Cell density classification method and device, electronic device and storage medium

Abstract

A method for classifying cell density, the method comprising: inputting a biological cell image to be tested into a trained convolutional neural network model until the reconstructed biological cell image obtained matches the biological cell image to be tested, the trained convolutional neural network model corresponding to the density range in which the cell density of the biological cell image is located; determining that the cell density of the biological cell image to be tested is the density range corresponding to the trained convolutional neural network model when it matches the reconstructed biological cell image. The present application also provides a cell density classification device, an electronic device and a storage medium, which can improve the speed of cell counting.

Description

Technical Field

[0001] The present invention relates to the technical field of computer learning, and particularly to a cell density classification method and device, an electronic device, and a computer-readable storage medium. Background Art

[0002] Currently, when studying biological cells, such as biological stem cells, it is often not necessary to know the exact number of stem cells in the image, but only the density range of the stem cells in the image. However, the existing biological cell counting method is to calculate the number of cells in the image and calculate the density range of the stem cells in the image according to the number of the cells. Thus, it will be time-consuming to count the cells. Summary of the Invention

[0003] In view of this, it is necessary to provide a cell density classification method and device, an electronic device, and a computer-readable storage medium, which can improve the speed of cell counting.

[0004] The first aspect of the present application provides a cell density classification method, and the method includes:

[0005] Input a to-be-tested biological cell image into a trained convolutional neural network model until the reconstructed biological cell image obtained matches the to-be-tested biological cell image, where the trained convolutional neural network model corresponds to the density range in which the cell density of the biological cell image is located;

[0006] Determine that the cell density of the to-be-tested biological cell image is the density range corresponding to the trained convolutional neural network model when the reconstructed biological cell image matches the to-be-tested biological cell image.

[0007] Preferably, before inputting the to-be-tested biological cell image into the trained convolutional neural network model until the reconstructed biological cell image obtained matches the to-be-tested biological cell image, the method further includes:

[0008] Obtain a plurality of training biological cell images divided into a plurality of different density ranges;

[0009] Input the plurality of training biological cell images in each density range into different convolutional neural network models to obtain a plurality of trained convolutional neural network models.

[0010] Preferably, the density range formed by the plurality of different density ranges is 0-100%.

[0011] Preferably, the obtaining a plurality of training biological cell images divided into a plurality of different density ranges includes:

[0012] Obtain a plurality of training biological cell images;

[0013] Divide the multiple training biological cell images into multiple training biological cell images with multiple different density ranges.

[0014] Preferably, the step of inputting the biological cell image to be tested into the trained convolutional neural network model until the reconstructed biological cell image obtained matches the biological cell image to be tested includes:

[0015] Input the biological cell image to be tested into the trained convolutional neural network model to obtain a reconstructed biological cell image;

[0016] Determine whether the reconstructed biological cell image is similar to the biological cell image to be tested;

[0017] If the reconstructed biological cell image is similar to the biological cell image to be tested, determine that the reconstructed biological cell image matches the biological cell image to be tested.

[0018] Preferably, the method further includes:

[0019] If the reconstructed biological cell image is not similar to the biological cell image to be tested, input the biological cell image to be tested into the next trained convolutional neural network model to obtain a reconstructed biological cell image;

[0020] Determine whether the reconstructed biological cell image is similar to the biological cell image to be tested;

[0021] If the reconstructed biological cell image is not similar to the biological cell image to be tested, continue to obtain the reconstructed biological cell image and make the determination until the reconstructed biological cell image obtained matches the biological cell image to be tested.

[0022] Preferably, the cell density range of the reconstructed biological cell image is the same as the density range in which the cell density of the biological cell image corresponding to the trained convolutional neural network model is located.

[0023] The second aspect of the present application provides a cell density classification device, the device includes:

[0024] An input module, configured to input a biological cell image to be tested into a trained convolutional neural network model until the reconstructed biological cell image obtained matches the biological cell image to be tested, and the trained convolutional neural network model corresponds to the density range in which the cell density of the biological cell image is located;

[0025] A determination module, configured to determine that the cell density of the biological cell image to be tested is the density range corresponding to the trained convolutional neural network model when it matches the reconstructed biological cell image.

[0026] A third aspect of the present application provides an electronic device, which includes a processor and a memory. When the processor executes at least one instruction stored in the memory, the cell density classification method described in any one of the above is implemented.

[0027] A fourth aspect of the present application provides a computer-readable storage medium, which stores at least one instruction. When the at least one instruction is executed by a processor, the cell density classification method described in any one of the above is implemented.

[0028] This case uses a trained convolutional neural network model to determine the cell density of a biological cell image to be tested, and the cell density range can be determined without calculating the number of the cells, improving the speed of cell counting. Description of the Drawings

[0029] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly introduced below. Obviously, the drawings in the following description are some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0030] Figure 1 It is a block diagram of the cell density classification device provided in the first embodiment of the present invention.

[0031] Figure 2 It is a block diagram of the cell density classification device provided in the second embodiment of the present invention.

[0032] Figure 3 It is a flowchart of the cell density classification method provided in the third embodiment of the present invention.

[0033] Figure 4 is Figure 3 It is a flowchart of an embodiment in which a biological cell image to be tested is input into a trained convolutional neural network model until the reconstructed biological cell image obtained matches the biological cell image to be tested.

[0034] Figure 5 is Figure 3 It is a schematic diagram of another embodiment in which a biological cell image to be tested is input into a trained convolutional neural network model until the reconstructed biological cell image obtained matches the biological cell image to be tested.

[0035] Figure 6 It is a flowchart of the cell density classification method provided in the fourth embodiment of the present invention.

[0036] Figure 7It is a schematic diagram of obtaining multiple trained convolutional neural network models by inputting multiple training biological cell images in each density range into different convolutional neural network models.

[0037] Figure 8 It is a block diagram of the electronic device provided in Embodiment 5 of the present invention.

[0038] The following specific embodiments will further illustrate the present invention in conjunction with the above-mentioned drawings.

[0039] Main element symbol description

[0040] Cell density classification devices 10, 20

[0041] Input modules 101, 203

[0042] Determination modules 102, 204

[0043] Obtaining module 201

[0044] Training module 202

[0045] Electronic device 8

[0046] Memory 81

[0047] Processor 82

[0048] Computer program 83

[0049] The following specific embodiments will further illustrate the present invention in conjunction with the above-mentioned drawings. Specific embodiments

[0050] In order to more clearly understand the above-mentioned objects, features and advantages of the present invention, the present invention will be described in detail below with reference to the drawings and specific embodiments. It should be noted that, without conflict, the embodiments of the present application and the features in the embodiments can be combined with each other.

[0051] Many specific details are set forth in the following description in order to provide a thorough understanding of the present invention. The described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0052] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those of ordinary skill in the art belonging to the technical field of the present invention. The terms used in the description of the present invention herein are only for the purpose of describing specific embodiments and are not intended to limit the present invention.

[0053] Figure 1It is a block diagram of the cell density classification device provided in the first embodiment of the present invention. The cell density classification device 10 is applied to an electronic device. The electronic device can be a smart phone, a desktop computer, a tablet computer, etc. The cell density classification device 10 includes an input module 101 and a determination module 102. The input module 101 is used to input the biological cell image to be tested into the trained convolutional neural network model until the reconstructed biological cell image obtained matches the biological cell image to be tested. The trained convolutional neural network model corresponds to the density range in which the cell density of the biological cell image is located. The determination module 102 is used to determine that the cell density of the biological cell image to be tested is the density range corresponding to the trained convolutional neural network model when it matches the reconstructed biological cell image.

[0054] Figure 2 It is a block diagram of the cell density classification device provided in the second embodiment of the present invention. The cell density classification device 20 is applied to an electronic device. The electronic device can be a smart phone, a desktop computer, a tablet computer, etc. The cell density classification device 20 includes an acquisition module 201, a training module 202, an input module 203 and a determination module 204. The acquisition module 201 is used to acquire a plurality of training biological cell images divided into a plurality of different density ranges. The training module 202 is used to input the plurality of training biological cell images in each density range into different convolutional neural network models to obtain a plurality of trained convolutional neural network models. The input module 203 is used to input the biological cell image to be tested into the trained convolutional neural network model until the reconstructed biological cell image obtained matches the biological cell image to be tested. The trained convolutional neural network model corresponds to the density range in which the cell density of the biological cell image is located. The determination module 204 is used to determine that the cell density of the biological cell image to be tested is the density range corresponding to the trained convolutional neural network model when it matches the reconstructed biological cell image.

[0055] The specific functions of modules 101-102 and modules 201-204 will be described in detail below in conjunction with the flowchart of a cell density classification method.

[0056] Figure 3 It is a flowchart of the cell density classification method provided in the third embodiment of the present invention. The cell density classification method may include the following steps:

[0057] S31: Input the biological cell image to be tested into the trained convolutional neural network model until the reconstructed biological cell image obtained matches the biological cell image to be tested. The trained convolutional neural network model corresponds to the density range in which the cell density of the biological cell image is located.

[0058] The biological cell image can be, for example, a biological stem cell image. The biological stem cell image includes stem cells and other substances. The other substances can be impurities or other cells. The cell density range of the reconstructed biological cell image is the same as the density range in which the cell density of the biological cell image corresponding to the trained convolutional neural network model is located.

[0059] Please refer to Figure 4 , which is a flowchart of an embodiment for inputting the biological cell image to be tested into the trained convolutional neural network model until the reconstructed biological cell image obtained matches the biological cell image to be tested. The flowchart may include the following steps:

[0060] S41: Input the biological cell image to be tested into the trained convolutional neural network model to obtain a reconstructed biological cell image.

[0061] S42: Determine whether the reconstructed biological cell image is similar to the biological cell image to be tested.

[0062] S43: If the reconstructed biological cell image is similar to the biological cell image to be tested, determine that the reconstructed biological cell image matches the biological cell image to be tested.

[0063] S44: If the reconstructed biological cell image is not similar to the biological cell image to be tested, input the biological cell image to be tested into the next trained convolutional neural network model to obtain a reconstructed biological cell image.

[0064] S45: Determine whether the reconstructed biological cell image is similar to the biological cell image to be tested.

[0065] S46: If the reconstructed biological cell image is not similar to the biological cell image to be tested, continue to obtain the reconstructed biological cell image and make the determination until the reconstructed biological cell image obtained matches the biological cell image to be tested.

[0066] For example, input the biological cell image 1 to be tested into the trained convolutional neural network model 1 to obtain the reconstructed biological cell image 1, determine whether the reconstructed biological cell image 1 is similar to the biological cell image 1 to be tested, and determine that the reconstructed biological cell image 1 is not similar to the biological cell image 1 to be tested. At this time, input the biological cell image 1 to be tested into the trained convolutional neural network model 2 to obtain the reconstructed biological cell image 2, determine whether the reconstructed biological cell image 2 is similar to the biological cell image 1 to be tested, and determine that the reconstructed biological cell image 2 is similar to the biological cell image 1 to be tested. At this time, determine that the reconstructed biological cell image 2 matches the biological cell image 1 to be tested.

[0067] Please refer toFigure 5 , which is a schematic diagram of another embodiment for inputting a biological cell image to be tested into a trained convolutional neural network model until the reconstructed biological cell image obtained matches the biological cell image to be tested. In this other embodiment, the biological cell image to be tested is input into all the trained convolutional neural network models until the reconstructed biological cell image obtained matches the biological cell image to be tested. In Figure 5 , the biological cell image 3 to be tested is input into the trained convolutional neural network model 1, the trained convolutional neural network model 2, the trained convolutional neural network model 3, and the trained convolutional neural network model 4 respectively to obtain the reconstructed biological cell image 1, the reconstructed biological cell image 2, the reconstructed biological cell image 3, and the reconstructed biological cell image 4, among which the reconstructed biological cell image 3 obtained matches the biological cell image 3 to be tested.

[0068] S32: Determine the density range corresponding to the trained convolutional neural network model when the cell density of the biological cell image to be tested matches the reconstructed biological cell image.

[0069] The determination that the density range corresponding to the trained convolutional neural network model when the cell density of the biological cell image to be tested matches the reconstructed biological cell image can be, for example, in Figure 5 , the reconstructed biological cell image 3 obtained by the trained convolutional neural network model 3 matches the biological cell image 3 to be tested, and determine the cell density of the biological cell image 3 to be tested as the density range of 40% - 60% corresponding to the trained convolutional neural network model 3.

[0070] In Embodiment 3, the biological cell image to be tested is input into the trained convolutional neural network model until the reconstructed biological cell image obtained matches the biological cell image to be tested, and determine the cell density of the biological cell image to be tested as the density range corresponding to the trained convolutional neural network model when the reconstructed biological cell image matches it. Thus, in this case, the trained convolutional neural network model is used to determine the cell density of the biological cell image to be tested, and the cell density range can be determined without calculating the number of the cells, improving the speed of cell counting.

[0071] Figure 6 is a flowchart of the cell density classification method provided by Embodiment 4 of the present invention. The cell density classification method may include the following steps:

[0072] S61: Obtain multiple training biological cell images that are divided into multiple different density ranges.

[0073] The density ranges formed by multiple different density ranges are 0 - 100%. The sizes of the density ranges may be exactly the same or not exactly the same.

[0074] The obtaining of multiple training biological cell images divided into multiple different density ranges includes:

[0075] Obtaining multiple training biological cell images, and dividing the multiple training biological cell images into multiple training biological cell images with multiple different density ranges.

[0076] The dividing of the multiple training biological cell images into multiple training biological cell images with multiple different density ranges may be to divide the multiple training biological cell images into multiple training biological cell images with multiple different density ranges according to a preset rule or randomly.

[0077] S62: Inputting the multiple training biological cell images of each density range into different convolutional neural network models to obtain multiple trained convolutional neural network models.

[0078] The inputting of the multiple training biological cell images of each density range into different convolutional neural network models to obtain multiple trained convolutional neural network models may be, for example, as Figure 7 shown, inputting the multiple training biological cell images with a density range of 0 - 40% into convolutional neural network model 1, inputting the multiple training biological cell images with a density range of 40% - 60% into convolutional neural network model 2, inputting the multiple training biological cell images with a density range of 60% - 80% into convolutional neural network model 3, and inputting the multiple training biological cell images with a density range of 80% - 100% into convolutional neural network model 4, to obtain trained convolutional neural network model 1, trained convolutional neural network model 2, trained convolutional neural network model 3, and trained convolutional neural network model 4.

[0079] S63: Inputting the biological cell image to be tested into the trained convolutional neural network model until the reconstructed biological cell image obtained matches the biological cell image to be tested, where the trained convolutional neural network model corresponds to the density range in which the cell density of the biological cell image is located.

[0080] Step S63 in the fourth embodiment is similar to step S31 in the third embodiment. The specific description of step S63 in the fourth embodiment can refer to step S31 in the third embodiment, and will not be elaborated here.

[0081] S64: Determining that the cell density of the biological cell image to be tested is the density range corresponding to the trained convolutional neural network model when it matches the reconstructed biological cell image.

[0082] Step S64 in the fourth embodiment is similar to step S32 in the third embodiment. The specific description of step S63 in the fourth embodiment can refer to step S32 in the third embodiment, and will not be elaborated here.

[0083] Example 4: Obtain multiple training biological cell images that are divided into multiple different density ranges, input the multiple training biological cell images in each density range into different convolutional neural network models to obtain multiple trained convolutional neural network models, input the biological cell image to be tested into the trained convolutional neural network model until the reconstructed biological cell image obtained matches the biological cell image to be tested, and determine that the cell density of the biological cell image to be tested is the density range corresponding to the trained convolutional neural network model when it matches the reconstructed biological cell image. Thus, in this case, by first training the convolutional neural network model and then determining the cell density of the biological cell image to be tested according to the trained convolutional neural network model, the cell density range can be determined without calculating the number of the cells, improving the speed of cell counting.

[0084] Figure 8 It is a block diagram of the electronic device provided in Embodiment 3 of the present invention. The electronic device 8 includes: a memory 81, at least one processor 82, and a computer program 83 stored in the memory 81 and executable on the at least one processor 82. When the at least one processor 82 executes the computer program 83, the steps in the above method embodiments are implemented. Alternatively, when the at least one processor 82 executes the computer program 83, the functions of each module in the above device embodiments are implemented.

[0085] Exemplarily, the computer program 83 can be divided into one or more modules / units. The one or more modules / units are stored in the memory 81 and executed by the at least one processor 82 to complete the present invention. The one or more modules / units can be a series of computer program instruction segments capable of performing specific functions, and these instruction segments are used to describe the execution process of the computer program 83 in the electronic device 8. For example, the computer program 83 can be divided into Figure 1 the modules shown, and for the specific functions of each module, refer to Embodiment 1.

[0086] The electronic device 8 can be any kind of electronic product. For example, a personal computer, a tablet computer, a smart phone, a personal digital assistant (PDA), etc. Those skilled in the art can understand that the Figure 8 illustration is only an example of the electronic device 8, and does not constitute a limitation on the electronic device 8. It may include more or fewer components than shown in the figure, or combine certain components, or different components. For example, the electronic device 8 may further include a bus, etc.

[0087] The at least one processor 82 may be a Central Processing Unit (CPU), or may also be other general-purpose processors, Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field-Programmable Gate Arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The processor 82 may be a microprocessor or the processor 82 may also be any conventional processor, etc. The processor 82 is the control center of the electronic device 8, and connects various parts of the entire electronic device 8 through various interfaces and circuits.

[0088] The memory 81 can be used to store the computer program 83 and / or modules / units. The processor 82 realizes various functions of the electronic device 8 by running or executing the computer-readable instructions and / or modules / units stored in the memory 81, and by calling the data stored in the memory 81. The memory 81 may mainly include a program storage area and a data storage area. Among them, the program storage area can store an operating system, application programs 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 8 (such as audio data, etc.). In addition, the memory 81 may include a non-volatile computer-readable memory, such as a hard disk, a memory, a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) card, a Flash Card, at least one disk storage device, a flash memory device, or other non-volatile solid-state storage devices.

[0089] If the modules / units integrated in the electronic device 8 are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on such an understanding, to implement all or part of the processes in the above-described embodiment methods of the present invention, it can also be completed by instructing relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by a processor, the steps of the above-described various method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in the form of source code, object code, executable file, or some intermediate form, etc. The computer-readable medium can include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disc, computer memory, read-only memory (ROM, Read-Only Memory), etc.

[0090] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit them. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical solutions of the present invention can be modified or equivalently replaced without departing from the spirit scope of the technical solutions of the present invention.

Claims

1. A method for classifying cell density, characterized in that, The method includes: Inputting the biological cell image to be tested into a trained convolutional neural network model until the reconstructed biological cell image obtained matches the biological cell image to be tested. The trained convolutional neural network model corresponds to the density range in which the cell density of the biological cell image is located. Different trained convolutional neural network models are obtained by training with multiple training biological cell images in different density ranges, and different trained convolutional neural network models correspond to the density ranges in which the cell densities of different biological cell images are located. Determining that the cell density of the biological cell image to be tested is the density range corresponding to the trained convolutional neural network model that matches the reconstructed biological cell image among the multiple trained convolutional neural network models.

2. The cell density classification method according to claim 1, wherein Before inputting the biological cell image to be tested into the trained convolutional neural network model until the reconstructed biological cell image obtained matches the biological cell image to be tested, the method further includes: Obtaining multiple training biological cell images divided into multiple different density ranges. Inputting the multiple training biological cell images in each density range into different convolutional neural network models to obtain multiple trained convolutional neural network models.

3. The cell density classification method according to claim 2, characterized in that: The density ranges formed by the multiple different density ranges are from 0 to 100%.

4. The cell density classification method according to claim 2, characterized in that, The obtaining of multiple training biological cell images divided into multiple different density ranges includes: Obtaining multiple training biological cell images. Dividing the multiple training biological cell images into multiple training biological cell images in multiple different density ranges.

5. The cell density classification method according to claim 1, wherein The inputting of the biological cell image to be tested into the trained convolutional neural network model until the reconstructed biological cell image obtained matches the biological cell image to be tested includes: Inputting the biological cell image to be tested into the trained convolutional neural network model to obtain a reconstructed biological cell image. Judging whether the reconstructed biological cell image is similar to the biological cell image to be tested. If the reconstructed biological cell image is similar to the biological cell image to be tested, determining that the reconstructed biological cell image matches the biological cell image to be tested.

6. The cell density classification method according to claim 5, wherein The method further includes: If the reconstructed biological cell image is not similar to the biological cell image to be tested, inputting the biological cell image to be tested into the next trained convolutional neural network model to obtain a reconstructed biological cell image. Judging whether the reconstructed biological cell image is similar to the biological cell image to be tested. If the reconstructed biological cell image is not similar to the biological cell image to be tested, continuing to obtain the reconstructed biological cell image and make the judgment until the reconstructed biological cell image obtained matches the biological cell image to be tested.

7. The cell density classification method according to claim 1, wherein: The cell density range of the reconstructed biological cell image is the same as the density range in which the cell density of the biological cell image corresponding to the trained convolutional neural network model is located.

8. A cell density classification device, characterized in that, The device includes: An input module, configured to input a biological cell image to be tested into a trained convolutional neural network model until the reconstructed biological cell image obtained is matched with the biological cell image to be tested. The trained convolutional neural network model corresponds to the density range in which the cell density of the biological cell image is located. Different trained convolutional neural network models are trained by a plurality of training biological cell images in different density ranges, and different trained convolutional neural network models correspond to the density ranges in which the cell densities of different biological cell images are located; A determination module, configured to determine that the cell density of the biological cell image to be tested is the density range corresponding to the trained convolutional neural network model that matches the reconstructed biological cell image among the plurality of trained convolutional neural network models.

9. An electronic device, characterized in that, The electronic device includes a processor and a memory. The processor is configured to implement the cell density classification method according to any one of claims 1 to 7 when executing at least one instruction stored in the memory.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores at least one instruction, and the at least one instruction is executed by a processor to implement the cell density classification method according to any one of claims 1 to 7.

Images