CN112200803A - Method and device for detecting maturity of sperm nucleoprotein - Google Patents
Method and device for detecting maturity of sperm nucleoprotein Download PDFInfo
- Publication number
- CN112200803A CN112200803A CN202011216686.XA CN202011216686A CN112200803A CN 112200803 A CN112200803 A CN 112200803A CN 202011216686 A CN202011216686 A CN 202011216686A CN 112200803 A CN112200803 A CN 112200803A
- Authority
- CN
- China
- Prior art keywords
- network
- sperm
- nucleoprotein
- training
- sperm nucleoprotein
- 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
Images
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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- 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
- G06N3/045—Combinations of networks
-
- 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
- G06N3/047—Probabilistic or stochastic networks
-
- 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
- G06V10/20—Image preprocessing
- G06V10/25—Determination of region of interest [ROI] or a volume of interest [VOI]
-
- 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
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10056—Microscopic image
- G06T2207/10061—Microscopic image from scanning electron microscope
-
- 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
- G06T2207/20—Special algorithmic details
- G06T2207/20092—Interactive image processing based on input by user
- G06T2207/20104—Interactive definition of region of interest [ROI]
-
- 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
- G06T2207/30024—Cell structures in vitro; Tissue sections in vitro
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Health & Medical Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Biophysics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Biomedical Technology (AREA)
- Computational Linguistics (AREA)
- Software Systems (AREA)
- Mathematical Physics (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Multimedia (AREA)
- Medical Informatics (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Radiology & Medical Imaging (AREA)
- Quality & Reliability (AREA)
- Probability & Statistics with Applications (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Investigating Or Analysing Biological Materials (AREA)
- Image Analysis (AREA)
Abstract
The invention belongs to the technical field of medical image processing, and particularly discloses a method and a device for detecting the maturity of sperm nucleoprotein. The sperm nucleoprotein dyeing microscopic image is obtained and passes through the preset sperm nucleoprotein detection model, so that the sperm nucleoprotein image, the position information of the sperm nucleoprotein in the image and the sperm nucleoprotein maturity detection result are obtained, and the identification rate and the accuracy of the sperm nucleoprotein maturity are greatly improved compared with the traditional target detection algorithm.
Description
Technical Field
The invention belongs to the technical field of medical image processing, and particularly relates to a method and a device for detecting the maturity of sperm nucleoprotein.
Background
The sperm nucleoprotein detection needs to be carried out by staining with a nucleoprotein reagent (aniline blue reagent), then the maturity of nucleoprotein is judged by color under a 100-fold microscope, and the nucleoprotein component of mature sperm is protamine which is rich in arginine and cystine residues; the nucleoprotein component of immature sperm is histone, rich in lysine residue. Under acidic conditions, aniline blue binds to lysine residues to produce a violet-blue compound, indicating the presence of immature nucleoprotein, while nucleoprotein-mature spermatozoa stain red.
The traditional sperm nucleoprotein detection method mainly comprises the steps of placing a stained slide under a microscope with a magnification of 100 times for photographing, then carrying out sperm target detection on an image obtained by photographing through a traditional target detection algorithm (such as Cascade + HOG/DPM + Haar/SVM), and then carrying out classification judgment on sperm nucleoprotein through a traditional classification algorithm.
Disclosure of Invention
In view of the above, the present application provides a method and an apparatus for detecting the maturity of sperm nuclear protein, which can solve or at least partially solve the above existing problems.
In order to solve the technical problems, the technical scheme provided by the invention is a method for detecting the maturity of the sperm nucleoprotein, which comprises the following steps:
s11: obtaining a sperm nucleoprotein staining microscopic image;
s12: and (3) passing the sperm nucleoprotein staining microscopic image through a sperm nucleoprotein detection model to obtain a sperm nucleoprotein image, position information of the sperm nucleoprotein in the image and a mature or immature sperm nucleoprotein detection result.
Preferably, the method for detecting the maturity of the sperm nucleoprotein further comprises S10: generating a sperm nucleoprotein detection model; the method of S10 includes:
s101: screening sperm nucleoprotein staining microscopic images of the large samples;
s102: marking mature or immature sperm nucleoprotein on the sperm nucleoprotein dyeing microscopic image, and dividing the marked sperm nucleoprotein dyeing microscopic image into a training image set and a testing image set;
s103: and (3) training the training image set by adopting a fast-RCNN + ResNet network model under a TensorFlow framework, verifying and updating parameters of the fast-RCNN + ResNet network model through the test image set, and then training, and circulating the process until a final sperm nucleoprotein detection model is obtained.
Preferably, in S103, under a TensorFlow framework, the method for training the training image set by using the fast-RCNN + ResNet network model includes:
adjusting the network structure of fast-rcnn, replacing the basic network with a ResNet50 network, and adjusting the corresponding training parameters: learning rate, training image quantity, iteration times, selection of an optimizer and selection of a loss function;
extracting the features of the training image set by using a group of basic conv + relu + posing layers, and sharing the extracted features to the regional suggestion network layer and the full connection layer for processing;
the regional suggestion network layer is used for generating a regional suggestion frame, judging whether the suggestion frame is correct or not through a softmax loss function, and correcting the suggestion frame by utilizing border frame regression to accurately acquire the suggestion frame;
the region-of-interest pooling layer is used for collecting input features and suggestion boxes, and after the information is integrated, the information is sent to a subsequent full-connection layer to judge the target category;
full connectivity layer utilization interestCalculating the category of the suggestion frame, namely the category whether the sperm nucleoprotein is mature or not, by the suggestion frame obtained by the regional pooling layer, and obtaining the final accurate position of the detection frame by using the regression of the bounding box, wherein the formula is as follows:
wherein xiAs input data for the fast-RCNN + ResNet network, wijFor the weight values of the input data to the output data, biIs the corresponding deviation value, yiIs the corresponding output value.
Preferably, the method for verifying and updating the fast-RCNN + ResNet network model parameters by the test image set in S103 and then training, and repeating the process until the final sperm nucleoprotein detection model is obtained comprises:
on the trained sperm nucleoprotein detection model, training a regional suggestion network for the first time to obtain the first trained regional suggestion network;
collecting a suggestion frame by utilizing the first trained regional suggestion network and the test image set;
training a fast-rcnn network for the first time;
the second training area suggests a network to obtain a second trained RPN network;
collecting a suggestion frame by utilizing the second trained regional suggestion network and the test image set;
the fast-rcnn network is trained a second time.
The invention also provides a device for detecting the maturity of the sperm nucleoprotein, which comprises:
the sperm image acquisition module is used for acquiring a sperm nucleoprotein staining microscopic image;
and the nucleoprotein detection module is used for enabling the sperm nucleoprotein staining microscopic image to pass through the sperm nucleoprotein detection model to obtain the sperm nucleoprotein image, the position information of the sperm nucleoprotein in the image and the mature or immature sperm nucleoprotein detection result.
Preferably, the device for detecting the maturity of the sperm nucleoprotein further comprises: the detection model generation module is used for generating a sperm nucleoprotein detection model; the detection model generation module comprises:
the sample data screening unit is used for screening sperm nucleoprotein staining microscopic images of the large samples;
the sample data labeling unit is used for labeling the mature or immature sperm nucleoprotein on the sperm nucleoprotein dyeing microscopic image and dividing the labeled sperm nucleoprotein dyeing microscopic image into a training image set and a test image set;
and the detection model training unit is used for training the training image set by adopting a Faster-RCNN + ResNet network model under a TensorFlow framework, verifying and updating parameters of the Faster-RCNN + ResNet network model through the test image set, and then training, and circulating the process until a final sperm nucleoprotein detection model is obtained.
Preferably, the method for training the training image set by the detection model training unit under the Tensorflow framework by using the fast-RCNN + ResNet network model comprises the following steps:
adjusting the network structure of fast-rcnn, replacing the basic network with a ResNet50 network, and adjusting the corresponding training parameters: learning rate, training image quantity, iteration times, selection of an optimizer and selection of a loss function;
extracting the features of the training image set by using a group of basic conv + relu + posing layers, and sharing the extracted features to the regional suggestion network layer and the full connection layer for processing;
the regional suggestion network layer is used for generating a regional suggestion frame, judging whether the suggestion frame is correct or not through a softmax loss function, and correcting the suggestion frame by utilizing border frame regression to accurately acquire the suggestion frame;
the region-of-interest pooling layer is used for collecting input features and suggestion boxes, and after the information is integrated, the information is sent to a subsequent full-connection layer to judge the target category;
the full-junction layer calculates the category of the suggestion frame by using the suggestion frame obtained by the interested region pooling layer, namely the category whether the sperm nucleoprotein is mature or not, and simultaneously obtains the final accurate position of the detection frame by using the bounding box regression, wherein the formula is as follows:
wherein xiAs input data for the fast-RCNN + ResNet network, wijFor the weight values of the input data to the output data, biIs the corresponding deviation value, yiIs the corresponding output value.
Preferably, the method for verifying and updating the fast-RCNN + ResNet network model parameters by the detection model training unit through testing the image set and then training the fast-RCNN + ResNet network model parameters, and circulating the process until the final sperm nucleoprotein detection model is obtained comprises the following steps:
on the trained sperm nucleoprotein detection model, training a regional suggestion network for the first time to obtain the first trained regional suggestion network;
collecting a suggestion frame by utilizing the first trained regional suggestion network and the test image set;
training a fast-rcnn network for the first time;
the second training area suggests a network to obtain a second trained RPN network;
collecting a suggestion frame by utilizing the second trained regional suggestion network and the test image set;
the fast-rcnn network is trained a second time.
The invention also provides a device for detecting the maturity of the sperm nucleoprotein, which comprises:
a memory for storing a computer program;
a processor for executing the computer program to implement the steps of the above-mentioned sperm nucleoprotein maturity detection method.
Compared with the prior art, the beneficial effects of the method are detailed as follows: the sperm nucleoprotein dyeing microscopic image is obtained and passes through the preset sperm nucleoprotein detection model, so that the sperm nucleoprotein image, the position information of the sperm nucleoprotein in the image and the sperm nucleoprotein maturity detection result are obtained, and the identification rate and the accuracy of the sperm nucleoprotein maturity are greatly improved compared with the traditional target detection algorithm.
Drawings
In order to illustrate the embodiments of the present invention more clearly, the drawings that are needed in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and that other drawings can be obtained by those skilled in the art without inventive effort.
FIG. 1 is a schematic flow chart of a method for detecting the maturity of an sperm nucleoprotein according to an embodiment of the present invention;
FIG. 2 is a schematic flow chart of another method for detecting the maturity of sperm nuclear protein according to the present invention;
FIG. 3 is a schematic flow chart of a method for generating a sperm nucleoprotein assay model according to an embodiment of the present invention;
FIG. 4 is a schematic structural diagram of an apparatus for detecting the maturity of sperm nucleoprotein according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments obtained by a person of ordinary skill in the art based on the embodiments of the present invention without any creative work belong to the protection scope of the present invention.
In order to make the technical solutions of the present invention better understood by those skilled in the art, the present invention will be further described in detail with reference to the accompanying drawings and specific embodiments.
As shown in fig. 1, the present invention provides a method for detecting the maturity of an sperm nucleoprotein, which can be applied to a system for detecting the maturity of an sperm nucleoprotein, the method comprising:
s11: obtaining a sperm nucleoprotein staining microscopic image;
specifically, firstly, a sperm is stained by a nucleoprotein reagent (aniline blue reagent), then a stained sperm slide is placed under a microscope with a magnification of 100 times for photographing to obtain a sperm nucleoprotein staining microscopic image, and then the sperm nucleoprotein staining microscopic image is input into a sperm nucleoprotein maturity detection system, namely the sperm nucleoprotein maturity detection system receives or acquires the sperm nucleoprotein staining microscopic image.
S12: and (3) passing the sperm nucleoprotein staining microscopic image through a sperm nucleoprotein detection model to obtain a sperm nucleoprotein image, position information of the sperm nucleoprotein in the image and a mature or immature sperm nucleoprotein detection result.
Specifically, a sperm nucleoprotein staining microscopic image collected under a 100-fold microscope is tested by a neural network model-sperm nucleoprotein detection model obtained through fast-rcnn training. The sperm nucleoprotein detection model can automatically identify the sperms in the image through the corresponding codes, output the sperm nucleoprotein image and the positions (the upper left coordinate + the width + the height) of the sperm nucleoprotein in the image, and automatically distinguish the mature or immature sperms of the nucleoprotein according to the types (the red is the sperms of nucleoprotein maturation, and the purple blue is the sperms of nucleoprotein immaturity).
It should be noted that, as shown in fig. 2, the present invention further provides a method for detecting the maturity of the sperm nucleoprotein, which adds step S10 on the basis of the embodiment of fig. 1: generating the sperm nucleoprotein detection model.
Specifically, as shown in fig. 3, the method of S10 includes:
s101: screening sperm nucleoprotein staining microscopic images of the large samples;
specifically, firstly, the stained sperm slide is placed under a microscope with the magnification of 100 times to be photographed, the photographed photos are arranged, and the photos with the photographing effect meeting the requirement are selected to be used as a data set, so that the screened sample (sperm nucleoprotein) is more diverse and more balanced.
S102: marking mature or immature sperm nucleoprotein on the sperm nucleoprotein dyeing microscopic image, and dividing the marked sperm nucleoprotein dyeing microscopic image into a training image set and a testing image set;
specifically, sperm nucleoprotein on images in a data set is marked, the coordinates and the corresponding width and height of the upper left corner of a nucleoprotein marking frame of each sperm are recorded, and the sperm nucleoprotein marking frame is divided into two types, namely mature sperm nucleoprotein and immature sperm nucleoprotein, to generate a data file in a json format, and a data set of the data file is divided into two types, namely a training image set and a testing image set; and finally, generating tfrechrd format data from the marked files so as to facilitate training.
S103: and (3) training the training image set by adopting a fast-RCNN + ResNet network model under a TensorFlow framework, verifying and updating parameters of the fast-RCNN + ResNet network model through the test image set, and then training, and circulating the process until a final sperm nucleoprotein detection model is obtained.
Specifically, target detection is performed through the neural network, compared with the traditional target detection method, the network structure is deepened, and more extracted features are provided, so that more useful information can be obtained, and the target detection effect is improved. The neural network structures currently used for target detection are the rcnn series, the ssd series and the YOLO series. The rcnn series is a two-step method, the ssd series and the YOLO series are one-step methods, and as the rcnn series is more accurate relative to the ssd series and the YOLO series, and the ssd series and the YOLO series are Faster relative to the rcnn series, in order to obtain higher accuracy, the Faster-rcnn + ResNet50 network in the rcnn series is adopted to train the sperm nucleoprotein under the tensorflow framework.
It should be noted that, in S103, under the TensorFlow framework, the method for training the training image set by using the fast-RCNN + ResNet network model includes:
adjusting the network structure of fast-rcnn, replacing the basic network with a ResNet50 network, and adjusting the corresponding training parameters: learning rate, training image quantity, iteration times, selection of an optimizer and selection of a loss function;
extracting the features of the training image set by using a group of basic conv + relu + posing layers, and sharing the extracted features to the regional suggestion network layer and the full connection layer for processing;
the regional suggestion network layer is used for generating a regional suggestion frame, judging whether the suggestion frame is correct or not through a softmax loss function, and correcting the suggestion frame by utilizing border frame regression to accurately acquire the suggestion frame;
the region-of-interest pooling layer is used for collecting input features and suggestion boxes, and after the information is integrated, the information is sent to a subsequent full-connection layer to judge the target category;
the full-junction layer calculates the category of the suggestion frame by using the suggestion frame obtained by the interested region pooling layer, namely the category whether the sperm nucleoprotein is mature or not, and simultaneously obtains the final accurate position of the detection frame by using the bounding box regression, wherein the formula is as follows:
wherein xiAs input data for the fast-RCNN + ResNet network, wijFor the weight values of the input data to the output data, biIs the corresponding deviation value, yiIs the corresponding output value.
Specifically, the process of training the sperm nucleoprotein under the tenserflow framework by the fast-rcnn + ResNet50 network (wherein ResNet50 is the basic network) comprises the main content of the fast-rcnn and the image processing process inside the fast-rcnn. The method specifically comprises the following steps: and adjusting a network structure of fast-rcnn, replacing a basic network with a ResNet50 network, and adjusting corresponding training parameters such as learning rate, training image quantity, iteration times, selection of an optimizer, selection of a loss function and the like. The learning rate that can adopt is 0.001, and training image quantity is about 3000, and wherein the sperm sample is 10000 more, and the number of iterations is 10 ten thousand, and the SGD that the optimizer selected, loss function softmax. The fast-rcnn processes the image mainly, that is, some main methods adopted include: 1) extracting the features of the image by using a group of basic conv + relu + posing layers (a convolutional layer, an active layer and a pooling layer), and sharing the extracted features to an RPN (regional suggestion network) layer and a full connection layer for processing; 2) the RPN network is used to generate a region suggestion box. The layer judges whether the suggestion frame is correct or not through a softmax loss function, and corrects the suggestion frame by using the regression of the boundary frame to accurately acquire the suggestion frame. 3) Pooling of the region of interest (roi pooling). The layer is used for collecting input features and suggestion boxes, and after the information is integrated, the information is sent to a subsequent full-connection layer for judgmentA target category; 4) and (6) classifying. And the full-junction layer calculates the category of the suggestion frame by using the suggestion frame obtained by the interested region pooling layer, namely the category of whether the sperm nucleoprotein is mature or not, and simultaneously, the final accurate position of the detection frame is obtained by performing bounding box regression again. The formula is as follows:
wherein xiAs input data to the neural network, wijFor the weight values of the input data to the output data, biIs the corresponding deviation value, yiIs the corresponding output value.
It should be noted that the method for verifying and updating the fast-RCNN + ResNet network model parameters by testing the image set in S103 and then training, and repeating the process until the final sperm nucleoprotein detection model is obtained includes:
on the trained sperm nucleoprotein detection model, training a regional suggestion network for the first time to obtain the first trained regional suggestion network;
collecting a suggestion frame by utilizing the first trained regional suggestion network and the test image set;
training a fast-rcnn network for the first time;
the second training area suggests a network to obtain a second trained RPN network;
collecting a suggestion frame by utilizing the second trained regional suggestion network and the test image set;
the fast-rcnn network is trained a second time.
Specifically, a corresponding training code is run, and the test image set is trained to finally obtain a trained final sperm nucleoprotein detection model. The method comprises the following steps: 1) training an RPN network on the trained model; 2) collecting propusals (a suggestion box) by utilizing the RPN trained in the step 1); 3) training a fast-rcnn network for the first time; 4) training the RPN network for the second time; 5) collecting the proposals by using the RPN trained in the step 4) again; 6) the fast-rcnn network is trained a second time. The above steps are the process of processing images inside the network during the training process of fast-rcnn.
The invention principle of the application is to detect the sperm nucleoprotein based on a neural network model so as to identify the maturity of the sperm nucleoprotein. Firstly, marking sperm nucleoprotein in a shot sperm nucleoprotein dyeing microscopic image to manufacture a data format required by training, then training the marked data through a neural network model to obtain a final sperm nucleoprotein detection model, finally detecting the sperm nucleoprotein through the sperm nucleoprotein detection model, and analyzing the maturity of the sperm nucleoprotein through a detection result. Compared with the traditional target detection algorithm, the method greatly improves the identification rate and accuracy of the maturity of the sperm nucleoprotein.
As shown in fig. 4, the present invention also provides an apparatus for detecting the maturity of sperm nucleoprotein, comprising:
a sperm image acquisition module 21 for acquiring a sperm nucleoprotein staining microscopic image;
the nucleoprotein detection module 22 is used for enabling the sperm nucleoprotein staining microscopic image to pass through the sperm nucleoprotein detection model to obtain the sperm nucleoprotein image, the position information of the sperm nucleoprotein in the image and the mature or immature detection result of the sperm nucleoprotein.
It should be noted that the sperm nucleoprotein maturity detection apparatus further comprises: a detection model generation module 20 for generating a sperm nucleoprotein detection model; the detection model generation module 20 includes:
the sample data screening unit is used for screening sperm nucleoprotein staining microscopic images of the large samples;
the sample data labeling unit is used for labeling the mature or immature sperm nucleoprotein on the sperm nucleoprotein dyeing microscopic image and dividing the labeled sperm nucleoprotein dyeing microscopic image into a training image set and a test image set;
and the detection model training unit is used for training the training image set by adopting a Faster-RCNN + ResNet network model under a TensorFlow framework, verifying and updating parameters of the Faster-RCNN + ResNet network model through the test image set, and then training, and circulating the process until a final sperm nucleoprotein detection model is obtained.
It should be noted that, the method for training the training image set by the detection model training unit in the TensorFlow framework by using the fast-RCNN + ResNet network model includes:
adjusting the network structure of fast-rcnn, replacing the basic network with a ResNet50 network, and adjusting the corresponding training parameters: learning rate, training image quantity, iteration times, selection of an optimizer and selection of a loss function;
extracting the features of the training image set by using a group of basic conv + relu + posing layers, and sharing the extracted features to the regional suggestion network layer and the full connection layer for processing;
the regional suggestion network layer is used for generating a regional suggestion frame, judging whether the suggestion frame is correct or not through a softmax loss function, and correcting the suggestion frame by utilizing border frame regression to accurately acquire the suggestion frame;
the region-of-interest pooling layer is used for collecting input features and suggestion boxes, and after the information is integrated, the information is sent to a subsequent full-connection layer to judge the target category;
the full-junction layer calculates the category of the suggestion frame by using the suggestion frame obtained by the interested region pooling layer, namely the category whether the sperm nucleoprotein is mature or not, and simultaneously obtains the final accurate position of the detection frame by using the bounding box regression, wherein the formula is as follows:
wherein xiAs input data for the fast-RCNN + ResNet network, wijFor the weight values of the input data to the output data, biIs the corresponding deviation value, yiIs the corresponding output value.
It should be noted that the method for verifying and updating the fast-RCNN + ResNet network model parameters by the detection model training unit through testing the image set and then training the same, and repeating the process until the final sperm nucleoprotein detection model is obtained includes:
on the trained sperm nucleoprotein detection model, training a regional suggestion network for the first time to obtain the first trained regional suggestion network;
collecting a suggestion frame by utilizing the first trained regional suggestion network and the test image set;
training a fast-rcnn network for the first time;
the second training area suggests a network to obtain a second trained RPN network;
collecting a suggestion frame by utilizing the second trained regional suggestion network and the test image set;
the fast-rcnn network is trained a second time.
The invention also provides a device for detecting the maturity of the sperm nucleoprotein, which comprises: a memory for storing a computer program; a processor for executing a computer program to implement the steps of the above-mentioned sperm nucleoprotein maturity detection method.
For the description of the features in the embodiment corresponding to fig. 4, reference may be made to the related description of the embodiments corresponding to fig. 1 to fig. 3, which is not repeated here.
The method and the device for detecting the maturity of the sperm nucleoprotein provided by the embodiment of the invention are described in detail above. The embodiments are described in a progressive manner in the specification, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other. The device disclosed by the embodiment corresponds to the method disclosed by the embodiment, so that the description is simple, and the relevant points can be referred to the method part for description. It should be noted that, for those skilled in the art, it is possible to make various improvements and modifications to the present invention without departing from the principle of the present invention, and those improvements and modifications also fall within the scope of the claims of the present invention.
Those of skill would further appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, computer software, or combinations of both, and that the various illustrative components and steps have been described above generally in terms of their functionality in order to clearly illustrate this interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
The steps of a method or algorithm described in connection with the embodiments disclosed herein may be embodied directly in hardware, in a software module executed by a processor, or in a combination of the two. A software module may reside in Random Access Memory (RAM), memory, Read Only Memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.
Claims (9)
1. A method for detecting the maturity of an sperm nucleoprotein, which is characterized by comprising the following steps:
s11: obtaining a sperm nucleoprotein staining microscopic image;
s12: and (3) passing the sperm nucleoprotein staining microscopic image through a sperm nucleoprotein detection model to obtain a sperm nucleoprotein image, position information of the sperm nucleoprotein in the image and a mature or immature sperm nucleoprotein detection result.
2. The method for detecting the maturity of sperm nuclear protein according to claim 1, further comprising S10: generating a sperm nucleoprotein detection model; the method of S10 includes:
s101: screening sperm nucleoprotein staining microscopic images of the large samples;
s102: marking mature or immature sperm nucleoprotein on the sperm nucleoprotein dyeing microscopic image, and dividing the marked sperm nucleoprotein dyeing microscopic image into a training image set and a testing image set;
s103: and (3) training the training image set by adopting a fast-RCNN + ResNet network model under a TensorFlow framework, verifying and updating parameters of the fast-RCNN + ResNet network model through the test image set, and then training, and circulating the process until a final sperm nucleoprotein detection model is obtained.
3. The S of claim 2, wherein the method for training the set of training images in S103 under the TensorFlow framework using the fast-RCNN + ResNet network model comprises:
adjusting the network structure of fast-rcnn, replacing the basic network with a ResNet50 network, and adjusting the corresponding training parameters: learning rate, training image quantity, iteration times, selection of an optimizer and selection of a loss function;
extracting the features of the training image set by using a group of basic conv + relu + posing layers, and sharing the extracted features to the regional suggestion network layer and the full connection layer for processing;
the regional suggestion network layer is used for generating a regional suggestion frame, judging whether the suggestion frame is correct or not through a softmax loss function, and correcting the suggestion frame by utilizing border frame regression to accurately acquire the suggestion frame;
the region-of-interest pooling layer is used for collecting input features and suggestion boxes, and after the information is integrated, the information is sent to a subsequent full-connection layer to judge the target category;
the full-junction layer calculates the category of the suggestion frame by using the suggestion frame obtained by the interested region pooling layer, namely the category whether the sperm nucleoprotein is mature or not, and simultaneously obtains the final accurate position of the detection frame by using the bounding box regression, wherein the formula is as follows:
4. The method for detecting the maturity of sperm nucleoprotein as claimed in claim 3, wherein the method for verifying and updating the parameters of the fast-RCNN + ResNet network model by the test image set in S103 and performing training, and repeating the process until the final sperm nucleoprotein detection model is obtained comprises:
on the trained sperm nucleoprotein detection model, training a regional suggestion network for the first time to obtain the first trained regional suggestion network;
collecting a suggestion frame by utilizing the first trained regional suggestion network and the test image set;
training a fast-rcnn network for the first time;
the second training area suggests a network to obtain a second trained RPN network;
collecting a suggestion frame by utilizing the second trained regional suggestion network and the test image set;
the fast-rcnn network is trained a second time.
5. An apparatus for detecting the maturity of an sperm nucleoprotein, comprising:
the sperm image acquisition module is used for acquiring a sperm nucleoprotein staining microscopic image;
and the nucleoprotein detection module is used for enabling the sperm nucleoprotein staining microscopic image to pass through the sperm nucleoprotein detection model to obtain the sperm nucleoprotein image, the position information of the sperm nucleoprotein in the image and the mature or immature sperm nucleoprotein detection result.
6. The sperm nucleoprotein maturity detection device of claim 5, further comprising: the detection model generation module is used for generating a sperm nucleoprotein detection model; the detection model generation module comprises:
the sample data screening unit is used for screening sperm nucleoprotein staining microscopic images of the large samples;
the sample data labeling unit is used for labeling the mature or immature sperm nucleoprotein on the sperm nucleoprotein dyeing microscopic image and dividing the labeled sperm nucleoprotein dyeing microscopic image into a training image set and a test image set;
and the detection model training unit is used for training the training image set by adopting a Faster-RCNN + ResNet network model under a TensorFlow framework, verifying and updating parameters of the Faster-RCNN + ResNet network model through the test image set, and then training, and circulating the process until a final sperm nucleoprotein detection model is obtained.
7. The sperm nucleoprotein maturity detection apparatus of claim 6, wherein the detection model training unit is configured to train the training image set by using a fast-RCNN + ResNet network model under a TensorFlow framework, and the method comprises:
adjusting the network structure of fast-rcnn, replacing the basic network with a ResNet50 network, and adjusting the corresponding training parameters: learning rate, training image quantity, iteration times, selection of an optimizer and selection of a loss function;
extracting the features of the training image set by using a group of basic conv + relu + posing layers, and sharing the extracted features to the regional suggestion network layer and the full connection layer for processing;
the regional suggestion network layer is used for generating a regional suggestion frame, judging whether the suggestion frame is correct or not through a softmax loss function, and correcting the suggestion frame by utilizing border frame regression to accurately acquire the suggestion frame;
the region-of-interest pooling layer is used for collecting input features and suggestion boxes, and after the information is integrated, the information is sent to a subsequent full-connection layer to judge the target category;
the full-junction layer calculates the category of the suggestion frame by using the suggestion frame obtained by the interested region pooling layer, namely the category whether the sperm nucleoprotein is mature or not, and simultaneously obtains the final accurate position of the detection frame by using the bounding box regression, wherein the formula is as follows:
8. The sperm nucleoprotein maturity detection apparatus of claim 6 wherein the detection model training unit verifies and updates the fast-RCNN + ResNet network model parameters by testing the image set and trains the same, and the method of repeating the process until the final sperm nucleoprotein detection model is obtained comprises:
on the trained sperm nucleoprotein detection model, training a regional suggestion network for the first time to obtain the first trained regional suggestion network;
collecting a suggestion frame by utilizing the first trained regional suggestion network and the test image set;
training a fast-rcnn network for the first time;
the second training area suggests a network to obtain a second trained RPN network;
collecting a suggestion frame by utilizing the second trained regional suggestion network and the test image set;
the fast-rcnn network is trained a second time.
9. An apparatus for detecting the maturity of an sperm nucleoprotein, comprising:
a memory for storing a computer program;
a processor for executing the computer program to carry out the steps of the method for detecting the maturity of sperm nuclear protein as defined in any one of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011216686.XA CN112200803B (en) | 2020-11-04 | 2020-11-04 | Sperm nucleoprotein maturity detection method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011216686.XA CN112200803B (en) | 2020-11-04 | 2020-11-04 | Sperm nucleoprotein maturity detection method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112200803A true CN112200803A (en) | 2021-01-08 |
| CN112200803B CN112200803B (en) | 2023-10-10 |
Family
ID=74033201
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011216686.XA Active CN112200803B (en) | 2020-11-04 | 2020-11-04 | Sperm nucleoprotein maturity detection method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112200803B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115861319A (en) * | 2023-02-28 | 2023-03-28 | 中国科学院长春光学精密机械与物理研究所 | Cumulus cell complex maturity analysis method, device, equipment and medium |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100002929A1 (en) * | 2004-05-13 | 2010-01-07 | The Charles Stark Draper Laboratory, Inc. | Image-based methods for measuring global nuclear patterns as epigenetic markers of cell differentiation |
| CN107492095A (en) * | 2017-08-02 | 2017-12-19 | 西安电子科技大学 | Medical image pulmonary nodule detection method based on deep learning |
| US20190347828A1 (en) * | 2018-05-09 | 2019-11-14 | Beijing Kuangshi Technology Co., Ltd. | Target detection method, system, and non-volatile storage medium |
| CN110458821A (en) * | 2019-08-07 | 2019-11-15 | 屈晨 | A kind of sperm morphology analysis method based on deep neural network model |
| WO2020090947A1 (en) * | 2018-10-31 | 2020-05-07 | 合同会社みらか中央研究所 | Program, learning model, information processing device, information processing method, information display method, and method for producing learning model |
| CN111402232A (en) * | 2020-03-16 | 2020-07-10 | 深圳市瑞图生物技术有限公司 | Method for detecting sperm aggregation in semen |
| WO2020181685A1 (en) * | 2019-03-12 | 2020-09-17 | 南京邮电大学 | Vehicle-mounted video target detection method based on deep learning |
-
2020
- 2020-11-04 CN CN202011216686.XA patent/CN112200803B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100002929A1 (en) * | 2004-05-13 | 2010-01-07 | The Charles Stark Draper Laboratory, Inc. | Image-based methods for measuring global nuclear patterns as epigenetic markers of cell differentiation |
| CN107492095A (en) * | 2017-08-02 | 2017-12-19 | 西安电子科技大学 | Medical image pulmonary nodule detection method based on deep learning |
| US20190347828A1 (en) * | 2018-05-09 | 2019-11-14 | Beijing Kuangshi Technology Co., Ltd. | Target detection method, system, and non-volatile storage medium |
| WO2020090947A1 (en) * | 2018-10-31 | 2020-05-07 | 合同会社みらか中央研究所 | Program, learning model, information processing device, information processing method, information display method, and method for producing learning model |
| WO2020181685A1 (en) * | 2019-03-12 | 2020-09-17 | 南京邮电大学 | Vehicle-mounted video target detection method based on deep learning |
| CN110458821A (en) * | 2019-08-07 | 2019-11-15 | 屈晨 | A kind of sperm morphology analysis method based on deep neural network model |
| CN111402232A (en) * | 2020-03-16 | 2020-07-10 | 深圳市瑞图生物技术有限公司 | Method for detecting sperm aggregation in semen |
Non-Patent Citations (3)
| Title |
|---|
| 刘德一;H.W.GORDON BAKER;: "精子功能检测与男性不育诊治的新进展", 中华男科学杂志, no. 02 * |
| 王高峰;徐子同;卢玮;王翠翠;高涛;: "基于卷积神经网络的目标检测与识别", 计算机与数字工程, no. 02 * |
| 谷龙杰;陈振文;: "人类精子核成熟度检测及其临床意义", 国际生殖健康/计划生育杂志, no. 04 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115861319A (en) * | 2023-02-28 | 2023-03-28 | 中国科学院长春光学精密机械与物理研究所 | Cumulus cell complex maturity analysis method, device, equipment and medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112200803B (en) | 2023-10-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111448582B (en) | System and method for single channel whole cell segmentation | |
| CN105224960B (en) | Corn seed classification hyperspectral imagery identification model update method based on clustering algorithm | |
| CN108830332A (en) | A kind of vision vehicle checking method and system | |
| CN109886928A (en) | A kind of target cell labeling method, device, storage medium and terminal device | |
| CN110796661B (en) | Fungal microscopic image segmentation detection method and system based on convolutional neural network | |
| CN115088022A (en) | Federal learning system for training machine learning algorithms and maintaining patient privacy | |
| CN110853006A (en) | Method for evaluating quality of digital pathological image acquired by scanner | |
| CN112365497A (en) | High-speed target detection method and system based on Trident Net and Cascade-RCNN structures | |
| CN104680185B (en) | Hyperspectral image classification method based on boundary point reclassification | |
| CN114359199A (en) | Fish counting method, device, equipment and medium based on deep learning | |
| CN113674216A (en) | Subway tunnel disease detection method based on deep learning | |
| CN105427327B (en) | The method for registering images and device of a kind of DNA sequencing | |
| CN113012129A (en) | System and device for counting area positioning and marked nerve cells of brain slice image | |
| CN113205511B (en) | Electronic component batch information detection method and system based on deep neural network | |
| CN110728269A (en) | High-speed rail contact net support pole number plate identification method | |
| CN112200803A (en) | Method and device for detecting maturity of sperm nucleoprotein | |
| CN111062437A (en) | Bridge structure disease automatic target detection model based on deep learning | |
| CN108805181B (en) | Image classification device and method based on multi-classification model | |
| Tu et al. | AIseed: An automated image analysis software for high-throughput phenotyping and quality non-destructive testing of individual plant seeds | |
| Kaur et al. | Geometric feature extraction of selected rice grains using image processing techniques | |
| CN113793385A (en) | Method and device for positioning fish head and fish tail | |
| US20160321512A1 (en) | Automated staining and segmentation quality control | |
| CN110738641B (en) | Image processing and KELM based qualitative detection method for concentration of medical reagent | |
| CN113378831A (en) | Mouse embryo organ identification and scoring method and system | |
| CN112084941A (en) | Target detection and identification method based on remote sensing image |
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 |