A sheep estrus monitoring system based on cell image morphology recognition

Abstract

The application discloses a kind of based on cell image morphological identification's sheep estrus monitoring system, including its features in, including sample acquisition module (100) obtains sheep vaginal epithelial cell sample and carries out dyeing treatment to cell sample;Microscopic imaging module (200) carries out optical amplification to the cell sample after dyeing and generates cell morphology image;Image processing module (300) extracts cell edge contour and quantifies morphological irregular feature;Intelligent analysis module (400) is determined by the comprehensive analysis to nuclear deviation center proportion and morphological irregular index, judges sheep estrus state.The application has beneficial effect for proposing a kind of based on cell image morphological identification's sheep estrus monitoring system, by fusing the double morphological criterion of nuclear space displacement analysis and contour geometric distortion detection, realizes the high sensitivity capture to early estrus biological marker, significantly improves the timeliness and precision of reproduction control.

Description

Technical Field

[0001] This invention belongs to the field of animal reproductive examination, and in particular to a sheep estrus monitoring system based on cell image morphology recognition. Background Technology

[0002] In modern livestock management, sheep reproductive efficiency directly impacts economic benefits, and accurate estrus detection is a crucial aspect of reproductive control. Currently, existing technologies for sheep estrus monitoring mainly fall into three categories: manual observation, biochemical detection, and traditional image analysis.

[0003] These current estrus detection methods have significant drawbacks, including sensitivity deficiencies, efficiency bottlenecks, and cost constraints. Current methods cannot capture early estrus cell morphological changes, while cell classification and counting systems are insensitive to features such as irregular morphology and nuclear deviation, resulting in a high false negative rate. Biochemical testing requires a laboratory environment, with an average delay of 3.5 hours from sampling to results, which cannot meet the real-time decision-making needs during the breeding window. They also rely on imported high-resolution microscopy equipment and are not adapted to the unique cell morphological characteristics of local Chinese sheep breeds.

[0004] The more fundamental technical contradiction lies in the fact that current technological systems do not use nuclear spatial displacement and outline geometric distortion as criteria for estrus detection, even though these two are early biological markers of native Chinese sheep breeds (see *China Animal Husbandry Journal*, 2024, 56(05):231-235). Therefore, there is an urgent need to develop an estrus monitoring system that combines morphological micro-variation recognition capabilities with low cost and farm-deployability. Currently, there is no suitable system on the market that can solve the above problems. Summary of the Invention

[0005] The purpose of this section is to outline some aspects of embodiments of the present invention and to briefly describe some preferred embodiments. Simplifications or omissions may be made in this section, as well as in the abstract and title of this application, to avoid obscuring the purpose of these documents; however, such simplifications or omissions should not be construed as limiting the scope of the invention.

[0006] In view of the problems existing in the above and / or existing sheep estrus monitoring systems based on cell image morphology recognition, the present invention is proposed.

[0007] Therefore, the problem to be solved by this invention is how to develop a system for efficiently detecting the estrus state of sheep through cell image detection.

[0008] To solve the above-mentioned technical problems, the present invention provides the following technical solution: a sheep estrus monitoring system based on cell image morphology recognition, comprising,

[0009] It includes a sample acquisition module, a microscopic imaging module, an image processing module, an intelligent analysis module, and a monitoring output module;

[0010] The sample collection module includes a cell extraction unit and a staining unit. The cell extraction unit is used to obtain sheep vaginal epithelial cell samples, and the staining unit is used to stain the cell samples.

[0011] The microscopic imaging module is used to perform optical magnification imaging on stained cell samples to generate cell morphology images.

[0012] The image processing module includes a nuclear localization unit and a morphology recognition unit. The nuclear localization unit is used to identify the position of the cell nucleus and detect the state of the nucleus deviating from the center. The morphology recognition unit is used to extract the cell edge contour and quantify the irregular morphological features.

[0013] The intelligent analysis module uses a preset cell morphology discrimination algorithm to comprehensively analyze the proportion of nuclear deviation from the center and the morphological irregularity index to determine the estrus status of the sheep.

[0014] The monitoring output module records the judgment results of the intelligent analysis module in real time, generates an estrus status monitoring report, and updates it dynamically.

[0015] As a preferred embodiment of the sheep estrus monitoring system based on cell image morphology recognition described in this invention, the estrus threshold model of the state determination unit includes:

[0016] Estrus status conditions: nuclear deviation > 0.5 and morphological irregularity index > 0.75, such as Figures 6-7 The two images show the state of being in heat;

[0017] Non-estrus state conditions: nuclear deviation ≤ 0.3 or morphological irregularity index ≤ 0.4. Figures 2-3 The two pictures show the state before estrus;

[0018] Transitional state conditions: kernel deviation ∈ (0.3, 0.5] and morphological irregularity index ∈ (0.4, 0.75], such as... Figure 4 This is the transitional stage of estrus, during which mating is not suitable. From a clinical or veterinary perspective, it is considered the initial stage of estrus. Figure 5 It is clearly visible that the epithelial cells have become keratinized, and the cells no longer have nuclei; they have degenerated. This is the optimal time for mating.

[0019] The threshold parameter is dynamically updated based on the statistical distribution of historical data in the monitoring output module.

[0020] As a preferred embodiment of the sheep estrus monitoring system based on cell image morphology recognition described in this invention, the morphology recognition unit performs the following operations:

[0021] Fourier descriptors of cell contours are extracted using an edge detection algorithm, and the first 20 harmonic components are retained.

[0022] Calculate the Hausdorff distance between the reconstructed contour and the original contour;

[0023] The variance of contour curvature is calculated as an index of morphological irregularity, and its expression is as follows:

[0024]

[0025] Where k i For the curvature of the contour points, Where is the average curvature, N is the number of contour points, and Hausdorff distance is a measure of the maximum mismatch between two point sets.

[0026] As a preferred embodiment of the sheep estrus monitoring system based on cell image morphology recognition described in this invention, the nuclear localization unit calculates the nuclear deviation as follows:

[0027] Network segmentation technology was used to segment the cell nucleus and cytoplasm regions;

[0028] If multiple cell nuclei are detected coexisting in the same cytoplasmic region, the maximum nucleus deviation value is taken.

[0029] Cell radius is calculated based on the equivalent circle diameter:

[0030]

[0031] A represents the pixel area of ​​the cytoplasmic region;

[0032] Locate the cell centroid (Cx, Cy) and the nuclear centroid (Nx, Ny);

[0033] Calculate the deviation:

[0034] .

[0035] As a preferred embodiment of the sheep estrus monitoring system based on cell image morphology recognition described in this invention, the staining unit uses Wright's staining solution to stain the cell samples for 3-5 minutes.

[0036] As a preferred embodiment of the sheep estrus monitoring system based on cell image morphology recognition described in this invention, the microscopic imaging module includes: a microscope, a high-speed focusing mechanism, a multispectral LED light source, and an image fusion processor;

[0037] The image fusion processor synthesizes high signal-to-noise ratio images from different bands and focal plane images.

[0038] As a preferred embodiment of the sheep estrus monitoring system based on cell image morphology recognition described in this invention, the monitoring output module, before triggering the estrus confirmation report:

[0039] The system retrieves the average white blood cell density of the sheep over the past 30 days from the monitoring output module; if the currently detected white blood cell density W... c If the value is <0.6 and the percentage of keratinocytes is >65%, then continuous detection will be activated;

[0040] Otherwise, maintain the single test report mode.

[0041] As a preferred embodiment of the sheep estrus monitoring system based on cell image morphology recognition described in this invention, the estrus confirmation report includes:

[0042] A statistical chart of cell subtypes, showing a heatmap of the spatial distribution of keratinocytes, nucleated cells, and leukocytes;

[0043] The estrus risk coefficient R = α⋅Dev + β⋅Index, where α = 0.7 and β = 0.3.

[0044] The reproductive window prediction curve is generated by fitting historical estrus interval data.

[0045] In a second aspect, some embodiments of the present invention provide an electronic device, including: one or more processors; and a storage device having one or more programs stored thereon, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement the system described in any of the implementations of the first aspect above.

[0046] Thirdly, some embodiments of the present invention provide a computer-readable medium having a computer program stored thereon, wherein the program, when executed by a processor, implements the system described in any of the implementations of the first aspect above.

[0047] The beneficial effects of this invention are that it proposes a sheep estrus monitoring system based on cell image morphology recognition. By integrating the dual morphological criteria of cell nuclear spatial displacement analysis and contour geometric distortion detection, it achieves high-sensitivity capture of early estrus biological markers. It effectively overcomes the long-standing technical bottlenecks of traditional methods, such as high recognition lag, weak perception of subtle features, and strong equipment dependence. It significantly improves the timeliness and accuracy of reproductive regulation, and provides a low-threshold, highly reliable automated monitoring solution for large-scale farms. It has outstanding technological breakthrough and industrial promotion value. Attached Figure Description

[0048] To more clearly illustrate the technical solutions in this invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0049] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort. Wherein:

[0050] Figure 1 This is a flowchart of a sheep estrus monitoring system based on cell image morphology recognition in Example 1.

[0051] Figure 2 This is a non-estrus type 1 illustration of an estrus monitoring system based on cell image morphology recognition in Example 1.

[0052] Figure 3 This is an example of a non-estrus type 2 image from an estrus monitoring system based on cell image morphology recognition in Example 1.

[0053] Figure 4 This is an example diagram of the estrus transition period in a sheep estrus monitoring system based on cell image morphology recognition, as shown in Example 1.

[0054] Figure 5 This is a preliminary estrus status diagram of an estrus monitoring system for sheep based on cell image morphology recognition in Example 1.

[0055] Figure 6 This is an example of estrus type 1 in an estrus monitoring system for sheep based on cell image morphology recognition, as described in Example 1.

[0056] Figure 7 This is an illustration of estrus type 2 in an estrus monitoring system for sheep based on cell image morphology recognition, as shown in Example 1. Detailed Implementation

[0057] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

[0058] Many specific details are set forth in the following description in order to provide a full understanding of the invention. However, the invention may also be practiced in other ways different from those described herein, and those skilled in the art can make similar extensions without departing from the spirit of the invention. Therefore, the invention is not limited to the specific embodiments disclosed below.

[0059] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The phrase "in one embodiment" appearing in different places in this specification does not necessarily refer to the same embodiment, nor is it a single or selective embodiment that is mutually exclusive with other embodiments. Example

[0060] Reference Figures 1 to 7 This is the first embodiment of the present invention, which provides a sheep estrus monitoring system based on cell image morphology recognition, comprising:

[0061] A sheep estrus monitoring system based on cell image morphology recognition, characterized in that it includes a sample acquisition module 100, a microscopic imaging module 200, an image processing module 300, an intelligent analysis module 400, and a monitoring output module 500, the logical structure of which is as follows: Figure 1 As shown;

[0062] The sample collection module 100 includes a cell extraction unit 101 and a staining unit 102. The cell extraction unit 101 is used to obtain sheep vaginal epithelial cell samples, and the staining unit 102 is used to stain the cell samples. The staining unit 102 uses Wright's staining solution to stain the cell samples for 3-5 minutes.

[0063] The microscopic imaging module 200 is used to perform optical magnification imaging on the stained cell sample to generate cell morphology images.

[0064] The microscopic imaging module 200 includes: a microscope, a high-speed focusing mechanism, a multispectral LED light source, and an image fusion processor;

[0065] The image fusion processor synthesizes high signal-to-noise ratio images from different bands and focal plane images.

[0066] The image processing module 300 includes a nuclear localization unit 301 and a morphology recognition unit 302. The nuclear localization unit 301 is used to identify the position of the cell nucleus and detect the state of the nucleus deviating from the center. The morphology recognition unit 302 is used to extract the cell edge contour and quantify the irregular morphological features. The morphology recognition unit 302 performs the following operations:

[0067] When calculating the nuclear deviation, the nuclear positioning unit 301:

[0068] Network segmentation technology was used to segment the cell nucleus and cytoplasm regions;

[0069] If multiple cell nuclei are detected coexisting in the same cytoplasmic region, the maximum nucleus deviation value is taken.

[0070] Cell radius is calculated based on the equivalent circle diameter:

[0071]

[0072] A represents the pixel area of ​​the cytoplasmic region;

[0073] Positioning the cell centroid (C x C y ) and the cell nucleus centroid (N x N y );

[0074] Calculate the deviation:

[0075] .

[0076] Fourier descriptors of cell contours are extracted using an edge detection algorithm, and the first 20 harmonic components are retained.

[0077] Calculate the Hausdorff distance between the reconstructed contour and the original contour;

[0078] The variance of contour curvature is calculated as an index of morphological irregularity, and its expression is as follows:

[0079]

[0080] Where k i For the curvature of the contour points, Where is the average curvature, N is the number of contour points, and Hausdorff distance is a measure of the maximum mismatch between two point sets.

[0081] The intelligent analysis module 400 uses a preset cell morphology discrimination algorithm to comprehensively analyze the proportion of nuclear deviation from the center and the morphological irregularity index to determine the estrus status of the sheep.

[0082] The intelligent analysis module 400 determines the estrus status of sheep by including:

[0083] Estrus status conditions: nuclear deviation > 0.5 and morphological irregularity index > 0.75;

[0084] Non-estrus state conditions: nuclear deviation ≤ 0.3 or morphological irregularity index ≤ 0.4;

[0085] Transitional state conditions: kernel deviation ∈ (0.3, 0.5] and morphological irregularity index ∈ (0.4, 0.75],

[0086] The threshold parameter is dynamically updated based on the statistical distribution of historical data in the monitoring output module 500.

[0087] The monitoring output module 500 records the judgment results of the intelligent analysis module 400 in real time, generates an estrus status monitoring report, and updates it dynamically.

[0088] Before the estrus confirmation report is triggered, the monitoring output module 500:

[0089] The average white blood cell density of the sheep over the past 30 days was retrieved from the monitoring output module 500. If the current white blood cell density W c <0.6 If the percentage of keratinocytes is >65%, then continuous detection will be activated;

[0090] Otherwise, maintain the single test report mode.

[0091] The estrus confirmation report includes:

[0092] A statistical chart of cell subtypes, showing a heatmap of the spatial distribution of keratinocytes, nucleated cells, and leukocytes;

[0093] The estrus risk coefficient R = α⋅Dev + β⋅Index, where α = 0.7 and β = 0.3.

[0094] The reproductive window prediction curve is generated by fitting historical estrus interval data. Example

[0095] The second embodiment of the present invention differs from the first embodiment in that it further includes a practical process for monitoring estrus in sheep based on cell image morphology recognition:

[0096] 1. Experiment Preparation and Implementation Process

[0097] Six healthy Small-tailed Han sheep (numbered S01-S06), aged 2-3 years and weighing 45±5 kg, were selected for the experiment and were in their normal reproductive cycle. The sample collection module used sterile cotton swabs to scrape epithelial cells from the anterior fornix of the vagina, which were then fixed and stained with Wright's stain (concentration 4.0±0.5%, staining time 9±0.5 minutes). The microscopic imaging module was equipped with a 20x objective lens and a three-band LED light source (405nm / 488nm / 635nm). Five focal plane images were acquired through a high-speed focusing mechanism. The image fusion processor used a weighted superposition algorithm to synthesize high-resolution cell images with a signal-to-noise ratio >35dB. The image processing module performed dual-path analysis: the nuclear localization unit used a U-Net network to segment the cell nucleus (red stained area) and cytoplasm (blue stained area) and calculated the nuclear centroid offset distance; the morphology recognition unit extracted contours through Canny edge detection, reconstructed the contours using Fourier descriptors while retaining the first 20 harmonic components, and calculated the Hausdorff distance and curvature variance between the original and reconstructed contours. The intelligent analysis module was initialized with a nuclear deviation threshold of 0.5 and a morphological irregularity index of 0.75, and the thresholds were dynamically updated every 24 hours based on historical data. The monitoring output module activated the reproductive window prediction when estrus conditions were met for three consecutive tests and the white blood cell density was <0.6 (keratinocyte percentage >65%). The experiment lasted for 30 days, with samples collected at fixed times each day and simultaneous manual microscopic examination (gold standard) for comparison and verification.

[0098] 2. Test Data Recording Table

[0099] Table 1: Raw data of cell morphology parameters (samples from day 15)

[0100]

[0101] Table 2: Dynamic Threshold Update Record (S01 sheep)

[0102]

[0103] Table 3: Comparison of Consistency Between System and Manual Judgment

[0104]

[0105] Table 4: Additional parameters for estrus confirmation (sample during estrus period)

[0106]

[0107] Table 5: Comparison of Multispectral Imaging Quality

[0108]

[0109] Table 6: Comparison of reproductive efficiency (with traditional smear microscopy)

[0110]

[0111] 3. Data Analysis and Innovation Validation

[0112] Table 1 shows that the system's determination of the state strictly corresponds to the cell morphology parameters: the nuclear deviation (0.62 / 0.73) and morphological irregularity index (0.81 / 0.89) of the estrus samples (S01, S04) both exceed the initial threshold, and the proportion of keratinized cells is >75%, while the white blood cell density is <0.6, meeting the conditions for estrus activation. The parameters of the transitional samples (S02, S05) are in the critical threshold range (nuclear deviation 0.41 / 0.35, morphological index 0.58 / 0.49). At this time, traditional methods are prone to misjudgment (Table 3 shows that the human misjudgment rate is 7.1-8.3%), while the system improves the accuracy of transitional period identification to over 92% through a dynamic threshold update mechanism (Table 2: the threshold of S01 is adjusted to 0.52 / 0.74 at D15) (Table 3 shows that the system misjudgment rate is ≤5.0%).

[0113] Table 4 validates that the estrus risk coefficient R (R=0.7×Dev+0.3×Index) quantifies estrus intensity. The R value of S04 (0.79) is higher than that of S01 (0.71), consistent with its keratinocyte percentage (82.6% vs 78.2%) and shortened prediction window (18-30h vs 24-36h), indicating that the formula effectively integrates multiple parameters to predict the reproductive window. Table 5 demonstrates that the multispectral fusion technology improves the signal-to-noise ratio by 27.6% (mean 28.5dB→35.7dB), significantly improves the accuracy of cell nucleus identification to 92.3%, and overcomes the focus blurring problem caused by cell thickness differences in single-band imaging.

[0114] In summary, the embodiments, through mutual corroboration of six sets of data, demonstrate that the system, through dynamic threshold updates, multi-parameter fusion decision-making, and high-precision imaging processing, solves the core problems of high misjudgment rate during the transition period and reliance on subjective experience in the prior art.

[0115] In the description of this invention, it should be noted that the terms "center," "upper," "lower," "left," "right," "vertical," "horizontal," "inner," and "outer," etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. They are used only for the convenience of describing the invention and for simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on the invention. The terms "first," "second," and "third" are used for descriptive purposes only and should not be construed as indicating or implying relative importance. Furthermore, unless otherwise explicitly specified and limited, the terms "installed," "connected," and "linked" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal connection of two components. Those skilled in the art can understand the specific meaning of the above terms in this invention based on the specific circumstances.

[0116] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A sheep estrus monitoring system based on cell image morphology recognition, characterized in that, It includes a sample acquisition module (100), a microscopic imaging module (200), an image processing module (300), an intelligent analysis module (400), and a monitoring output module (500); The sample collection module (100) includes a cell extraction unit (101) and a staining unit (102). The cell extraction unit (101) is used to obtain sheep vaginal epithelial cell samples, and the staining unit (102) is used to stain the cell samples. The microscopic imaging module (200) is used to perform optical magnification imaging on stained cell samples to generate cell morphology images; The image processing module (300) includes a nuclear localization unit (301) and a morphology recognition unit (302). The nuclear localization unit (301) is used to identify the position of the cell nucleus and detect the state of the nucleus deviating from the center. The morphology recognition unit (302) is used to extract the cell edge contour and quantify the irregular morphological features. The intelligent analysis module (400) uses a preset cell morphology discrimination algorithm to comprehensively analyze the proportion of nuclear deviation from the center and the morphological irregularity index to determine the estrus status of the sheep. The monitoring output module (500) records the judgment results of the intelligent analysis module (400) in real time, generates an estrus status monitoring report and updates it dynamically; The intelligent analysis module (400) determines the estrus status of sheep by including: Estrus status conditions: nuclear deviation > 0.5 and morphological irregularity index > 0.75; Non-estrus state conditions: nuclear deviation ≤ 0.3 or morphological irregularity index ≤ 0.4; Transitional state conditions: kernel deviation ∈ (0.3, 0.5] and morphological irregularity index ∈ (0.4, 0.75], The threshold parameter is dynamically updated based on the statistical distribution of historical data in the monitoring output module (500); The morphology recognition unit (302) performs the following operations: Fourier descriptors of cell contours are extracted using an edge detection algorithm, and the first 20 harmonic components are retained. Calculate the Hausdorff distance between the reconstructed contour and the original contour; The variance of contour curvature is calculated as an index of morphological irregularity, and its expression is as follows: ； Where k i For the curvature of the contour points, The mean curvature is N, the number of contour points is N, and the Hausdorff distance is a measure of the maximum mismatch between two point sets. When the nuclear positioning unit (301) calculates the nuclear deviation: Network segmentation technology was used to segment the cell nucleus and cytoplasm regions; If multiple cell nuclei are detected coexisting in the same cytoplasmic region, the maximum nucleus deviation value is taken. Cell radius is calculated based on the equivalent circle diameter: ； A represents the pixel area of ​​the cytoplasmic region; Locate the cell centroid (Cx, Cy) and the nuclear centroid (Nx, Ny); Calculate the deviation: 。 2. The sheep estrus monitoring system based on cell image morphology recognition according to claim 1, characterized in that, The staining unit (102) uses Wright's staining solution to stain the cell samples for 3-5 minutes.

3. The sheep estrus monitoring system based on cell image morphology recognition according to claim 1, characterized in that, The microscopic imaging module (200) includes: a microscope, a high-speed focusing mechanism, a multispectral LED light source, and an image fusion processor; The image fusion processor synthesizes high signal-to-noise ratio images from different bands and focal plane images.

4. The sheep estrus monitoring system based on cell image morphology recognition according to claim 1, characterized in that, Before the monitoring output module (500) triggers the estrus confirmation report: The average white blood cell density of the sheep over the past 30 days was retrieved from the monitoring output module (500). If the current white blood cell density W c <0.6 If the percentage of keratinocytes is > 65%, then continuous detection will be activated; Otherwise, maintain the single test report mode.

5. The sheep estrus monitoring system based on cell image morphology recognition according to claim 4, characterized in that, The estrus confirmation report includes: A statistical chart of cell subtypes, showing a heatmap of the spatial distribution of keratinocytes, nucleated cells, and leukocytes; The estrus risk coefficient R = α⋅Dev + β⋅Index, where α = 0.7 and β = 0.

3. The reproductive window prediction curve is generated by fitting historical estrus interval data.

6. An electronic device, characterized in that... include: One or more processors; A storage device on which one or more programs are stored; When the one or more programs are executed by the one or more processors, the one or more processors implement the system as described in any one of claims 1-5.

7. A computer-readable storage medium having executable instructions stored thereon, characterized in that... When executed by the processor, this instruction causes the processor to implement the system as described in any one of claims 1-5.

Images