Intelligent embryo screening system and method based on sample library

Abstract

The invention discloses an intelligent embryo screening system and method based on a sample library, and particularly relates to the technical field of embryo screening. Original multi-source data of embryo morphology, metabolite, cell cycle and other data are collected; processing the data, including morphological parameter operation, metabolite data normalization and cell cycle and standard comparison, to obtain preprocessed data; generating an embryo characteristic analysis value based on the preprocessed data; screening out high-quality embryos according to the analysis value and the high-quality embryo standard; and summarizing related information to establish a high-quality embryo information summary sheet. According to the intelligent embryo screening system and method based on the sample library, by constructing the intelligent embryo screening system and method based on the sample library, multi-source data acquisition, a scientific data processing algorithm and an accurate feature analysis and screening strategy are comprehensively utilized, so that the accuracy and efficiency of embryo screening are improved; and a more reliable technical support is provided for the field of assisted reproduction.

Description

Technical Field

[0001] The present invention relates to the technical field of embryo screening, and particularly to an intelligent embryo screening system and method based on a sample library. Background Art

[0002] The technical field of intelligent embryo screening includes a series of technologies that use various technical means to evaluate and screen embryos to obtain embryos with high developmental potential. The core content is to judge the quality and developmental potential of embryos by analyzing multiple characteristics of embryos using specific methods; in this technical field, various factors such as the morphological characteristics and developmental speed of embryos are comprehensively considered, and auxiliary tools such as computer technology are used to achieve objective and accurate screening of embryos, so as to provide support for fields such as assisted reproduction.

[0003] Among them, the intelligent embryo screening system and method based on a sample library refer to technical matters for embryo screening, including constructing an embryo sample library and collecting embryo-related data, etc. Specifically, by establishing a sample library containing a large amount of embryo information, these information include embryo morphology, developmental stage, metabolite content, etc., using the data in the sample library to train a specific model to establish the connection between embryo characteristics and developmental potential, and realizing the intelligent screening of embryos by collecting various data of the embryos to be screened and inputting them into the trained model. The screening means include quantitative analysis of embryo morphology, monitoring the time course of embryo development, analyzing the components of embryo metabolites, etc. to judge the quality and developmental status of embryos. Summary of the Invention

[0004] The main object of the present invention is to provide an intelligent embryo screening system and method based on a sample library, which can effectively solve the problems of low accuracy of traditional embryo screening and difficulty in accurately judging developmental potential.

[0005] To achieve the above object, the technical solution adopted by the present invention is as follows:

[0006] An intelligent embryo screening method based on a sample library, the system includes the following steps:

[0007] S1. Collect the length, width, and height parameters of embryo morphology, obtain the types and content data of embryo metabolites, record the time intervals of embryo cell cycles and the duration data of each stage, and obtain the original embryo multi-source data;

[0008] S2. Process the original embryo multi-source data, perform operations on the length, width, and height parameters of embryo morphology, normalize the metabolite content data, compare the cell cycle time intervals with the standard time interval range, and obtain the pre-processed embryo data;

[0009] S3. Based on the preprocessed embryo data, compare the embryo morphological operation results with the set threshold, sort the normalized metabolite content data, and generate an embryo characteristic analysis value by combining the cell cycle judgment result and the comparison result of the mitochondrial activity parameter with the normal activity range;

[0010] S4. According to the embryo characteristic analysis value, select the embryos that meet the standards according to the high-quality embryo criteria to obtain the high-quality embryo screening result;

[0011] S5. Summarize and organize the relevant information in the high-quality embryo screening result to establish a high-quality embryo information summary table.

[0012] Preferably, when obtaining the embryo morphological length, width, and height parameters in S1, a high-resolution imaging device is used to take multiple-angle photos of the embryo, and an image recognition algorithm based on a convolutional neural network model is used to extract the embryo morphological parameters. This model is obtained by training a large number of embryo images with known sizes.

[0013] Preferably, in S2, for the embryo morphological length, width, and height parameters, perform a sum-of-squares operation according to the formula F = l 2 + w 2 + h 2 to obtain the morphological comprehensive index F;

[0014] The metabolite content data is normalized using the maximum-minimum normalization method for normalization processing;

[0015] where x is the original metabolite content value, x min is the minimum value of this metabolite in all samples, and x max is the maximum value of this metabolite in all samples;

[0016] The standard time interval range is obtained based on the statistical analysis of a large amount of normal embryo cell cycle data. The range [μ - kσ, μ + kσ] is determined using the mean μ and standard deviation σ in statistics, where k is a constant, usually taking 2 or 3.

[0017] Preferably, in S3, the specific set threshold is determined by comparing and analyzing the morphological operation results of known high-quality embryos and non-high-quality embryos using the ROC curve analysis method;

[0018] Generate the embryo characteristic analysis value S through a weighted scoring formula:

[0019] S = αM + βR + γC + δA;

[0020] where α, β, γ, δ are weight coefficients, R is the metabolite ranking score, C is the cell cycle score, and the mitochondrial activity parameter A needs to be compared with the normal activity range [A min , Amax Comparison.

[0021] Preferably, in S4, in addition to the embryo characteristic analysis value meeting specific conditions, the high-quality embryo standard also includes that the embryo mitochondrial activity parameter needs to be higher than the set mitochondrial activity benchmark value, which is determined by a professional institution through statistical analysis methods based on a large amount of experimental data.

[0022] Preferably, in S5, a database management system (such as MySQL) is used to store and manage the relevant information of the embryos, including but not limited to the embryo source and collection time.

[0023] Preferably, after sorting the normalized metabolite content data in S3, the top three metabolites in terms of content are selected for analysis, and the correlation degree with the embryo development status is determined through a correlation analysis algorithm (such as the Pearson correlation coefficient).

[0024] A screening system applying the embryo intelligent screening method based on a sample library described in any one of the above, the system includes the following modules:

[0025] A data acquisition module, used to collect the length, width, and height parameters of the embryo morphology, obtain the types and content data of embryo metabolites, record the cell cycle time interval and the duration data of each stage of the embryo, so as to provide original embryo multi-source data;

[0026] A data preprocessing module, receives the original embryo multi-source data, performs operations on the length, width, and height parameters of the embryo morphology, normalizes the metabolite content data, compares the cell cycle time interval with the standard time interval range, and outputs the preprocessed embryo data;

[0027] A feature analysis module, based on the preprocessed embryo data, compares the operation result of the embryo morphology with the set threshold, sorts the normalized metabolite content data, combines the cell cycle judgment result and the comparison result of the mitochondrial activity parameter with the normal activity range, and calculates and generates an embryo characteristic analysis value;

[0028] An embryo screening module, according to the embryo characteristic analysis value, screens out the embryos that meet the standard according to the high-quality embryo standard, and obtains the high-quality embryo screening result;

[0029] An information summary module, summarizes and organizes the relevant information in the high-quality embryo screening result, establishes a high-quality embryo information summary table, and stores the information using a database management system;

[0030] Data is sequentially transmitted between each module and corresponding operations are executed according to the method flow sequence described in S1 to S5.

[0031] Compared with the prior art, the present invention has the following beneficial effects:

[0032] 1. The present invention constructs an intelligent embryo screening system and method based on a sample library, comprehensively applying multi-source data collection, scientific data processing algorithms, and precise feature analysis and screening strategies, significantly improving the accuracy and efficiency of embryo screening, providing more reliable technical support for the field of assisted reproduction, and strongly promoting the development and progress of technologies in this field.

[0033] 2. The present invention collects embryo morphological parameters by using a high-resolution imaging device in combination with an advanced image recognition algorithm, obtains embryo metabolite data with the help of equipment such as a high-performance liquid chromatograph, and conducts targeted processing on various types of data. For example, normalization processing is carried out on metabolite content data, enabling different types of data to be analyzed under the same standard, greatly improving the usability and comparability of the data, and laying a solid foundation for subsequent accurate analysis of embryo characteristics.

[0034] 3. The present invention compares the embryo morphological operation results with specific thresholds, sorts and conducts correlation analysis on metabolite content data, integrates the cell cycle judgment results, and compares the mitochondrial activity parameters with the normal range, and uses a weighted scoring formula to generate an embryo feature analysis value, comprehensively and accurately depicting the embryo development state. Compared with traditional single-dimensional analysis methods, it can more deeply explore the potential development information of embryos and effectively reduce analysis errors.

[0035] 4. The present invention comprehensively considers and screens multiple indicators such as the embryo feature analysis value according to the rigorous and scientific high-quality embryo standards. The selected high-quality embryos have higher development potential, can effectively improve the success rate of assisted reproduction, reduce the risk of transplantation failure caused by poor embryo quality, and bring more hope to many families with fertility needs. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] Figure 1 is a schematic diagram of the overall process of the intelligent embryo screening of the present invention;

[0037] Figure 2 is a schematic diagram of the detailed process of multi-source data collection of embryos of the present invention;

[0038] Figure 3 is a schematic diagram of the detailed process of embryo feature analysis of the present invention;

[0039] Figure 4 is a schematic diagram of the detailed process of screening high-quality embryos of the present invention;

[0040] Figure 5 is a schematic diagram of the interactive process of the screening system modules of the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0041] In order to make the technical means, creative features, achieved purposes and functions of the present invention easy to understand, the present invention will be further described below in conjunction with specific embodiments.

[0042] As Figure 1 shown, the present invention specifically relates to an intelligent screening method for embryos based on a sample library. The system includes the following steps:

[0043] S1. Collect the length, width, and height parameters of the embryo's morphology, obtain the types and content data of the embryo's metabolites, record the time intervals of the embryo's cell cycle and the duration data of each stage, and obtain the original multi-source embryo data;

[0044] S2. Process the original multi-source embryo data, perform operations on the length, width, and height parameters of the embryo's morphology, normalize the metabolite content data, compare the cell cycle time interval with the standard time interval range, and obtain the preprocessed embryo data;

[0045] S3. Based on the preprocessed embryo data, compare the operation results of the embryo's morphology with a specific set threshold, sort the normalized metabolite content data, combine the cell cycle judgment results and the comparison results of the mitochondrial activity parameters with the normal activity range, and generate an embryo characteristic analysis value;

[0046] S4. According to the embryo characteristic analysis value, select the embryos that meet the standards according to the high-quality embryo standards to obtain the high-quality embryo screening results;

[0047] S5. Summarize and organize the relevant information in the high-quality embryo screening results to establish a high-quality embryo information summary table.

[0048] Example 1. This example specifically elaborates on the collection and preliminary calculation process of multi-source embryo data;

[0049] Specifically, as Figure 2 shown, when obtaining the length, width, and height parameters of the embryo's morphology in S1, a high-resolution imaging device is used, and a microscope with a resolution accuracy of 0.1 micrometer is used to take multiple-angle pictures of the embryo, including at least three angles: the front, side, and top;

[0050] Use an image recognition algorithm based on a convolutional neural network model to extract the embryo morphology parameters. This model is obtained by training a large number of embryo images with known sizes, and the number of used images is not less than 10,000 known-size embryo images.

[0051] Extract the length, width, and height parameters of the embryo from the taken pictures through the image recognition algorithm. Preset an existing embryo, and the sizes extracted by the algorithm from the collected images are: length 100 micrometers, width 80 micrometers, and height 60 micrometers;

[0052] Furthermore, for the collection of embryo metabolite data, use a high-performance liquid chromatograph to analyze the embryo metabolites.

[0053] After detection, it is determined that the embryonic metabolites include glucose, lactic acid, pyruvic acid, etc. Among them, the glucose content is 5 mmol / L, the lactic acid content is 3 mmol / L, and the pyruvic acid content is 1 mmol / L.

[0054] In the recording of embryonic cell cycle data, the process of embryonic cell division is monitored by a real-time fluorescence microscope, and the cell cycle time intervals and the durations of each stage are recorded.

[0055] Assume that the total duration of the cell cycle of this embryo is 24 hours, among which the duration of the G1 phase is 10 hours, the duration of the S phase is 8 hours, the duration of the G2 phase is 4 hours, and the duration of the M phase is 2 hours.

[0056] Among them, the G1 phase (Gap1 phase): that is, the first gap phase of the cell cycle, is the stage for cell growth and preparation for DNA synthesis;

[0057] The S phase (Synthesis phase): is the DNA synthesis phase. In this stage, the cell will replicate DNA, accurately replicate the genome, and double the DNA content in the cell;

[0058] The G2 phase (Gap2 phase): is the second gap phase of the cell cycle. After DNA replication is completed, the cell enters the G2 phase;

[0059] The M phase (Mitosis phase): that is, the mitosis phase, is the stage of cell division, including nuclear division and cytoplasmic division.

[0060] In S2, for the parameters of the length, width, and height of the embryo, the formula F = l 2 + w 2 + h 2 is used to perform the sum of squares operation to obtain the morphological comprehensive index F;

[0061] For the parameters of the length, width, and height of the embryo, the formula F = l 2 + w 2 + h 2 is used to perform the sum of squares operation, that is, F = 100 2 + 80 2 + 60 2 = 10000 + 6400 + 3600 = 20000, and the morphological comprehensive index F is obtained as 20000.

[0062] These collected data are summarized to obtain the original multi-source data of the embryo.

[0063] Example 2. In this example, on the basis of Example 1, the original multi-source data of the embryo is processed and compared;

[0064] Specifically, such as Figure 3As shown, the maximum-minimum normalization method is adopted to normalize the metabolite content data, and the metabolites include but are not limited to glucose, lactate, pyruvate, glutamine, glutamate, aspartic acid, asparagine, citric acid, malic acid, succinic acid, palmitic acid, and adenine nucleotides;

[0065] where x is the original metabolite content value, x min is the minimum value of the metabolite in all samples, and x max is the maximum value of the metabolite in all samples.

[0066] Taking glucose as an example, assuming that in a database containing 100 embryo samples, the minimum value x of glucose content min is 1 mmol / L, and the maximum value x max is 10 mmol / L, then the normalized value of glucose is

[0067] Furthermore, in terms of comparing the cell cycle time interval with the standard time interval range, the standard time interval range is obtained based on the statistical analysis of a large number of normal embryo cell cycle data. The range is determined as [μ - kσ, μ + kσ] using the mean μ and standard deviation σ in statistics, where k is a constant, usually taking 2 or 3.

[0068] Assuming that through the statistical analysis of 1000 normal embryo cell cycle data, the mean μ of the total cell cycle duration is 22 hours, and the standard deviation σ is 2 hours. Taking k = 2, the standard time interval range is:

[0069] [μ - kσ, μ + kσ] = [22 - 2×2, 22 + 2×2] = [18, 26] h;

[0070] In this embodiment, the total cell cycle duration of the embryo is 24 hours, which is within this standard range.

[0071] Furthermore, the specific set threshold is determined by comparing and analyzing the morphological operation results of known high-quality embryos and non-high-quality embryos, using the ROC curve analysis method, and is labeled as T F ;

[0072] Compare the morphological sum of squares operation result F of the embryo with the specific set threshold T M , and the specific set threshold T M is obtained by comparing and analyzing the morphological sum of squares operation results of 500 known high-quality embryos and 500 non-high-quality embryos.

[0073] Assume that the determined T F is 18000, and in this embodiment, F = 20000, which is greater than T M .

[0074] Finally, sort the normalized metabolite content data in S3, select the top three metabolites in terms of content, and analyze their correlation with the embryonic development status through the Pearson correlation coefficient.

[0075] Example 3: On the basis of Example 2, this example further conducts embryo screening and result summary;

[0076] Specifically, as Figure 4 shown, combining the cell cycle judgment result and the comparison result of the mitochondrial activity parameter with the normal activity range, generate the embryo characteristic analysis value S through the weighted scoring formula S = αM + βR + γC + δA.

[0077] Among them, the mitochondrial activity parameter A needs to be compared with the normal activity range [A min , A max ;

[0078] Specifically, the mitochondrial activity parameter A is a key indicator to measure the mitochondrial function status of the embryo. During embryonic development, maintaining the mitochondrial activity at an appropriate level can provide sufficient energy for activities such as cell division and differentiation of embryonic cells, ensuring normal embryonic development. If the mitochondrial activity parameter A is lower than the lower limit A min of the normal range, it may mean that the mitochondrial function is damaged and the embryonic development potential decreases; conversely, if it is higher than the upper limit A max of the normal range, it may also imply that there is an abnormal metabolic situation in the embryo. The normal activity range [A min , A max is obtained by measuring and statistically analyzing a large number of healthy embryo samples. In the present invention, assume that the normal activity range is [0.6, 1.2], and assume that the mitochondrial activity parameter A is 0.8, which is within the normal range.

[0079] Assume that the weight coefficients α = 0.4, β = 0.3, γ = 0.2, δ = 0.1, the metabolite ranking score R is assigned according to the ranking situation (assuming that the ranking score R = 8 in this example), the cell cycle score C is assigned according to whether it is within the standard range (C = 10 within the range), and the mitochondrial activity parameter A is assumed to be 0.8, then S = 0.4×20000 + 0.3×8 + 0.2×10 + 0.1×0.8 = 8000 + 2.4 + 2 + 0.08 = 8004.48.

[0080] According to the embryo characteristic analysis value S, screen embryos according to the high-quality embryo standard;

[0081] In S4, in addition to the embryo characteristic analysis value needing to meet specific conditions, the high-quality embryo standard also includes that the embryo mitochondrial activity parameter needs to be higher than the set mitochondrial activity benchmark value. Assume that the set mitochondrial activity benchmark value is A baseis 0.7. In this embodiment, A = 0.8, which meets the condition.

[0082] And assume that the threshold value S of the embryo characteristic analysis value in the high-quality embryo standard threshold is 8000. In this embodiment, S = 8004.48, which meets the high-quality embryo standard. Select this embryo to obtain the high-quality embryo screening result;

[0083] Among them, the reference value is determined by a professional institution through statistical analysis methods based on a large amount of experimental data.

[0084] In S5, summarize the relevant information in the high-quality embryo screening result, including the embryo source (assumed to be the 10th sample of a certain reproductive center), the collection time (assumed to be January 1, 2025), various parameters and analysis values, etc., and use the database management system MySQL to establish a high-quality embryo information summary table for storage and management.

[0085] Example 4, as Figure 5 shown, on the basis of Examples 1 to 3, this embodiment further discloses a screening system applying the above-mentioned embryo intelligent screening method based on a sample library. The system specifically includes a data acquisition module, a data preprocessing module, a feature analysis module, an embryo screening module, and an information summary module. Data is transmitted in sequence and corresponding operations are executed among the modules according to the method flow described in S1 to S5;

[0086] The data acquisition module is used to collect the length, width, and height parameters of the embryo morphology, obtain the types and content data of embryo metabolites, and record the time intervals of the embryo cell cycle and the durations of each stage to provide original embryo multi-source data;

[0087] Specifically, the data acquisition module is configured with an image acquisition card connected to a high-resolution microscope for collecting embryo morphology parameters, and transmits the collected image data to the data processing unit in real time;

[0088] It is also configured with a high-performance liquid chromatograph to analyze the metabolites of the embryo sample through an automatic sampling device, and the analysis result is transmitted to the data processing unit in the form of a digital signal;

[0089] Furthermore, a real-time fluorescence microscope is also set up to automatically identify the embryo cell division process and record the cell cycle data through specific image recognition software, and also transmit it to the data processing unit to complete the collection and summary of the original embryo multi-source data.

[0090] The data preprocessing module receives the original multi-source embryo data, processes the data using built-in algorithm programs, calculates the length, width, and height parameters of the embryo morphology, normalizes the metabolite content data, compares the cell cycle time intervals with the standard time interval range, reads out the standard time interval range data stored in the database, and compares it with the real-time collected cell cycle data for judgment, and outputs the preprocessed embryo data.

[0091] The feature analysis module, based on the preprocessed embryo data, compares the embryo morphology calculation result F with the specific set threshold T stored in the parameter database F performs sorting on the normalized metabolite content data using a sorting algorithm program, selects the top three metabolites, calculates the Pearson correlation coefficient through a special association analysis software, and combines the cell cycle judgment result and the comparison result of the mitochondrial activity parameter with the normal activity range;

[0092] Combines the cell cycle judgment result and the comparison result of the mitochondrial activity parameter with the normal activity range, and calculates and generates an embryo feature analysis value;

[0093] The embryo screening module, based on the embryo feature analysis value, reads the high-quality embryo standards from the parameter database, including the embryo feature analysis value threshold S threshold and the mitochondrial activity benchmark value A base , compares them with the S generated by the feature analysis module and the mitochondrial activity parameter A, selects the embryos that meet the standards, and obtains the high-quality embryo screening result;

[0094] The information summary module summarizes and organizes the relevant information in the high-quality embryo screening result, establishes a high-quality embryo information summary table, stores the information using a database management system, and uses the interface program of the MySQL database management system to write information such as the embryo source, collection time, various parameters, and analysis values into the database to establish a high-quality embryo information summary table;

[0095] This module also has a data backup function, regularly backing up the information in the database to an external storage device to prevent data loss.

[0096] The above shows and describes the basic principles, main features, and advantages of the present invention. Those skilled in the art of this industry should understand that the present invention is not limited by the above embodiments. What is described in the above embodiments and the specification only illustrates the principles of the present invention. Without departing from the spirit and scope of the present invention, the present invention will have various changes and improvements, and these changes and improvements all fall within the scope of the present invention claimed. The scope of protection claimed by the present invention is defined by the appended claims and their equivalents.

Claims

1. An intelligent embryo screening method based on a sample library, characterized in that, The system includes the following steps: S1. Collect the length, width, and height parameters of the embryo morphology, obtain the types and content data of embryo metabolites, record the time intervals of the embryo cell cycle and the duration of each stage, and obtain the original multi-source embryo data; S2. Process the original multi-source embryo data, calculate the length, width, and height parameters of the embryo morphology, normalize the metabolite content data, compare the cell cycle time interval with the standard time interval range, and obtain the preprocessed embryo data; S3. Based on the preprocessed embryo data, compare the operation result of the embryo morphology with the set threshold, sort the normalized metabolite content data, combine the cell cycle judgment result and the comparison result of the mitochondrial activity parameter with the normal activity range, and generate an embryo characteristic analysis value; S4. According to the embryo characteristic analysis value, select the embryos that meet the standards according to the high-quality embryo standards, and obtain the high-quality embryo screening result; S5. Summarize and organize the relevant information in the high-quality embryo screening result, and establish a high-quality embryo information summary table.

2. The embryo intelligent screening method based on a sample library according to claim 1, characterized in that: When obtaining the length, width, and height parameters of the embryo morphology in S1, a high-resolution imaging device is used to take multi-angle photos of the embryo, and an image recognition algorithm based on a convolutional neural network model is used to extract the embryo morphology parameters. This model is obtained by training a large number of embryo images with known sizes.

3. The method for intelligent screening of embryos based on a sample library according to claim 1, characterized in that: In S2, for the parameters of the embryo's length, width, and height, the morphological comprehensive index F is obtained by performing the sum of squares operation on the formula F = l 2 + w 2 + h 2 ; The maximum-minimum normalization method is used for the metabolite content data for normalization processing; where x is the content value of the original metabolite, x min is the minimum value of this metabolite in all samples, x max is the maximum value of this metabolite in all samples; The standard time interval range is obtained based on the statistical analysis of a large amount of normal embryo cell cycle data. The range is determined as [μ - kσ, μ + kσ] using the mean μ and standard deviation σ in statistics, where k is a constant, usually taking 2 or 3.

4. The embryo intelligent screening method based on a sample library according to claim 1, wherein: In S3, the specific set threshold is determined by comparing and analyzing the operation results of known high-quality embryos and non-high-quality embryos using the ROC curve analysis method; The embryo characteristic analysis value S is generated through a weighted scoring formula: S = αM + βR + γC + δA; where α, β, γ, δ are weight coefficients, R is the metabolite ranking score, C is the cell cycle score, and the mitochondrial activity parameter A needs to be compared with the normal activity range [A min , A max .

5. The embryo intelligent screening method based on a sample library according to claim 1, wherein: In S4, in addition to the embryo characteristic analysis value needing to meet specific conditions, the high-quality embryo standards also include that the embryo mitochondrial activity parameter needs to be higher than the set mitochondrial activity benchmark value, which is determined by a professional institution through statistical analysis based on a large amount of experimental data.

6. The embryo intelligent screening method based on a sample library according to claim 1, wherein: In S5, a database management system (such as MySQL) is used to store and manage the relevant information of the embryo, including but not limited to the embryo source and collection time.

7. The method for intelligent embryo screening based on a sample library according to claim 1, wherein: After sorting the normalized metabolite content data in S3, select the top three metabolites in terms of content for analysis, and determine their degree of association with the embryo development status through an association analysis algorithm (such as Pearson correlation coefficient).

8. A screening system applying the embryo intelligent screening method based on a sample library according to any one of claims 1-7, characterized in that, The system includes the following modules: A data collection module, which is used to collect the length, width, and height parameters of the embryo morphology, obtain the types and content data of embryo metabolites, record the time intervals of the embryo cell cycle and the duration of each stage, so as to provide the original multi-source embryo data; A data preprocessing module, which receives the original multi-source embryo data, calculates the length, width, and height parameters of the embryo morphology, normalizes the metabolite content data, compares the cell cycle time interval with the standard time interval range, and outputs the preprocessed embryo data; The feature analysis module, based on the preprocessed embryo data, compares the operation results of embryo morphology with the set threshold, sorts the data of the content of metabolites after normalization, and combines the judgment results of the cell cycle and the comparison results of mitochondrial activity parameters with the normal activity range to calculate and generate the embryo feature analysis value; The embryo screening module, according to the embryo feature analysis value, screens out the embryos that meet the standards according to the high-quality embryo standards to obtain the high-quality embryo screening results; The information summary module summarizes and organizes the relevant information in the high-quality embryo screening results, establishes a high-quality embryo information summary table, and stores the information using a database management system; Data is sequentially transmitted between each module according to the method flow sequence described in S1 to S5, and corresponding operations are performed.

Images