Cell density determination method, device, electronic device and storage medium
By extracting and classifying cell density characteristics using pre-trained automatic encoder and neural network classifiers, the problem of inefficient cell density calculation in the prior art is solved, and more efficient and accurate cell density determination is achieved.
Patent Information
- Application Number
- CN202110004116.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2021-01-04
- Publication Date
- 2024-11-15
- Estimated Expiration
- 2041-01-04
AI Technical Summary
In the prior art, the calculation efficiency is low, time-consuming and poor robustness when determining cell density using multi-layer neural network models.
The cell density characteristics are extracted using a pre-trained automatic encoder, and the cell density is determined using a neural network classifier, which distinguishes different density ranges through feature distribution, and improves computing efficiency and accuracy.
It realizes faster and more accurate cell density calculation, avoids the time-consuming and poor robustness problems of traditional methods, and improves the efficiency of image classification and density range determination.
Smart Images

Figure CN114723652B_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of image recognition technology, and in particular to a method, device, electronic device and storage medium for determining cell density. Background Art
[0002] Currently, the cell density of an image can be determined by training a neural network model and using the trained neural network model. However, in practice, it is found that a neural network model often has multiple layers of networks and the calculation takes a long time.
[0003] Therefore, how to improve the calculation efficiency of cell density is a technical problem that needs to be solved urgently. Summary of the invention
[0004] In view of the above, it is necessary to provide a method, device, electronic device and storage medium for determining cell density, which can improve the calculation efficiency of cell density.
[0005] The first aspect of the present application provides a method for determining cell density, the method comprising:
[0006] Acquire images of cells to be detected;
[0007] Extracting cell density features of the cell image to be detected using a pre-trained autoencoder;
[0008] Inputting the cell density feature into a pre-trained neural network classifier to obtain a target feature type;
[0009] Acquiring a cell density corresponding to the target feature type;
[0010] The cell density is output.
[0011] In a possible implementation, before acquiring the image of the cells to be detected, the method for determining the cell density further includes:
[0012] Obtaining a preset first training image set;
[0013] The preset neural network is trained using the first training image set to obtain a trained autoencoder.
[0014] In a possible implementation, the first training image set includes multiple groups of training images, the cell densities of multiple training images in the same group belong to the same cell density range, and the cell densities of training images in different groups belong to different cell density ranges.
[0015] In a possible implementation, after the preset neural network is trained using the first training image set to obtain a trained autoencoder, the method further includes:
[0016] Inputting the multiple sets of training images into the autoencoder to obtain cell density features corresponding to the multiple sets of training images;
[0017] Determining characteristic distributions of all the cell density characteristics in different cell density ranges according to the cell density characteristics corresponding to the multiple groups of training images and the cell density ranges corresponding to the multiple groups of training images;
[0018] Get the initial classifier;
[0019] The initial classifier is trained using the feature distribution to obtain a trained neural network classifier.
[0020] In a possible implementation, the neural network classifier includes a fully connected layer and a normalization layer.
[0021] A second aspect of the present application provides a cell density determination device, the cell density determination device comprising:
[0022] An acquisition module, used for acquiring an image of cells to be detected;
[0023] An extraction module, used for extracting cell density features of the cell image to be detected using a pre-trained autoencoder;
[0024] An input module, used for inputting the cell density feature into a pre-trained neural network classifier to obtain a target feature type;
[0025] The acquisition module is also used to acquire the cell density corresponding to the target feature type;
[0026] An output module is used to output the cell density.
[0027] A third aspect of the present application provides an electronic device, comprising a processor and a memory, wherein the processor is configured to implement the cell density determination method when executing a computer program stored in the memory.
[0028] A fourth aspect of the present application provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the cell density determination method is implemented.
[0029] According to the above technical scheme, in this application, the feature extraction method of the automatic encoder can be used to ensure that the cell density features generated by it are within a limited distribution range. Images of different densities of the same category have slightly different features, and in the same range, different density sizes can be represented by different distribution ranges, thereby distinguishing the density of the image. Then a neural network classifier is used to determine the category, and then determine the cell density corresponding to the category. It avoids the shortcomings of traditional classifiers that are time-consuming and poor in robustness, can more accurately classify images, and determine the cell density range of images, thereby improving the efficiency of obtaining cell density. BRIEF DESCRIPTION OF THE DRAWINGS
[0030] Figure 1 It is a flow chart of a preferred embodiment of a method for determining cell density disclosed in the present application.
[0031] Figure 2 It is a functional module diagram of a preferred embodiment of a cell density determination device disclosed in the present application.
[0032] Figure 3 It is a schematic diagram of the structure of an electronic device of a preferred embodiment of the present application for implementing the method for determining cell density. DETAILED DESCRIPTION
[0033] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.
[0034] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which this application belongs. The terms used herein in the specification of this application are only for the purpose of describing specific embodiments and are not intended to limit this application.
[0035] The cell density determination method of the embodiment of the present application is applied in an electronic device, and can also be applied in a hardware environment consisting of an electronic device and a server connected to the electronic device via a network, and is executed by the server and the electronic device together. The network includes but is not limited to: a wide area network, a metropolitan area network or a local area network.
[0036] Among them, a server can refer to a computer system that can provide services to other devices (such as electronic devices) in the network. If a personal computer can provide File Transfer Protocol (FTP) services to the outside world, it can also be called a server. In a narrow sense, a server refers specifically to certain high-performance computers that can provide services to the outside world through the network. Compared with ordinary personal computers, it has higher requirements in terms of stability, security, and performance. Therefore, it is different from ordinary personal computers in terms of hardware such as CPU, chipset, memory, disk system, network, etc.
[0037] The electronic device is a device that can automatically perform numerical calculations and / or information processing according to pre-set or stored instructions, and its hardware includes but is not limited to microprocessors, application-specific integrated circuits (ASICs), field programmable gate arrays (FPGAs), digital signal processors (DSPs), embedded devices, etc. The electronic device may also include network devices and / or user devices. Among them, the network device includes but is not limited to a single network device, a server group composed of multiple network devices, or a cloud composed of a large number of hosts or network devices based on cloud computing (Cloud Computing), wherein cloud computing is a type of distributed computing, a super virtual computer composed of a group of loosely coupled computer sets. The user device includes but is not limited to any electronic product that can interact with the user through a keyboard, mouse, remote control, touchpad or voice control device, such as a personal computer, tablet computer, smart phone, personal digital assistant PDA, etc.
[0038] See also Figure 1 , Figure 1 This is a flow chart of a preferred embodiment of determining cell density disclosed in the present application. According to different requirements, the order of the steps in the flow chart can be changed, and some steps can be omitted.
[0039] S11, obtaining an image of the cells to be detected.
[0040] The cell image to be detected includes cells to be detected (such as stem cells, red blood cells, etc.), other cells and some impurities.
[0041] As an optional implementation, before acquiring the image of the cells to be detected, the method for determining the cell density further includes:
[0042] Obtaining a preset first training image set;
[0043] The preset neural network is trained using the first training image set to obtain a trained autoencoder.
[0044] The first training image set includes multiple groups of training images, the cell densities of multiple training images in the same group belong to the same cell density range, and the cell densities of training images in different groups belong to different cell density ranges.
[0045] In this optional embodiment, the cell images of the first training image set are annotated with corresponding cell density, and the first training image set is used for training so that the autoencoder can learn features that better represent cell density, thereby obtaining a trained autoencoder.
[0046] As an optional implementation, after using the first training image set to train a preset neural network to obtain a trained autoencoder, the method further includes:
[0047] Inputting the multiple sets of training images into the autoencoder to obtain cell density features corresponding to the multiple sets of training images;
[0048] Determining characteristic distributions of all the cell density characteristics in different cell density ranges according to the cell density characteristics corresponding to the multiple groups of training images and the cell density ranges corresponding to the multiple groups of training images;
[0049] Get the initial classifier;
[0050] The initial classifier is trained using the feature distribution to obtain a trained neural network classifier.
[0051] In this optional embodiment, because the cell densities of the training images of different groups belong to different cell density ranges, the cell densities of the multiple training images of the same group all belong to the same cell density range. The cell density features corresponding to the multiple groups of training images correspond to different cell density ranges, and the feature distribution of all the cell density features in different cell density ranges can be determined. After obtaining the feature distribution of all the cell density features in different cell density ranges, the initial classifier can be trained using the feature distribution so that the classifier can classify different features. Different types correspond to different cell density ranges.
[0052] S12. Using a pre-trained autoencoder to extract cell density features of the cell image to be detected.
[0053] Wherein, the cell density feature is characteristic information describing the cell density.
[0054] Among them, the autoencoder (AE) can be an unsupervised neural network model that can learn the implicit features of the input data, which is called coding, and the learned new features can be used to reconstruct the original input data, which is called decoding. The autoencoder can be used for feature dimensionality reduction and can also extract more effective new features. In addition to feature dimensionality reduction, the new features learned by the autoencoder can be fed into a supervised learning model, so the autoencoder can play the role of a feature extractor, and the features extracted by the autoencoder are learned and can efficiently represent a certain type of features of the cell image to be detected.
[0055] S13, inputting the cell density feature into a pre-trained neural network classifier to obtain a target feature type.
[0056] Wherein, the neural network classifier includes a fully connected layer and a normalization layer.
[0057] Among them, the fully connected layers (FC) are used to map feature information to the sample label space, that is, to integrate the feature information into a numerical value. The normalization layer (Softmax) is used, for example, there are currently one hundred categories of image classification, then the output of the normalization layer is a one hundred-dimensional vector. The first value in the vector is the probability value that the current image belongs to the first category, the second value in the vector is the probability value that the current image belongs to the second category, and so on. The final result is a one hundred-dimensional vector, and the sum of these one hundred-dimensional vectors is 1.
[0058] The target feature type may be a preset character, such as different letters, character strings, number combinations, etc., which may be used to uniquely identify a type.
[0059] S14. Obtaining a cell density corresponding to the target feature type.
[0060] Among them, different types correspond to different cell density ranges.
[0061] S15. Output the cell density.
[0062] The cell density may refer to a density range, such as 10% to 20%, 40% to 50%, or 70% to 80%.
[0063] exist Figure 1In the described method flow, the feature extraction method of the autoencoder can be used to ensure that the cell density features generated by it are within a limited distribution range. Images of the same category with different densities have slightly different features, and in the same range, different density sizes can be represented by different distribution ranges, thereby distinguishing the density of the image. Then a neural network classifier is used to determine the category, and then determine the cell density corresponding to the category. It avoids the shortcomings of traditional classifiers that are time-consuming and poor in robustness, can more accurately classify images, and determine the cell density range of images, thereby improving the efficiency of obtaining cell density.
[0064] Figure 2 It is a functional module diagram of a preferred embodiment of a cell density determination device disclosed in the present application.
[0065] See also Figure 2 The cell density determination device 20 may be operated in an electronic device. The cell density determination device 20 may include a plurality of functional modules composed of program code segments. The program code of each program segment in the cell density determination device 20 may be stored in a memory and executed by at least one processor to perform Figure 1 Some or all of the steps in the described method for determining cell density.
[0066] In this embodiment, the cell density determination device 20 can be divided into multiple functional modules according to the functions it performs. The functional modules may include: an acquisition module 201, an extraction module 202, an input module 203 and an output module 204. The module referred to in this application refers to a series of computer program segments that can be executed by at least one processor and can complete fixed functions, which are stored in a memory.
[0067] The acquisition module 201 is used to acquire the image of the cell to be detected.
[0068] The cell image to be detected includes cells to be detected (such as stem cells, red blood cells, etc.), other cells and some impurities.
[0069] The extraction module 202 is used to extract the cell density features of the cell image to be detected using a pre-trained autoencoder.
[0070] Wherein, the cell density feature is characteristic information describing the cell density.
[0071] Among them, the autoencoder (AE) can be an unsupervised neural network model that can learn the implicit features of the input data, which is called coding, and the learned new features can be used to reconstruct the original input data, which is called decoding. The autoencoder can be used for feature dimensionality reduction and can also extract more effective new features. In addition to feature dimensionality reduction, the new features learned by the autoencoder can be fed into a supervised learning model, so the autoencoder can play the role of a feature extractor, and the features extracted by the autoencoder are learned and can efficiently represent a certain type of features of the cell image to be detected.
[0072] The input module 203 is used to input the cell density feature into a pre-trained neural network classifier to obtain a target feature type.
[0073] Wherein, the neural network classifier includes a fully connected layer and a normalization layer.
[0074] Among them, the fully connected layers (FC) are used to map feature information to the sample label space, that is, to integrate the feature information into a numerical value. The normalization layer (Softmax) is used, for example, there are currently one hundred categories of image classification, then the output of the normalization layer is a one hundred-dimensional vector. The first value in the vector is the probability value that the current image belongs to the first category, the second value in the vector is the probability value that the current image belongs to the second category, and so on. The final result is a one hundred-dimensional vector, and the sum of these one hundred-dimensional vectors is 1.
[0075] The target feature type may be a preset character, such as different letters, character strings, number combinations, etc., which may be used to uniquely identify a type.
[0076] The acquisition module 201 is further used to acquire the cell density corresponding to the target feature type.
[0077] Among them, different types correspond to different cell density ranges.
[0078] The output module 204 is used to output the cell density.
[0079] The cell density may refer to a density range, such as 10% to 20%, 40% to 50%, or 70% to 80%.
[0080] As an optional implementation, the acquisition module is further used to acquire a preset first training image set before acquiring the image of the cell to be detected;
[0081] The cell density determination device 20 further comprises:
[0082] A training module is used to train a preset neural network using the first training image set to obtain a trained autoencoder.
[0083] The first training image set includes multiple groups of training images, the cell densities of multiple training images in the same group belong to the same cell density range, and the cell densities of training images in different groups belong to different cell density ranges.
[0084] In this optional embodiment, the cell images of the first training image set are annotated with corresponding cell density, and the first training image set is used for training so that the autoencoder can learn features that better represent cell density, thereby obtaining a trained autoencoder.
[0085] As an optional implementation, the input module 203 is also used for the training module to train a preset neural network using the first training image set, and after obtaining a trained autoencoder, the multiple sets of training images are input into the autoencoder to obtain cell density features corresponding to the multiple sets of training images;
[0086] The cell density determination device 20 further comprises:
[0087] A determination module, configured to determine characteristic distributions of all the cell density characteristics in different cell density ranges according to the cell density characteristics corresponding to the multiple groups of training images and the cell density ranges corresponding to the multiple groups of training images;
[0088] The acquisition module 201 is also used to acquire an initial classifier;
[0089] The training module is used to train the initial classifier using the feature distribution to obtain a trained neural network classifier.
[0090] In this optional embodiment, because the cell densities of the training images of different groups belong to different cell density ranges, the cell densities of the multiple training images of the same group all belong to the same cell density range. The cell density features corresponding to the multiple groups of training images correspond to different cell density ranges, and the feature distribution of all the cell density features in different cell density ranges can be determined. After obtaining the feature distribution of all the cell density features in different cell density ranges, the initial classifier can be trained using the feature distribution so that the classifier can classify different features. Different types correspond to different cell density ranges.
[0091] exist Figure 2In the described cell density determination device 20, the feature extraction method of the automatic encoder can be used to ensure that the cell density features generated by it are within a limited distribution range. Images of the same category with different densities have slightly different features, and in the same range, different density sizes can be represented by different distribution ranges, thereby distinguishing the density of the image. Then, a neural network classifier is used to determine the category, and then the cell density corresponding to the category is determined. The shortcomings of the traditional classifier, which is time-consuming and poor in robustness, are avoided, and the image can be classified more accurately, and the cell density range of the image can be determined, thereby improving the efficiency of obtaining the cell density.
[0092] like Figure 3 As shown, Figure 3 Schematic diagram of the structure of an electronic device for realizing a preferred embodiment of the method for determining cell density of the present application. The electronic device 3 comprises a memory 31, at least one processor 32, a computer program 33 stored in the memory 31 and executable on the at least one processor 32, and at least one communication bus 34.
[0093] Those skilled in the art will understand that Figure 3 The schematic diagram shown is merely an example of the electronic device 3 and does not constitute a limitation on the electronic device 3. It may include more or fewer components than shown in the figure, or a combination of certain components, or different components. For example, the electronic device 3 may also include input and output devices, network access devices, etc.
[0094] The electronic device 3 also includes but is not limited to any electronic product that can interact with the user through a keyboard, mouse, remote control, touch pad or voice control device, such as a personal computer, tablet computer, smart phone, personal digital assistant (PDA), game console, interactive network television (IPTV), smart wearable device, etc. The network where the electronic device 3 is located includes but is not limited to the Internet, wide area network, metropolitan area network, local area network, virtual private network (VPN), etc.
[0095] The at least one processor 32 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), or other programmable logic devices, transistor logic devices, discrete hardware components, etc. The processor 32 may be a microprocessor or any conventional processor, etc. The processor 32 is the control center of the electronic device 3, and uses various interfaces and lines to connect various parts of the entire electronic device 3.
[0096] The memory 31 can be used to store the computer program 33 and / or modules / units. The processor 32 implements various functions of the electronic device 3 by running or executing the computer program and / or modules / units stored in the memory 31 and calling the data stored in the memory 31. The memory 31 can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, an application required for at least one function (such as a sound playback function, an image playback function, etc.), etc.; the data storage area can store data created according to the use of the electronic device 3, etc. In addition, the memory 31 can include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (SmartMedia Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), at least one disk storage device, a flash memory device, etc.
[0097] Combination Figure 1 The memory 31 in the electronic device 3 stores a plurality of instructions to implement a method for determining a cell density, and the processor 32 can execute the plurality of instructions to implement:
[0098] Acquire images of cells to be detected;
[0099] Extracting cell density features of the cell image to be detected using a pre-trained autoencoder;
[0100] Inputting the cell density feature into a pre-trained neural network classifier to obtain a target feature type;
[0101] Acquiring a cell density corresponding to the target feature type;
[0102] The cell density is output.
[0103] Specifically, the specific implementation method of the processor 32 for the above instructions can refer to Figure 1 The description of the relevant steps in the corresponding embodiments will not be repeated here.
[0104] exist Figure 3 In the described electronic device 3, the feature extraction method of the automatic encoder can be used to ensure that the cell density features generated by it are within a limited distribution range. Images of the same category with different densities have slightly different features, and in the same range, different density sizes can be represented by different distribution ranges, thereby distinguishing the density of the image. Then, a neural network classifier is used to determine the category, and then the cell density corresponding to the category is determined. The shortcomings of the traditional classifier, which is time-consuming and poor in robustness, are avoided, and the image can be classified more accurately, and the cell density range of the image can be determined, thereby improving the efficiency of obtaining the cell density.
[0105] If the module / unit integrated in the electronic device 3 is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present application implements all or part of the process in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. Among them, the computer program code can be in the form of source code, object code, executable file or some intermediate form. The computer-readable medium may include: any entity or device that can carry the computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory).
[0106] In the several embodiments provided in this application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only illustrative, for example, the division of the modules is only a logical function division, and there may be other division methods in actual implementation.
[0107] The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
[0108] In addition, each functional module in each embodiment of the present application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The above integrated unit can be implemented in the form of hardware or in the form of hardware plus software functional modules.
[0109] It is obvious to those skilled in the art that the present application is not limited to the details of the above exemplary embodiments, and that the present application can be implemented in other specific forms without departing from the spirit or basic features of the present application. Therefore, from any point of view, the embodiments should be regarded as exemplary and non-restrictive, and the scope of the present application is limited by the attached claims rather than the above description, so it is intended to include all changes that fall within the meaning and scope of the equivalent elements of the claims in the present application. Any attached figure mark in the claims should not be regarded as limiting the claims involved. In addition, it is obvious that the word "comprising" does not exclude other units or steps, and the singular does not exclude the plural. The multiple units or devices stated in the present application can also be implemented by one unit or device through software or hardware. The words first, second, etc. are used to indicate names, and do not indicate any particular order.
[0110] Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present application and are not intended to limit it. Although the present application has been described in detail with reference to the preferred embodiments, a person of ordinary skill in the art should understand that the technical solution of the present application may be modified or replaced by equivalents without departing from the spirit and scope of the technical solution of the present application.
Claims
1. A method for determining cell density, characterized in that: The cell density determination method comprises: Acquire an image of the cell to be detected; Extracting cell density features of the cell image to be detected using a pre-trained autoencoder, wherein the cell density features are characteristic information describing cell density; Inputting the cell density feature into a pre-trained neural network classifier to obtain a target feature type, wherein the target feature type is a preset character used to uniquely identify a type; Acquiring a cell density corresponding to the target feature type; The cell density is output.
2. The method for determining cell density according to claim 1, characterized in that: Before acquiring the image of the cells to be detected, the method for determining the cell density further includes: Obtaining a preset first training image set; The preset neural network is trained using the first training image set to obtain a trained autoencoder.
3. The method for determining cell density according to claim 2, characterized in that: The first training image set includes multiple groups of training images, the cell densities of multiple training images in the same group belong to the same cell density range, and the cell densities of training images in different groups belong to different cell density ranges.
4. The method for determining cell density according to claim 3, after training a preset neural network using the first training image set to obtain a trained autoencoder, and before acquiring the image of the cell to be detected, the method for determining cell density further comprises: Inputting the multiple sets of training images into the autoencoder to obtain cell density features corresponding to the multiple sets of training images; Determining characteristic distributions of all the cell density characteristics in different cell density ranges according to the cell density characteristics corresponding to the multiple groups of training images and the cell density ranges corresponding to the multiple groups of training images; Get the initial classifier; The initial classifier is trained using the feature distribution to obtain a trained neural network classifier.
5. The method for determining cell density according to any one of claims 1 to 4, characterized in that: The neural network classifier includes a fully connected layer and a normalization layer.
6. A cell density determination device, characterized in that: The cell density determination device comprises: An acquisition module, used for acquiring an image of cells to be detected; An extraction module, used to extract cell density features of the cell image to be detected using a pre-trained autoencoder, wherein the cell density features are characteristic information describing cell density; An input module, used for inputting the cell density feature into a pre-trained neural network classifier to obtain a target feature type, wherein the target feature type is a preset character used to uniquely identify a type; The acquisition module is further used to acquire the cell density corresponding to the target feature type; An output module is used to output the cell density.
7. The cell density determination device according to claim 6, characterized in that: The acquisition module is further used to acquire a preset first training image set before acquiring the image of the cell to be detected; The cell density determination device also includes: A training module is used to train a preset neural network using the first training image set to obtain a trained autoencoder.
8. The cell density determination device according to claim 7, characterized in that: The input module is further used for training the preset neural network using the first training image set in the training module to obtain the trained autoencoder, and before the acquisition module acquires the cell image to be detected, inputting multiple sets of training images into the autoencoder to obtain the cell density features corresponding to the multiple sets of training images; The cell density determination device also includes: A determination module, configured to determine characteristic distributions of all the cell density characteristics in different cell density ranges according to the cell density characteristics corresponding to the multiple groups of training images and the cell density ranges corresponding to the multiple groups of training images; The acquisition module is also used to acquire an initial classifier; The training module is also used to train the initial classifier using the feature distribution to obtain a trained neural network classifier.
9. An electronic device, characterized in that: The electronic device comprises a processor and a memory, wherein the processor is configured to execute a computer program stored in the memory to implement the cell density determination method according to any one of claims 1 to 5.
10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores at least one instruction, and when the at least one instruction is executed by a processor, the method for determining cell density according to any one of claims 1 to 5 is implemented.
