the above embodiments when executed by a processor.

[0174] The embodiments of the present application disclose a computer program product, including a computer program, and the computer program can be executed by a processor to implement the methods described in the above embodiments.

[0175] A person skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program, and the program can be stored in a non-volatile computer-readable storage medium, and when the program is executed, it can include the processes of the embodiments of the above-mentioned methods. The storage medium can be a disk, an optical disk, a read-only memory (ROM), etc.

[0176] Any reference to memory, storage, database or other medium as used herein may include non-volatile and / or volatile memory. Suitable non-volatile memory may include ROM, programmable ROM (Programmable ROM, PROM), erasable PROM (Erasable PROM, EPROM), electrically erasable PROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM), which is used as an external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), memory bus direct RAM (RDRAM) and direct memory bus dynamic RAM (DRDRAM).

[0177] It should be understood that the "one embodiment" or "an embodiment" mentioned throughout the specification means that the specific features, structures or characteristics related to the embodiment are included in at least one embodiment of the present application. Therefore, "in one embodiment" or "in an embodiment" appearing throughout the specification does not necessarily refer to the same embodiment. In addition, these specific features, structures or characteristics can be combined in one or more embodiments in any suitable manner. Those skilled in the art should also be aware that the embodiments described in the specification are all optional embodiments, and the actions and modules involved are not necessarily required for the present application.

[0178] In the various embodiments of the present application, it should be understood that the size of the serial numbers of the above-mentioned processes does not necessarily mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0179] The technical features of the above embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0180] The units described above as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0181] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0182] If the above-mentioned integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-accessible memory. Based on this understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product, which is stored in a memory and includes several requests for a computer device (which can be a personal computer, server or network device, etc., specifically a processor in a computer device) to perform some or all of the steps of the above-mentioned methods of various embodiments of the present application.

[0183] The above is a detailed introduction to the microecological detection method, device and computer equipment of a vaginal sample disclosed in the embodiment of the present application. The principles and implementation methods of the present application are described in detail using specific examples herein. The description of the above embodiments is only used to help understand the method and core idea of ​​the present application. At the same time, for those of ordinary skill in the art, according to the idea of ​​the present application, there will be changes in the specific implementation method and scope of application. In summary, the content of this specification should not be understood as a limitation on the present application.

Claims

1. A method for detecting microecology of vaginal samples, characterized in that: Applied to a computer device, the computer device includes a processor, and the method executed by the processor includes: Acquire a sample image corresponding to a target vaginal sample; Extracting features of each microorganism contained in the sample image to obtain image features corresponding to each microorganism; Matching the first image feature corresponding to the first microorganism with the biological features corresponding to the target microorganism type contained in the standard library; the first microorganism is any microorganism in the sample image; the target microorganism type is a microorganism type of normal microorganism that is beneficial to health or normally exists in the female vagina under normal circumstances; If there is any biological feature corresponding to the target microorganism type in the standard library that successfully matches the first image feature, then removing the first microorganism from the sample image; Identify one or more microbial groups contained in a new sample image, and determine the image area corresponding to each of the microbial groups; the new sample image is a sample image obtained after removing microorganisms that successfully match the biological features corresponding to the target microorganism type; Extracting features from the image regions corresponding to the respective microbial populations to obtain population features corresponding to the respective microbial populations, and determining the number of microorganisms contained in the respective microbial populations; Determining the microorganism type corresponding to each of the microorganism groups according to the group characteristics corresponding to each of the microorganism groups; Determining the microecological conditions corresponding to the target vaginal sample according to the microbial types and microbial quantities corresponding to each of the microbial populations; Determining the microecological conditions corresponding to the target vaginal sample according to the microbial types and microbial quantities corresponding to each of the microbial populations includes: Acquire a first size of the oil objective lens and a second size of the sample image, and use a ratio of the first size to the second size as a unit oil objective lens ratio; Multiplying the unit oil-immersion ratio by the number of microorganism types contained in the sample image to obtain the type richness corresponding to the target vaginal sample under the unit oil-immersion ratio; Multiplying the unit oil immersion ratio by the sum of the number of microorganisms corresponding to each of the microbial groups to obtain the microbial density corresponding to the target vaginal sample under the unit oil immersion; If it is detected that the microbial density is within a preset density range, and the type richness is within a preset richness range, then determining the microecological balance corresponding to the target vaginal sample; If it is detected that the microbial density is not within a preset density range, and / or the type richness is not within a preset richness range, then it is determined that the microecological imbalance corresponding to the target vaginal sample is present.

2. The method according to claim 1, characterized in that Before determining the microecological conditions corresponding to the target vaginal sample according to the microbial types and microbial quantities corresponding to each of the microbial groups, the method further includes: According to the microorganism types and microorganism quantities corresponding to each of the microorganism groups, determining the ratio of the number of microorganisms corresponding to each microorganism type to the total number of microorganisms in the sample image; Determining the microecological conditions corresponding to the target vaginal sample according to the microbial types and microbial quantities corresponding to each of the microbial populations includes: If the ratios corresponding to the various microbial types are all within the preset ratio ranges corresponding to the various microbial types, the microecological conditions corresponding to the target vaginal sample are determined according to the ratios corresponding to the various microbial types.

3. The method according to claim 2, characterized in that The method further comprises: If there is a ratio corresponding to a first microorganism type that exceeds a preset ratio range corresponding to the first microorganism type, an artificial prompt is output; the artificial prompt is used to prompt the manual determination of the microecological situation corresponding to the target vaginal sample; the first microorganism type is any microorganism type in the sample image.

4. The method according to any one of claims 1 to 3, characterized in that Determining the microorganism type corresponding to each microorganism group according to the group characteristics corresponding to each microorganism group includes: Matching the first population characteristics corresponding to the first microbial population with the biological characteristics corresponding to each microbial type contained in the standard library; the first microbial population is any of the microbial populations; If the first population feature successfully matches the biological feature in the standard library, the microorganism type corresponding to the biological feature matching the first population feature is used as the microorganism type corresponding to the first microbial population.

5. The method according to claim 4, characterized in that After matching the first population feature corresponding to the first microbial population with the biological features corresponding to each microbial type contained in the standard library, the method further includes: If there is a second microbial population among the one or more microbial populations whose population characteristics do not match the biological characteristics corresponding to each microbial type contained in the standard library, the microbial type corresponding to the second microbial population is determined as a special microorganism; Determining the microecological conditions corresponding to the target vaginal sample according to the microbial types and microbial quantities corresponding to each of the microbial populations includes: If the second microbial population is included in the one or more microbial populations, and the number of microorganisms included in the second microbial population is greater than a preset number threshold, it is determined that the microecological imbalance corresponding to the target vaginal sample is present.

6. A vaginal sample microecological detection device, characterized in that: Applied to computer equipment, the device comprises: An image acquisition module, used to acquire a sample image corresponding to a target vaginal sample; A microorganism removal module is used to extract features of each microorganism contained in the sample image to obtain image features corresponding to each microorganism; match the first image feature corresponding to the first microorganism with the biological features corresponding to the target microorganism type contained in the standard library; the first microorganism is any microorganism in the sample image; the target microorganism type is a microorganism type of normal microorganism that is beneficial to health or normally exists in the female vagina under normal circumstances; if the biological feature corresponding to any target microorganism type in the standard library successfully matches the first image feature, then remove the first microorganism from the sample image; A microorganism identification module is used to identify one or more microorganism groups contained in a new sample image and determine the image area corresponding to each of the microorganism groups; the new sample image is a sample image obtained by removing the microorganisms that successfully match the biological characteristics corresponding to the target microorganism type; A feature extraction module is used to extract features from the image area corresponding to each of the microbial groups, obtain the group features corresponding to each of the microbial groups, and determine the number of microorganisms contained in each of the microbial groups; A type determination module, used to determine the microorganism type corresponding to each microorganism group according to the group characteristics corresponding to each microorganism group; A microecological determination module, used to determine the microecological conditions corresponding to the target vaginal sample according to the microbial types and microbial quantities corresponding to each of the microbial populations; The microecological determination module is also used to obtain a first size of the oil objective and a second size of the sample image, and use the ratio of the first size to the second size as a unit oil objective ratio; multiply the unit oil objective ratio by the number of microbial types contained in the sample image to obtain the type richness corresponding to the target vaginal sample under the unit oil objective; multiply the unit oil objective ratio by the sum of the number of microorganisms corresponding to each of the microbial groups to obtain the microbial density corresponding to the target vaginal sample under the unit oil objective; if it is detected that the microbial density is within a preset density range, and the type richness is within a preset richness range, the microecological balance corresponding to the target vaginal sample is determined; if it is detected that the microbial density is not within the preset density range, and / or the type richness is not within the preset richness range, the microecological imbalance corresponding to the target vaginal sample is determined.

7. A computer device, characterized in that: The method comprises a memory and a processor, wherein a computer program is stored in the memory, and when the computer program is executed by the processor, the processor implements the method according to any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1 to 5 is implemented.

Images