A morphological evaluation method for cattle frozen embryos

Abstract

The present invention relates to the field of image analysis technology, and in particular to a method for morphological evaluation of frozen cattle embryos, the method comprising: obtaining surface images of a frozen cattle embryo to be evaluated and each reference frozen cattle embryo after thawing; determining internal biological characteristic values corresponding to the frozen cattle embryo to be evaluated and each reference frozen cattle embryo; extracting target parameter values of the frozen cattle embryo under each morphological parameter, and determining the evaluation reference of the frozen cattle embryo to be evaluated under each morphological parameter; screening out target morphological parameters; and determining morphological evaluation indicators corresponding to the frozen cattle embryo to be evaluated based on the internal biological characteristic values and the evaluation reference, thereby performing morphological evaluation on the frozen cattle embryo to be evaluated. The present invention realizes morphological evaluation of the frozen cattle embryo by analyzing the target surface image and the reference surface image, and improves the accuracy of morphological evaluation of the frozen cattle embryo.

Description

Technical Field

[0001] The present invention relates to the technical field of image analysis, and in particular to a method for morphological evaluation of cattle frozen embryos. Background Art

[0002] In cattle breeding, cryopreservation often involves preserving embryos at extremely low temperatures. Rapidly cooling the embryos almost halts their metabolism, extending their shelf life and promoting the rapid propagation and genetic improvement of superior breeds. However, during the freeze-thaw process, embryos are often subject to adverse effects such as ice crystal damage and increased cell fragmentation, which can reduce their developmental potential and, in turn, affect the success rate of transplantation. Therefore, morphological assessments of frozen cattle embryos are often necessary to determine their developmental potential.

[0003] Currently, morphological evaluation of cattle frozen embryos is often performed through manual observation. However, when morphological evaluation of cattle frozen embryos is performed through manual observation, the results are often affected by human subjective factors, which may lead to poor accuracy of morphological evaluation of cattle frozen embryos. Summary of the Invention

[0004] In order to solve the technical problem of poor accuracy in morphological evaluation of cattle frozen embryos, the present invention proposes a morphological evaluation method for cattle frozen embryos.

[0005] In a first aspect, the present invention provides a method for morphological evaluation of cattle frozen embryos, the method comprising:

[0006] Acquire a target surface image of the thawed frozen cattle embryo to be evaluated, and a reference surface image of each reference frozen cattle embryo after thaw;

[0007] Determining internal biological characteristic values corresponding to the cattle frozen embryo to be evaluated and each reference cattle frozen embryo based on the grayscale distribution within the target surface image and each reference surface image;

[0008] Extracting target parameter values for each morphological parameter of the frozen cattle embryo to be evaluated and each reference frozen cattle embryo, and determining the evaluation reference of the frozen cattle embryo to be evaluated under each morphological parameter based on all target parameter values and all internal biological characteristic values;

[0009] According to the evaluation reference of the cattle frozen embryos to be evaluated under all morphological parameters, the target morphological parameters are screened out from all morphological parameters;

[0010] According to the internal biological characteristic values corresponding to the frozen cattle embryos to be evaluated and their evaluation reference under the target morphological parameters, the morphological evaluation indicators corresponding to the frozen cattle embryos to be evaluated are determined, and based on the morphological evaluation indicators, a morphological evaluation of the frozen cattle embryos to be evaluated is performed.

[0011] In conjunction with the first aspect above, in one possible implementation, determining the internal biometric characteristic values corresponding to the to-be-evaluated frozen cattle embryo and each reference frozen cattle embryo based on the grayscale distribution within the target surface image and each reference surface image includes:

[0012] performing edge detection and segmentation on the target surface image and the embryo region in each reference surface image to obtain segmentation blocks;

[0013] Determining an internal biological feature value corresponding to the cattle frozen embryo to be evaluated based on a grayscale difference between a background area and an embryo area in the target surface image, and a grayscale difference between different segments in the target surface image;

[0014] Similarly, the internal biological feature value corresponding to each reference cattle frozen embryo is determined based on the grayscale difference between the background area and the embryo area in the reference surface image corresponding to each reference cattle frozen embryo, and the grayscale difference between different segments in the reference surface image corresponding to each reference cattle frozen embryo.

[0015] In conjunction with the first aspect above, in one possible implementation, determining the evaluation reference of the cattle frozen embryo to be evaluated under each morphological parameter based on all target parameter values and all internal biological characteristic values includes:

[0016] Determining any one morphological parameter as a marker morphological parameter, and determining each morphological parameter among all morphological parameters except the marker morphological parameter as a reference morphological parameter;

[0017] The cattle frozen embryo to be evaluated and each reference cattle frozen embryo are collectively referred to as cattle frozen embryos;

[0018] Based on the target parameter value of each cattle frozen embryo under the marked morphological parameter and its target parameter value under each reference morphological parameter, constructing a coordinate point of each cattle frozen embryo between the marked morphological parameter and each reference morphological parameter, wherein the target parameter value under the marked morphological parameter is the ordinate of the coordinate point, and the target parameter value under the reference morphological parameter is the abscissa of the coordinate point;

[0019] Performing curve fitting on the coordinate points between the marker morphological parameter and each reference morphological parameter for all cattle frozen embryos to obtain a parameter change curve between the marker morphological parameter and each reference morphological parameter;

[0020] Determine the ordinate corresponding to the coordinate point of the cattle frozen embryo to be evaluated between the marked morphological parameter and each reference morphological parameter on the parameter change curve as the fitted value of the cattle frozen embryo to be evaluated between the marked morphological parameter and each reference morphological parameter;

[0021] Determining the reliability of the morphological evaluation of the cattle frozen embryo to be evaluated under the marked morphological parameters according to the fitted values between the marked morphological parameters and all reference morphological parameters of the cattle frozen embryo to be evaluated, and the target parameter values under the marked morphological parameters;

[0022] The reference value of the evaluation of the frozen cattle embryo to be evaluated under the marked morphological parameters is determined based on the reliability of the morphological evaluation of the frozen cattle embryo to be evaluated under the marked morphological parameters, the fitting value of the frozen cattle embryo to be evaluated between the marked morphological parameters and all reference morphological parameters, and all internal biological characteristic values.

[0023] In combination with the first aspect above, in one possible implementation, the formula corresponding to the internal biological characteristic value corresponding to the frozen cattle embryo to be evaluated is:

[0024] ; Wherein, N is the internal biological characteristic value corresponding to the cattle frozen embryo to be evaluated; is the absolute value function; G is the mean of the grayscale values corresponding to all pixels in the embryo area in the target surface image; It is the mean of the grayscale values corresponding to all pixels in the background area of the target surface image; is a natural exponential function; M is the number of segments in the target surface image; j and m are the serial numbers of different segments in the target surface image; is the mean of the grayscale values corresponding to all pixels in the jth segmentation block in the target surface image; It is the mean of the grayscale values corresponding to all pixels in the mth segmentation block in the target surface image.

[0025] In combination with the first aspect above, in one possible implementation, the formula corresponding to the reliability of the morphological evaluation of the frozen cattle embryo to be evaluated under the marked morphological parameters is:

[0026] ;

[0027] ; Wherein, E is the reliability of the morphological evaluation of the cattle frozen embryo to be evaluated under the marked morphological parameters; is the natural exponential function; H is the number of reference morphological parameters; t is the sequence number of the reference morphological parameter; It is A and Pearson correlation coefficient between them; A is the data set consisting of the target parameter values of all cattle frozen embryos under the marked morphological parameters; is a dataset consisting of the target parameter values of all cattle frozen embryos under the tth reference morphological parameter; is the image quality interference between the marked morphological parameter and the tth reference morphological parameter of the cattle frozen embryo to be evaluated; is the absolute value function; Y is the target parameter value of the cattle frozen embryo to be evaluated under the marked morphological parameters; is the fitted value between the marker morphological parameter and the tth reference morphological parameter of the cattle frozen embryo to be evaluated.

[0028] In combination with the first aspect above, in a possible implementation, determining the evaluation reference of the cattle frozen embryo to be evaluated under the marked morphological parameters according to the morphological evaluation reliability of the cattle frozen embryo to be evaluated under the marked morphological parameters, the fitting value of the cattle frozen embryo to be evaluated between the marked morphological parameters and all reference morphological parameters, and all internal biological feature values, includes:

[0029] Determine the data set consisting of the fitting values of the cattle frozen embryo to be evaluated between the marked morphological parameters and all reference morphological parameters as the fitting value set of the cattle frozen embryo to be evaluated under the marked morphological parameters;

[0030] A data set consisting of internal biological characteristic values corresponding to all cattle frozen embryos is determined as an internal biological characteristic value set;

[0031] Based on the morphological evaluation reliability and fitting value set of the cattle frozen embryo to be evaluated under the marked morphological parameters, as well as the internal biological feature value set, the evaluation reference of the cattle frozen embryo to be evaluated under the marked morphological parameters is determined.

[0032] In conjunction with the first aspect above, in one possible implementation, the formula corresponding to the evaluation reference of the cattle frozen embryo to be evaluated under the marked morphological parameters is:

[0033] ; Wherein, T is the evaluation reference of the cattle frozen embryo to be evaluated under the marked morphological parameters; is the normalization function; is the Pearson correlation coefficient between XN and XY; XN is the set of internal biological feature values; XY is the fitted value set of the cattle frozen embryo to be evaluated under the marked morphological parameters; E is the reliability of the morphological evaluation of the cattle frozen embryo to be evaluated under the marked morphological parameters.

[0034] In combination with the first aspect above, in one possible implementation, the target morphological parameters are screened out from all morphological parameters based on the evaluation reference of the cattle frozen embryo to be evaluated under all morphological parameters, including:

[0035] The morphological parameter with the greatest reference value for the evaluation of the frozen cattle embryo to be evaluated is selected from all morphological parameters and used as the target morphological parameter.

[0036] In conjunction with the first aspect above, in one possible implementation, determining the morphological evaluation index corresponding to the cattle frozen embryo to be evaluated based on the internal biological characteristic value corresponding to the cattle frozen embryo to be evaluated and its evaluation reference under the target morphological parameters includes:

[0037] The morphological evaluation indicators corresponding to the cattle frozen embryos to be evaluated are determined based on the internal biological characteristic values corresponding to the cattle frozen embryos to be evaluated and their evaluation reference under the target morphological parameters, the fitting values of the cattle frozen embryos to be evaluated between the target morphological parameters and all other morphological parameters, and the target parameter values of the cattle frozen embryos to be evaluated under the target morphological parameters.

[0038] In combination with the first aspect above, in one possible implementation, the formula corresponding to the morphological evaluation index corresponding to the cattle frozen embryo to be evaluated is:

[0039] ; Wherein, L is the morphological evaluation index corresponding to the cattle frozen embryo to be evaluated; is a normalization function; N is the internal biological characteristic value corresponding to the cattle frozen embryo to be evaluated; ZT is the evaluation reference of the cattle frozen embryo to be evaluated under the target morphological parameters; It is the absolute value function; is the target parameter value of the cattle frozen embryo to be evaluated under the target morphological parameter; ZY is the mean of the fitting values between the target morphological parameter and all other morphological parameters of the cattle frozen embryo to be evaluated.

[0040] In a second aspect, the present invention provides a cattle frozen embryo morphology evaluation system, the system comprising:

[0041] An image acquisition module is used to acquire a target surface image of the frozen cattle embryo to be evaluated after thawing, and a reference surface image of each reference frozen cattle embryo after thawing;

[0042] An internal biometric value determination module is used to determine the internal biometric value corresponding to the cattle frozen embryo to be evaluated and each reference cattle frozen embryo based on the grayscale distribution within the target surface image and each reference surface image;

[0043] an extraction and determination module, configured to extract target parameter values for the cattle frozen embryo to be evaluated and each reference cattle frozen embryo under each morphological parameter, and determine the evaluation reference of the cattle frozen embryo to be evaluated under each morphological parameter based on all target parameter values and all internal biological characteristic values;

[0044] A parameter screening module is used to screen target morphological parameters from all morphological parameters based on the evaluation reference of the cattle frozen embryos to be evaluated under all morphological parameters;

[0045] An evaluation module is determined, which is used to determine the morphological evaluation indicators corresponding to the cattle frozen embryos to be evaluated based on the internal biological characteristic values corresponding to the cattle frozen embryos to be evaluated and their evaluation reference under the target morphological parameters, and to perform morphological evaluation on the cattle frozen embryos to be evaluated based on the morphological evaluation indicators.

[0046] In a third aspect, a server is provided, comprising a memory and a processor. The memory is configured to store executable program code, and the processor is configured to call and execute the executable program code from the memory, so that the device executes the method of the first aspect or any possible implementation of the first aspect.

[0047] In a fourth aspect, a computer program product is provided, comprising: a computer program code, which, when executed on a computer, enables the computer to execute the method in the first aspect or any possible implementation of the first aspect.

[0048] In a fifth aspect, a computer-readable storage medium is provided, which stores a computer program code. When the computer program code runs on a computer, the computer executes the method in the above-mentioned first aspect or any possible implementation of the first aspect.

[0049] The present invention has the following beneficial effects:

[0050] The present invention provides a method for morphological assessment of cattle frozen embryos. By analyzing a target surface image and a reference surface image, the method achieves morphological assessment of cattle frozen embryos, thereby resolving the technical problem of poor accuracy in morphological assessment of cattle frozen embryos and improving the accuracy of morphological assessment of cattle frozen embryos. Compared to manual observation for morphological assessment of cattle frozen embryos, the present invention comprehensively considers multiple features related to morphological assessment of cattle frozen embryos, such as internal biological characteristic values, morphological parameters, assessment references, and morphological assessment indicators, when performing morphological assessment of cattle frozen embryos. This allows for morphological assessment of cattle frozen embryos to be assessed, reduces the influence of human subjective factors to a certain extent, and thereby improves the accuracy of morphological assessment of cattle frozen embryos. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] In order to more clearly illustrate the technical solutions and advantages of the embodiments of the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the prior art descriptions. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0052] Figure 1 This is a flow chart of a method for morphological evaluation of cattle frozen embryos of the present invention;

[0053] Figure 2 This is a schematic diagram of the structure of a cattle frozen embryo morphology evaluation system of the present invention;

[0054] Figure 3 The figure is a structural diagram of a computer device of the present invention. DETAILED DESCRIPTION

[0055] To further illustrate the technical means and effects employed by the present invention to achieve its intended objectives, the following, in conjunction with the accompanying drawings and preferred embodiments, describes in detail the specific implementations, structures, features, and effects of the technical solutions proposed by the present invention. In the following description, references to "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. Furthermore, specific features, structures, or characteristics of one or more embodiments may be combined in any suitable manner.

[0056] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

[0057] refer to Figure 1, shows the process of some embodiments of a method for morphological evaluation of cattle frozen embryos according to the present invention. The method for morphological evaluation of cattle frozen embryos comprises the following steps:

[0058] Step S1, obtaining a target surface image of the cattle frozen embryo to be evaluated after thawing, and a reference surface image of each reference cattle frozen embryo after thawing.

[0059] The cattle frozen embryo to be evaluated may be a cattle frozen embryo to be subjected to morphological evaluation. The cattle frozen embryo may be a cattle embryo that has been cryopreserved. The target surface image may be a grayscale image of the thawed cattle frozen embryo to be evaluated under a microscope. The reference cattle frozen embryo may be another cattle frozen embryo used to assist in the morphological evaluation of the cattle frozen embryo to be evaluated. The reference surface image may be a grayscale image of the thawed reference cattle frozen embryo under a microscope.

[0060] As an example, cattle embryos can be thawed from liquid nitrogen and quickly rinsed in preheated culture medium to remove residual cryoprotectant. The thawed embryos are evenly distributed on a glass slide and imaged using a high-resolution inverted microscope. One of these embryos, designated for morphological evaluation, is designated the target frozen embryo, while the others are designated the reference frozen embryos. To ensure consistent image acquisition, the microscope's lighting, magnification, and acquisition environment are standardized to ensure consistent resolution and contrast for each sample. The captured raw embryo images are preprocessed. Color images can be converted to grayscale to reduce data dimensionality and simplify processing. Median filtering can be used to denoise the images to eliminate interference caused by uneven illumination or instrument noise during acquisition. Histogram equalization can be used to enhance image contrast, clarifying the embryo's outlines and cellular structures. The resulting image of the target frozen embryo is designated the target surface image, while the resulting image of the reference frozen embryo is designated the reference surface image.

[0061] Step S2: determining the internal biological characteristic values corresponding to the cattle frozen embryo to be evaluated and each reference cattle frozen embryo according to the grayscale distribution in the target surface image and each reference surface image.

[0062] It is important to note that the morphological characteristics of frozen cattle embryos can be observed and quantified in surface images to assess embryo quality and developmental potential, thereby conducting a morphological assessment of the embryo. The internal structure of the embryo often directly reflects its biological state and developmental potential. Even with suboptimal image quality, the internal structural features still possess strong biological significance and stability, making them an important basis for assessing embryo quality.

[0063] As an example, this step may include the following steps:

[0064] In the first step, edge detection and segmentation are performed on the target surface image and the embryo region in each reference surface image to obtain segmentation blocks.

[0065] The embryo region in the target surface image may be a region of the frozen cattle embryo to be evaluated in the target surface image, and the embryo region in the reference surface image may be a region of the frozen cattle embryo to be evaluated in the reference surface image.

[0066] For example, the Sobel bidirectional edge detection method can be used to detect the embryo contours in the target surface image and each reference surface image, and morphological operations can be performed to repair the edges to ensure the connectivity of the embryonic region, thereby segmenting the embryonic region representing the cattle embryo. The embryonic region can be segmented by edge detection using the Canny edge detection segmentation algorithm to obtain multiple segmentation blocks.

[0067] In the second step, based on the grayscale difference between the background area and the embryo area in the target surface image, and the grayscale difference between different segments in the target surface image, the internal biological feature value corresponding to the frozen cattle embryo to be evaluated is determined.

[0068] The background area may be an area other than the embryo area in the image.

[0069] For example, the formula for determining the internal biological characteristic value corresponding to the frozen cattle embryo to be evaluated can be:

[0070] ; Wherein, N is the internal biological characteristic value corresponding to the cattle frozen embryo to be evaluated. is the absolute value function. G is the mean grayscale value of all pixels in the embryo region of the target surface image. It is the mean of the grayscale values corresponding to all pixels in the background area of the target surface image. is a natural exponential function. M is the number of segments in the target surface image. j and m are the serial numbers of different segments in the target surface image. It is the mean of the grayscale values corresponding to all pixels in the jth segmentation block in the target surface image. It is the mean of the grayscale values corresponding to all pixels in the mth segmentation block in the target surface image.

[0071] It should be noted that if the image quality is affected, it may cause problems in the edge extraction of the embryo. At this time, the integrity and regularity of the embryo's contour are often difficult to judge specifically, while the extraction of the embryo's internal structural characteristics is relatively less disturbed. At the same time, the internal structure of the embryo often reflects its biological state. In the normal embryonic development process, the regularity of the internal structure is often an important sign of embryonic health. Any abnormal cell division, deformity of cell morphology or disorder of cell arrangement will often affect the development of the embryo and even lead to developmental stagnation or abnormality. Therefore, the internal structural characteristics of the embryo can serve as an important basis for morphological evaluation. When When the value is larger, it often indicates that the grayscale difference between the embryo region and the background region in the target surface image is greater, and the color contrast between the embryo represented by the embryo region in the target surface image and the background is greater, and the internal biological characteristics of the embryo represented by the embryo region in the target surface image are relatively more significant. The larger the value is, the greater the grayscale difference between the jth segmentation block and the mth segmentation block in the target surface image. The smaller the value, the smaller the grayscale difference between different segments in the target surface image, the more uniform the grayscale distribution within the embryo region in the target surface image, the more regular the cell arrangement within the embryo region in the target surface image, the more normal the cell division within the embryo region, the better the morphological characteristics within the embryo region, and the more significant the internal biological characteristics of the embryo represented by the embryo region in the target surface image. Therefore, when N is larger, the more significant the internal biological characteristics of the embryo represented by the embryo region in the target surface image, the better the morphological characteristics within the embryo region, and the higher the survival rate of the cattle frozen embryos to be evaluated.

[0072] In the third step, similarly, the internal biological feature value corresponding to each reference cattle frozen embryo is determined based on the grayscale difference between the background area and the embryo area in the reference surface image corresponding to each reference cattle frozen embryo, and the grayscale difference between different segments in the reference surface image corresponding to each reference cattle frozen embryo.

[0073] It should be noted that the method for obtaining the internal biometric characteristic values corresponding to the reference cattle frozen embryos is the same as the method for obtaining the internal biometric characteristic values corresponding to the cattle frozen embryos to be evaluated, and will not be repeated here.

[0074] Step S3, extracting the target parameter values of the cattle frozen embryo to be evaluated and each reference cattle frozen embryo under each morphological parameter, and determining the evaluation reference of the cattle frozen embryo to be evaluated under each morphological parameter based on all target parameter values and all internal biological characteristic values.

[0075] Among them, the morphological parameters can be parameters related to the morphology of the cattle frozen embryos. The number of morphological parameters can be pre-set, which can be 4. For example, the morphological parameters can be, but are not limited to: embryo area parameter, roundness parameter, zona pellucida thickness parameter, and zona pellucida integrity parameter. The target parameter value under the morphological parameter is the numerical value under the morphological parameter. For example, the target parameter value under the embryo area parameter can be embryo area. The target parameter value under the roundness parameter can be roundness. The target parameter value under the zona pellucida thickness parameter can be zona pellucida thickness. The target parameter value under the zona pellucida integrity parameter can be zona pellucida integrity.

[0076] Embryonic area typically refers to the area occupied by the embryo in a cross-section or two-dimensional plane observed under a microscope. Roundness is a measure of the regularity of the embryo's shape. It is calculated by comparing the actual shape of the embryo to that of a perfect circle and is typically expressed on a scale of 0 to 1, with 1 indicating a perfect circle. The zona pellucida is a glycoprotein membrane on the outside of the embryo that surrounds the cells and protects them from the external environment. The thickness of the zona pellucida refers to its width. Zona pellucida integrity refers to whether the zona pellucida is intact and its structure is continuous, without ruptures or defects.

[0077] It should be noted that judging embryo quality by its internal structural characteristics can reduce the evaluation error caused by image quality. However, observation of a single structure may not fully reflect the overall developmental potential of the embryo. Frozen cattle embryos may experience local damage to the cell membrane or changes in internal cell color during the thawing process. A comprehensive evaluation based on the external morphological characteristics of the embryo is also required. The contrast blur caused by image quality may make it impossible to accurately obtain the edge contour of the embryo, resulting in errors in the extracted external morphological parameters. Therefore, the inherent correlation between embryo morphological parameters can be analyzed, and the complementarity between different indicators can be utilized to correct the errors caused by image quality problems through multivariate evaluation, thereby more accurately predicting the actual developmental potential of the embryo.

[0078] As an example, this step may include the following steps:

[0079] In the first step, the target parameter values of each morphological parameter of the cattle frozen embryos to be evaluated and each reference cattle frozen embryo were extracted.

[0080] For example, Python (Python Programming Language, a high-level programming language) and OpenCV (Open Source Computer Vision Library, an operating system) can be used to automatically extract target parameter values of cattle frozen embryos under different morphological parameters, such as embryo area, roundness, zona pellucida thickness, and zona pellucida integrity.

[0081] In the second step, any morphological parameter is determined as a marker morphological parameter, and each morphological parameter among all morphological parameters except the marker morphological parameter is determined as a reference morphological parameter.

[0082] In the third step, the above-mentioned cattle frozen embryos to be evaluated and each reference cattle frozen embryo are collectively referred to as cattle frozen embryos.

[0083] The fourth step is to construct the coordinate points of each cattle frozen embryo between the above-mentioned marked morphological parameters and each reference morphological parameter based on the target parameter value of each cattle frozen embryo under the above-mentioned marked morphological parameters and its target parameter value under each reference morphological parameter.

[0084] The target parameter value under the marked morphological parameter may be the ordinate of the coordinate point, and the target parameter value under the reference morphological parameter may be the abscissa of the coordinate point.

[0085] For example, if the marked morphological parameter is the embryo area parameter and a reference morphological parameter is the roundness parameter, then the horizontal coordinate of the coordinate point of the cattle frozen embryo between the embryo area parameter and the roundness parameter can be the roundness of the cattle frozen embryo, and its vertical coordinate can be the embryo area corresponding to the cattle frozen embryo.

[0086] The fifth step is to perform curve fitting on the coordinate points of all cattle frozen embryos between the above-mentioned marked morphological parameters and each reference morphological parameter to obtain a parameter change curve between the above-mentioned marked morphological parameters and each reference morphological parameter.

[0087] For example, if the marked morphological parameter is the embryo area parameter and one reference morphological parameter is the roundness parameter, then the parameter change curve of the cattle frozen embryo between the embryo area parameter and the roundness parameter can be: a curve obtained by curve fitting the coordinate points between the embryo area parameter and the roundness parameter of all cattle frozen embryos.

[0088] It should be noted that image quality often affects the accuracy of morphological parameter extraction. To evaluate and correct errors using external morphological parameters, it is often necessary to ensure the reliability of the extracted data. The morphological parameters of frozen cattle embryos are generally not independent but rather have certain mathematical relationships. There are often intrinsic correlations between embryonic morphological parameters. For example, an intact zona pellucida maintains the morphological integrity of the embryo and also maintains a high degree of roundness. A damaged zona pellucida may lead to irregular embryo morphology and reduced roundness. In other words, when image quality is high, there are often intrinsic correlations between the different morphological parameters detected. The parameter change curve between the marker morphological parameter and each reference morphological parameter can characterize the changing relationship between the marker morphological parameter and each reference morphological parameter.

[0089] The sixth step is to determine the vertical coordinate corresponding to the coordinate point of the above-mentioned yellow cattle frozen embryo to be evaluated between the above-mentioned marked morphological parameters and each reference morphological parameter on the parameter change curve as the fitting value of the above-mentioned yellow cattle frozen embryo to be evaluated between the above-mentioned marked morphological parameters and each reference morphological parameter.

[0090] Among them, the ordinate of the corresponding point on the parameter change curve to which the coordinate point belongs is the fitting value corresponding to the coordinate point.

[0091] The seventh step is to determine the reliability of the morphological evaluation of the above-mentioned cattle frozen embryos to be evaluated under the above-mentioned marked morphological parameters based on the fitting values between the above-mentioned marked morphological parameters and all reference morphological parameters, as well as the target parameter values under the above-mentioned marked morphological parameters.

[0092] For example, the formula for determining the reliability of the morphological evaluation of the frozen cattle embryo to be evaluated under the above-mentioned marked morphological parameters can be:

[0093] ;

[0094] ; Wherein, E is the reliability of morphological evaluation of the frozen cattle embryos to be evaluated under the marked morphological parameters. is the natural exponential function. H is the number of reference morphological parameters. t is the ordinal number of the reference morphological parameter. It is A and The Pearson correlation coefficient between them is . A is a dataset consisting of the target parameter values of all cattle frozen embryos under the marked morphological parameters. It is a dataset consisting of the target parameter values of all cattle frozen embryos under the tth reference morphological parameter. is the image quality interference between the marked morphological parameter and the tth reference morphological parameter of the cattle frozen embryo to be evaluated. is the absolute value function. Y is the target parameter value of the cattle frozen embryo under the marked morphological parameters to be evaluated. is the fitted value between the marker morphological parameter and the tth reference morphological parameter of the cattle frozen embryo to be evaluated.

[0095] It should be noted that the internal structural information of the embryo reflects the cell division of the embryo and is an important basis for the morphological evaluation of the embryo. However, due to the limitations of freezing technology, frozen embryos may have the following limitations: for example, the freezing fluid may affect the osmotic pressure difference between the inside and outside of the embryonic cell membrane, causing slight changes in the color inside the embryo. The internal biological characteristics obtained above are based on color contrast. At the same time, due to the influence of image quality, the final morphological evaluation results may still have certain errors. Therefore, error correction can be performed through external morphological characteristics. The larger the value is, the greater the deviation between the target parameter value and the fitting value of the cattle frozen embryo under the marked morphological parameters is, which often indicates that the image quality of the target surface image is relatively worse, and the identified morphological abnormalities are more likely to be caused by image quality, which often indicates that the evaluation reliability of the marked morphological parameters is relatively poor. Can be used as When When the larger the value, it often means that A and The greater the correlation between the changes in E and , the more likely there is a correlation between the marker morphological parameter and the tth reference morphological parameter. Therefore, a larger E indicates that the extracted marker morphological parameters of the evaluated cattle frozen embryo are relatively more accurate, and the morphological evaluation of the evaluated cattle frozen embryo under the marker morphological parameters is more reliable.

[0096] The eighth step is to determine the reference value of the evaluation of the above-mentioned cattle frozen embryos under the above-mentioned marked morphological parameters based on the reliability of the morphological evaluation of the above-mentioned cattle frozen embryos under the above-mentioned marked morphological parameters, the fitting values between the above-mentioned marked morphological parameters and all reference morphological parameters, and all internal biological characteristic values.

[0097] It should be noted that during the actual image acquisition process of frozen cattle embryos, problems such as noise, low contrast, and blurred edges can lead to inaccurate extraction of certain embryo morphological parameters, resulting in biased assessment results. By establishing intrinsic correlation curves between parameters and leveraging redundant information between parameters, outliers caused by image quality issues can be corrected. This improves the accuracy of frozen cattle embryo morphological assessments, reduces the impact of different acquisition conditions on assessment results, and comprehensively improves the accuracy of predicting embryo developmental potential.

[0098] For example, determining the evaluation reference of the above-mentioned cattle frozen embryo to be evaluated under the above-mentioned marked morphological parameters may include the following sub-steps:

[0099] In the first sub-step, a data set consisting of fitting values of the above-mentioned cattle frozen embryos to be evaluated between the above-mentioned marked morphological parameters and all reference morphological parameters is determined as a fitting value set of the above-mentioned cattle frozen embryos to be evaluated under the above-mentioned marked morphological parameters.

[0100] In the second sub-step, a data set consisting of internal biological characteristic values corresponding to all cattle frozen embryos is determined as an internal biological characteristic value set.

[0101] The third sub-step is to determine the evaluation reference of the above-mentioned cattle frozen embryos to be evaluated under the above-mentioned marked morphological parameters based on the morphological evaluation reliability and fitting value set of the above-mentioned cattle frozen embryos to be evaluated under the above-mentioned marked morphological parameters, as well as the internal biological feature value set.

[0102] It should be noted that the changes in the morphological parameters of frozen cattle embryos are often synchronized. Due to the interference of image quality, the internal structural information of the embryo that is less affected can be selected as the main basis for morphological evaluation. At the same time, in order to reduce the error caused by image quality, it is also necessary to combine external morphological features for auxiliary evaluation. For example, during the freezing process, due to the limitations of freezing technology, the internal cells of the embryo become abnormal. The freezing fluid increases the osmotic pressure difference of the embryo, and its cells severely lose water and shrink, resulting in a smaller embryo area. The calculated internal biological characteristics will also be reduced accordingly due to the reduced contrast with the external background color, which will often affect other morphological parameters. It is necessary to verify and obtain a type of morphological parameter with the most stable relationship with the internal biological characteristics of the embryo. The evaluation results can be corrected by the morphological parameters with the most stable relationship. Therefore, based on the synchronization of changes in the internal biological characteristics of the embryo and the morphological parameter data, the evaluation reference of each type of morphological parameter of each embryo can be obtained.

[0103] For example, the formula for determining the evaluation reference of the cattle frozen embryo under the marked morphological parameters can be:

[0104] ; Wherein, T is the evaluation reference of the cattle frozen embryo under the marked morphological parameters. is the normalization function. is the Pearson correlation coefficient between XN and XY. XN is the set of internal biological feature values. XY is the set of fitted values for the cattle frozen embryos under the labeled morphological parameters. E is the reliability of the morphological assessment of the cattle frozen embryos under the labeled morphological parameters.

[0105] It should be noted that when When E is larger, it is often shown that the correlation between the internal biological characteristics of the embryo and the labeled morphological parameters is larger, and it is often shown that the change between the internal biological characteristics of the embryo and the labeled morphological parameter data has a certain synchronization. When E is larger, it is often shown that the labeled morphological parameters of the cattle frozen embryo to be evaluated extracted are relatively more accurate, and it is often shown that the morphological assessment reliability of the cattle frozen embryo to be evaluated under the labeled morphological parameters is larger. Therefore, when T is larger, it is often shown that the accuracy of the labeled morphological parameter data extraction of the cattle frozen embryo to be evaluated is relatively higher, and it is often shown that the morphological assessment reliability of the cattle frozen embryo to be evaluated under the labeled morphological parameters is larger.

[0106] Step S4: selecting target morphological parameters from all morphological parameters based on the evaluation reference of the cattle frozen embryos to be evaluated under all morphological parameters.

[0107] The evaluation reference of the frozen cattle embryo to be evaluated under the target morphological parameters may be equal to the maximum value of the evaluation reference of the frozen cattle embryo to be evaluated under all morphological parameters.

[0108] As an example, the morphological parameter with the greatest reference value for the evaluation of the above-mentioned frozen cattle embryo to be evaluated can be screened out from all morphological parameters and used as the target morphological parameter.

[0109] Step S5: determining the morphological evaluation index corresponding to the cattle frozen embryo to be evaluated according to the internal biological characteristic value corresponding to the cattle frozen embryo to be evaluated and its evaluation reference under the target morphological parameters, and performing a morphological evaluation on the cattle frozen embryo to be evaluated based on the morphological evaluation index.

[0110] As an example, this step may include the following steps:

[0111] The first step is to determine the morphological evaluation indicators corresponding to the cattle frozen embryos to be evaluated based on the internal biological characteristic values corresponding to the cattle frozen embryos to be evaluated and their evaluation references under the target morphological parameters, the fitting values between the above-mentioned target morphological parameters and all other morphological parameters of the cattle frozen embryos to be evaluated, and the target parameter values of the cattle frozen embryos to be evaluated under the target morphological parameters.

[0112] It should be noted that during the morphological assessment of frozen cattle embryos, image quality issues can lead to errors in the extraction of morphological parameters, thus affecting the accuracy of embryo quality assessment. Based on the intrinsic relationships between embryo morphological parameters, statistical correlations between individual parameters can be analyzed to identify mappings between relatively stable parameters and closely related morphological parameters, thereby correcting the morphological assessment results. Relatively stable parameters are those that are least affected by image quality, i.e., target morphological parameters. This can effectively reduce assessment errors caused by image quality issues and improve the reliability and accuracy of frozen cattle embryo morphological assessment.

[0113] For example, the formula for determining the morphological evaluation index corresponding to the frozen cattle embryo to be evaluated can be:

[0114] ; Wherein, L is the morphological evaluation index corresponding to the cattle frozen embryo to be evaluated. is a normalization function. N is the internal biological characteristic value corresponding to the cattle frozen embryo to be evaluated. ZT is the evaluation reference of the cattle frozen embryo to be evaluated under the target morphological parameters. It is the absolute value function. is the target parameter value of the cattle frozen embryo under the target morphological parameter. ZY is the mean of the fitted values between the target morphological parameter and all other morphological parameters of the cattle frozen embryo under evaluation.

[0115] It should be noted that when N is larger, it often means that the internal biological characteristics of the embryo represented by the embryo region in the target surface image are relatively more significant, and often means that the morphological characteristics inside the embryo region are relatively better, and often means that the survival rate of the cattle frozen embryo to be evaluated is relatively higher. When ZT is larger, it often means that the accuracy of the target morphological parameter data extraction of the cattle frozen embryo to be evaluated is relatively higher, and often means that the morphological evaluation reliability of the cattle frozen embryo to be evaluated under the target morphological parameters is greater. When A larger value indicates that the target morphological parameter, which is the most relevant for the internal structural characteristics of the evaluated cattle frozen embryo, has deviated significantly from image quality, indicating more severe image quality issues and potentially greater errors in the corresponding internal biological characteristics. This indicates that some anomalies are more likely to be caused by image quality and require stronger correction. Therefore, a larger value for L indicates that the morphological characteristics of the evaluated cattle frozen embryo are relatively better, their developmental potential is relatively greater, and their survival rate is relatively higher.

[0116] The second step is to conduct a morphological evaluation of the cattle frozen embryos based on the morphological evaluation indicators.

[0117] For example, if the morphological evaluation index is greater than a preset evaluation threshold, the morphological characteristics of the cattle frozen embryo to be evaluated are determined to be good, which often indicates that the survival rate of the cattle frozen embryo to be evaluated is relatively high. Otherwise, the survival rate is relatively low. The preset evaluation threshold can be a pre-set threshold, which can be 0.6.

[0118] refer to Figure 2 Based on the same inventive concept as the above method embodiment, the present invention provides a cattle frozen embryo morphology evaluation system, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the computer program is executed by the processor, the steps of a cattle frozen embryo morphology evaluation method may specifically include:

[0119] An image acquisition module 201 is used to acquire a target surface image of the thawed frozen cattle embryo to be evaluated, and a reference surface image of each reference frozen cattle embryo after thaw;

[0120] An internal biometric value determination module 202 is configured to determine the internal biometric value corresponding to the cattle frozen embryo to be evaluated and each reference cattle frozen embryo based on the grayscale distribution within the target surface image and each reference surface image;

[0121] An extraction and determination module 203 is configured to extract target parameter values for the cattle frozen embryo to be evaluated and each reference cattle frozen embryo under each morphological parameter, and determine the evaluation reference of the cattle frozen embryo to be evaluated under each morphological parameter based on all target parameter values and all internal biological characteristic values;

[0122] A parameter screening module 204 is configured to screen target morphological parameters from all morphological parameters based on the evaluation reference of the cattle frozen embryos to be evaluated under all morphological parameters;

[0123] The evaluation module 205 is determined to determine the morphological evaluation index corresponding to the cattle frozen embryo to be evaluated based on the internal biological characteristic value corresponding to the cattle frozen embryo to be evaluated and its evaluation reference under the target morphological parameters, and perform a morphological evaluation on the cattle frozen embryo to be evaluated based on the morphological evaluation index.

[0124] Figure 3 FIG. 1 is a schematic diagram of the structure of a computer device provided by an embodiment of the present invention. For example, Figure 3 As shown, the computer device 300 includes: a memory 301, a processor 302, and a computer program 303 stored in the memory 301 and running on the processor 302, wherein when the processor 302 executes the computer program 303, the computer device can execute any one of the cattle frozen embryo morphology evaluation methods introduced above.

[0125] Based on the same inventive concept as the above-described method embodiments, the present invention provides a server comprising a memory and a processor. The memory is configured to store executable program code, and the processor is configured to retrieve and execute the executable program code from the memory, thereby enabling the device to perform any of the above-described methods for evaluating cattle frozen embryo morphology.

[0126] Based on the same inventive concept as the above-mentioned method embodiment, the present invention provides a computer program product, which includes: computer program code, which, when running on a computer, enables the computer to execute any of the above-mentioned cattle frozen embryo morphology evaluation methods.

[0127] Based on the same inventive concept as the above-mentioned method embodiment, the present invention provides a computer-readable storage medium, which stores computer program code. When the computer program code runs on a computer, the computer executes any one of the above-mentioned cattle frozen embryo morphology evaluation methods.

[0128] In summary, compared with the morphological evaluation of cattle frozen embryos through manual observation, the present invention comprehensively considers multiple characteristics related to the morphological evaluation of cattle frozen embryos when performing morphological evaluation of cattle frozen embryos, such as internal biological characteristic values, morphological parameters, evaluation references and morphological evaluation indicators, thereby realizing the morphological evaluation of cattle frozen embryos to be evaluated, and reducing the influence of human subjective factors to a certain extent, thereby improving the accuracy of morphological evaluation of cattle frozen embryos.

[0129] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the scope of the technical solutions of the embodiments of the present invention, and should all be included in the scope of protection of the present invention.

Claims

1. A method for morphological evaluation of frozen cattle embryos, characterized in that: The following steps are involved: Acquire a target surface image of the thawed frozen cattle embryo to be evaluated, and a reference surface image of each reference frozen cattle embryo after thaw; Determining internal biological characteristic values corresponding to the cattle frozen embryo to be evaluated and each reference cattle frozen embryo based on the grayscale distribution within the target surface image and each reference surface image; Extracting target parameter values for each morphological parameter of the frozen cattle embryo to be evaluated and each reference frozen cattle embryo, and determining the evaluation reference of the frozen cattle embryo to be evaluated under each morphological parameter based on all target parameter values and all internal biological characteristic values; According to the evaluation reference of the cattle frozen embryos to be evaluated under all morphological parameters, the target morphological parameters are screened out from all morphological parameters; Determine the morphological evaluation indicators corresponding to the cattle frozen embryos to be evaluated based on the internal biological characteristic values corresponding to the cattle frozen embryos to be evaluated and their evaluation reference under the target morphological parameters, and perform a morphological evaluation on the cattle frozen embryos to be evaluated based on the morphological evaluation indicators; The evaluation reference of the cattle frozen embryo to be evaluated under each morphological parameter is determined based on all target parameter values and all internal biological characteristic values, including: Determining any one morphological parameter as a marker morphological parameter, and determining each morphological parameter among all morphological parameters except the marker morphological parameter as a reference morphological parameter; The cattle frozen embryo to be evaluated and each reference cattle frozen embryo are collectively referred to as cattle frozen embryos; Based on the target parameter value of each cattle frozen embryo under the marked morphological parameter and its target parameter value under each reference morphological parameter, constructing a coordinate point of each cattle frozen embryo between the marked morphological parameter and each reference morphological parameter, wherein the target parameter value under the marked morphological parameter is the ordinate of the coordinate point, and the target parameter value under the reference morphological parameter is the abscissa of the coordinate point; Performing curve fitting on the coordinate points between the marker morphological parameter and each reference morphological parameter for all cattle frozen embryos to obtain a parameter change curve between the marker morphological parameter and each reference morphological parameter; Determine the ordinate corresponding to the coordinate point of the cattle frozen embryo to be evaluated between the marked morphological parameter and each reference morphological parameter on the parameter change curve as the fitted value of the cattle frozen embryo to be evaluated between the marked morphological parameter and each reference morphological parameter; Determining the reliability of the morphological evaluation of the cattle frozen embryo to be evaluated under the marked morphological parameters according to the fitted values between the marked morphological parameters and all reference morphological parameters of the cattle frozen embryo to be evaluated, and the target parameter values under the marked morphological parameters; The reference value of the evaluation of the frozen cattle embryo to be evaluated under the marked morphological parameters is determined based on the reliability of the morphological evaluation of the frozen cattle embryo to be evaluated under the marked morphological parameters, the fitting value of the frozen cattle embryo to be evaluated between the marked morphological parameters and all reference morphological parameters, and all internal biological characteristic values.

2. The method for morphological evaluation of cattle frozen embryos according to claim 1, wherein: Determining internal biological characteristic values corresponding to the cattle frozen embryo to be evaluated and each reference cattle frozen embryo based on the grayscale distribution within the target surface image and each reference surface image includes: performing edge detection and segmentation on the target surface image and the embryo region in each reference surface image to obtain segmentation blocks; Determining an internal biological feature value corresponding to the cattle frozen embryo to be evaluated based on a grayscale difference between a background area and an embryo area in the target surface image, and a grayscale difference between different segments in the target surface image; Similarly, the internal biological feature value corresponding to each reference cattle frozen embryo is determined based on the grayscale difference between the background area and the embryo area in the reference surface image corresponding to each reference cattle frozen embryo, and the grayscale difference between different segments in the reference surface image corresponding to each reference cattle frozen embryo.

3. A cattle frozen embryo morphology evaluation method according to claim 2, characterized in that: The formula for the internal biological characteristic value corresponding to the frozen cattle embryo to be evaluated is: ; Wherein, N is the internal biological characteristic value corresponding to the cattle frozen embryo to be evaluated; is the absolute value function; G is the mean of the grayscale values corresponding to all pixels in the embryo area in the target surface image; It is the mean of the grayscale values corresponding to all pixels in the background area of the target surface image; is a natural exponential function; M is the number of segments in the target surface image; j and m are the serial numbers of different segments in the target surface image; is the mean of the grayscale values corresponding to all pixels in the jth segmentation block in the target surface image; It is the mean of the grayscale values corresponding to all pixels in the mth segmentation block in the target surface image.

4. The method for morphological evaluation of cattle frozen embryos according to claim 1, wherein: The formula corresponding to the reliability of the morphological evaluation of the frozen cattle embryo to be evaluated under the aforementioned marker morphological parameters is: ； ; Wherein, E is the reliability of the morphological evaluation of the cattle frozen embryo to be evaluated under the marked morphological parameters; is the natural exponential function; H is the number of reference morphological parameters; t is the sequence number of the reference morphological parameter; It is A and Pearson correlation coefficient between them; A is the data set consisting of the target parameter values of all cattle frozen embryos under the marked morphological parameters; is a dataset consisting of the target parameter values of all cattle frozen embryos under the tth reference morphological parameter; is the image quality interference between the marked morphological parameter and the tth reference morphological parameter of the cattle frozen embryo to be evaluated; is the absolute value function; Y is the target parameter value of the cattle frozen embryo to be evaluated under the marked morphological parameters; is the fitted value between the marker morphological parameter and the tth reference morphological parameter of the cattle frozen embryo to be evaluated.

5. The method for morphological evaluation of cattle frozen embryos according to claim 1, wherein: The method further comprises determining the evaluation reference of the cattle frozen embryo to be evaluated under the marked morphological parameters based on the morphological evaluation reliability of the cattle frozen embryo to be evaluated under the marked morphological parameters, the fitting value of the cattle frozen embryo to be evaluated between the marked morphological parameters and all reference morphological parameters, and all internal biological characteristic values, including: Determine the data set consisting of the fitting values of the cattle frozen embryo to be evaluated between the marked morphological parameters and all reference morphological parameters as the fitting value set of the cattle frozen embryo to be evaluated under the marked morphological parameters; A data set consisting of internal biological characteristic values corresponding to all cattle frozen embryos is determined as an internal biological characteristic value set; Based on the morphological evaluation reliability and fitting value set of the cattle frozen embryo to be evaluated under the marked morphological parameters, as well as the internal biological feature value set, the evaluation reference of the cattle frozen embryo to be evaluated under the marked morphological parameters is determined.

6. The method for morphological evaluation of cattle frozen embryos according to claim 5, characterized in that: The corresponding formula for the evaluation reference of the cattle frozen embryos under the marked morphological parameters is: ; Wherein, T is the evaluation reference of the cattle frozen embryo to be evaluated under the marked morphological parameters; is the normalization function; is the Pearson correlation coefficient between XN and XY; XN is the set of internal biological feature values; XY is the fitted value set of the cattle frozen embryo to be evaluated under the marked morphological parameters; E is the reliability of the morphological evaluation of the cattle frozen embryo to be evaluated under the marked morphological parameters.

7. The method for morphological evaluation of cattle frozen embryos according to claim 1, wherein: According to the evaluation reference of the cattle frozen embryos to be evaluated under all morphological parameters, the target morphological parameters are screened out from all morphological parameters, including: The morphological parameter with the greatest reference value for the evaluation of the frozen cattle embryo to be evaluated is selected from all morphological parameters and used as the target morphological parameter.

8. The method for morphological evaluation of cattle frozen embryos according to claim 1, wherein: Determining the morphological evaluation index corresponding to the cattle frozen embryo to be evaluated based on the internal biological characteristic value corresponding to the cattle frozen embryo to be evaluated and its evaluation reference under the target morphological parameters includes: The morphological evaluation indicators corresponding to the cattle frozen embryos to be evaluated are determined based on the internal biological characteristic values corresponding to the cattle frozen embryos to be evaluated and their evaluation reference under the target morphological parameters, the fitting values of the cattle frozen embryos to be evaluated between the target morphological parameters and all other morphological parameters, and the target parameter values of the cattle frozen embryos to be evaluated under the target morphological parameters.

9. The method for morphological evaluation of cattle frozen embryos according to claim 8, characterized in that: The formula corresponding to the morphological evaluation index of the cattle frozen embryo to be evaluated is: ; Wherein, L is the morphological evaluation index corresponding to the cattle frozen embryo to be evaluated; is a normalization function; N is the internal biological characteristic value corresponding to the cattle frozen embryo to be evaluated; ZT is the evaluation reference of the cattle frozen embryo to be evaluated under the target morphological parameters; It is the absolute value function; is the target parameter value of the cattle frozen embryo to be evaluated under the target morphological parameter; ZY is the mean of the fitting values between the target morphological parameter and all other morphological parameters of the cattle frozen embryo to be evaluated.

Images