System and method for automatically detecting semen quality

Abstract

The invention relates to the field of beauty and skin care, and discloses a system and method for automatically detecting semen quality, and the system comprises a form defect rate calculation module which is used for calculating the form defect rate corresponding to a target semen sample; the dysfunctional sperm identification module is used for identifying dysfunctional sperms in the target sperm sample; the reproductive function score evaluation module is used for evaluating a reproductive function score corresponding to the target semen sample; and the dynamic activity potential scoring evaluation module is used for preparing an adaptive culture solution corresponding to the target semen sample, putting the target semen sample into the adaptive culture solution for culture treatment, recording sperm motility rate reference parameters in the culture treatment process, and calculating the sperm survival rate of the target semen sample. Evaluating a dynamic activity potential score corresponding to the target semen sample; and the semen quality analysis module is used for generating a semen quality analysis report corresponding to the target semen sample. The detection accuracy of the semen quality can be improved.

Description

Technical Field

[0001] The present invention relates to the field of beauty and skin care technology, and in particular to a system and method for automatically detecting semen quality. Background Art

[0002] In the current field of medicine and reproductive health, semen quality testing plays a vital role in evaluating male fertility, diagnosing reproductive system diseases and the implementation of assisted reproductive technology. Therefore, the requirements for the accuracy, efficiency and comprehensiveness of semen quality testing are constantly increasing.

[0003] At present, semen quality testing mainly adopts three methods: traditional manual testing, semi-automatic testing and fully automatic testing. Traditional manual testing is highly dependent on the professional skills and experience of the inspectors. They need to manually observe the morphology of sperm, count the number of sperm and evaluate indicators such as sperm motility under a microscope. Although this method can provide more detailed results to a certain extent, the testing process is time-consuming and laborious, and there are large subjective differences between different inspectors, resulting in poor accuracy and repeatability of the test results. Semi-automatic testing uses some basic automated equipment, such as sperm counters, to a certain extent to improve the detection efficiency and reduce the manual burden. However, in the complex analysis of sperm movement trajectory and morphological characteristics and the comprehensive evaluation of multi-dimensional data, a lot of manual intervention is still required, making it difficult to achieve comprehensive and accurate detection of semen quality. Although fully automatic testing uses advanced image recognition, data analysis algorithms and other technologies to quickly obtain a large amount of semen data, it is insufficient in the accurate identification of sperm microscopic morphology, accurate analysis of complex movement patterns and in-depth mining of the uniqueness of individual semen samples, which leads to low accuracy of semen quality detection. Summary of the invention

[0004] The present invention provides a system and method for automatically detecting semen quality, the main purpose of which is to improve the detection accuracy of semen quality.

[0005] To achieve the above-mentioned purpose, the present invention provides a system for automatically detecting semen quality, comprising: a morphological defect rate calculation module, a dysfunctional sperm identification module, a reproductive function scoring and evaluation module, a dynamic vitality potential scoring and evaluation module, and a semen quality analysis module;

[0006] The morphological defect rate calculation module is used to obtain a target semen sample to be tested, collect a sample optical microscopic image and semen dynamic data of the target semen sample, perform image segmentation processing on the sample optical microscopic image to obtain a sperm segmentation image, and calculate the morphological defect rate corresponding to the target semen sample based on the sperm segmentation image;

[0007] The dysfunctional sperm recognition module is used to extract the trajectory dynamic data and the swing dynamic data from the semen dynamic data, perform clustering processing on the trajectory dynamic data to obtain a set of clustered motion trajectories, analyze the trajectory behavior patterns corresponding to the set of clustered motion trajectories, and identify the dysfunctional sperm in the target semen sample based on the trajectory behavior patterns;

[0008] The reproductive function score evaluation module is used to extract the swing dynamic features from the swing dynamic data, evaluate the sperm motility intensity in the target semen sample based on the swing dynamic features, and evaluate the reproductive function score corresponding to the target semen sample by combining the morphological defect rate, the dysfunctional sperm, and the sperm motility intensity;

[0009] The dynamic vitality potential score evaluation module is used to configure the appropriate culture medium corresponding to the target semen sample, place the target semen sample in the appropriate culture medium for culture treatment, and record the sperm viability reference parameters during the culture treatment. Based on the sperm viability reference parameters, calculate the sperm survival rate of the target semen sample, and evaluate the dynamic vitality potential score corresponding to the target semen sample based on the sperm survival rate;

[0010] The semen quality analysis module is used to generate a semen quality analysis report corresponding to the target semen sample by combining the reproductive function score and the dynamic vitality potential score.

[0011] A method for automatically detecting semen quality, characterized in that the method includes:

[0012] Obtain a target semen sample to be detected, collect the sample optical microscopic image and semen dynamic data of the target semen sample, perform image segmentation processing on the sample optical microscopic image to obtain a sperm segmentation image, and calculate the morphological defect rate corresponding to the target semen sample based on the sperm segmentation image;

[0013] Extract the trajectory dynamic data and the swing dynamic data from the semen dynamic data, perform clustering processing on the trajectory dynamic data to obtain a set of clustered motion trajectories, analyze the trajectory behavior patterns corresponding to the set of clustered motion trajectories, and identify the dysfunctional sperm in the target semen sample based on the trajectory behavior patterns;

[0014] Extract the swing dynamic features from the swing dynamic data, evaluate the sperm motility intensity in the target semen sample based on the swing dynamic features, and evaluate the reproductive function score corresponding to the target semen sample by combining the morphological defect rate, the dysfunctional sperm, and the sperm motility intensity;

[0015] Configure the adaptation culture medium corresponding to the target semen sample, place the target semen sample in the adaptation culture medium for culture treatment, and record the sperm motility benchmark parameters during the culture treatment. Based on the motility benchmark parameters, calculate the sperm survival rate of the target semen sample. Based on the sperm survival rate, evaluate the dynamic vitality potential score corresponding to the target semen sample;

[0016] Combine the reproductive function score and the dynamic vitality potential score to generate a semen quality analysis report corresponding to the target semen sample.

[0017] Through image segmentation processing of the sample optical microscopic image, the present invention can obtain an image that clearly distinguishes sperm from other impurities and accurately identifies sperm morphology, which can not only intuitively display the details of sperm morphology, but also help accurately calculate the sperm morphology defect rate. Optionally, through clustering processing of the trajectory dynamic data, the present invention obtains a set of clustering movement trajectories, which can integrate the sperm trajectory information with similar movement characteristics and quickly locate different movement mode groups. The present invention extracts the swing dynamic characteristics in the swing dynamic data, which can accurately capture the subtle characteristics of sperm movement and provide an intuitive and reliable quantitative basis for evaluating the reproductive function score corresponding to the target semen sample. By configuring the adaptation culture medium corresponding to the target semen sample, the present invention facilitates the refined and targeted culture of the target semen sample. Place the target semen sample in the adaptation culture medium for culture treatment, and record the sperm motility benchmark parameters during the culture treatment, thereby facilitating the subsequent accurate calculation of the sperm survival rate. By combining the reproductive function score and the dynamic vitality potential score, the present invention generates a semen quality analysis report corresponding to the target semen sample, and can obtain a high-quality semen quality analysis result. Therefore, the detection accuracy of semen quality is improved. Brief Description of the Drawings

[0018] Figure 1 It is a functional module diagram of a system for automatically detecting semen quality provided by an embodiment of the present invention;

[0019] Figure 2 It is a schematic flowchart of a method for automatically detecting semen quality provided by an embodiment of the present invention;

[0020] The realization, functional features and advantages of the object of the present invention will be further described with reference to the embodiments and the accompanying drawings. Detailed Embodiments

[0021] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Apparently, the described embodiments are some, but not all, of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0022] In addition, the sequence of steps in the following method embodiments is only an example and is not strictly limited.

[0023] In fact, the server devices deployed by the system for automatically detecting semen quality may consist of one or more devices. The above system for automatically detecting semen quality can be implemented as: a business instance, a virtual machine, or a hardware device. For example, the system for automatically detecting semen quality can be implemented as a business instance deployed on one or more devices in a cloud node. Simply put, the system for automatically detecting semen quality can be understood as a software deployed on a cloud node for providing the service of automatically detecting semen quality to each client. Alternatively, the system for automatically detecting semen quality can also be implemented as a virtual machine deployed on one or more devices in a cloud node. An application software for managing each client is installed in the virtual machine. Or, the system for automatically detecting semen quality can also be implemented as a server composed of many identical or different types of hardware devices, and one or more hardware devices are set to provide the service of automatically detecting semen quality to each client.

[0024] In terms of implementation form, the system for automatically detecting semen quality and the client adapt to each other. That is, if the system for automatically detecting semen quality is an application installed on a cloud service platform, then the client is a client that establishes a communication connection with the application; or if the system for automatically detecting semen quality is implemented as a website, then the client is implemented as a web page; or if the system for automatically detecting semen quality is implemented as a cloud service platform, then the client is implemented as a mini-program in an instant messaging application.

[0025] Refer to Figure 1 As shown, it is a functional module diagram of the system for automatically detecting semen quality provided by an embodiment of the present invention.

[0026] The automated semen quality detection system 100 described in the present invention can be set in a cloud server. In terms of implementation form, it can be used as one or more service devices, or can be installed as an application on the cloud (such as a server for automated semen quality detection, a server cluster, etc.), or can also be developed into a website. According to the functions achieved, the automated semen quality detection system 100 includes a morphological defect rate calculation module 101, a dysfunctional sperm recognition module 102, a reproductive function score evaluation module 103, a dynamic vitality potential score evaluation module 104, and a semen quality analysis module 105.

[0027] In the embodiments of the present invention, in the tracking of automated semen quality detection, each of the above modules can be independently implemented and called with other modules. Here, the call can be understood as that a certain module can be connected to multiple modules of another type and provide corresponding services for the multiple modules it is connected to. In the automated semen quality detection system provided by the embodiments of the present invention, without modifying the program code, the applicable range of the architecture of the automated semen quality detection can be adjusted by adding modules and directly calling them, realizing cluster-level horizontal expansion, so as to achieve the purpose of quickly and flexibly expanding the automated semen quality detection system. In practical applications, the above modules can be set in the same device or different devices, or can also be set in virtual devices, such as service instances in a cloud server.

[0028] The following will describe each component and the specific working process of the automated semen quality detection system in combination with specific embodiments.

[0029] The morphological defect rate calculation module 101 is used to obtain a target semen sample to be detected, collect a sample optical microscopic image and semen dynamic data of the target semen sample, perform image segmentation processing on the sample optical microscopic image to obtain a sperm segmentation image, and calculate the morphological defect rate corresponding to the target semen sample based on the sperm segmentation image.

[0030] By performing image segmentation processing on the sample optical microscopic image of the present invention, an image that can clearly distinguish sperm from other impurities and accurately identify the sperm morphology can be obtained. It can not only intuitively display the details of sperm morphology, but also help accurately calculate the sperm morphological defect rate. Among them, the target semen sample is a semen entity to be detected and evaluated, the sample optical microscopic image is an image obtained by photographing the target semen sample with an optical microscope, the semen dynamic data is data generated during the movement of sperm in the target semen sample, and the sperm segmentation image is an image formed by separating and extracting sperm from the background and other impurities through image segmentation processing in the sample optical microscopic image. Further, the collection of the sample optical microscopic image and semen dynamic data of the target semen sample can be realized by a high-resolution microscope and a sensor with a movement trajectory tracking function.

[0031] As an embodiment of the present invention, the image segmentation process for the sample optical microscopic image to obtain a sperm segmentation image includes:

[0032] Perform image denoising processing on the sample optical microscopic image to obtain a denoised optical microscopic image;

[0033] Perform grayscale processing on the denoised optical microscopic image to obtain a grayscale optical microscopic image;

[0034] Perform region division on the grayscale optical microscopic image to obtain an optical microscopic region image, and extract the grayscale distribution characteristics corresponding to the optical microscopic region image;

[0035] Based on the grayscale distribution characteristics, determine the segmentation threshold corresponding to the grayscale optical microscopic image;

[0036] Based on the segmentation threshold, perform image segmentation on the grayscale optical microscopic image to obtain an initial sperm segmentation image;

[0037] Perform morphological optimization processing on the initial sperm segmentation image to obtain a sperm segmentation image.

[0038] Wherein, the denoised optical microscopic image is the image obtained by performing image denoising processing on the sample optical microscopic image; the grayscale optical microscopic image is the image obtained by performing grayscale processing on the denoised optical microscopic image; the optical microscopic region image is the local region image selected and divided from the grayscale optical microscopic image; the grayscale distribution characteristics are the distribution characteristics of pixels with different grayscale values corresponding to the optical microscopic region image; the initial sperm segmentation image is the image obtained by performing threshold segmentation on the grayscale optical microscopic image.

[0039] Optionally, the sample optical microscopic image can be subjected to image denoising processing through a Gaussian filtering algorithm to obtain a denoised optical microscopic image; the denoised optical microscopic image can be subjected to grayscale processing by converting a color image into grayscale values according to a specific algorithm to obtain a grayscale optical microscopic image; the grayscale optical microscopic image can be subjected to region division through an adaptive region growing algorithm to obtain an optical microscopic region image; the grayscale distribution characteristics corresponding to the optical microscopic region image can be extracted by statistically counting the number and proportion of pixels with different grayscale values; based on the grayscale distribution characteristics, the Otsu algorithm is used to determine the segmentation threshold corresponding to the grayscale optical microscopic image; based on the segmentation threshold, the grayscale optical microscopic image can be subjected to image segmentation through a threshold segmentation algorithm to obtain an initial sperm segmentation image; the initial sperm segmentation image can be subjected to morphological optimization processing through morphological operations such as erosion, dilation, opening, and closing to obtain a sperm segmentation image.

[0040] Based on the sperm segmentation image, the present invention calculates the morphological defect rate corresponding to the target semen sample, and the sperm morphological health status corresponding to the target semen sample can be understood through the morphological defect rate, laying an important basis for the evaluation of the reproductive function score corresponding to the target semen sample. Among them, the morphological defect rate represents the morphological defect ratio corresponding to the target semen sample.

[0041] As an embodiment of the present invention, the calculating the morphological defect rate corresponding to the target semen sample based on the sperm segmentation image includes:

[0042] Extract the morphological parameters in the sperm segmentation image, and based on the morphological parameters, identify the morphologically abnormal sperm in the sperm segmentation image;

[0043] Based on the morphological parameters, statistically analyze the sperm morphological characteristics in the sperm segmentation image;

[0044] Based on the sperm morphological characteristics, determine the severity of abnormality corresponding to the morphologically abnormal sperm;

[0045] Assign the abnormal weight corresponding to the morphologically abnormal sperm, and combine the severity of abnormality and the abnormal weight to calculate the abnormal defect value corresponding to the morphologically defective sperm;

[0046] Based on the abnormal defect value, screen out the morphologically defective sperm from the morphologically abnormal sperm;

[0047] Based on the morphologically defective sperm, calculate the morphological defect rate corresponding to the target semen sample.

[0048] Among them, the morphological parameters are various quantitative indicators in the sperm segmentation image for describing the sperm morphology, such as length, width, area, perimeter, etc.; the morphologically abnormal sperm are the sperm in the sperm segmentation image whose morphology does not conform to the normal standard; the sperm morphological characteristics are the appearance characteristics such as the shape, size, and proportion of each part of the sperm head, midpiece, tail, etc. in the sperm segmentation image; the severity of abnormality is a measure of the degree that the morphologically abnormal sperm may affect sperm function and fertility; the abnormal weight is the relative importance value given to the morphologically abnormal sperm according to the degree of its impact on fertility; the abnormal defect value represents the quantitative value comprehensively reflecting the degree of morphological abnormality corresponding to the morphologically defective sperm; the morphologically defective sperm are the sperm among the morphologically abnormal sperm that are further evaluated and determined to have morphological defects affecting fertility.

[0049] Optionally, morphological parameters in the sperm segmentation image can be extracted through built-in functions of an image analysis library; based on the morphological parameters, by comparing with a preset normal morphology standard and threshold, morphologically abnormal sperm in the sperm segmentation image can be identified; based on the morphological parameters, sperm morphological characteristics in the sperm segmentation image can be statistically analyzed, such as the aspect ratio and ellipticity of the sperm head, the thickness and length of the midpiece, the curvature of the tail, as well as the area and perimeter of each part, and accordingly, the frequencies of abnormal characteristics such as acrosome integrity, presence of head deformities, tail curling or breakage can be quantitatively statistically analyzed; based on the sperm morphological characteristics, referring to established grading standards in the medical field, the severity of the abnormality corresponding to the morphologically abnormal sperm can be determined. For example, when more than 50% of the abnormal morphological changes occur in the sperm head, or there are obvious swelling and distortion in the midpiece, and features such as multiple folds and short tails in the tail that seriously deviate from the normal morphology appear, it is rated as severely abnormal; if there are only slight irregularities in the head morphology and mild tail curvature, it is rated as mildly abnormal, and those in between are classified as moderately abnormal; the abnormal weight corresponding to the morphologically abnormal sperm can be assigned through a combination of expert experience and data training; combining the severity of the abnormality and the abnormal weight, a weighted calculation formula can be used to calculate the abnormal defect value corresponding to the morphologically defective sperm; based on the abnormal defect value, a reasonable screening threshold can be set to screen out morphologically defective sperm from the morphologically abnormal sperm. For example, the critical value of the abnormal defect value determined in advance through a large number of clinical sample tests and data analysis can be used as the screening threshold, and morphologically abnormal sperm with a value higher than this threshold are determined as morphologically defective sperm; based on the morphologically defective sperm, by statistically analyzing the proportion of morphologically defective sperm in the total number of sperm, the morphological defect rate corresponding to the target semen sample can be calculated.

[0050] The dysfunctional sperm recognition module 102 is used to extract the trajectory dynamic data and the swing dynamic data from the semen dynamic data, perform clustering processing on the trajectory dynamic data to obtain a set of clustered movement trajectories, analyze the trajectory behavior patterns corresponding to the set of clustered movement trajectories, and based on the trajectory behavior patterns, identify the dysfunctional sperm in the target semen sample.

[0051] In the present invention, by performing clustering processing on the trajectory dynamic data, a set of clustered movement trajectories can be obtained, which can integrate sperm trajectory information with similar movement characteristics and quickly locate different movement mode groups. Among them, the trajectory dynamic data is the part of the semen dynamic data that records the sperm movement path, the swing dynamic data is the part of the semen dynamic data that describes the swing amplitude and frequency of the sperm tail, etc., and the set of clustered movement trajectories is a set formed by classifying data with similar movement trajectories in the trajectory dynamic data into one category. Further, the extraction of the trajectory dynamic data and the swing dynamic data in the semen dynamic data can be achieved through specific extraction functions, and the specific extraction functions are compiled by programming languages.

[0052] As an embodiment of the present invention, the clustering process for the trajectory dynamic data to obtain a set of clustered motion trajectories includes:

[0053] Performing a trajectory repair process on the trajectory dynamic data to obtain purified trajectory data;

[0054] Analyzing the motion trajectory corresponding to the purified trajectory data, performing a trajectory segmentation process on the motion trajectory to obtain segmented trajectories, and extracting multi-dimensional motion features from the segmented trajectories;

[0055] Based on the multi-dimensional motion features, constructing a trajectory feature matrix corresponding to the purified trajectory data;

[0056] Calculating the matrix similarity between the trajectory feature matrices, and when the matrix similarity is greater than a preset similarity, performing a clustering process on the motion trajectory to obtain a set of clustered motion trajectories.

[0057] Wherein, the motion trajectory is the actual motion path corresponding to the purified trajectory data; the segmented trajectory is a segment obtained by segmenting the motion trajectory according to certain rules; the multi-dimensional motion features are parameters of multiple dimensions in the segmented trajectory that can reflect motion characteristics; the trajectory feature matrix is a matrix constructed with multi-dimensional motion features as elements corresponding to the purified trajectory data; the matrix similarity represents a quantization value of the similarity degree between the trajectory feature matrices; the preset similarity is a threshold set in advance for judging matrix similarity, which can be set to 0.8 or can be set according to the actual application scenario.

[0058] Further, the trajectory repair process for the trajectory dynamic data can be performed based on the wavelet transform algorithm to obtain purified trajectory data; the motion trajectory corresponding to the purified trajectory data can be analyzed through a spatial coordinate mapping and parameter fitting algorithm; the trajectory segmentation process can be performed on the motion trajectory through a method based on time series segmentation or key node identification to obtain segmented trajectories; the multi-dimensional motion features can be extracted from the segmented trajectories for parameters such as speed, acceleration, and curvature; based on the multi-dimensional motion features, the trajectory feature matrix corresponding to the purified trajectory data can be constructed through a data structured reorganization algorithm; when the matrix similarity is greater than the preset similarity, the motion trajectory can be clustered through classical clustering algorithms such as K-Means to obtain a set of clustered motion trajectories.

[0059] Further, as an alternative embodiment of the present invention, the calculation of the matrix similarity between the trajectory feature matrices includes:

[0060] Calculate the Euclidean distance between the trajectory feature matrices, perform vectorization processing on the trajectory feature matrices to obtain matrix vectors;

[0061] Calculate the vector similarity between the matrix vectors, and based on the vector similarity, determine the cosine similarity between the trajectory feature matrices;

[0062] Calculate the dynamic programming distance between the trajectory feature matrices, and combine the Euclidean distance, the cosine similarity, and the dynamic programming distance to calculate the matrix similarity between the trajectory feature matrices through the following formula

[0063]

[0064] where β represents the matrix similarity between the trace feature matrices, d a (A, B) represents the Euclidean distance between the A-th matrix and the B-th matrix in the trajectory feature matrices, cos(A, B) represents the cosine similarity between the A-th matrix and the B-th matrix in the trajectory feature matrices, d t (A, B) represents the time series distance.

[0065] Among them, the Euclidean distance is a measure based on the square root of the sum of the squares of the element differences between the trajectory feature matrices; the matrix vector is a vector obtained by transforming or extracting the trajectory feature matrices in a certain way; the vector similarity represents the similarity degree between the matrix vectors in terms of direction and length, etc.; the cosine similarity represents the similarity measured by calculating the cosine value of the vector angle between the trajectory feature matrices; the dynamic programming distance is the cumulative distance under the optimal alignment path found by using the dynamic programming algorithm between the trajectory feature matrices.

[0066] Optionally, the Euclidean distance between the trajectory feature matrices can be calculated through a mathematical operation of summing the squares of the differences of the corresponding elements of the trajectory feature matrices and then taking the square root; the trajectory feature matrices can be vectorized by methods such as extracting elements row by row or column by column, principal component analysis, etc. to obtain matrix vectors; the vector similarity between the matrix vectors can be calculated by calculating the inner product of the matrix vectors and combining the vector norms, and the cosine similarity between the matrix vectors can be obtained by summing the vector similarities; the dynamic programming distance between the trajectory feature matrices can be calculated iteratively by constructing a cost matrix and using the recurrence formula of the dynamic programming algorithm.

[0067] By analyzing the trajectory behavior patterns corresponding to the set of clustered motion trajectories, the present invention can summarize the sperm motility rules, clarify the characteristics and differences of different motility patterns, and construct an accurate trajectory behavior classification system; based on the trajectory behavior patterns, dysfunctional sperm in the target semen sample can be identified, and the types and proportions of dysfunctional sperm in the semen sample can be obtained, providing scientific and reliable data support for clinical male fertility assessment. Among them, the trajectory behavior pattern is a motility pattern with specific rules and characteristics corresponding to the set of clustered motion trajectories, and the dysfunctional sperm are sperm with abnormal motility, morphology, or other functions in the target semen sample. Further, based on the trajectory behavior patterns, dysfunctional sperm in the target semen sample are identified. For example, sperm corresponding to trajectory behavior patterns such as highly irregular motion trajectories and speeds significantly deviating from the normal range are determined as dysfunctional sperm.

[0068] As an embodiment of the present invention, the analysis of the trajectory behavior patterns corresponding to the set of clustered motion trajectories includes:

[0069] According to a preset basic motion state, the set of clustered motion trajectories is marked with states to obtain the trajectory motion states;

[0070] Based on the trajectory motion states, a state transition log corresponding to the set of clustered motion trajectories is generated;

[0071] According to the state transition log, a motion state sequence corresponding to the set of clustered motion trajectories is constructed;

[0072] The state transition probabilities corresponding to the motion state sequence are calculated, and based on the state transition probabilities, a transition matrix corresponding to each trajectory in the set of clustered motion trajectories is constructed;

[0073] Based on the transition matrix, a pattern feature vector corresponding to each trajectory in the set of clustered motion trajectories is generated;

[0074] Based on the pattern feature vector, the trajectory behavior patterns corresponding to the set of clustered motion trajectories are analyzed.

[0075] Among them, the basic motion state is a pre-set state set for describing the basic motion characteristics of sperm, such as static, linear motion, curvilinear motion, etc. The trajectory motion state is the specific motion state situation presented after the clustering motion trajectory set is marked according to the basic motion state. The state transition log is an information set corresponding to the clustering motion trajectory set that records the changes in the motion state of each sperm at different times. The motion state sequence is a sequence of the motion states of sperm corresponding to the clustering motion trajectory set arranged in chronological order. The state transition probability is a numerical value corresponding to the motion state sequence that represents the likelihood of transitioning from one motion state to another. The transition matrix is a matrix corresponding to each trajectory in the clustering motion trajectory set for describing the transition probability between motion states. The pattern feature vector is a vector corresponding to each trajectory in the clustering motion trajectory set that can reflect its motion pattern characteristics.

[0076] Optionally, according to the pre-set basic motion state, the clustering motion trajectory set can be state-marked by means of pairwise trajectory comparison and matching to obtain the trajectory motion state. Based on the trajectory motion state, the state transition log corresponding to the clustering motion trajectory set can be generated by recording the changes in the motion state at adjacent time points. According to the state transition log, the motion state sequence corresponding to the clustering motion trajectory set can be constructed by means of sorting in chronological order. The state transition probability corresponding to the motion state sequence can be calculated by statistically counting the frequencies of each state transition and normalizing. Based on the state transition probability, the transition matrix corresponding to each trajectory in the clustering motion trajectory set can be constructed by filling in the corresponding state transition probability values. Based on the transition matrix, the pattern feature vector corresponding to each trajectory in the clustering motion trajectory set can be generated by extracting the key parameters and eigenvalues of the matrix. Based on the pattern feature vector, the trajectory behavior pattern corresponding to the clustering motion trajectory set can be analyzed by means of feature induction, such as sorting out the commonalities and differences of the feature vector in dimensions such as speed change, direction turning, and displacement fluctuation, and inducing typical trajectory behavior patterns such as linear acceleration, spiral hovering, and disordered tremor.

[0077] The reproductive function scoring and evaluation module 103 is used to extract the swing dynamic features in the swing dynamic data, and based on the swing dynamic features, evaluate the sperm motility in the target semen sample. Combining the morphological defect rate, the dysfunctional sperm, and the sperm motility, evaluate the reproductive function score corresponding to the target semen sample.

[0078] By extracting the swinging dynamic features from the swinging dynamic data, the subtle characteristics of sperm movement can be accurately captured, providing an intuitive and reliable quantitative basis for the evaluation of the reproductive function score corresponding to the target semen sample. Among them, the swinging dynamic features are a set of parameters in the swinging dynamic data that can characterize the swinging behavior characteristics of sperm, quantify the swinging behavior process, and provide key information for sperm movement state analysis and semen quality assessment, such as swinging frequency, amplitude, path tortuosity, etc.

[0079] As an embodiment of the present invention, the extraction of the swinging dynamic features from the swinging dynamic data includes:

[0080] Extract the swinging dynamic signal corresponding to the swinging dynamic data, perform intrinsic mode decomposition processing on the swinging dynamic signal to obtain signal intrinsic modes;

[0081] Calculate the modal energy proportion corresponding to the signal intrinsic modes, and based on the modal energy proportion, construct a swinging energy spectrum corresponding to the swinging dynamic signal;

[0082] Perform spectral peak detection on the swinging energy spectrum to obtain energy spectrum peak features;

[0083] Extract the time-domain spectral peak features and frequency-domain spectral peak features from the energy spectrum peak features, and perform feature fusion processing on the time-domain spectral peak features and the frequency-domain spectral peak features to obtain the swinging dynamic features in the swinging dynamic data.

[0084] Among them, the swinging dynamic signal is a time-series signal corresponding to the swinging dynamic data; the signal intrinsic mode is a component with different time-scale characteristics obtained by performing intrinsic mode decomposition processing on the swinging dynamic signal; the modal energy proportion is the proportion of the energy of each component corresponding to the signal intrinsic mode in the total energy; the swinging energy spectrum is an energy-frequency distribution map constructed based on the modal energy proportion corresponding to the swinging dynamic signal; the energy spectrum peak feature is a feature reflecting the peak characteristics of energy distribution obtained after spectral peak detection of the swinging energy spectrum; the time-domain spectral peak feature and the frequency-domain spectral peak feature are respectively relevant feature parameters describing the spectral peak in the time domain and frequency domain in the energy spectrum peak feature.

[0085] Further, the swing dynamic signal corresponding to the swing dynamic data can be extracted through a conversion algorithm based on the sensor principle and data acquisition specifications; the swing dynamic signal can be subjected to intrinsic mode decomposition processing through an empirical mode decomposition (EMD) algorithm to obtain signal intrinsic modes; based on the modal energy ratio, the swing energy spectrum corresponding to the swing dynamic signal can be constructed through a plotting algorithm that arranges the energy ratios of each IMF in the frequency or time dimension; the swing energy spectrum can be subjected to spectral peak detection through a detection algorithm based on peak search and threshold judgment to obtain energy spectrum peak characteristics; the time-domain spectrum peak characteristics and frequency-domain spectrum peak characteristics in the energy spectrum peak characteristics can be extracted through a parameter extraction method defined based on time-domain and frequency-domain characteristics, and the time-domain spectrum peak characteristics and the frequency-domain spectrum peak characteristics can be subjected to feature fusion processing through fusion strategies such as splicing and weighted summation to obtain the swing dynamic characteristics in the swing dynamic data.

[0086] Further, as an optional embodiment of the present invention, calculating the modal energy ratio corresponding to the signal intrinsic mode includes:

[0087]

[0088] where δ represents the modal energy ratio corresponding to the signal intrinsic mode, and IMF k (t) represents the modal energy value corresponding to the k-th mode in the signal intrinsic mode at time t, k represents the serial number corresponding to the signal intrinsic mode, N represents the number of modes corresponding to the signal intrinsic mode, t represents the starting time point corresponding to the signal intrinsic mode, and T represents the ending time point corresponding to the signal intrinsic mode.

[0089] Based on the swinging dynamic characteristics, the present invention evaluates the sperm motility intensity in the target semen sample, which can accurately quantify the vitality performance of sperm during movement. By combining the morphological defect rate, the dysfunctional sperm, and the sperm motility intensity, the reproductive function score corresponding to the target semen sample is evaluated, so as to comprehensively and thoroughly evaluate the semen quality from multiple dimensions and obtain a description of the reproductive ability performance of the target semen sample. Among them, the sperm motility intensity is an index of vitality and intensity shown by sperm in the target semen sample during movement, and the reproductive function score is a quantitative score corresponding to the target semen sample that comprehensively reflects its fertility ability. Further, based on the swinging dynamic characteristics, to evaluate the sperm motility intensity in the target semen sample, first, the swinging dynamic characteristics are disassembled, key parameters such as the swinging frequency and amplitude are extracted, and movement data such as sperm displacement and speed change per unit time are calculated using them. Then, according to clinical experience and research data, these data are compared with the standard threshold to determine the sperm motility intensity level, thus realizing the evaluation of the sperm motility intensity in the target semen sample; by combining the morphological defect rate, the dysfunctional sperm, and the sperm motility intensity, to evaluate the reproductive function score corresponding to the target semen sample, the proportion of dysfunctional sperm is calculated based on the dysfunctional sperm, the proportion of dysfunctional sperm, the morphological defect rate, and the sperm motility intensity are normalized, and the average value of the normalized values is calculated to obtain the reproductive function score corresponding to the target semen sample.

[0090] The dynamic vitality potential score evaluation module 104 is used to configure the adapted culture solution corresponding to the target semen sample, place the target semen sample in the adapted culture solution for culture treatment, record the sperm viability benchmark parameters during the culture treatment process, calculate the sperm survival rate of the target semen sample based on the viability benchmark parameters, and evaluate the dynamic vitality potential score corresponding to the target semen sample based on the sperm survival rate.

[0091] The present invention facilitates the refined and targeted cultivation of the target semen sample by configuring the adaptation culture medium corresponding to the target semen sample; the target semen sample is placed in the adaptation culture medium for cultivation, and the sperm motility benchmark parameters during the cultivation process are recorded, thereby facilitating the subsequent accurate calculation of sperm survival rate. Among them, the adaptation culture medium is a liquid that simulates the survival environment configured according to the usage scenario of the target semen sample, and the sperm motility benchmark parameters are the basic data reflecting the survival and movement status of sperm during the cultivation process, such as the number of motile sperm per unit volume. Further, the steps for configuring the adaptation culture medium corresponding to the target semen sample are as follows: query the application scenario corresponding to the target semen sample, analyze the physical and chemical characteristics corresponding to the application scenario, determine the basic formula of the culture medium according to the physical and chemical characteristics, combine the physiological requirements of sperm, adjust the proportion of nutrients and additives in the basic formula, and prepare the adaptation culture medium according to the adjusted formula; the recording of the sperm motility benchmark parameters during the cultivation process can be achieved through a microscopic observation device equipped with image analysis software. Using a phase contrast microscope or a fluorescence microscope, capture the sperm movement images, and the image analysis software automatically identifies and counts the number of motile sperm per unit volume.

[0092] The present invention calculates the sperm survival rate of the target semen sample based on the motility benchmark parameters, so as to understand the sperm survival status corresponding to the target semen sample, and then intuitively master the proportion of surviving sperm in the semen sample, providing a basis for the subsequent evaluation and processing of the reproductive function score corresponding to the target semen sample. Among them, the sperm survival rate represents the proportion of surviving sperm in the total number of sperm in the target semen sample.

[0093] As an embodiment of the present invention, the calculation of the sperm survival rate of the target semen sample based on the motility benchmark parameters includes:

[0094] Identify the motility evaluation indexes corresponding to the motility benchmark parameters, and the motility evaluation indexes include speed evaluation indexes and direction evaluation indexes;

[0095] Combined with the speed evaluation index, the direction evaluation index and the motility benchmark parameters, perform vitality grading and marking processing on the sperm in the target semen sample to obtain a marking result;

[0096] The marking results are divided into: forward movement category, non-forward movement category and immotile category. Respectively count the number of sperm corresponding to the forward movement category, the non-forward movement category and the immotile category to obtain the first sperm number, the second sperm number and the third sperm number;

[0097] Combined with the first sperm number, the second sperm number and the third sperm number, calculate the sperm survival rate of the target semen sample through the following formula:

[0098]

[0099] Among them, φ represents the sperm survival rate of the target semen sample, D represents the first sperm count, E represents the second sperm count, and F represents the third sperm count.

[0100] Among them, the viability evaluation index is the evaluation dimension corresponding to the viability benchmark parameter, which is used to measure sperm motility; the speed evaluation index and the direction evaluation index are respectively the key components of the viability evaluation index, the former quantifies the speed of sperm movement, and the latter describes the direction of sperm movement path; the forward movement category is the classification of sperm with a movement speed ≥25μm / s and a movement direction angle <45°, the non-forward movement category is the classification of sperm with a movement speed ≥5μm / s but not meeting the forward movement standard, and the inactive category is the classification of sperm with a movement speed <5μm / s that is almost without motility.

[0101] Furthermore, the viability evaluation index corresponding to the viability benchmark parameter can be identified according to preset rules, and the preset rules can be set according to the World Health Organization; in combination with the speed evaluation index, the direction evaluation index and the viability benchmark parameter, a convolutional neural network (CNN) classifier with a built-in World Health Organization (WHO) classification standard can be used to perform viability grading and labeling processing on the sperm in the target semen sample to obtain a labeling result.

[0102] The present invention evaluates the dynamic vitality potential score corresponding to the target semen sample based on the sperm survival rate, so as to understand the potential ability of the sperm corresponding to the target semen sample to maintain continuous activity and achieve the fertilization process, wherein the dynamic vitality potential score is a quantitative value corresponding to the target semen sample that measures the possibility of the sperm continuing to exert vitality and achieve conception during the fertilization process. Furthermore, based on the sperm survival rate, the dynamic vitality potential score corresponding to the target semen sample is evaluated. For example, if the sperm survival rate is ≥80%: when the sperm survival rate is 80% or above, it means that most of the sperm in the sample are active. Combined with the forward movement The proportion of motile sperm: if the proportion of forward-moving sperm exceeds 60%, a higher dynamic motility potential score can be given, which means that the sample has excellent fertility potential; 60% ≤ sperm survival rate <80%: the sperm survival rate is in the range of 60% to 80%. If the proportion of non-forward-moving sperm is high and the proportion of sperm with normal morphology is high, a medium to high dynamic motility potential score will be given; if there are more abnormal sperm, the score will be reduced accordingly; 40% ≤ sperm survival rate <60%: the sperm survival rate is between 40% and 60%, and a medium dynamic motility potential score can be given; survival rate <40%: when the sperm survival rate is lower than 40%, it indicates that the sample quality is poor and a lower score is given.

[0103] The semen quality analysis module 105 is configured to generate a semen quality analysis report corresponding to the target semen sample by combining the reproductive function score and the dynamic vitality potential score.

[0104] By combining the reproductive function score and the dynamic vitality potential score to generate a semen quality analysis report corresponding to the target semen sample, high-quality semen quality analysis results can be obtained. The semen quality analysis report is the result of a comprehensive quality analysis corresponding to the target semen sample. Further, by combining the reproductive function score and the dynamic vitality potential score to generate a semen quality analysis report corresponding to the target semen sample, for example, presenting each score in tabular form and analyzing the quality of semen with text.

[0105] By performing image segmentation processing on the sample optical microscopic image, an image that clearly distinguishes sperm from other impurities and accurately identifies sperm morphology can be obtained. It can not only intuitively display the details of sperm morphology but also help accurately calculate the sperm morphology defect rate. Optionally, by performing clustering processing on the trajectory dynamic data, a set of clustered movement trajectories can be obtained, which can integrate sperm trajectory information with similar movement characteristics and quickly locate different movement pattern groups. By extracting the swing dynamic characteristics in the swing dynamic data, the subtle characteristics of sperm movement can be accurately captured, providing an intuitive and reliable quantitative basis for the evaluation of the reproductive function score corresponding to the target semen sample. By configuring an adapted culture solution corresponding to the target semen sample, it is convenient to perform refined and targeted cultivation on the target semen sample. Placing the target semen sample in the adapted culture solution for cultivation and recording the sperm viability benchmark parameters during the cultivation process, and then facilitating the subsequent accurate calculation of sperm survival rate. By combining the reproductive function score and the dynamic vitality potential score to generate a semen quality analysis report corresponding to the target semen sample, high-quality semen quality analysis results can be obtained. Therefore, the detection accuracy of semen quality is improved.

[0106] As Figure 2 shown, it is a schematic flowchart of a method for automatically detecting semen quality provided by an embodiment of the present invention. In this embodiment, the method for automatically detecting semen quality includes:

[0107] Obtain a target semen sample to be detected, collect the sample optical microscopic image and semen dynamic data of the target semen sample, perform image segmentation processing on the sample optical microscopic image to obtain a sperm segmentation image, and calculate the morphology defect rate corresponding to the target semen sample based on the sperm segmentation image.

[0108] Extract the trajectory dynamic data and the swing dynamic data from the semen dynamic data, perform clustering processing on the trajectory dynamic data to obtain a set of clustered motion trajectories, analyze the trajectory behavior patterns corresponding to the set of clustered motion trajectories, and identify the dysfunctional sperm in the target semen sample based on the trajectory behavior patterns;

[0109] Extract the swing dynamic features from the swing dynamic data, evaluate the sperm motility intensity in the target semen sample based on the swing dynamic features, and combine the morphological defect rate, the dysfunctional sperm, and the sperm motility intensity to evaluate the reproductive function score corresponding to the target semen sample;

[0110] Configure the appropriate culture medium corresponding to the target semen sample, place the target semen sample in the appropriate culture medium for culture processing, and record the sperm viability reference parameters during the culture processing. Calculate the sperm survival rate of the target semen sample based on the viability reference parameters, and evaluate the dynamic viability potential score corresponding to the target semen sample based on the sperm survival rate;

[0111] Generate a semen quality analysis report corresponding to the target semen sample by combining the reproductive function score and the dynamic viability potential score.

[0112] In several embodiments provided by the present invention, it should be understood that the provided systems and methods can be implemented in other ways. For example, the system embodiments described above are merely illustrative. For example, the division of the modules is only a logical function division, and there can be other division methods in actual implementation.

[0113] In addition, each functional module in various embodiments of the present invention can be integrated in a processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit. The above integrated unit can be implemented in the form of hardware, or in the form of a combination of hardware and software functional modules.

[0114] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit them. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical solutions of the present invention can be modified or equivalently replaced without departing from the spirit and scope of the technical solutions of the present invention.

Claims

1. An automated semen quality detection system, characterized in that, The system for automatically detecting semen quality includes: a morphological defect rate calculation module, a dysfunctional sperm recognition module, a reproductive function score evaluation module, a dynamic vitality potential score evaluation module, and a semen quality analysis module; The morphological defect rate calculation module is used to obtain a target semen sample to be detected, collect a sample optical microscopic image and semen dynamic data of the target semen sample, perform image segmentation processing on the sample optical microscopic image to obtain a sperm segmentation image, and calculate the morphological defect rate corresponding to the target semen sample based on the sperm segmentation image; The dysfunctional sperm recognition module is used to extract trajectory dynamic data and swing dynamic data from the semen dynamic data, perform clustering processing on the trajectory dynamic data to obtain a set of clustered motion trajectories, analyze the trajectory behavior patterns corresponding to the set of clustered motion trajectories, and recognize dysfunctional sperm in the target semen sample based on the trajectory behavior patterns; The reproductive function score evaluation module is used to extract swing dynamic features from the swing dynamic data, evaluate the sperm motility intensity in the target semen sample based on the swing dynamic features, and evaluate the reproductive function score corresponding to the target semen sample by combining the morphological defect rate, the dysfunctional sperm, and the sperm motility intensity; The dynamic vitality potential score evaluation module is used to configure an adapted culture medium corresponding to the target semen sample, place the target semen sample in the adapted culture medium for culture processing, record the sperm viability reference parameters during the culture processing, calculate the sperm survival rate of the target semen sample based on the viability reference parameters, and evaluate the dynamic vitality potential score corresponding to the target semen sample based on the sperm survival rate; The semen quality analysis module is used to generate a semen quality analysis report corresponding to the target semen sample by combining the reproductive function score and the dynamic vitality potential score.

2. The system for automatically detecting semen quality according to claim 1, characterized in that The performing image segmentation processing on the sample optical microscopic image to obtain a sperm segmentation image includes: Performing image denoising processing on the sample optical microscopic image to obtain a denoised optical microscopic image; Performing grayscale processing on the denoised optical microscopic image to obtain a grayscale optical microscopic image; Performing region division on the grayscale optical microscopic image to obtain an optical microscopic region image, and extracting the grayscale distribution features corresponding to the optical microscopic region image; Determining the segmentation threshold corresponding to the grayscale optical microscopic image based on the grayscale distribution features; Performing image segmentation on the grayscale optical microscopic image based on the segmentation threshold to obtain an initial sperm segmentation image; Performing morphological optimization processing on the initial sperm segmentation image to obtain a sperm segmentation image.

3. The automated semen quality detection system according to claim 1, characterized in that, The calculating the morphological defect rate corresponding to the target semen sample based on the sperm segmentation image includes: Extracting morphological parameters from the sperm segmentation image, and identifying morphologically abnormal sperm in the sperm segmentation image based on the morphological parameters; Statistically analyzing the sperm morphological characteristics in the sperm segmentation image based on the morphological parameters; Based on the morphological characteristics of the sperm, determine the severity of the abnormality corresponding to the morphologically abnormal sperm; Assign the abnormality weight corresponding to the morphologically abnormal sperm, and combine the severity of the abnormality and the abnormality weight to calculate the abnormality defect value corresponding to the morphologically defective sperm; Based on the abnormality defect value, screen out the morphologically defective sperm from the morphologically abnormal sperm; Based on the morphologically defective sperm, calculate the morphological defect rate corresponding to the target semen sample.

4. The system for automatically detecting semen quality according to claim 1, wherein The clustering process of the trajectory dynamic data to obtain a set of clustered motion trajectories includes: Perform trajectory repair processing on the trajectory dynamic data to obtain purified trajectory data; Analyze the motion trajectory corresponding to the purified trajectory data, perform trajectory segmentation processing on the motion trajectory to obtain segmented trajectories, and extract multi-dimensional motion features from the segmented trajectories; Based on the multi-dimensional motion features, construct a trajectory feature matrix corresponding to the purified trajectory data; Calculate the matrix similarity between the trajectory feature matrices. When the matrix similarity is greater than the preset similarity, perform clustering processing on the motion trajectories to obtain a set of clustered motion trajectories.

5. The automated semen quality detection system according to claim 4, wherein The calculation of the matrix similarity between the trajectory feature matrices includes: Calculate the Euclidean distance between the trajectory feature matrices, perform vectorization processing on the trajectory feature matrices to obtain matrix vectors; Calculate the vector similarity between the matrix vectors, and based on the vector similarity, determine the cosine similarity between the trajectory feature matrices; Calculate the dynamic programming distance between the trajectory feature matrices, and combine the Euclidean distance, the cosine similarity, and the dynamic programming distance to calculate the matrix similarity between the trajectory feature matrices.

6. The system for automatically detecting semen quality according to claim 1, characterized in that, The analysis of the trajectory behavior pattern corresponding to the set of clustered motion trajectories includes: According to the preset basic motion state, perform state marking on the set of clustered motion trajectories to obtain the trajectory motion state; Based on the trajectory motion state, generate a state transition log corresponding to the set of clustered motion trajectories; According to the state transition log, construct a motion state sequence corresponding to the set of clustered motion trajectories; Calculate the state transition probability corresponding to the motion state sequence, and based on the state transition probability, construct a transition matrix corresponding to each trajectory in the set of clustered motion trajectories; Based on the transition matrix, generate a pattern feature vector corresponding to each trajectory in the set of clustered motion trajectories; Based on the pattern feature vector, analyze the trajectory behavior pattern corresponding to the set of clustered motion trajectories.

7. The automated semen quality detection system according to claim 1, wherein The extraction of the swing dynamic features in the swing dynamic data includes: Extract the swing dynamic signal corresponding to the swing dynamic data, perform intrinsic mode decomposition processing on the swing dynamic signal to obtain the signal intrinsic mode; Calculate the modal energy proportion corresponding to the signal intrinsic mode, and based on the modal energy proportion, construct a swing energy spectrum corresponding to the swing dynamic signal; Perform spectral peak detection on the swing energy spectrum to obtain the energy spectrum peak feature; Extract the time-domain spectral peak features and frequency-domain spectral peak features in the energy spectral peak features, perform feature fusion processing on the time-domain spectral peak features and the frequency-domain spectral peak features, and obtain the swing dynamic features in the swing dynamic data.

8. The automated semen quality detection system according to claim 1, characterized in that Calculating the sperm survival rate of the target semen sample based on the viability reference parameter includes: Identifying the viability evaluation indicators corresponding to the viability reference parameter, where the viability evaluation indicators include a speed evaluation indicator and a direction evaluation indicator; Combining the speed evaluation indicator, the direction evaluation indicator, and the viability reference parameter, perform viability grading annotation processing on the sperm in the target semen sample to obtain an annotation result; The annotation results are divided into: forward movement category, non-forward movement category, and immotile category. Respectively count the number of sperm corresponding to the forward movement category, the non-forward movement category, and the immotile category to obtain the first sperm number, the second sperm number, and the third sperm number; Combining the first sperm number, the second sperm number, and the third sperm number, calculate the sperm survival rate of the target semen sample.

9. A method for automatically detecting semen quality, which is implemented based on the system described in claim 1, characterized in that, The method includes: Obtain a target semen sample to be detected, collect the sample optical microscopic image and semen dynamic data of the target semen sample, perform image segmentation processing on the sample optical microscopic image to obtain a sperm segmentation image, and calculate the morphological defect rate corresponding to the target semen sample based on the sperm segmentation image; Extract the trajectory dynamic data and swing dynamic data in the semen dynamic data, perform clustering processing on the trajectory dynamic data to obtain a set of clustered movement trajectories, analyze the trajectory behavior patterns corresponding to the set of clustered movement trajectories, and identify dysfunctional sperm in the target semen sample based on the trajectory behavior patterns; Extract the swing dynamic features in the swing dynamic data, evaluate the sperm movement intensity in the target semen sample based on the swing dynamic features, and combine the morphological defect rate, the dysfunctional sperm, and the sperm movement intensity to evaluate the reproductive function score corresponding to the target semen sample; Configure the appropriate culture medium corresponding to the target semen sample, place the target semen sample in the appropriate culture medium for culture processing, and record the sperm viability reference parameter during the culture processing. Calculate the sperm survival rate of the target semen sample based on the viability reference parameter, and evaluate the dynamic viability potential score corresponding to the target semen sample based on the sperm survival rate; Combine the reproductive function score and the dynamic viability potential score to generate a semen quality analysis report corresponding to the target semen sample.

Images