A microsphere counting method, system and electronic device based on microscopic imaging

Abstract

The present invention relates to a microsphere counting method, system and electronic device based on microscopic imaging, the method comprising: based on microscopic imaging technology, obtaining a first image to be tested in each area to be counted of a microsphere solution to be tested; preprocessing each first image to be tested to obtain a second image to be tested in each area to be counted; and counting each circular connected domain in each second image to be tested to obtain the number of each microsphere in the microsphere solution to be tested. The present invention uses microscopic imaging technology to obtain the number of microspheres of different diameters, and combines microscopic imaging technology with computer vision technology to overcome the defects of existing microsphere counting software such as low resolution and narrow application range, while achieving automatic recognition, classification and statistics of microsphere images, further broadening the universality of the microscopic imaging microsphere counting platform, and greatly improving the speed and accuracy of analysis and detection.

Description

Background Art

[0002] Most of the existing microsphere counting systems use biosensors for analysis and detection, such as electrochemical biosensors, mechanical biosensors, and magnetic relaxation biosensors. Although they have advantages such as high sensitivity and fast analysis speed, their signal readout methods and equipment have many defects that need to be solved. Electrochemical biosensors usually require modification of the working electrode, and their signal processing methods are complex, requiring a special signal acquisition card; mechanical biosensors have high requirements for the processing difficulty of the device and are difficult to mass produce; magnetic relaxation biosensors require a special low-field nuclear magnetic resonance instrument, which has strict temperature requirements and a large device size, making it difficult to adapt to rapid on-site detection. Optical biosensors mainly use the light signal generated by the reaction between the test substance and the detection reagent as the detection basis, and are usually composed of three functional elements: a light sensing layer, a light signal conversion element, and a signal amplification and processing element. Despite this, the economic cost of existing optical sensors is relatively high, the structure is precise, the signal processing requirements are high, and their stability is also somewhat different from that of other biosensors.

[0003] Therefore, there is an urgent need to develop new optical sensing platforms, improve biological functional substances, explore new optical labeling materials or signal probes, etc., which is of great significance for the further development and application of optical biosensors. Summary of the invention

[0004] In order to solve the above technical problems, the present invention provides a microsphere counting method, system and electronic equipment based on microscopic imaging.

[0005] The technical solution of a microsphere counting method based on microscopic imaging of the present invention is as follows:

[0006] S1. Based on the microscopic imaging technology, obtain the first image of the microsphere solution to be tested in each area to be counted;

[0007] S2, preprocessing each first image to be tested to obtain a second image to be tested of each area to be counted, and each second image to be tested includes at least one circular connected domain, and one circular connected domain corresponds to a microsphere of one diameter;

[0008] S3. Count each type of circular connected domain in each second image to be tested, and obtain the number of each type of microspheres in the microsphere solution to be tested.

[0009] The beneficial effects of the microsphere counting method based on microscopic imaging of the present invention are as follows:

[0010] The method of the present invention obtains the number of microspheres of different diameters by adopting microscopic imaging technology, and combines microscopic imaging technology with computer vision technology. While overcoming the defects of existing microsphere counting software such as low resolution and narrow application range, it realizes automatic recognition, classification and statistics of microsphere images, further broadens the universality of the microscopic imaging microsphere counting platform, and greatly improves the speed and accuracy of analysis and detection.

[0011] Based on the above scheme, the microsphere counting method based on microscopic imaging of the present invention can also be improved as follows.

[0012] Further, the S2 specifically includes:

[0013] S21, performing grayscale conversion on each of the first images to be tested to obtain a first preprocessed image of each of the first images to be tested;

[0014] S22, performing binarization processing on each first pre-processed image to obtain a second pre-processed image of each first image to be tested;

[0015] S23, filtering interference information on each second pre-processed image to obtain each second image to be tested.

[0016] Further, the S23 specifically includes: setting a first threshold, and filtering interference information of each of the second pre-processed images according to the first threshold to obtain each of the second images to be tested; wherein the first threshold is predicted using a ResNet50 neural network model.

[0017] Further, the S3 specifically includes:

[0018] S31, marking each type of circular connected domain in each second image to be tested, to obtain a marked image corresponding to each second image to be tested;

[0019] S32, identifying and counting the number of each mark in each marked image to obtain the number of each circular connected domain;

[0020] S33. Obtain the number of each type of microspheres in the microsphere solution to be tested according to the number of each type of circular connected domains.

[0021] Furthermore, the diameter of each microsphere is not less than 2 microns.

[0022] The technical solution of a microsphere technology system based on microscopic imaging of the present invention is as follows:

[0023] It includes: a first processing module, a second processing module and a counting module;

[0024] The first processing module is used to: obtain a first image to be tested of the microsphere solution to be tested in each area to be counted based on microscopic imaging technology;

[0025] The second processing module is used to pre-process each first image to be tested to obtain a second image to be tested of each area to be counted, and each second image to be tested includes at least one circular connected domain, and one circular connected domain corresponds to a microsphere of one diameter;

[0026] The counting module is used to count each circular connected domain in each second image to be tested, respectively, to obtain the number of each microsphere in the microsphere solution to be tested.

[0027] The beneficial effects of the microsphere technology system based on microscopic imaging of the present invention are as follows:

[0028] The system of the present invention obtains the number of microspheres of different diameters by adopting microscopic imaging technology and combines microscopic imaging technology with computer vision technology. While overcoming the defects of existing microsphere counting software such as low resolution and narrow application range, it realizes automatic recognition, classification and statistics of microsphere images, further broadens the universality of the microscopic imaging microsphere counting platform, and greatly improves the speed and accuracy of analysis and detection.

[0029] Based on the above solution, the microsphere technology system based on microscopic imaging of the present invention can also be improved as follows.

[0030] Further, the second processing module specifically includes: a first preprocessing module, a second preprocessing module and a third preprocessing module;

[0031] The first preprocessing module is used to: perform grayscale conversion on each of the first images to be tested to obtain a first preprocessed image of each of the first images to be tested;

[0032] The second preprocessing module is used to: perform binarization processing on each first preprocessed image to obtain a second preprocessed image of each first image to be tested;

[0033] The third preprocessing module is used to filter interference information on each second preprocessed image to obtain each second image to be tested.

[0034] Further, the counting module specifically includes: a first counting module, a second counting module and a third counting module;

[0035] The first counting module is used to: mark each circular connected domain in each second image to be tested, and obtain a marked image corresponding to each second image to be tested;

[0036] The second counting module is used to: identify and count the number of each mark in each mark image to obtain the number of each circular connected domain;

[0037] The third counting module is used to obtain the number of each type of microspheres in the microsphere solution to be tested according to the number of each type of circular connected domains.

[0038] A technical solution of a storage medium of the present invention is as follows:

[0039] The storage medium stores instructions, and when a computer reads the instructions, the computer executes the steps of a microsphere counting method based on microscopic imaging of the present invention.

[0040] The technical solution of an electronic device of the present invention is as follows:

[0041] The invention comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the computer is caused to execute the steps of a microsphere counting method based on microscopic imaging according to the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] Figure 1 A schematic diagram of a process of a microsphere counting method based on microscopic imaging according to an embodiment of the present invention;

[0043] Figure 2 The figure is a schematic structural diagram of a microsphere counting system based on microscopic imaging according to an embodiment of the present invention. DETAILED DESCRIPTION

[0044] like Figure 1 As shown, a first embodiment of a microsphere counting method based on microscopic imaging of the present invention comprises the following steps:

[0045] S1. Based on the microscopic imaging technology, the first image of the microsphere solution to be tested in each area to be counted is obtained.

[0046] Among them, the microscopic imaging technology uses the magnified imaging function of a bright-field optical microscope, the model of which is LK-50, purchased from Tianjin Leco Co., Ltd. It should be noted that the imaging acquisition equipment, in addition to the bright-field optical microscope, can also be a dark-field optical microscope, a smartphone with a camera function, a CMOS camera, etc., without any restrictions.

[0047] The microsphere solution in this embodiment takes a polystyrene microsphere solution as an example, and may also be microspheres made of any other polymer material, such as latex microspheres, silica microspheres, etc., without limitation.

[0048] The microspheres in the polystyrene microsphere solution are 2 microns in diameter.2000 , 4 micron PS 4000 , 6 micron PS 6000 The carboxyl-modified microspheres were purchased from Bangs Laboratories.

[0049] It should be noted that the microspheres in this embodiment are carboxyl-modified microspheres with diameters of 2 microns, 4 microns, and 6 microns. Microspheres with a diameter of not less than 2 microns can also be used according to actual needs, and there is no limitation here.

[0050] For the convenience of explanation, pure water was used to separate PS 2000 Gradient dilution to 1μg / mL, 0.5μg / mL, 0.25μg / mL, 0.1μg / mL, 0.05μg / mL, 0.01μg / mL; PS was diluted with pure water 4000 Gradient dilution to 10μg / mL, 5μg / mL, 2μg / mL, 1μg / mL, 0.5μg / mL, 0.25μg / mL; PS was diluted with pure water 6000 Gradient dilution to 30μg / mL, 20μg / mL, 10μg / mL, 5μg / mL, 1μg / mL, 0.5μg / mL; the microsphere solution to be tested is based on PS 2000 , P.S. 4000 , P.S. 6000 For example, PS with a concentration of 0.5 μg / mL 2000 10ml, 5μg / mL PS 4000 10ml, 20μg / mL PS 6000 10ml of the microsphere solution to be tested was prepared.

[0051] Specifically, the microsphere solution to be tested is placed in an ultrasonic cleaner for 15 minutes. To ensure good observation results, the coverslip is soaked and washed with an ethanol-water solution (75%, v / v), and wiped dry with lens paper. 10 μL of the microsphere solution to be tested is dripped onto the counting area of ​​a clean blood cell counting plate, and the wiped coverslip is gently covered. Be careful not to generate bubbles during this process. Under the action of capillary phenomena, the microsphere solution to be tested will fill the entire counting area. After standing for 3 minutes, the particles in the counting area naturally settle and stabilize. To avoid counting errors caused by stratification, the assembled slide is placed under an optical microscope, and a 10x eyepiece and a 20x objective are selected. The image in the counting area is captured on the computer screen through computer software (such as ImageView).

[0052] Among them, the blood cell counter was purchased from Shanghai Qiujing Biochemical Reagent Instrument Co., Ltd.; the ultrasonic cleaner model was BX5200HP, purchased from Shanghai Xinmiao Medical Instrument Manufacturing Co., Ltd.; and ethanol was purchased from Sinopharm Chemical Reagent Co., Ltd.

[0053] Among them, a blood cell counter includes two sample addition areas, each sample addition area corresponds to an area to be counted. In order to increase the accuracy of the method and the reliability of the results, this embodiment chooses to capture and identify the images of microspheres in two counting plates (four areas to be counted).

[0054] It should be noted that the number of counting zones can be set according to demand. The more counting zones are captured, the higher the accuracy, but the time cost will increase accordingly.

[0055] The first image to be tested is an image of the microspheres in the area to be counted captured by computer software (ImageView).

[0056] S2. Preprocess each first image to be tested to obtain a second image to be tested of each area to be counted, and each second image to be tested includes at least one circular connected domain, and one circular connected domain corresponds to a microsphere of one diameter.

[0057] The preprocessing process generally includes the following steps: grayscale image processing, binarization processing, and image interference information filtering.

[0058] The second image to be tested includes at least one circular connected domain, each circular connected domain has a different diameter, and one circular connected domain corresponds to a microsphere of one diameter.

[0059] S3. Count each type of circular connected domain in each second image to be tested, and obtain the number of each type of microspheres in the microsphere solution to be tested.

[0060] Among them, the microspheres themselves are spherical, but in the first image to be tested captured under an optical microscope, the microspheres initially appear to be circular. In the second image to be tested obtained by preprocessing the first image to be tested, it can be more clearly distinguished that the microspheres appear to be circular, so the second image to be tested is a circular connected domain.

[0061] Each circular connected domain is marked differently, so that the software can easily identify the number of each object to be identified.

[0062] Among them, after each circular connected domain is identified, the number of each circular connected domain is obtained, and classification and statistics are performed based on the number of each circular connected domain to obtain the number of each microsphere of each diameter; finally, the data information in the image is classified and counted into a table for easy reference.

[0063] Preferably, the S2 specifically includes:

[0064] S21 . Perform grayscale conversion on each of the first images to be tested to obtain a first preprocessed image of each of the first images to be tested.

[0065] The purpose of performing grayscale conversion on the first image to be tested is to avoid interference of natural light on color information in the image.

[0066] The first pre-processed image is an image obtained after the first image to be tested is converted into a grayscale image.

[0067] S22, performing binarization processing on each first pre-processed image to obtain a second pre-processed image of each first image to be tested.

[0068] The purpose of binarization of the first preprocessed image is to set the grayscale value of the pixels on the image to 0 or 255, that is, to make the entire image appear in obvious black and white, so that the information in the first preprocessed image can be processed by computer language.

[0069] The second pre-processed image is an image obtained after the first image to be tested is binarized.

[0070] S23, filtering interference information on each second pre-processed image to obtain each second image to be tested.

[0071] Each of the second images to be tested includes at least one circular connected domain.

[0072] Preferably, the S23 specifically includes: setting a first threshold, and filtering interference information of each of the second pre-processed images according to the first threshold to obtain each of the second images to be tested; wherein the first threshold is predicted using a ResNet50 neural network model.

[0073] Specifically, since the background of each counting board (counter) is relatively simple, the target to be detected (circular connected domain) and the background have obvious differences in color depth (the darker the color, the smaller the grayscale value of the pixel, and the lighter the color, the larger the grayscale value of the pixel). Utilizing this feature, a first threshold is set, and pixels greater than the set threshold are set to the maximum value of 255, and pixels less than the threshold are set to 0. In this way, it is possible to filter out noise information and focus on the position information of the target to be detected.

[0074] It should be noted that the first threshold is generally set manually. This embodiment uses the neural network model ResNet50 for prediction to replace the global threshold and improve its detection accuracy.

[0075] Preferably, the S3 specifically includes:

[0076] S31 . Mark each circular connected region in each second image to be tested to obtain a marked image corresponding to each second image to be tested.

[0077] S32, identifying and counting the number of each mark in each mark image to obtain the number of each circular connected domain.

[0078] S33. Obtain the number of each type of microspheres in the microsphere solution to be tested according to the number of each type of circular connected domains.

[0079] Preferably, the diameter of each microsphere is not less than 2 microns.

[0080] Among them, microspheres are used as signal probes because they can be observed when their size is greater than or equal to 2 microns.

[0081] In this embodiment, four to-be-counted areas are used by default for counting, classification and identification.

[0082] The microsphere counting method (system) of this embodiment has a sensitive and stable signal readout function and can be applied to the fields of rapid food safety detection, in vitro diagnosis, and environmental monitoring.

[0083] The technical solution of this embodiment adopts microscopic imaging technology to obtain the number of microspheres with different diameters. By combining microscopic imaging technology with computer vision technology, it overcomes the defects of existing microsphere counting software such as low resolution and narrow application range, while realizing automatic recognition, classification and statistics of microsphere images, further broadens the universality of the microscopic imaging microsphere counting platform, and greatly improves the speed and accuracy of analysis and detection.

[0084] In this embodiment, by preparing a series of microsphere solutions with concentrations of 2μm, 4μm, 6μm and three diameters, and counting the number of particles in the counting area by optical microscopy, it is found that when the concentration of the solution increases, the number of particles will also increase, and there is a good correlation between the two. Through linear fitting, the linear equations between the concentrations of 2μm, 4μm, and 6μm microspheres and the corresponding numbers in the counting area are: Y = 450.86X-1.79 (R2 = 0.997), Y = 39.822X + 0.21 (R2 = 0.992), and Y = 23.94X-5.38 (R2 = 0.993).

[0085] At the same time, manual counting and QSCounting counting were used to count the number of microspheres in the counting area. The results showed that the manual counting was consistent with the microsphere counting results based on microscopic imaging in this embodiment. Among them, the microspheres with diameters of 4μm and 6μm were linearly fitted with the manual counting results as the horizontal coordinates and the counting results of this embodiment as the vertical coordinates. The linear equations were: Y = 0.97X + 1.11, Y = 0.97X + 1.04, and the correlation coefficient (R2) reached 0.999. For microspheres with a diameter of 2μm, the linear equation was: Y = 0.97X + 0.16, and R2 was 0.996.

[0086] In summary, as the concentration of microspheres gradually increases, the number of microspheres in the counting area increases accordingly. Through parameter optimization, the computer vision microsphere counting software also achieves good accuracy, which greatly improves the analysis efficiency. This proves that the microscopic imaging microsphere counting system made by the method of this embodiment is a sensitive and stable signal reading device, which has great potential for application in the fields of rapid food safety detection, in vitro diagnosis and environmental monitoring.

[0087] The advantages of the technical solution of this embodiment are: (1) The manufacturing process of bright-field optical microscopes is mature, the manufacturing cost is low, and it is easy to miniaturize; (2) Unlike fluorescent microspheres, which require complex modification processes and strict storage conditions, microspheres, as a polymer material, have stable chemical properties and simple storage conditions; (3) The combined use of microspheres of different diameters provides a new direction for the simultaneous detection of multiple targets; (4) The combination of the microscopic imaging platform and computer vision technology can realize the automatic recognition, classification, and statistics of batch images, which can greatly improve the efficiency of analysis and detection.

[0088] A second embodiment of a microsphere counting method based on microscopic imaging of the present invention is based on the above-mentioned first embodiment, and the technical solution of this embodiment also includes:

[0089] S100, based on microscopic imaging technology, obtaining a first image of the microsphere solution in each area to be counted.

[0090] S200, preprocessing each first image to be tested to obtain a second image to be tested of each area to be counted, and each second image to be tested includes at least one circular connected domain, and one circular connected domain corresponds to a microsphere of one diameter; wherein the second image to be tested includes: microspheres to be tested and free microspheres.

[0091] The microspheres to be tested are the microspheres that need to be counted in this embodiment; and the free microspheres are the microspheres that do not need to be counted in this embodiment.

[0092] S300 , counting each circular connected domain of the microspheres to be tested in each second image to be tested, to obtain the number of each type of microspheres to be tested in the microsphere solution to be tested.

[0093] Specifically, for example, there is a microsphere with a diameter of 6 microns in the second image to be tested, and a number of microspheres with a diameter of 2 microns are connected around the microsphere; at this time, the microsphere to be tested is: a 2-micron microsphere attached to a 6-micron microsphere, and the free microspheres are: a 6-micron microsphere and a 2-micron microsphere in a free state; step S300 is used to only count the number of 2-micron microspheres attached to the 6-micron microsphere in the image.

[0094] It should be noted that in this embodiment, there are no specific requirements for the material, diameter and other parameters of the microspheres, which can be in any range.

[0095] The technical solution of this embodiment, based on the first embodiment, can also effectively reduce the steps of biochemical reactions and improve the speed of analysis and detection.

[0096] like Figure 2 As shown, a microsphere counting system 200 based on microscopic imaging according to an embodiment of the present invention comprises: a first processing module 210, a second processing module 220 and a counting module 230;

[0097] The first processing module 210 is used to: obtain a first image of the microsphere solution to be tested in each area to be counted based on microscopic imaging technology;

[0098] The second processing module 220 is used to: pre-process each first image to be tested to obtain a second image to be tested of each area to be counted, and each second image to be tested includes at least one circular connected domain, and one circular connected domain corresponds to a microsphere of one diameter;

[0099] The counting module 230 is used to count each circular connected domain in each second image to be tested, respectively, to obtain the number of each microsphere in the microsphere solution to be tested, wherein one circular connected domain corresponds to a microsphere of one diameter.

[0100] Preferably, the second processing module 220 specifically includes: a first preprocessing module, a second preprocessing module and a third preprocessing module;

[0101] The first preprocessing module is used to: perform grayscale conversion on each of the first images to be tested to obtain a first preprocessed image of each of the first images to be tested;

[0102] The second preprocessing module is used to: perform binarization processing on each first preprocessed image to obtain a second preprocessed image of each first image to be tested;

[0103] The third preprocessing module is used to filter interference information on each second preprocessed image to obtain each second image to be tested.

[0104] Preferably, the counting module 230 specifically includes: a first counting module, a second counting module and a third counting module;

[0105] The first counting module is used to: mark each circular connected domain in each second image to be tested, and obtain a marked image corresponding to each second image to be tested;

[0106] The second counting module is used to: identify and count the number of each mark in each mark image to obtain the number of each circular connected domain;

[0107] The third counting module is used to obtain the number of each type of microspheres in the microsphere solution to be tested according to the number of each type of circular connected domains.

[0108] The technical solution of this embodiment adopts microscopic imaging technology to obtain the number of microspheres with different diameters. By combining microscopic imaging technology with computer vision technology, it overcomes the defects of existing microsphere counting software such as low resolution and narrow application range, while realizing automatic recognition, classification and statistics of microsphere images, further broadens the universality of the microscopic imaging microsphere counting platform, and greatly improves the speed and accuracy of analysis and detection.

[0109] The above parameters and steps for each module to implement corresponding functions in the microsphere counting system 200 based on microscopic imaging of this embodiment can refer to the parameters and steps in the first embodiment of the microsphere counting method based on microscopic imaging, which will not be repeated here.

[0110] A storage medium provided in an embodiment of the present invention includes: instructions stored in the storage medium, and when a computer reads the instructions, the computer executes the steps of a microsphere counting method based on microscopic imaging. For details, please refer to the parameters and steps in the first embodiment of a microsphere counting method based on microscopic imaging above, which will not be repeated here.

[0111] Computer storage media such as USB flash drives, mobile hard disks, etc.

[0112] An electronic device provided by an embodiment of the present invention includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the computer is caused to execute steps of a microsphere counting method based on microscopic imaging. For details, reference may be made to the parameters and steps in the first embodiment of a microsphere counting method based on microscopic imaging described above, which will not be described in detail herein.

[0113] Those skilled in the art will appreciate that the present invention may be implemented as a method, a system, a storage medium, and an electronic device.

[0114] Therefore, the present invention can be specifically implemented in the following forms, that is, it can be complete hardware, it can be complete software (including firmware, resident software, microcode, etc.), or it can be a combination of hardware and software, which is generally referred to as "circuit", "module" or "system" herein. In addition, in some embodiments, the present invention can also be implemented in the form of a computer program product in one or more computer-readable media, and the computer-readable medium contains computer-readable program code. Any combination of one or more computer-readable media can be used. The computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. The computer-readable storage medium can be, for example, but not limited to - an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media (a non-exhaustive list) include: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this document, a computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in conjunction with an instruction execution system, apparatus, or device. Although the embodiments of the present invention have been shown and described above, it is understood that the above embodiments are exemplary and cannot be construed as limiting the present invention, and those skilled in the art may make changes, modifications, substitutions, and variations to the above embodiments within the scope of the present invention.

Claims

1. A microsphere counting method based on microscopic imaging, characterized in that: include: S1. Based on the microscopic imaging technology, obtain the first image of the microsphere solution to be tested in each area to be counted; S2, preprocessing each first image to be tested to obtain a second image to be tested of each area to be counted, and each second image to be tested includes at least one circular connected domain, and one circular connected domain corresponds to a microsphere of one diameter; S3, counting each circular connected domain in each second image to be tested, to obtain the number of each microsphere in the microsphere solution to be tested; The S2 specifically includes: S21, performing grayscale conversion on each of the first images to be tested to obtain a first preprocessed image of each of the first images to be tested; S22, performing binarization processing on each first pre-processed image to obtain a second pre-processed image of each first image to be tested; S23, filtering interference information on each second pre-processed image to obtain each second image to be tested.

2. The microsphere counting method based on microscopic imaging according to claim 1, characterized in that: The S23 specifically includes: setting a first threshold, and filtering interference information of each of the second pre-processed images according to the first threshold to obtain each of the second images to be tested; wherein the first threshold is predicted using a ResNet50 neural network model.

3. The microsphere counting method based on microscopic imaging according to claim 1, characterized in that: The S3 specifically includes: S31, marking each type of circular connected domain in each second image to be tested, to obtain a marked image corresponding to each second image to be tested; S32, identifying and counting the number of each mark in each marked image to obtain the number of each circular connected domain; S33. Obtain the number of each type of microspheres in the microsphere solution to be tested according to the number of each type of circular connected domains.

4. The microsphere counting method based on microscopic imaging according to claim 3, characterized in that: The diameter of each microsphere is not less than 2 microns.

5. A microsphere counting system based on microscopic imaging, characterized in that: include: A first processing module, a second processing module and a counting module; The first processing module is used to: obtain a first image to be tested of the microsphere solution to be tested in each area to be counted based on microscopic imaging technology; The second processing module is used to pre-process each first image to be tested to obtain a second image to be tested of each area to be counted, and each second image to be tested includes at least one circular connected domain, and one circular connected domain corresponds to a microsphere of one diameter; The counting module is used to: count each circular connected domain in each second image to be tested, and obtain the number of each microsphere in the microsphere solution to be tested; The second processing module specifically includes: a first preprocessing module, a second preprocessing module and a third preprocessing module; The first preprocessing module is used to: perform grayscale conversion on each of the first images to be tested to obtain a first preprocessed image of each of the first images to be tested; The second preprocessing module is used to: perform binarization processing on each first preprocessed image to obtain a second preprocessed image of each first image to be tested; The third preprocessing module is used to filter interference information on each second preprocessed image to obtain each second image to be tested.

6. The microsphere counting system based on microscopic imaging according to claim 5, characterized in that: The counting module specifically includes: a first counting module, a second counting module and a third counting module; The first counting module is used to: mark each circular connected domain in each second image to be tested, and obtain a marked image corresponding to each second image to be tested; The second counting module is used to: identify and count the number of each mark in each mark image to obtain the number of each circular connected domain; The third counting module is used to obtain the number of each type of microspheres in the microsphere solution to be tested according to the number of each type of circular connected domains.

7. A storage medium, characterized in that: The storage medium stores instructions, and when a computer reads the instructions, the computer executes the microsphere counting method based on microscopic imaging as described in any one of claims 1 to 4.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the computer is caused to perform the microsphere counting method based on microscopic imaging according to any one of claims 1 to 4.

Images