CN116416616B - DC cell in-vitro culture screening method, device and computer readable medium - Google Patents

DC cell in-vitro culture screening method, device and computer readable medium Download PDF

Info

Publication number
CN116416616B
CN116416616B CN202310397576.5A CN202310397576A CN116416616B CN 116416616 B CN116416616 B CN 116416616B CN 202310397576 A CN202310397576 A CN 202310397576A CN 116416616 B CN116416616 B CN 116416616B
Authority
CN
China
Prior art keywords
image
fuzzy
sample
tensor
cell
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.)
Active
Application number
CN202310397576.5A
Other languages
Chinese (zh)
Other versions
CN116416616A (en
Inventor
聂宵
田国忠
张鹏
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Watson Click Beijing Biotechnology Co ltd
Original Assignee
Watson Click Beijing Biotechnology Co ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Watson Click Beijing Biotechnology Co ltd filed Critical Watson Click Beijing Biotechnology Co ltd
Priority to CN202310397576.5A priority Critical patent/CN116416616B/en
Publication of CN116416616A publication Critical patent/CN116416616A/en
Application granted granted Critical
Publication of CN116416616B publication Critical patent/CN116416616B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/60—Type of objects
    • G06V20/69—Microscopic objects, e.g. biological cells or cellular parts
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T5/00—Image enhancement or restoration
    • G06T5/70—Denoising; Smoothing
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/90—Determination of colour characteristics
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/60—Type of objects
    • G06V20/69—Microscopic objects, e.g. biological cells or cellular parts
    • G06V20/695—Preprocessing, e.g. image segmentation
    • 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

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Biomedical Technology (AREA)
  • General Health & Medical Sciences (AREA)
  • Molecular Biology (AREA)
  • Multimedia (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Image Analysis (AREA)

Abstract

The invention provides a DC cell in-vitro culture screening method, a device and a computer readable medium, wherein the method firstly acquires a DC cell microscopic image carrying a mark, and the mark comprises a sample number and a time stamp; then, performing background selection and differential calculation on the DC cell microscopic image to generate a pretreatment image; then, counting the image information entropy of the preprocessed image, and constructing a time sequence sample of the image information entropy and a time stamp; then inputting the time sequence sample into a prediction model, and calculating a prediction result; and finally, screening the DC cell samples according to the prediction result. Therefore, the in-vitro culture state of the DC cells can be predicted in advance, DC cell in-vitro culture samples with poor culture state are screened out in advance, the waste of raw materials and experimental resources is effectively avoided, the consumption of manpower and material resources is reduced, and the accuracy of subsequent experiments is improved.

Description

DC cell in-vitro culture screening method, device and computer readable medium
[ field of technology ]
The invention relates to the field of biotechnology, in particular to a DC cell in-vitro culture screening method, a DC cell in-vitro culture screening device and a computer readable medium.
[ background Art ]
DC (Dendritic Cell) cells, also known as Dendritic cells, are a type of white blood Cell found in mammals. It is present in blood and in tissues exposed to the environment, such as the skin and the epithelium of the nose, lungs, stomach and small intestine, and serves to regulate the innate and acquired immune responses to current environmental stimuli.
DC cell induction culture plays an important role in the application of the latest biological technology. The DC cell induction culture method has harsh conditions for laboratory requirements, and if DC cells with poor culture conditions cannot be effectively screened, raw materials and experimental resources are wasted, a large amount of manpower and material resources are consumed, and the experimental precision is affected.
[ invention ]
In view of this, embodiments of the present invention provide a method, apparatus and computer readable medium for DC cell in vitro culture sieving.
The application provides a DC cell in-vitro culture screening method, which comprises the following steps:
s1, acquiring a DC cell microscopic image carrying an identifier, wherein the identifier comprises a sample number and a time stamp;
s2, performing background selection and differential calculation on the DC cell microscopic image to generate a preprocessing image;
s3, counting the image information entropy of the preprocessed image, and constructing a time sequence sample of the image information entropy and a time stamp;
s4, inputting the time sequence samples into a prediction model, and calculating a prediction result;
s5, screening the DC cell samples according to the prediction result.
Further, the DC cell microscopic image is specifically generated by:
and acquiring initial microscopic images of all samples at a plurality of moments according to a preset period, wherein the initial microscopic images of the same sample at each moment are a group of initial microscopic image groups, and after the sample number and the time stamp are attached to each initial microscopic image group of each group, a DC cell microscopic image is obtained.
Further, the step S2 specifically includes the following steps:
s21, selecting an image to be processed from an initial microscopic image group, and acquiring three-dimensional coordinates of the processed image, wherein the three-dimensional coordinates carry RGB information; taking the three-dimensional coordinate at the central position of the image to be processed as a standard three-dimensional coordinate;
s22, performing difference calculation on RGB information of other three-dimensional coordinates and RGB information of standard three-dimensional coordinates, recognizing the three-dimensional coordinates with difference exceeding a preset threshold as invalid areas, selecting all the invalid areas and setting the invalid areas as a background;
s23, performing sum value calculation and difference value calculation on other three-dimensional coordinates and standard three-dimensional coordinate information to obtain sum value and difference value of the three-dimensional coordinates;
s24, three-dimensional coordinate difference information is obtained based on the three-dimensional coordinate difference value and the three-dimensional coordinate sum value, and a preprocessing image is generated according to the coordinate difference information.
Further, the step S3 specifically includes the following steps:
s31, formula H (a) =α.pi (a) F [ exp (U (b) +V (b))]-β·∑(a)·F -1 [exp(U(b)+V(b))] 2/ω Calculating the image information entropy of the preprocessed image, wherein H (a) is the image information entropy, alpha is a first priori parameter, beta is a second priori parameter, pi (a) is Laplacian filtering smoothing processing, sigma (a) is Gaussian filter smoothing processing, F is Fourier transform and F -1 For inverse fourier transform, U (b) is the spectral residual of the pre-processed image, V (b) is the phase spectrum of the pre-processed image;
s32, let H (a) =x, then the time-series samples of the image information entropy and the time stamp are expressed asWherein the sequence input is x i ＝(x 1i ,x 2i ,...,x ti )，x ti For the entropy of the image information of the sample i at the t-th moment, the sequence output is y= [ y ] 1 ,y 2 ,...,y N ] T N is the number of samples;
s33, mapping each data of the data set into 0-1 to obtain a time sequence data sample, wherein the normalization formula is as follows:x ti for any element in sample i, x max X is the maximum value in the sample element min Is the minimum in the sample element;
further, the predictive model is trained by:
constructing a first fuzzy primitive function from training samplesA second fuzzy primitive functionWherein z=x i -m i ，/>m i For mean value->Is the standard deviation of the first fuzzy primitive function,σ i standard deviation as a second fuzzy primitive function;
and constructing a group of smooth fuzzy combinations by using the first fuzzy primitive function and the second fuzzy primitive function as operators through a smooth triangular mode and a smooth triangular residual mode, wherein the smooth fuzzy combinations are expressed as follows:
wherein,and->Respectively corresponding to the fuzzy primitive functions constructed by the smooth triangular residual mode and the smooth triangular mode;
triangular residual model based on smooth blurringAnd smooth fuzzy triangular mode->Constructing a third fuzziness element function:
wherein pi is an uncertainty adjustment parameter and pi > 0;
defining randomly generated input weightsAnd a randomly generated offset τ il Wherein i=1, 2,..n, l=1, 2;
constructing the following three arrays through the first fuzzy primitive function, the second fuzzy primitive function and the third fuzzy primitive function:
wherein,andΨ :,:,:,3 tensor results of the first, second and third fuzzier functions, respectively, of the interval-three fuzzification set +.>AndΨ :,:,:,3 is N x 2 x I in all dimensions,andΨ :,:,:,3 all are third-order tensors and can construct fourth-order tensors;
constructing a Zhang Lianghua interval three-type smooth fuzzy neural network, and expressing the three-type smooth fuzzy neural network by using the following tensor equation:is the hidden layer output tensor of the tensor interval three-type model neural network,is the output weight tensor, +.>Is any non-zero tensor,>is the output tensor;
calculating an optimal solution of the output weight:
given an initial fourth-order tensorArbitrary non-zero fourth order tensor->Random fourth order tensor->Setting the error as epsilon > 0;
calculation of
Setting up
Calculation of
Set the cycle, cyclic coefficient κ=1, 2..:
the cycle cut-off conditions were:obtaining the optimal solution of the hidden layer output tensor after the circulation is finished>
The light output of the Zhang Lianghua interval three-type smooth fuzzy neural network is expressed as follows:Zhang Liangvector->And outputting the vector.
Further, the step S4 specifically includes the following steps:
and after the time series samples are processed into the same format as the training samples, inputting a prediction model to calculate a prediction result.
Further, the step S5 specifically includes the following steps:
judging whether the predicted result reaches a preset threshold value, if so, continuing culturing the DC cells of the group of samples; if not, the culture of the set of DC cells is stopped.
In another aspect, the invention also provides a DC cell in vitro culture screening device, comprising:
the acquisition module acquires a DC cell microscopic image carrying an identifier, wherein the identifier comprises a sample number and a time stamp;
the preprocessing module is used for generating a preprocessing image after carrying out background selection and differential calculation on the DC cell microscopic image;
and the processing module is used for counting the image information entropy of the preprocessed image and constructing a time sequence sample of the image information entropy and the time stamp.
The calculation module is used for calculating a prediction result after the time sequence sample is input into the prediction model;
and the screening module is used for screening the DC cell samples according to the prediction result.
The apparatus includes at least one processor and a memory coupled to the memory for reading and executing instructions in the memory to perform the method of any of the above.
In yet another aspect, the invention provides a computer readable medium, characterized in that the computer readable medium stores a program code which, when run on a computer, causes the computer to perform any of the above methods for DC cell culture in vitro screening.
One of the above technical solutions has the following beneficial effects:
the invention provides a DC cell in-vitro culture screening method, which comprises the steps of firstly, acquiring a DC cell microscopic image carrying a mark, wherein the mark comprises a sample number and a time stamp; then, performing background selection and differential calculation on the DC cell microscopic image to generate a pretreatment image; then, counting the image information entropy of the preprocessed image, and constructing a time sequence sample of the image information entropy and a time stamp; then inputting the time sequence sample into a prediction model, and calculating a prediction result; and finally, screening the DC cell samples according to the prediction result. Therefore, the in-vitro culture state of the DC cells can be predicted in advance, DC cell in-vitro culture samples with poor culture state are screened out in advance, the waste of raw materials and experimental resources is effectively avoided, the consumption of manpower and material resources is reduced, and the experimental precision is improved.
[ description of the drawings ]
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings that are needed in the embodiments will be briefly described below, it being obvious that the drawings in the following description are only some embodiments of the present invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a schematic flow chart of an in vitro culture sieving method for DC cells according to an embodiment of the present invention;
FIG. 2 is a block diagram of an in vitro culture sieving device for DC cells according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of the hardware architecture of an in vitro culture sieving device for DC cells according to the present invention.
[ detailed description ] of the invention
In order to better understand the technical scheme of the present invention, the following detailed description of the embodiments of the present invention is provided.
It should be understood that the described embodiments are merely some, but not all, embodiments of the invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
The terminology used in the embodiments of the invention is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. As used in this application and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise.
It should be understood that the term "and/or" as used herein is merely one relationship describing the association of the associated objects, meaning that there may be three relationships, e.g., a and/or B, may represent: a exists alone, A and B exist together, and B exists alone. In addition, the character "/" herein generally indicates that the front and rear associated objects are an "or" relationship.
Referring to fig. 1, the present application provides a method for screening DC cells in vitro culture, the method comprising the steps of:
s1, acquiring a DC cell microscopic image carrying an identifier, wherein the identifier comprises a sample number and a time stamp;
s2, performing background selection and differential calculation on the DC cell microscopic image to generate a preprocessing image;
s3, counting the image information entropy of the preprocessed image, and constructing a time sequence sample of the image information entropy and a time stamp;
s4, inputting the time sequence samples into a prediction model, and calculating a prediction result;
s5, screening the DC cell samples according to the prediction result.
The invention provides a DC cell in-vitro culture screening method, which comprises the steps of firstly, acquiring a DC cell microscopic image carrying a mark, wherein the mark comprises a sample number and a time stamp; then, performing background selection and differential calculation on the DC cell microscopic image to generate a pretreatment image; then, counting the image information entropy of the preprocessed image, and constructing a time sequence sample of the image information entropy and a time stamp; then inputting the time sequence sample into a prediction model, and calculating a prediction result; and finally, screening the DC cell samples according to the prediction result. Therefore, the in-vitro culture state of the DC cells can be predicted in advance, DC cell in-vitro culture samples with poor culture state are screened out in advance, the waste of raw materials and experimental resources is effectively avoided, the consumption of manpower and material resources is reduced, and the experimental precision is improved.
The DC cell microscopic image of the embodiment of the present application is specifically generated by:
and acquiring initial microscopic images of all samples at a plurality of moments according to a preset period, wherein the initial microscopic images of the same sample at each moment are a group of initial microscopic image groups, and after the sample number and the time stamp are attached to each initial microscopic image group of each group, a DC cell microscopic image is obtained.
Thus, each culture sample has a plurality of initial microscopic images formed at different moments, and after the sample numbers and the time stamps are attached, a plurality of initial microscopic image groups are formed by a plurality of culture samples.
Specifically, the embodiment of the application further refines S2, and S2 specifically includes the following steps:
s21, selecting an image to be processed from an initial microscopic image group, and acquiring three-dimensional coordinates of the processed image, wherein the three-dimensional coordinates carry RGB information; taking the three-dimensional coordinate at the central position of the image to be processed as a standard three-dimensional coordinate;
s22, performing difference calculation on RGB information of other three-dimensional coordinates and RGB information of standard three-dimensional coordinates, recognizing the three-dimensional coordinates with difference exceeding a preset threshold as invalid areas, selecting all the invalid areas and setting the invalid areas as a background;
s23, performing sum value calculation and difference value calculation on other three-dimensional coordinates and standard three-dimensional coordinate information to obtain sum value and difference value of the three-dimensional coordinates;
s24, three-dimensional coordinate difference information is obtained based on the three-dimensional coordinate difference value and the three-dimensional coordinate sum value, and a preprocessing image is generated according to the coordinate difference information.
Specifically, the embodiment of the application further refines S3, where S3 specifically includes the following steps:
s31, formula H (a) =α.pi (a) F [ exp (U (b) +V (b))]-β·∑(a)·F -1 [exp(U(b)+V(b))] 2/ω Calculating the image information entropy of the preprocessed image, wherein H (a) is the image information entropy, alpha is a first priori parameter, beta is a second priori parameter, pi (a) is Laplacian filtering smoothing processing, sigma (a) is Gaussian filter smoothing processing, F is Fourier transform and F -1 For inverse fourier transform, U (b) is the spectral residual of the pre-processed image, V (b) is the phase spectrum of the pre-processed image;
s32, let H (a) =x, then the time-series samples of the image information entropy and the time stamp are expressed asWherein the sequence input is x i ＝(x 1i ,x 2i ,...,x ti )，x ti For the entropy of the image information of the sample i at the t-th moment, the sequence output is y= [ y ] 1 ,y 2 ,...,y N ] T N is the number of samples;
s33, mapping each data of the data set into 0-1 to obtain a time sequence data sample, wherein the normalization formula is as follows:x ti for the sampleAny element in i, x max X is the maximum value in the sample element min Is the minimum in the sample element;
further, the predictive model is trained by:
constructing a first fuzzy primitive function from training samplesA second fuzzy primitive functionWherein z=x i -m i ，/>m i For mean value->Is the standard deviation of the first fuzzy primitive function,σ i standard deviation as a second fuzzy primitive function;
and constructing a group of smooth fuzzy combinations by using the first fuzzy primitive function and the second fuzzy primitive function as operators through a smooth triangular mode and a smooth triangular residual mode, wherein the smooth fuzzy combinations are expressed as follows:
wherein,and->Respectively corresponding to the fuzzy primitive functions constructed by the smooth triangular residual mode and the smooth triangular mode;
based onSmooth fuzzy triangle residual mouldAnd smooth fuzzy triangular mode->Constructing a third fuzziness element function:
wherein pi is an uncertainty adjustment parameter and pi > 0;
defining randomly generated input weightsAnd a randomly generated offset τ il Wherein i=1, 2,..n, l=1, 2;
constructing the following three arrays through the first fuzzy primitive function, the second fuzzy primitive function and the third fuzzy primitive function:
wherein,andΨ :,:,:,3 tensor results of the first, second and third fuzzier functions, respectively, of the interval-three fuzzification set +.>AndΨ :,:,:,3 is N x 2 x I in all dimensions,andΨ :,:,:,3 all are third-order tensors and can construct fourth-order tensors;
constructing a Zhang Lianghua interval three-type smooth fuzzy neural network, and expressing the three-type smooth fuzzy neural network by using the following tensor equation:is the hidden layer output tensor of the tensor interval three-type model neural network,is the output weight tensor, +.>Is any non-zero tensor,>is the output tensor;
calculating an optimal solution of the output weight:
given an initial fourth-order tensorArbitrary non-zero fourth order tensor->Random fourth order tensor->Setting the error as epsilon > 0;
calculation of
Setting up
Calculation of
Set the cycle, cyclic coefficient κ=1, 2..:
the cycle cut-off conditions were:obtaining the optimal solution of the hidden layer output tensor after the circulation is finished>
The light output of the Zhang Lianghua interval three-type smooth fuzzy neural network is expressed as follows:Zhang Liangvector->And outputting the vector.
Specifically, S4 specifically includes the following steps:
and after the time series samples are processed into the same format as the training samples, inputting a prediction model to calculate a prediction result.
Specifically, S5 specifically includes the following steps:
judging whether the predicted result reaches a preset threshold value, if so, continuing culturing the DC cells of the group of samples; if not, the culture of the set of DC cells is stopped.
The invention also provides a DC cell in-vitro culture screening device, which comprises:
an acquisition module 210 that acquires a DC cell microscopic image carrying an identification, the identification comprising a sample number and a timestamp;
the preprocessing module 220 is used for generating a preprocessed image after performing background selection and differential calculation on the DC cell microscopic image;
the processing module 230 is configured to perform statistics on the image information entropy of the preprocessed image, and construct a time sequence sample of the image information entropy and a time stamp;
a calculation module 240, configured to calculate a prediction result after inputting the time-series sample into a prediction model;
and the screening module 250 is used for screening the DC cell samples according to the prediction result.
Please refer to fig. 3, which is a schematic diagram of a hardware structure of an in vitro culture sieving device for DC cells according to the present invention. The data prediction device comprises at least one processor and a memory, wherein the at least one processor is coupled with the memory and is used for reading and executing instructions in the memory so as to execute the DC cell in-vitro culture screening method provided by the embodiment of the invention.
In a third aspect, embodiments of the present invention provide a computer-readable medium. The computer readable medium stores program code which, when run on a computer, causes the computer to perform the DC cell in vitro culture sieving method provided by the embodiments of the invention.
The system, apparatus, module or unit set forth in the above embodiments may be implemented in particular by a computer chip or entity, or by a product having a certain function. One typical implementation is a computer. In particular, the computer may be, for example, a personal computer, a laptop computer, a cellular telephone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.
For convenience of description, the above apparatus is described as being functionally divided into various units or modules, respectively. Of course, the functions of each unit or module may be implemented in one or more pieces of software and/or hardware when implementing the invention.
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 methods, apparatus (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.
In one typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.
The memory may include volatile memory in a computer-readable medium, random Access Memory (RAM) and/or nonvolatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). Memory is an example of computer-readable media.
Computer readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of storage media for a computer include, but are not limited to, phase change memory (PRAM), static Random Access Memory (SRAM), dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), read Only Memory (ROM), electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium, which can be used to store information that can be accessed by a computing device. Computer-readable media, as defined herein, does not include transitory computer-readable media (transmission media), such as modulated data signals and carrier waves.
It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article or apparatus that comprises the element.
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 invention may be described in the general context of computer-executable instructions, such as program modules, being executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform particular tasks or implement particular abstract data types. The invention may also be practiced in distributed computing environments where tasks are performed by remote processing devices that are linked through a communications network. In a distributed computing environment, program modules may be located in both local and remote computer storage media including memory storage devices.
The embodiments of the present invention are described in a progressive manner, and the same and similar parts of the embodiments are all referred to each other, and each embodiment is mainly described in the differences from the other embodiments. In particular, for system embodiments, since they are substantially similar to method embodiments, the description is relatively simple, as relevant to see a section of the description of method embodiments.
The foregoing is merely exemplary of the present invention and is not intended to limit the present invention. Various modifications and variations of the present invention will be apparent to those skilled in the art. Any modification, equivalent replacement, improvement, etc. which come within the spirit and principles of the invention are to be included in the scope of the claims of the present invention.

Claims (6)

1. A method for screening a DC cell in vitro culture, comprising the steps of:
s1, acquiring a DC cell microscopic image carrying an identifier, wherein the identifier comprises a sample number and a time stamp;
s2, performing background selection and differential calculation on the DC cell microscopic image to generate a preprocessing image;
s3, counting the image information entropy of the preprocessed image, and constructing a time sequence sample of the image information entropy and a time stamp;
s4, inputting the time sequence samples into a prediction model, and calculating a prediction result;
s5, screening the DC cell sample according to the prediction result;
the DC cell microscopic image is specifically generated by the following steps:
collecting initial microscopic images of all samples at a plurality of moments according to a preset period, wherein the initial microscopic images of the same sample at each moment are a group of initial microscopic image groups, and after each initial microscopic image group is attached with a sample number and a time stamp, DC cell microscopic images are obtained;
the step S2 specifically comprises the following steps:
s21, selecting an image to be processed from an initial microscopic image group, and acquiring three-dimensional coordinates of the processed image, wherein the three-dimensional coordinates carry RGB information; taking the three-dimensional coordinate at the central position of the image to be processed as a standard three-dimensional coordinate;
s22, performing difference calculation on RGB information of other three-dimensional coordinates and RGB information of standard three-dimensional coordinates, recognizing the three-dimensional coordinates with difference exceeding a preset threshold as invalid areas, selecting all the invalid areas and setting the invalid areas as a background;
s23, performing sum value calculation and difference value calculation on other three-dimensional coordinates and standard three-dimensional coordinate information to obtain sum value and difference value of the three-dimensional coordinates;
s24, three-dimensional coordinate difference information is obtained based on the three-dimensional coordinate difference value and the three-dimensional coordinate sum value, and a preprocessing image is generated according to the coordinate difference information;
the step S3 specifically comprises the following steps:
s31, formula H (a) =α.pi (a) F [ exp (U (b) +V (b))]-β·Σ(a)·F -1 [exp(U(b)+V(b))] 2/ω Calculating the image information entropy of the preprocessed image, wherein H (a) is the image information entropy, alpha is a first priori parameter, beta is a second priori parameter, pi (a) is Laplacian filtering smoothing processing, sigma (a) is Gaussian filter smoothing processing, F is Fourier transform and F -1 For inverse fourier transform, U (b) is the spectral residual of the pre-processed image, V (b) is the phase spectrum of the pre-processed image;
s32, let H (a) =x, then the time-series samples of the image information entropy and the time stamp are expressed asWherein the sequence input is x i ＝(x 1i ,x 2i ,...,x ti )，x ti For the entropy of the image information of the sample i at the t-th moment, the sequence output is y= [ y ] 1 ,y 2 ,...,y N ] T N is the number of samples;
s33, mapping each data of the data set into 0-1 to obtain a time sequence data sample, wherein the normalization formula is as follows:x ti for any element in sample i, x max X is the maximum value in the elements of the sample min Is the minimum in the elements of the sample;
wherein, the training sample and the input sample are both obtained by processing in the steps S31-S33;
the prediction model is trained by the following method:
constructing a first fuzzy primitive function from training samplesA second fuzzy primitive functionWherein z=x i -m i ，/>m i For mean value->Is the standard deviation of the first fuzzy primitive function,σ i standard deviation as a second fuzzy primitive function;
and constructing a group of smooth fuzzy combinations by using the first fuzzy primitive function and the second fuzzy primitive function as operators through a smooth triangular mode and a smooth triangular residual mode, wherein the smooth fuzzy combinations are expressed as follows:
wherein,and->Respectively corresponding to the fuzzy primitive functions constructed by the smooth triangular residual mode and the smooth triangular mode;
triangular residual model based on smooth blurringAnd smooth fuzzy triangular mode->Constructing a third fuzziness element function:
wherein pi is an uncertainty adjustment parameter and pi > 0;
defining randomly generated input weightsAnd a randomly generated offset τ il Wherein i=1, 2,..n, l=1, 2;
constructing the following three arrays through the first fuzzy primitive function, the second fuzzy primitive function and the third fuzzy primitive function:
wherein,andΨ :,:,:,3 tensor results of the first, second and third fuzzier functions, respectively, of the interval-three fuzzification set +.>AndΨ :,:,:,3 is N x 2 x I in all dimensions,andΨ :,:,:,3 all are third-order tensors and can construct fourth-order tensors;
construction of Zhang Lianghua Interval three-type smooth fuzzy godVia the network, by the following tensor equation: is the hidden layer output tensor of the tensor interval three-type model neural network>Is the output weight tensor, +.>Is any non-zero tensor,>is the output tensor;
calculating an optimal solution of the output weight:
given an initial fourth-order tensorArbitrary non-zero fourth order tensor->Arbitrary non-zero tensor->Setting the error as epsilon > 0;
calculation of
Setting up
Calculation of
Set the cycle, cyclic coefficient κ=1, 2..:
the cycle cut-off conditions were:obtaining the optimal solution of the hidden layer output tensor after the circulation is finished>
The light output of the Zhang Lianghua interval three-type smooth fuzzy neural network is expressed as follows:Zhang Liangvector->And outputting the vector.
2. The method for in vitro culture sieving of DC cells according to claim 1, wherein said S4 comprises the steps of:
and after the time series samples are processed into the same format as the training samples, inputting a prediction model to calculate a prediction result.
3. The method for in vitro culture sieving of DC cells according to claim 1, wherein said S5 comprises the steps of:
judging whether the predicted result reaches a preset threshold value, if so, continuing culturing the DC cells of the sample corresponding to the judged result; if not, the culture of the DC cells of the sample corresponding to the judgment result is stopped.
4. A DC cell in vitro culture screening device, comprising:
the acquisition module acquires a DC cell microscopic image carrying an identifier, wherein the identifier comprises a sample number and a time stamp;
the preprocessing module is used for generating a preprocessing image after carrying out background selection and differential calculation on the DC cell microscopic image;
the processing module is used for counting the image information entropy of the preprocessed image and constructing a time sequence sample of the image information entropy and the time stamp;
the calculation module is used for calculating a prediction result after the time sequence sample is input into the prediction model;
the screening module is used for screening the DC cell samples according to the prediction result;
the DC cell microscopic image is specifically generated by the following steps:
collecting initial microscopic images of all samples at a plurality of moments according to a preset period, wherein the initial microscopic images of the same sample at each moment are a group of initial microscopic image groups, and after each initial microscopic image group is attached with a sample number and a time stamp, DC cell microscopic images are obtained;
the preprocessing module is specifically configured to perform:
s21, selecting an image to be processed from an initial microscopic image group, and acquiring three-dimensional coordinates of the processed image, wherein the three-dimensional coordinates carry RGB information; taking the three-dimensional coordinate at the central position of the image to be processed as a standard three-dimensional coordinate;
s22, performing difference calculation on RGB information of other three-dimensional coordinates and RGB information of standard three-dimensional coordinates, recognizing the three-dimensional coordinates with difference exceeding a preset threshold as invalid areas, selecting all the invalid areas and setting the invalid areas as a background;
s23, performing sum value calculation and difference value calculation on other three-dimensional coordinates and standard three-dimensional coordinate information to obtain sum value and difference value of the three-dimensional coordinates;
s24, three-dimensional coordinate difference information is obtained based on the three-dimensional coordinate difference value and the three-dimensional coordinate sum value, and a preprocessing image is generated according to the coordinate difference information;
the processing module is specifically configured to perform:
s31, formula H (a) =α.pi (a) F [ exp (U (b) +V (b))]-β·Σ(a)·F -1 [exp(U(b)+V(b))] 2/ω Calculating the image information entropy of the preprocessed image, wherein H (a) is the image information entropy, alpha is a first priori parameter, beta is a second priori parameter, pi (a) is Laplacian filtering smoothing processing, sigma (a) is Gaussian filter smoothing processing, F is Fourier transform and F -1 For inverse fourier transform, U (b) is the spectral residual of the pre-processed image, V (b) is the phase spectrum of the pre-processed image;
s32, let H (a) =x, then the time-series samples of the image information entropy and the time stamp are expressed asWherein the sequence input is x i ＝(x 1i ,x 2i ,...,x ti )，x ti For the entropy of the image information of the sample i at the t-th moment, the sequence output is y= [ y ] 1 ,y 2 ,...,y N ] T N is the number of samples;
s33, mapping each data of the data set into 0-1 to obtain a time sequence data sample, wherein the normalization formula is as follows:x ti for any element in sample i, x max X is the maximum value in the elements of the sample min Is the minimum in the elements of the sample;
wherein, the training sample and the input sample are both obtained by processing in the steps S31-S33;
the prediction model is trained by the following method:
constructing a first fuzzy primitive function from training samplesA second fuzzy primitive functionWherein z=x i -m i ，/>m i For mean value->Is the standard deviation of the first fuzzy primitive function,σ i standard deviation as a second fuzzy primitive function;
and constructing a group of smooth fuzzy combinations by using the first fuzzy primitive function and the second fuzzy primitive function as operators through a smooth triangular mode and a smooth triangular residual mode, wherein the smooth fuzzy combinations are expressed as follows:
wherein,and->Respectively corresponding to the fuzzy primitive functions constructed by the smooth triangular residual mode and the smooth triangular mode;
triangular residual model based on smooth blurringAnd smooth fuzzy triangular mode->Constructing a third fuzziness element function:
wherein pi is an uncertainty adjustment parameter and pi > 0;
defining randomly generated input weightsAnd a randomly generated offset τ il Wherein i=1, 2,..n, l=1, 2;
constructing the following three arrays through the first fuzzy primitive function, the second fuzzy primitive function and the third fuzzy primitive function:
wherein,andΨ :,:,:,3 tensor results of the first, second and third fuzzier functions, respectively, of the interval-three fuzzification set +.>AndΨ :,:,:,3 is N x 2 x I in all dimensions,andΨ :,:,:,3 all are third-order tensors and can construct fourth-order tensors;
constructing a Zhang Lianghua interval three-type smooth fuzzy neural network, and expressing the three-type smooth fuzzy neural network by using the following tensor equation: is the hidden layer output tensor of the tensor interval three-type model neural network>Is the output weight tensor, +.>Is any non-zero tensor,>is the output tensor;
calculating an optimal solution of the output weight:
given an initial fourth-order tensorArbitrary non-zero fourth order tensor->Arbitrary non-zero tensor->Setting the error as epsilon > 0;
calculation of
Setting up
Calculation of
Set the cycle, cyclic coefficient κ=1, 2..:
the cycle cut-off conditions were:obtaining the optimal solution of the hidden layer output tensor after the circulation is finished>
The light output of the Zhang Lianghua interval three-type smooth fuzzy neural network is expressed as follows:Zhang Liangvector->And outputting the vector.
5. A DC cell in vitro culture screening device comprising at least one processor and a memory, the at least one processor being coupled to the memory for reading and executing instructions in the memory to perform the method of any one of claims 1-3.
6. A computer readable medium, characterized in that the computer readable medium stores a program code which, when run on a computer, causes the computer to perform the method according to any of claims 1-3.
CN202310397576.5A 2023-04-13 2023-04-13 DC cell in-vitro culture screening method, device and computer readable medium Active CN116416616B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202310397576.5A CN116416616B (en) 2023-04-13 2023-04-13 DC cell in-vitro culture screening method, device and computer readable medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202310397576.5A CN116416616B (en) 2023-04-13 2023-04-13 DC cell in-vitro culture screening method, device and computer readable medium

Publications (2)

Publication Number Publication Date
CN116416616A CN116416616A (en) 2023-07-11
CN116416616B true CN116416616B (en) 2024-01-05

Family

ID=87049294

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202310397576.5A Active CN116416616B (en) 2023-04-13 2023-04-13 DC cell in-vitro culture screening method, device and computer readable medium

Country Status (1)

Country Link
CN (1) CN116416616B (en)

Citations (13)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107423740A (en) * 2017-05-12 2017-12-01 西安万像电子科技有限公司 The acquisition methods and device of salient region of image
WO2018012601A1 (en) * 2016-07-14 2018-01-18 大日本印刷株式会社 Image analysis system, culture management system, image analysis method, culture management method, cell group structure method, and program
CN110378400A (en) * 2019-07-08 2019-10-25 北京三快在线科技有限公司 A kind of model training method and device for image recognition
CN111553206A (en) * 2020-04-14 2020-08-18 中国科学院深圳先进技术研究院 Cell identification method and device based on machine learning
CN111739017A (en) * 2020-07-22 2020-10-02 湖南国科智瞳科技有限公司 Cell identification method and system of microscopic image under sample unbalance condition
CN111973630A (en) * 2020-07-15 2020-11-24 沃森克里克（北京）生物科技有限公司 Cell growth factor preparation derived from mesenchymal stem cells and preparation method and application thereof
CN112734650A (en) * 2019-10-14 2021-04-30 武汉科技大学 Virtual multi-exposure fusion based uneven illumination image enhancement method
CN113160109A (en) * 2020-12-15 2021-07-23 宁波大学 Cell image segmentation method for preventing background difference
CN114363615A (en) * 2021-12-27 2022-04-15 上海商汤科技开发有限公司 Data processing method and device, electronic equipment and storage medium
CN114942396A (en) * 2022-05-21 2022-08-26 鹤壁职业技术学院 New energy power generation assembly quality detection method and device
CN115588191A (en) * 2022-09-15 2023-01-10 桂林航天工业学院 Cell sorting method and system based on image acoustic flow control cell sorting model
CN115731419A (en) * 2022-11-24 2023-03-03 山东大学 Cell growth state discrimination method and system based on intelligent discrimination algorithm
CN115730214A (en) * 2022-11-25 2023-03-03 内蒙古大学 Sequence prediction model training method and device and computer readable medium

Patent Citations (13)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2018012601A1 (en) * 2016-07-14 2018-01-18 大日本印刷株式会社 Image analysis system, culture management system, image analysis method, culture management method, cell group structure method, and program
CN107423740A (en) * 2017-05-12 2017-12-01 西安万像电子科技有限公司 The acquisition methods and device of salient region of image
CN110378400A (en) * 2019-07-08 2019-10-25 北京三快在线科技有限公司 A kind of model training method and device for image recognition
CN112734650A (en) * 2019-10-14 2021-04-30 武汉科技大学 Virtual multi-exposure fusion based uneven illumination image enhancement method
CN111553206A (en) * 2020-04-14 2020-08-18 中国科学院深圳先进技术研究院 Cell identification method and device based on machine learning
CN111973630A (en) * 2020-07-15 2020-11-24 沃森克里克（北京）生物科技有限公司 Cell growth factor preparation derived from mesenchymal stem cells and preparation method and application thereof
CN111739017A (en) * 2020-07-22 2020-10-02 湖南国科智瞳科技有限公司 Cell identification method and system of microscopic image under sample unbalance condition
CN113160109A (en) * 2020-12-15 2021-07-23 宁波大学 Cell image segmentation method for preventing background difference
CN114363615A (en) * 2021-12-27 2022-04-15 上海商汤科技开发有限公司 Data processing method and device, electronic equipment and storage medium
CN114942396A (en) * 2022-05-21 2022-08-26 鹤壁职业技术学院 New energy power generation assembly quality detection method and device
CN115588191A (en) * 2022-09-15 2023-01-10 桂林航天工业学院 Cell sorting method and system based on image acoustic flow control cell sorting model
CN115731419A (en) * 2022-11-24 2023-03-03 山东大学 Cell growth state discrimination method and system based on intelligent discrimination algorithm
CN115730214A (en) * 2022-11-25 2023-03-03 内蒙古大学 Sequence prediction model training method and device and computer readable medium

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
A Tensor Based Stacked Fuzzy Networks for Efficient Data Regression;jie li et al.;《research square》;全文 *

Also Published As

Publication number Publication date
CN116416616A (en) 2023-07-11

Similar Documents

Publication Publication Date Title
Wahab et al. Transfer learning based deep CNN for segmentation and detection of mitoses in breast cancer histopathological images
CN106557778B (en) General object detection method and device, data processing device and terminal equipment
Nketia et al. Analysis of live cell images: Methods, tools and opportunities
Hilsenbeck et al. fastER: a user-friendly tool for ultrafast and robust cell segmentation in large-scale microscopy
Versari et al. Long-term tracking of budding yeast cells in brightfield microscopy: CellStar and the Evaluation Platform
Hallou et al. Deep learning for bioimage analysis in developmental biology
Sun et al. Deep learning‐based single‐cell optical image studies
Klibisz et al. Fast, simple calcium imaging segmentation with fully convolutional networks
CN106530010B (en) The collaborative filtering method and device of time of fusion factor
CN109299716A (en) Training method, image partition method, device, equipment and the medium of neural network
Shen et al. Automated tracking of gene expression in individual cells and cell compartments
Prangemeier et al. Yeast cell segmentation in microstructured environments with deep learning
CN110163250A (en) Image desensitization process system, method and device based on distributed scheduling
CN109948429A (en) Image analysis method, device, electronic equipment and computer-readable medium
Salem et al. Yeastnet: Deep-learning-enabled accurate segmentation of budding yeast cells in bright-field microscopy
Wajeed et al. Image Based Tumor Cells Identification Using Convolutional Neural Network and Auto Encoders.
CN112233102A (en) Method, device and equipment for identifying noise in image sample set and storage medium
Junaidi et al. Image classification for egg incubator using transfer learning of VGG16 and VGG19
CN116416616B (en) DC cell in-vitro culture screening method, device and computer readable medium
CN105608440B (en) Based on the micro- expression sequence signature abstracting method of face for minimizing error
Reich et al. Multi-stylegan: Towards image-based simulation of time-lapse live-cell microscopy
CN107194319B (en) Mitosis positioning and identifying method based on support vector machine sequencing
CN113284122A (en) Method and device for detecting roll paper packaging defects based on deep learning and storage medium
Li et al. ILEE: Algorithms and toolbox for unguided and accurate quantitative analysis of cytoskeletal images
Hopkins A simple generative model of trilobite segmentation and growth

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
CB02 Change of applicant information
CB02 Change of applicant information

Address after: 123/125, 1st Floor, Building 1, No. 538 Yongfengtun, Haidian District, Beijing, 100094

Applicant after: WATSON CLICK (BEIJING) BIOTECHNOLOGY Co.,Ltd.

Address before: 106, 1st Floor, Incubation Building, No. 7 Fengxian Middle Road, Haidian District, Beijing, 100094

Applicant before: WATSON CLICK (BEIJING) BIOTECHNOLOGY Co.,Ltd.

GR01 Patent grant
GR01 Patent grant