CN117911407A - Image recognition method for sperm defect morphology - Google Patents
Image recognition method for sperm defect morphology Download PDFInfo
- Publication number
- CN117911407A CN117911407A CN202410309236.7A CN202410309236A CN117911407A CN 117911407 A CN117911407 A CN 117911407A CN 202410309236 A CN202410309236 A CN 202410309236A CN 117911407 A CN117911407 A CN 117911407A
- Authority
- CN
- China
- Prior art keywords
- sperm
- defect
- morphology
- image
- evaluation index
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 230000007547 defect Effects 0.000 title claims abstract description 338
- 238000000034 method Methods 0.000 title claims abstract description 74
- 238000011156 evaluation Methods 0.000 claims abstract description 183
- 230000002950 deficient Effects 0.000 claims abstract description 75
- 238000005516 engineering process Methods 0.000 claims abstract description 15
- 230000000877 morphologic effect Effects 0.000 claims description 43
- 230000008569 process Effects 0.000 claims description 33
- 238000012545 processing Methods 0.000 claims description 22
- 238000013527 convolutional neural network Methods 0.000 claims description 17
- 238000013136 deep learning model Methods 0.000 claims description 15
- 238000004364 calculation method Methods 0.000 claims description 11
- 238000007781 pre-processing Methods 0.000 claims description 9
- 230000001419 dependent effect Effects 0.000 claims description 8
- 238000012549 training Methods 0.000 claims description 6
- 238000000605 extraction Methods 0.000 claims description 5
- 238000011176 pooling Methods 0.000 claims description 5
- 238000000611 regression analysis Methods 0.000 claims description 5
- 238000012417 linear regression Methods 0.000 claims description 4
- 238000013507 mapping Methods 0.000 claims description 4
- 230000000007 visual effect Effects 0.000 claims description 4
- 206010061199 Head deformity Diseases 0.000 claims description 3
- 230000002708 enhancing effect Effects 0.000 claims description 3
- 230000035558 fertility Effects 0.000 abstract description 7
- 230000036541 health Effects 0.000 abstract description 5
- 238000005457 optimization Methods 0.000 abstract description 2
- 210000003739 neck Anatomy 0.000 description 47
- 230000002159 abnormal effect Effects 0.000 description 12
- 238000004458 analytical method Methods 0.000 description 11
- 230000000875 corresponding effect Effects 0.000 description 8
- 238000004590 computer program Methods 0.000 description 7
- 238000005452 bending Methods 0.000 description 6
- 238000010586 diagram Methods 0.000 description 6
- 230000008961 swelling Effects 0.000 description 5
- 230000006870 function Effects 0.000 description 4
- 238000012986 modification Methods 0.000 description 4
- 230000004048 modification Effects 0.000 description 4
- 238000003860 storage Methods 0.000 description 4
- 238000013473 artificial intelligence Methods 0.000 description 3
- 230000001850 reproductive effect Effects 0.000 description 3
- 230000009933 reproductive health Effects 0.000 description 3
- 231100000182 Sperm DNA damage Toxicity 0.000 description 2
- 230000004075 alteration Effects 0.000 description 2
- 238000013135 deep learning Methods 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 238000010606 normalization Methods 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000001276 controlling effect Effects 0.000 description 1
- 230000002596 correlated effect Effects 0.000 description 1
- 238000013079 data visualisation Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 201000010099 disease Diseases 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000005713 exacerbation Effects 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 238000010191 image analysis Methods 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 230000036512 infertility Effects 0.000 description 1
- 208000000509 infertility Diseases 0.000 description 1
- 231100000535 infertility Toxicity 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000005477 standard model Effects 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 230000001131 transforming effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0012—Biomedical image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/0464—Convolutional networks [CNN, ConvNet]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20084—Artificial neural networks [ANN]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30004—Biomedical image processing
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Software Systems (AREA)
- Artificial Intelligence (AREA)
- Computing Systems (AREA)
- Medical Informatics (AREA)
- Multimedia (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Data Mining & Analysis (AREA)
- Computational Linguistics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Molecular Biology (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Radiology & Medical Imaging (AREA)
- Quality & Reliability (AREA)
- Image Processing (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses an image recognition method of sperm defect morphology, which is characterized in that the quality and the health condition of sperms can be accurately evaluated by calculating the sperm defect morphology image evaluation index, measuring the sperm defect degree, judging the severity of sperm defects, further predicting the fertility and the conception success rate of men, helping to formulate personalized treatment schemes and suggestions so as to improve the fertility of men and the success rate of assisted reproduction technology, analyzing the sperm defect morphology image coincidence degree, calculating the sperm defect morphology image coincidence coefficient, recognizing defective sperm images, helping doctors and researchers to better understand the sperm quality and the health condition, and assisting the selection and optimization of reproduction technology.
Description
Technical Field
The invention relates to the technical field of artificial intelligence, in particular to an image recognition method of sperm defect morphology.
Background
With the continuous development of science and technology, people have more and more attention to reproductive health.
Sperm quality is an important factor affecting reproductive health, and sperm defect morphology is an important index of sperm quality, and in addition, with the decrease of fertility and the exacerbation of infertility problems, assisted reproductive technology has become a means of increasing home dependence.
For example, publication No.: CN114518362a discloses sperm quality analysis devices, systems, methods, and readable storage media, through which sperm quality analysis devices, including a microscopic image scanning system, a processor, and a temperature control system; the sperm quality analysis system comprises an automatic objective lens conversion system, an automatic moving platform, a phase contrast imaging recognition system, an image processing system and a constant temperature control system; the sperm morphology classifying system based on deep learning takes a preprocessing morphology picture as input to finish the work of sperm morphology recognition and classification, and the image preprocessing firstly selectively processes target sperm of an image to improve the visual effect of the image and converts the target sperm into a form which is more suitable for being processed by an analyzer; then the processor respectively performs sperm dynamics analysis, sperm morphology analysis and sperm DNA damage analysis on the sperm; realize the integration of full-automatic sperm morphology analysis and sperm DNA damage analysis.
Traditional sperm detection and assessment methods rely on manual manipulation and observation, are time consuming and laborious and are susceptible to subjective factors.
And the image recognition is performed by utilizing an artificial intelligence technology, so that the automatic identification and classification of a large number of sperm images can be realized, and the accuracy and efficiency are improved.
Disclosure of Invention
Aiming at the defects of the prior art, the invention provides an image recognition method of sperm defect morphology, which solves the problems of the background technology.
In order to achieve the above purpose, the invention is realized by the following technical scheme: an image recognition method of sperm defect morphology comprises the following steps: s1, acquiring a sperm morphology image to be identified and a defective sperm morphology image, and preprocessing the sperm morphology image to be identified and the defective sperm morphology image to acquire sperm morphology image data to be identified and defective sperm morphology image data; s2, processing the sperm morphology image data to be identified and the defective sperm morphology image data by using a convolutional neural network of a deep learning model based on the sperm morphology image data to be identified and the defective sperm morphology image data, and establishing a sperm defect image identification model; s3, analyzing the sperm morphology image data to be identified based on a sperm defect image identification model, and calculating a sperm head defect morphology image evaluation index, a sperm neck defect morphology image evaluation index and a sperm tail defect morphology image evaluation index; s4, calculating a sperm defect morphology image evaluation index based on the sperm head defect morphology image evaluation index, the sperm neck defect morphology image evaluation index and the sperm tail defect morphology image evaluation index, wherein the sperm defect morphology image evaluation index is used for measuring the sperm defect degree; s5, analyzing the coincidence degree of the sperm defect morphology image based on the sperm defect morphology image evaluation index, and calculating a sperm defect morphology image coincidence coefficient which is used for evaluating the coincidence degree of the sperm defect morphology image; s6, identifying the defective sperm image based on the sperm defect morphology image coincidence coefficient.
Further, preprocessing the sperm morphology image to be identified and the defective sperm morphology image, and acquiring the sperm morphology image data to be identified and the defective sperm morphology image data comprises the following specific processes: loading the sperm morphology image to be identified and the defective sperm morphology image into visual software, and converting the sperm morphology gray level image to be identified and the defective sperm morphology gray level image; performing histogram equalization on the sperm morphology gray image to be identified and the defective sperm morphology gray image by using an image processing technology, and enhancing the contrast ratio and the definition of the sperm morphology gray image to be identified and the defective sperm morphology gray image; normalizing the sperm morphology gray level image to be identified and the defective sperm morphology gray level image by using a computer vision technology, mapping pixel values to a specified range, and obtaining sperm morphology image data to be identified and defective sperm morphology image data.
Further, the convolutional neural network of the deep learning model is used for processing the sperm morphology image data to be identified and the defective sperm morphology image data, and the specific process for establishing the sperm defect image identification model is as follows: feature extraction is carried out on sperm morphology image data to be identified and defective sperm morphology image data by using a convolutional neural network CNN of a deep learning model, and features with different levels and degrees of abstraction are extracted through a plurality of convolutional layers and pooling layers, so that a feature set of defective sperm morphology is constructed; and taking a convolutional neural network model of the deep learning model as a reference model, performing training fitting on the reference model based on a characteristic set of the defective sperm morphology, and establishing a sperm defective image recognition model.
Further, based on the sperm defect image recognition model, the specific process of analyzing the sperm morphology image data to be recognized is as follows: recognizing sperm morphology image data to be recognized based on a sperm defect image recognition model to acquire sperm defect morphology image data; sperm defect morphology image data includes: sperm head defect morphology image data, sperm neck defect morphology image data, and sperm tail defect morphology image data.
Further, the specific process of calculating the sperm defect morphology image evaluation index is as follows: analyzing the degree of sperm head deformity based on the sperm head defect morphological image data, and calculating a sperm head defect morphological image evaluation index; based on the morphological image data of the sperm neck defect, analyzing the degree of sperm neck defect, and calculating the morphological image evaluation index of the sperm neck defect; analyzing the degree of the tail deformity of the sperm based on the sperm tail defect morphology image data, and calculating a sperm tail defect morphology image evaluation index; calculating the sperm defect morphology image evaluation index based on the sperm head defect morphology image evaluation index, the sperm neck defect morphology image evaluation index and the sperm tail defect morphology image evaluation index.
Further, the specific formula of the sperm defect morphology image evaluation index is as follows:
；
In the method, in the process of the invention, Image evaluation index representing sperm defect morphology,/>Image evaluation index for representing sperm head defect morphology,/>Image evaluation index for representing neck defect of sperm,/>An image evaluation index indicating the defect morphology of the tail of the sperm,Weight factor representing sperm head defect morphology image evaluation index corresponding to sperm defect morphology image evaluation index,/>Weight factor representing sperm neck defect morphology image evaluation index corresponding to sperm defect morphology image evaluation index,/>And the weight factor which represents the sperm tail defect morphology image evaluation index corresponds to the sperm defect morphology image evaluation index.
Further, the specific calculation process of the weight factors of the sperm defect morphology image assessment index corresponding to the sperm head defect morphology image assessment index, the sperm neck defect morphology image assessment index and the sperm tail defect morphology image assessment index is as follows: using multiple linear regression model, taking the sperm head defect morphology image evaluation index, the sperm neck defect morphology image evaluation index and the sperm tail defect morphology image evaluation index as independent variables X, taking the sperm defect morphology image evaluation index as dependent variables Y, and setting the intercept asAnd error term/>; Establishing association between independent variable X and dependent variable Y, and settingAnd fitting the established regression model by using a regression analysis method to obtain the regression coefficient of each independent variable as the weight factors of the sperm defect morphology image evaluation index corresponding to the sperm head defect morphology image evaluation index, the sperm neck defect morphology image evaluation index and the sperm tail defect morphology image evaluation index.
Further, based on the sperm defect morphology image evaluation index, analyzing the sperm defect morphology image coincidence degree, and calculating the sperm defect morphology image coincidence coefficient comprises the following specific processes: based on the sperm defect morphology image evaluation index, comparing the sperm defect morphology image evaluation index with a threshold value of the sperm defect morphology image evaluation index, and calculating a difference value between the sperm defect morphology image evaluation index and the threshold value of the sperm defect morphology image evaluation index; comparing the difference value of the sperm defect morphology image evaluation index and the threshold value of the sperm defect morphology image evaluation index with the allowable deviation value of the sperm defect morphology image evaluation index, and calculating the sperm defect morphology image coincidence coefficient.
Further, the specific calculation formula of the sperm defect morphology image coincidence coefficient is as follows:
；
In the method, in the process of the invention, Image coincidence coefficient representing sperm defect morphology,/>An image evaluation index indicating the morphology of the sperm defect,Threshold value representing sperm defect morphology image evaluation index,/>And the deviation value allowed by the sperm defect morphology image evaluation index is represented.
Further, based on the sperm defect morphology image coincidence coefficient, the specific process of identifying the defective sperm image is as follows: based on the sperm defect morphological image coincidence coefficient, comparing the sperm defect morphological image coincidence coefficient with a standard value of the sperm defect morphological image coincidence coefficient, and if the sperm defect morphological image coincidence coefficient is larger than the standard value of the sperm defect morphological image coincidence coefficient, indicating that the sperm morphological image is a defective sperm morphological image.
The invention has the following beneficial effects:
(1) According to the image recognition method for the sperm defect morphology, the sperm defect degree is measured by calculating the sperm defect morphology image evaluation index, so that the quality and the health condition of sperms can be accurately evaluated, the severity of the sperm defect can be judged, the fertility and the conception success rate of men can be further predicted, and the personalized treatment scheme and suggestion can be made, so that the fertility of men and the success rate of assisted reproductive technologies can be improved.
(2) According to the image recognition method for the sperm defect morphology, the sperm defect morphology image coincidence degree is analyzed, the sperm defect morphology image coincidence coefficient is calculated, the defective sperm image is recognized, doctors and researchers can be helped to better know the sperm quality and the health condition, and the selection and the optimization of the reproduction technology are assisted.
Of course, it is not necessary for any one product to practice the invention to achieve all of the advantages set forth above at the same time.
Drawings
FIG. 1 is a flow chart of an image recognition method of sperm defect morphology according to the present invention.
FIG. 2 is a flow chart of the evaluation index of the sperm defect morphology image calculation in the invention.
Detailed Description
The embodiment of the application solves the problems of subjectivity, low efficiency and difficulty in processing large-scale data in the traditional sperm morphology identification assessment by an image identification method of sperm defect morphology.
The problems in the embodiment of the application have the following general ideas:
Firstly, collecting a sperm morphology image to be identified and a defective sperm morphology image, and preprocessing the sperm morphology image to be identified and the defective sperm morphology image to obtain sperm morphology image data to be identified and defective sperm morphology image data;
processing sperm morphology image data to be identified and defective sperm morphology image data by using a convolutional neural network of a deep learning model, and establishing a sperm defect image identification model;
analyzing the sperm morphology image data to be identified, and calculating a sperm defect morphology image evaluation index for measuring the sperm defect degree;
And finally, analyzing the coincidence degree of the sperm defect morphological image, calculating the coincidence coefficient of the sperm defect morphological image, and identifying the defective sperm image.
Referring to fig. 1, the embodiment of the invention provides a technical scheme: an image recognition method of sperm defect morphology comprises the following steps: s1, acquiring a sperm morphology image to be identified and a defective sperm morphology image, and preprocessing the sperm morphology image to be identified and the defective sperm morphology image to acquire sperm morphology image data to be identified and defective sperm morphology image data; s2, processing the sperm morphology image data to be identified and the defective sperm morphology image data by using a convolutional neural network of a deep learning model based on the sperm morphology image data to be identified and the defective sperm morphology image data, and establishing a sperm defect image identification model; s3, analyzing the sperm morphology image data to be identified based on a sperm defect image identification model, and calculating a sperm head defect morphology image evaluation index, a sperm neck defect morphology image evaluation index and a sperm tail defect morphology image evaluation index; s4, calculating a sperm defect morphology image evaluation index based on the sperm head defect morphology image evaluation index, the sperm neck defect morphology image evaluation index and the sperm tail defect morphology image evaluation index, wherein the sperm defect morphology image evaluation index is used for measuring the sperm defect degree; s5, analyzing the coincidence degree of the sperm defect morphology image based on the sperm defect morphology image evaluation index, and calculating a sperm defect morphology image coincidence coefficient which is used for evaluating the coincidence degree of the sperm defect morphology image; s6, identifying the defective sperm image based on the sperm defect morphology image coincidence coefficient.
Specifically, preprocessing the sperm morphology image to be identified and the defective sperm morphology image, and acquiring the sperm morphology image data to be identified and the defective sperm morphology image data comprises the following specific processes: loading the sperm morphology image to be identified and the defective sperm morphology image into visual software, and converting the sperm morphology gray level image to be identified and the defective sperm morphology gray level image; performing histogram equalization on the sperm morphology gray image to be identified and the defective sperm morphology gray image by using an image processing technology, and enhancing the contrast ratio and the definition of the sperm morphology gray image to be identified and the defective sperm morphology gray image; normalizing the sperm morphology gray level image to be identified and the defective sperm morphology gray level image by using a computer vision technology, mapping pixel values to a specified range, and obtaining sperm morphology image data to be identified and defective sperm morphology image data.
In this embodiment, histogram equalization is a common image enhancement technique, and the number of gray levels of an output image can be more uniformly distributed by transforming pixel values of the image, so as to enhance contrast and sharpness of the image; normalization is a process of mapping pixel values into a specified range, and is often used to compare and process images of different brightness or color spaces. The normalization processing can effectively reduce the data dimension and improve the efficiency and accuracy of image processing; visualization software refers to a software tool capable of realizing data visualization and interactive operation, and is generally used in the fields of scientific research, engineering design, artistic creation and the like. In the pretreatment process of the sperm morphology image, the visualization software can help to load and display the image, and is convenient for subsequent processing and analysis.
Specifically, a convolutional neural network of a deep learning model is used for processing sperm morphology image data to be identified and defective sperm morphology image data, and the specific process for establishing the sperm defect image identification model is as follows: feature extraction is carried out on sperm morphology image data to be identified and defective sperm morphology image data by using a convolutional neural network CNN of a deep learning model, and features with different levels and degrees of abstraction are extracted through a plurality of convolutional layers and pooling layers, so that a feature set of defective sperm morphology is constructed; and taking a convolutional neural network model of the deep learning model as a reference model, performing training fitting on the reference model based on a characteristic set of the defective sperm morphology, and establishing a sperm defective image recognition model.
In this embodiment, a machine learning method of the deep learning model learns and extracts high-level features of data by constructing a multi-layer neural network, which is a structure commonly used in deep learning and is suitable for an image processing task; in the image recognition task, features of different levels and degrees of abstraction of the image can be extracted step by step through a convolution layer and a pooling layer.
The convolution layer carries out convolution operation on the input image through different convolution cores to obtain different feature images.
The pooling layer reduces the dimension of the feature map through a downsampling operation and retains important feature information: the reference model is an initial model that is directly trained using a deep learning model without feature extraction.
The standard model is subjected to training fitting based on the characteristic set of the defective sperm morphology, so that the model is more focused on the specific problem of processing the sperm defective image, and the performance and generalization capability of the model are improved; the sperm defect image recognition model can be established by performing feature extraction on sperm morphology image data to be recognized and defect sperm morphology image data by using a convolutional neural network and performing training fitting on the model based on a feature set.
The model has better image processing capability and identification accuracy, and can be applied to automatic sperm morphology analysis and defect detection tasks.
Specifically, based on the sperm defect image recognition model, the specific process of analyzing the sperm morphology image data to be recognized is as follows: recognizing sperm morphology image data to be recognized based on a sperm defect image recognition model to acquire sperm defect morphology image data; sperm defect morphology image data includes: sperm head defect morphology image data, sperm neck defect morphology image data, and sperm tail defect morphology image data.
In this embodiment, the sperm head defect morphology image data includes: the offset distance of the sperm head, the percentage of the abnormal shape of the sperm head to the total sperm head area, the curvature of the sperm head outline; sperm neck defect morphology image data includes: the swelling length of the sperm neck, the spiral number of the sperm neck and the excessively slender number of the sperm neck; the sperm tail defect morphology image data comprises sperm tail bending length and the percentage of the abnormal shape of the sperm tail to the total sperm tail area.
Specifically, the specific process of calculating the sperm defect morphology image evaluation index is as follows: analyzing the degree of sperm head deformity based on the sperm head defect morphological image data, and calculating a sperm head defect morphological image evaluation index; based on the morphological image data of the sperm neck defect, analyzing the degree of sperm neck defect, and calculating the morphological image evaluation index of the sperm neck defect; analyzing the degree of the tail deformity of the sperm based on the sperm tail defect morphology image data, and calculating a sperm tail defect morphology image evaluation index; calculating the sperm defect morphology image evaluation index based on the sperm head defect morphology image evaluation index, the sperm neck defect morphology image evaluation index and the sperm tail defect morphology image evaluation index.
In this embodiment, the image data based on the morphology of the head defect of the sperm includes: the sperm head offset distance, the percentage of the abnormal shape of the sperm head to the total sperm head area, the curvature of the sperm head outline, and the number of the sperm is sequentially givenN represents the total number of sperms, and the calculation formula of the morphological image evaluation index of the head defect of the sperms is as follows:
; in the/> Image evaluation index for representing sperm head defect morphology and used for measuring sperm head defect degree,/>Represents the i-th sperm head offset distance,/>Representing the percentage of abnormal shape of the ith sperm head to total sperm head area; /(I)Representing the curvature of the head contour of the ith sperm,/>Threshold representing sperm head offset distance,/>Standard value representing the percentage of abnormal shape of sperm head to total sperm head area,/>A standard value representing the curvature of the sperm head contour; /(I)A weight factor representing the offset distance of the sperm head; /(I)A weight factor representing the percentage of abnormal shape of the sperm head to total sperm head area; /(I)A weight factor representing the curvature of the sperm head contour; based on sperm neck defect morphology image data comprising: the calculation formulas of the sperm neck excessive swelling quantity, the sperm neck spiral quantity and the sperm neck excessive slender quantity and the sperm neck defect morphological image evaluation index are as follows:
；
In the method, in the process of the invention, An evaluation index of the morphological image of the sperm neck defect is expressed and is used for measuring the degree of the sperm neck defect,Indicates the excessive swelling quantity of the neck of sperm,/>Representing the number of helices in the neck of sperm,/>Meaning that the neck of sperm is too slender,/>Threshold representing the number of excessive swelling of the neck of sperm,/>A threshold value representing the number of helices in the neck of the sperm,Threshold representing too slender number of sperm necks,/>Weight factor representing the number of excessive swelling of the neck of sperm,/>Weight factor representing the number of helices in the neck of sperm,/>A weighting factor that indicates that the sperm neck is too slender; based on sperm tail defect morphology image data comprising: the sperm tail defect morphology image data comprises the sperm tail bending length and the percentage of the abnormal shape of the sperm tail to the total sperm tail area, and the calculation formula of the sperm tail defect morphology image evaluation index is as follows:
; in the/> Image evaluation index for representing defect morphology of tail of sperm and used for measuring defect degree of neck of sperm,/>Represents the ith sperm tail bending length,/>Representing the percentage of abnormal shape of the ith sperm tail to total sperm tail area,/>Standard value representing the bent length of sperm tail,/>Standard value representing the percentage of abnormal shape of sperm tail to total sperm tail area,/>Weight factor of the tail bending length of episperm,/>A weight factor representing the percentage of abnormal shape of the sperm tail to total sperm tail area. And analyzing the influence degree of the sperm tail defect morphology image data comprising the sperm tail bending length and the abnormal shape of the sperm tail accounting for the percentage of the total sperm tail area based on the acquired sperm tail defect morphology image data comprising the sperm tail bending length and the abnormal shape of the sperm tail accounting for the percentage of the total sperm tail area through a statistical analysis and regression analysis method, so as to determine a weight factor.
Referring to fig. 2, specifically, the specific formula of the sperm defect morphology image evaluation index is as follows:
；
In the method, in the process of the invention, An image evaluation index showing the morphology of sperm defects for measuring the degree of sperm defects,/>Image evaluation index for representing sperm head defect morphology,/>Image evaluation index for representing neck defect of sperm,/>Image evaluation index for representing defect morphology of sperm tail,/>Weight factor representing sperm head defect morphology image evaluation index corresponding to sperm defect morphology image evaluation index,/>Weight factor representing sperm neck defect morphology image evaluation index corresponding to sperm defect morphology image evaluation index,/>And the weight factor which represents the sperm tail defect morphology image evaluation index corresponds to the sperm defect morphology image evaluation index.
In this embodiment, the sperm defect morphology image evaluation index can be obtained by performing weighted summation on the sperm head defect morphology image evaluation index, the sperm neck defect morphology image evaluation index and the sperm tail defect morphology image evaluation index, and the index can be used for measuring the sperm defect degree so as to evaluate the influence degree; using formulas for image analysis and calculation, sperm defect levels can be automatically assessed without manual observation and judgment. Therefore, the evaluation efficiency can be greatly improved, and the labor cost is reduced; by training and optimizing the model, the artificial intelligence-based method can learn and identify the characteristics of the sperm defect morphology, thereby providing a more accurate assessment result.
Compared with the traditional manual evaluation method, the method can obtain higher recognition accuracy.
Specifically, the specific calculation process of the weight factors of the sperm defect morphology image evaluation index corresponding to the sperm head defect morphology image evaluation index, the sperm neck defect morphology image evaluation index and the sperm tail defect morphology image evaluation index is as follows: using multiple linear regression model, taking the sperm head defect morphology image evaluation index, the sperm neck defect morphology image evaluation index and the sperm tail defect morphology image evaluation index as independent variables X, taking the sperm defect morphology image evaluation index as dependent variables Y, and setting the intercept asAnd error term/>; Establishing association between independent variable X and dependent variable Y, and settingAnd fitting the established regression model by using a regression analysis method to obtain the regression coefficient of each independent variable as the weight factors of the sperm defect morphology image evaluation index corresponding to the sperm head defect morphology image evaluation index, the sperm neck defect morphology image evaluation index and the sperm tail defect morphology image evaluation index.
In this embodiment, the independent variable X and the dependent variable Y are correlated using a multiple linear regression model in the form of; Wherein/>For intercept,/>Is an error term,/>Is an independent variable/>Regression coefficient of/>Is an independent variable/>Regression coefficient of/>Is an independent variable/>Regression coefficient of/>Index is assessed for sperm head defect morphology images,/>Index is assessed for sperm neck defect morphology image,/>Evaluating an index for the sperm tail defect morphology image; fitting the established regression model by using a regression analysis method to obtain regression coefficients of each independent variable; and obtaining the weight factor of each morphological defect index according to the regression coefficient of the regression model.
The regression coefficient represents the degree of influence of the independent variable on the dependent variable, and thus can be used as a weight factor for each morphological defect index.
Specifically, based on the sperm defect morphology image evaluation index, analyzing the sperm defect morphology image coincidence degree, and calculating the sperm defect morphology image coincidence coefficient comprises the following specific processes: based on the sperm defect morphology image evaluation index, comparing the sperm defect morphology image evaluation index with a threshold value of the sperm defect morphology image evaluation index, and calculating a difference value between the sperm defect morphology image evaluation index and the threshold value of the sperm defect morphology image evaluation index; comparing the difference value of the sperm defect morphology image evaluation index and the threshold value of the sperm defect morphology image evaluation index with the allowable deviation value of the sperm defect morphology image evaluation index, and calculating the sperm defect morphology image coincidence coefficient.
In this embodiment, the sperm-defect-morphology-image evaluation index is compared with a threshold value of the sperm-defect-morphology-image evaluation index, and the difference between the sperm-defect-morphology-image evaluation index and the threshold value of the sperm-defect-morphology-image evaluation index is calculated to determine whether the sperm-defect-morphology-image evaluation index exceeds the set threshold value.
If the threshold value is exceeded, the sperm is indicated to have a defective morphology; otherwise, it indicates that the sperm morphology is normal.
The difference represents the degree of deviation between the evaluation index and the threshold; comparing the difference value of the sperm defect morphology image evaluation index and the threshold value of the sperm defect morphology image evaluation index with the allowable deviation value of the sperm defect morphology image evaluation index, and calculating the sperm defect morphology image coincidence coefficient; and comprehensively considering the deviation degree between the evaluation index and the threshold value and the allowable deviation value, and calculating the coincidence coefficient of the sperm defect morphological image.
Specifically, the specific calculation formula of the sperm defect morphology image coincidence coefficient is as follows:
；
In the method, in the process of the invention, Represents the coincidence coefficient of the sperm defect morphology image, is used for evaluating the coincidence degree of the sperm defect morphology image,Image evaluation index representing sperm defect morphology,/>Threshold value representing sperm defect morphology image evaluation index,/>And the deviation value allowed by the sperm defect morphology image evaluation index is represented. In this embodiment, the threshold value of the sperm defect morphology image evaluation index is a value in a database for judging whether the image has a defect. If the evaluation index is greater than the threshold, the image is considered a defective sperm morphology image; the allowable deviation value of the sperm defect morphology image evaluation index is an allowable error range value and can be used for controlling the severity of the image.
If the difference between the evaluation index and the threshold is less than the deviation value, then it is considered to be a match; the degree of matching of the image to the defect morphology can be quantified and a threshold provided for determining whether a defect is present.
The method can help to automatically identify and analyze images and improve the efficiency and accuracy of the morphological diagnosis of the sperm defects.
Specifically, based on the sperm defect morphology image coincidence coefficient, the specific process of identifying the defective sperm image is as follows: based on the sperm defect morphological image coincidence coefficient, comparing the sperm defect morphological image coincidence coefficient with a standard value of the sperm defect morphological image coincidence coefficient, and if the sperm defect morphological image coincidence coefficient is larger than the standard value of the sperm defect morphological image coincidence coefficient, indicating that the sperm morphological image is a defective sperm morphological image.
In this embodiment, when comparing the coincidence coefficient of the sperm-defective morphology image with the standard value, if the coincidence coefficient is larger than the standard value, the image is determined to be a defective sperm morphology image.
This means that the image matches the defect morphology to a high degree, with certain defect characteristics.
In summary, the present application has at least the following effects:
The image recognition method of the sperm defect morphology is characterized in that the sperm defect morphology image evaluation index is calculated, the sperm defect degree is measured, the sperm quality and the health condition are accurately evaluated, the severity of the sperm defect can be judged, the fertility and the conception success rate of a male are further predicted, personalized treatment schemes and suggestions are formulated, the fertility of the male and the success rate of auxiliary reproductive technology are improved, the cause, the influence factors and the related diseases of the sperm defect can be deeply researched through analysis and comparison of large-scale image data, and support is provided for scientific research in the field of male reproductive health.
It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as a method, system, or computer program product.
Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects.
Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of systems, apparatuses (systems) and computer program products according to embodiments of the invention.
It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions.
These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
While preferred embodiments of the present invention have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts.
It is therefore intended that the following claims be interpreted as including the preferred embodiments and all such alterations and modifications as fall within the scope of the invention.
It will be apparent to those skilled in the art that various modifications and variations can be made to the present invention without departing from the spirit or scope of the invention.
Thus, it is intended that the present invention also include such modifications and alterations insofar as they come within the scope of the appended claims or the equivalents thereof.
Claims (10)
1. An image recognition method of sperm defect morphology is characterized by comprising the following steps:
s1, acquiring a sperm morphology image to be identified and a defective sperm morphology image, and preprocessing the sperm morphology image to be identified and the defective sperm morphology image to acquire sperm morphology image data to be identified and defective sperm morphology image data;
s2, processing the sperm morphology image data to be identified and the defective sperm morphology image data by using a convolutional neural network of a deep learning model based on the sperm morphology image data to be identified and the defective sperm morphology image data, and establishing a sperm defect image identification model;
S3, analyzing the sperm morphology image data to be identified based on a sperm defect image identification model, and calculating a sperm head defect morphology image evaluation index, a sperm neck defect morphology image evaluation index and a sperm tail defect morphology image evaluation index;
S4, calculating a sperm defect morphology image evaluation index based on the sperm head defect morphology image evaluation index, the sperm neck defect morphology image evaluation index and the sperm tail defect morphology image evaluation index, wherein the sperm defect morphology image evaluation index is used for measuring the sperm defect degree;
S5, analyzing the coincidence degree of the sperm defect morphology image based on the sperm defect morphology image evaluation index, and calculating a sperm defect morphology image coincidence coefficient which is used for evaluating the coincidence degree of the sperm defect morphology image;
S6, identifying the defective sperm image based on the sperm defect morphology image coincidence coefficient.
2. The method for image recognition of a morphology of sperm defects of claim 1, wherein: preprocessing the sperm morphology image to be identified and the defective sperm morphology image, and acquiring the sperm morphology image data to be identified and the defective sperm morphology image data comprises the following specific processes:
loading the sperm morphology image to be identified and the defective sperm morphology image into visual software, and converting the sperm morphology gray level image to be identified and the defective sperm morphology gray level image;
performing histogram equalization on the sperm morphology gray image to be identified and the defective sperm morphology gray image by using an image processing technology, and enhancing the contrast ratio and the definition of the sperm morphology gray image to be identified and the defective sperm morphology gray image;
normalizing the sperm morphology gray level image to be identified and the defective sperm morphology gray level image by using a computer vision technology, mapping pixel values to a specified range, and obtaining sperm morphology image data to be identified and defective sperm morphology image data.
3. The method for image recognition of a morphology of sperm defects of claim 1, wherein: the convolutional neural network of the deep learning model is used for processing the sperm morphology image data to be identified and the defective sperm morphology image data, and the specific process for establishing the sperm defect image identification model is as follows:
feature extraction is carried out on sperm morphology image data to be identified and defective sperm morphology image data by using a convolutional neural network CNN of a deep learning model, and features with different levels and degrees of abstraction are extracted through a plurality of convolutional layers and pooling layers, so that a feature set of defective sperm morphology is constructed;
And taking a convolutional neural network model of the deep learning model as a reference model, performing training fitting on the reference model based on a characteristic set of the defective sperm morphology, and establishing a sperm defective image recognition model.
4. The method for image recognition of a morphology of sperm defects of claim 1, wherein: based on the sperm defect image recognition model, the specific process of analyzing the sperm morphology image data to be recognized is as follows:
recognizing sperm morphology image data to be recognized based on a sperm defect image recognition model to acquire sperm defect morphology image data;
sperm defect morphology image data includes: sperm head defect morphology image data, sperm neck defect morphology image data, and sperm tail defect morphology image data.
5. The method for image recognition of a morphology of sperm defects as described in claim 4, wherein: the specific process of calculating the sperm defect morphology image evaluation index is as follows:
analyzing the degree of sperm head deformity based on the sperm head defect morphological image data, and calculating a sperm head defect morphological image evaluation index;
based on the morphological image data of the sperm neck defect, analyzing the degree of sperm neck defect, and calculating the morphological image evaluation index of the sperm neck defect;
analyzing the degree of the tail deformity of the sperm based on the sperm tail defect morphology image data, and calculating a sperm tail defect morphology image evaluation index;
calculating the sperm defect morphology image evaluation index based on the sperm head defect morphology image evaluation index, the sperm neck defect morphology image evaluation index and the sperm tail defect morphology image evaluation index.
6. The method for image recognition of a defective sperm morphology of claim 5, wherein: the specific formula of the sperm defect morphology image evaluation index is as follows:；
In the method, in the process of the invention, Image evaluation index representing sperm defect morphology,/>An evaluation index of the morphological image of the sperm head defect is shown,Image evaluation index for representing neck defect of sperm,/>Image evaluation index for representing defect morphology of sperm tail,/>Weight factor representing sperm head defect morphology image evaluation index corresponding to sperm defect morphology image evaluation index,/>Weight factor representing sperm neck defect morphology image evaluation index corresponding to sperm defect morphology image evaluation index,/>And the weight factor which represents the sperm tail defect morphology image evaluation index corresponds to the sperm defect morphology image evaluation index.
7. The method for image recognition of a morphology of sperm defects of claim 6, wherein: the specific calculation process of the weight factors of the sperm defect morphology image evaluation index corresponding to the sperm head defect morphology image evaluation index, the sperm neck defect morphology image evaluation index and the sperm tail defect morphology image evaluation index is as follows:
Using multiple linear regression model, taking the sperm head defect morphology image evaluation index, the sperm neck defect morphology image evaluation index and the sperm tail defect morphology image evaluation index as independent variables X, taking the sperm defect morphology image evaluation index as dependent variables Y, and setting the intercept as And error term/>; Association of independent variable X and dependent variable Y, and setting/>And fitting the established regression model by using a regression analysis method to obtain the regression coefficient of each independent variable as the weight factors of the sperm defect morphology image evaluation index corresponding to the sperm head defect morphology image evaluation index, the sperm neck defect morphology image evaluation index and the sperm tail defect morphology image evaluation index.
8. The method for image recognition of a morphology of sperm defects of claim 1, wherein: based on the sperm defect morphology image evaluation index, analyzing the sperm defect morphology image coincidence degree, and calculating the sperm defect morphology image coincidence coefficient comprises the following specific processes:
Based on the sperm defect morphology image evaluation index, comparing the sperm defect morphology image evaluation index with a threshold value of the sperm defect morphology image evaluation index, and calculating a difference value between the sperm defect morphology image evaluation index and the threshold value of the sperm defect morphology image evaluation index;
Comparing the difference value of the sperm defect morphology image evaluation index and the threshold value of the sperm defect morphology image evaluation index with the allowable deviation value of the sperm defect morphology image evaluation index, and calculating the sperm defect morphology image coincidence coefficient.
9. The method for image recognition of a morphology of sperm defects of claim 8, wherein: the specific calculation formula of the sperm defect morphology image coincidence coefficient is as follows:；
In the method, in the process of the invention, Image coincidence coefficient representing sperm defect morphology,/>Image evaluation index representing sperm defect morphology,/>Threshold value representing sperm defect morphology image evaluation index,/>And the deviation value allowed by the sperm defect morphology image evaluation index is represented.
10. The method for image recognition of a morphology of sperm defects of claim 1, wherein: based on the sperm defect morphology image coincidence coefficient, the specific process for identifying the defect sperm image is as follows:
based on the sperm defect morphological image coincidence coefficient, comparing the sperm defect morphological image coincidence coefficient with a standard value of the sperm defect morphological image coincidence coefficient, and if the sperm defect morphological image coincidence coefficient is larger than the standard value of the sperm defect morphological image coincidence coefficient, indicating that the sperm morphological image is a defective sperm morphological image.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410309236.7A CN117911407B (en) | 2024-03-19 | 2024-03-19 | Image recognition method for sperm defect morphology |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410309236.7A CN117911407B (en) | 2024-03-19 | 2024-03-19 | Image recognition method for sperm defect morphology |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117911407A true CN117911407A (en) | 2024-04-19 |
| CN117911407B CN117911407B (en) | 2024-06-14 |
Family
ID=90685510
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410309236.7A Active CN117911407B (en) | 2024-03-19 | 2024-03-19 | Image recognition method for sperm defect morphology |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117911407B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110705639A (en) * | 2019-09-30 | 2020-01-17 | 吉林大学 | Medical sperm image recognition system based on deep learning |
| US20200209221A1 (en) * | 2016-12-08 | 2020-07-02 | Sigtuple Technologies Private Limited | A method and system for evaluating quality of semen sample |
| CN113505865A (en) * | 2021-09-10 | 2021-10-15 | 浙江双元科技股份有限公司 | Sheet surface defect image recognition processing method based on convolutional neural network |
| CN115937211A (en) * | 2023-01-30 | 2023-04-07 | 福建省妇幼保健院 | Sperm quality evaluation method, system and equipment based on artificial intelligence |
| CN117250208A (en) * | 2023-11-20 | 2023-12-19 | 青岛天仁微纳科技有限责任公司 | Machine vision-based nano-imprint wafer defect accurate detection system and method |
-
2024
- 2024-03-19 CN CN202410309236.7A patent/CN117911407B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20200209221A1 (en) * | 2016-12-08 | 2020-07-02 | Sigtuple Technologies Private Limited | A method and system for evaluating quality of semen sample |
| CN110705639A (en) * | 2019-09-30 | 2020-01-17 | 吉林大学 | Medical sperm image recognition system based on deep learning |
| CN113505865A (en) * | 2021-09-10 | 2021-10-15 | 浙江双元科技股份有限公司 | Sheet surface defect image recognition processing method based on convolutional neural network |
| CN115937211A (en) * | 2023-01-30 | 2023-04-07 | 福建省妇幼保健院 | Sperm quality evaluation method, system and equipment based on artificial intelligence |
| CN117250208A (en) * | 2023-11-20 | 2023-12-19 | 青岛天仁微纳科技有限责任公司 | Machine vision-based nano-imprint wafer defect accurate detection system and method |
Non-Patent Citations (2)
| Title |
|---|
| G.B.BOE-HANSEN ET AL.: "Morphological detects, sperm DNA integrity, and protamination of bovine spermatozoa", ANDROLOGY, 6 April 2018 (2018-04-06) * |
| 安娜;吴银玲;葛少钦;: "圆头精子超微结构研究", 医学理论与实践, no. 20, 25 October 2017 (2017-10-25) * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117911407B (en) | 2024-06-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111179251B (en) | Defect detection system and method based on twin neural network and by utilizing template comparison | |
| CN109726746B (en) | Template matching method and device | |
| CN108764312B (en) | DS-based optimized multi-index dam defect image detection method | |
| CN111860106B (en) | Unsupervised bridge crack identification method | |
| CN113033704B (en) | Intelligent judging method and system for copper converter converting copper-making final point based on pattern recognition | |
| CN112308825A (en) | SqueezeNet-based crop leaf disease identification method | |
| CN112749675A (en) | Potato disease identification method based on convolutional neural network | |
| Naito et al. | Identification and segmentation of myelinated nerve fibers in a cross-sectional optical microscopic image using a deep learning model | |
| CN118246712B (en) | Pig farm production intelligent analysis system and method based on large language model | |
| Aristoteles et al. | Identification of human sperm based on morphology using the you only look once version 4 algorithm | |
| CN117911407B (en) | Image recognition method for sperm defect morphology | |
| CN112270404A (en) | Detection structure and method for bulge defect of fastener product based on ResNet64 network | |
| GB2604706A (en) | System and method for diagnosing small bowel cleanliness | |
| CN114359300B (en) | Optimization method, device and system of image segmentation model and storage medium | |
| CN115965786A (en) | Occlusion target identification method based on local semantic perception attention neural network | |
| CN115661042A (en) | Hierarchical classification defect detection method based on attention mechanism guidance | |
| Mashaal et al. | Classification of human sperms using ResNet-50 deep neural network | |
| CN108764337B (en) | Underwater robot propeller fault degree identification method based on relative gray correlation degree boundary constraint | |
| CN113052799A (en) | Osteosarcoma and osteochondroma prediction method based on Mask RCNN network | |
| CN117689880B (en) | Method and system for target recognition in biomedical images based on machine learning | |
| CN117078604B (en) | Unmanned laboratory intelligent management method and system | |
| CN117995417B (en) | IVF/ICSI preprocessing scheme optimizing system based on machine learning | |
| CN113920437B (en) | Conductive particle identification method, system, storage medium and computer equipment | |
| CN111754547B (en) | Multi-target automatic identification tracking positioning method for broiler chickens in dim light environment | |
| CN112816408B (en) | Flaw detection method for optical lens |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |