Visual detection method and device for cell growth status

Abstract

This specification provides a method and device for visual detection of cell growth status. Based on this method, the cell culture experimental equipment first determines and determines a matching target focus strategy based on the cell type of the target cell; then, based on the target focus strategy, the matching target acquisition position is determined by automatically focusing the microscope lens; the microscope lens is controlled to acquire a target image containing the target cell based on the target acquisition position; and the growth status of the target cell is determined by processing the target image according to the matching target processing rules. Thus, the automatic focusing of the microscope lens can be realized intelligently and efficiently, and the matching target acquisition position can be quickly found; and based on the target acquisition position, a target image with smaller error and better effect can be acquired through the microscope lens; and then, according to the matching target processing rules, the growth status of the target cell can be accurately detected and identified by processing the target image.

Description

Technical Field

[0001] The present invention relates to the field of cell culture technology, and in particular to a method and device for visually detecting cell growth status. Background Art

[0002] During the cell culture process, it is often necessary to observe the growth status of cells in real time and make corresponding adjustments and operations in time according to the growth status of cells in order to better complete the cell culture experiment.

[0003] Based on existing methods and experimental equipment, when observing the growth status of cells, most people use traditional microscopes to observe the cell morphology with the human eye; and manually open the lid to take samples, and then use a flow cytometer to evaluate data such as the number of cells and survival rate in the sample. Based on the above methods, the observation results obtained are prone to errors and low efficiency. In addition, the manual sampling and counting process is also prone to violent mixing of cells in existing culture containers, which will also affect the normal growth process of cells to a certain extent, and easily cause contamination and damage to cell culture.

[0004] To address the above problems, no effective solution has been proposed yet. Summary of the invention

[0005] The present specification provides a method and device for visually detecting the growth status of cells, which can intelligently and efficiently realize the automatic focusing of the microscope lens of the cell culture experimental equipment; and based on the autofocused microscope lens, the growth status of the target cells can be accurately detected and identified through the cell culture experimental equipment.

[0006] This specification provides a method for visually detecting cell growth status, which is applied to cell culture experimental equipment, including:

[0007] Determine the cell type of the target cell;

[0008] Determine a matching target focusing strategy according to the cell type of the target cell; wherein the target focusing strategy at least includes a plurality of matching reference positions and a matching target evaluation rule;

[0009] According to the target focusing strategy, the matching target acquisition position is determined by automatically focusing the microscope lens;

[0010] Controlling the microscope head to acquire a target image containing target cells based on the target acquisition position;

[0011] The growth state of the target cells is determined by processing the target image according to the matched target processing rule.

[0012] In one embodiment, according to the target focusing strategy, the matching target acquisition position is determined by automatically focusing the microscope lens, including:

[0013] According to the target focusing strategy, a plurality of reference positions for the microscope lens are determined; wherein different reference positions are spaced at different distances from the target cell along the optical axis;

[0014] Controlling the microscope head to collect images containing target cells based on the multiple reference positions respectively, to obtain multiple corresponding reference images;

[0015] Evaluate the plurality of reference images according to a target evaluation rule to obtain a plurality of corresponding evaluation results;

[0016] According to the multiple evaluation results, a matching target acquisition position is determined.

[0017] In one embodiment, the cell types of the target cells include: adherent cells, or suspension cells;

[0018] Correspondingly, the matching target evaluation rules include: an evaluation rule based on maximum boundary clarity and an evaluation rule based on maximum number of clear cells.

[0019] In one embodiment, determining the growth state of the target cell by processing the target image according to the matched target processing rule includes:

[0020] Preprocessing the target image according to the target processing rule to obtain a preprocessed target image;

[0021] Based on the preprocessed target image, edge detection is performed to obtain an image edge detection result;

[0022] According to the image edge detection result, a closed area is determined in the preprocessed target image; and the closed area is filled accordingly to obtain a corresponding filled area;

[0023] Based on the filled area, the growth status of the target cells is determined.

[0024] In one embodiment, preprocessing the target image according to the target processing rule to obtain the preprocessed target image includes:

[0025] According to the target processing rules, the target image is converted into a corresponding target grayscale image;

[0026] Using the target background image to perform background noise reduction on the target grayscale image, and obtaining a target grayscale image after noise reduction;

[0027] Adaptively binarize the denoised target grayscale image to obtain a preprocessed target image.

[0028] In one embodiment, after obtaining the corresponding filling area, the method further includes:

[0029] Detect whether the area of ​​the filling area is less than or equal to the lower limit of the preset area threshold;

[0030] When it is determined that the area of ​​the filling region is less than or equal to a lower limit value of a preset area threshold, the filling region is determined as noise data.

[0031] In one embodiment, after obtaining the corresponding filling area, the method further includes:

[0032] Detect whether the area of ​​the filling area is greater than the upper limit value of the preset area threshold;

[0033] When it is determined that the area of ​​the filling region is greater than the upper limit of the preset area threshold, performing boundary fitting on the filling region to obtain a filling region after boundary fitting;

[0034] Based on the filling area after boundary fitting, multiple arc segmentation is performed to obtain the corresponding arc segmentation results;

[0035] According to the arc segmentation result, the fill area is divided into multiple sub-fill areas.

[0036] In one embodiment, determining the growth state of the target cells based on the filling area includes:

[0037] Get the roundness characteristic parameters of the filling area;

[0038] Detecting whether the roundness characteristic parameter of the filling area is greater than or equal to a preset roundness characteristic reference value;

[0039] When it is determined that the roundness characteristic parameter of the filling area is greater than or equal to a preset roundness characteristic reference value, obtaining the shape characteristic of the filling area;

[0040] According to the shape characteristics of the filling area, the growth stage of the target cell corresponding to the filling area is determined by querying a preset cell morphology library.

[0041] In one embodiment, determining the growth state of the target cells based on the filling area further comprises:

[0042] Extracting a local image including a filling area from the preprocessed target image;

[0043] Performing fixed binarization processing on the local image to obtain a processed local image;

[0044] Detect whether the processed local image contains a circular ring area;

[0045] When it is determined that the processed local image contains a circular ring region, performing boundary fitting on the circular ring region;

[0046] The circularity characteristic parameters of the circular area after boundary fitting are obtained and the survival status of the target cells corresponding to the circular area is determined.

[0047] In one embodiment, after determining the growth status of the target cells, the method further comprises:

[0048] Determine the statistical data of the target cells according to the growth state of the target cells; wherein the statistical data of the target cells include at least one of the following: the density of the target cells, the survival rate of the target cells, the proportion of the growth stages of the target cells, and the total amount of the target cells;

[0049] Determine the rehydration time and / or subculture time of target cells according to the growth status and statistical data of the target cells;

[0050] According to the rehydration time and / or subculture time during the culture of the target cells, corresponding cell culture experiments are performed on the target cells in the cell culture vessel.

[0051] This specification also provides a visual detection device for cell growth status, which is applied to cell culture experimental equipment, including:

[0052] A first determination module is used to determine the cell type of the target cell;

[0053] A second determination module is used to determine a matching target focusing strategy according to the cell type of the target cell; wherein the target focusing strategy at least includes a plurality of matching reference positions and a matching target evaluation rule;

[0054] The third determination module is used to determine the matching target acquisition position by automatically focusing the microscope lens according to the target focusing strategy;

[0055] An acquisition module, used for controlling the microscope lens to acquire a target image containing target cells based on the target acquisition position;

[0056] The fourth determination module is used to determine the growth status of the target cells by processing the target image according to the matched target processing rule.

[0057] The present specification also provides a computer-readable storage medium having computer instructions stored thereon, wherein the instructions, when executed by a processor, implement the following steps: determining the cell type of the target cell; determining a matching target focus strategy based on the cell type of the target cell; wherein the target focus strategy includes at least a plurality of matching reference positions and a matching target evaluation rule; determining a matching target acquisition position by performing autofocus processing on a microscope lens according to the target focus strategy; controlling the microscope lens to acquire a target image containing the target cell based on the target acquisition position; and determining the growth state of the target cell by processing the target image according to the matching target processing rule.

[0058] Based on the visual detection method and device for cell growth status provided in this specification, before specific implementation, the original cell culture experimental equipment can be modified in advance to obtain a modified cell culture experimental equipment that at least includes a cell growth detection module; wherein the above-mentioned cell growth detection module at least includes: a translation stage, an illumination light source, a connecting plate, a microscope lens and a camera and other structures; at the same time, matching focus strategies and processing rules are also pre-configured for different cell types; during specific implementation, the matching target focus strategy can be first determined and determined according to the cell type of the target cell; wherein the target focus strategy at least includes a plurality of matching reference positions and a matching target evaluation rule; then based on the cell growth detection module, according to the target focus strategy, the matching target acquisition position is determined by automatically focusing the microscope lens; the microscope lens is controlled to acquire a target image containing the target cell based on the target acquisition position; the cell culture experimental module can determine the growth state of the target cell by processing the above-mentioned target image according to the matching target processing rule. In this way, the automatic focusing of the microscope lens of the cell culture experimental equipment can be realized intelligently and efficiently, and the matching target acquisition position can be quickly determined; and based on the target acquisition position, the cell culture experimental equipment can acquire a target image with smaller error and better effect; and then the cell culture experimental equipment can accurately detect and identify the growth state of the target cell by processing the target image according to the matching target processing rules, thereby effectively reducing the cell detection error and improving the cell detection accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] In order to more clearly illustrate the embodiments of this specification, the drawings required for use in the embodiments will be briefly introduced below. The drawings described below are only some embodiments recorded in this specification. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0060] Figure 1is a schematic flow chart of a method for visually detecting cell growth status provided by an embodiment of the present specification;

[0061] Figure 2 It is a schematic diagram of an embodiment of the structural composition of a cell growth detection module of a cell culture experimental device using the visual detection method of cell growth status provided in the embodiments of this specification;

[0062] Figure 3 is a schematic diagram of an embodiment of a visual detection method for cell growth status provided by an embodiment of this specification, in a scenario example;

[0063] Figure 4 is a schematic diagram of an embodiment of a visual detection method for cell growth status provided by an embodiment of this specification, in a scenario example;

[0064] Figure 5 is a schematic diagram of an embodiment of a visual detection method for cell growth status provided by an embodiment of this specification, in a scenario example;

[0065] Figure 6 is a schematic diagram of an embodiment of a visual detection method for cell growth status provided by an embodiment of this specification, in a scenario example;

[0066] Figure 7 is a schematic diagram of an embodiment of a visual detection method for cell growth status provided by an embodiment of this specification, in a scenario example;

[0067] Figure 8 is a schematic diagram of an embodiment of a visual detection method for cell growth status provided by an embodiment of this specification, in a scenario example;

[0068] Fig. 9 is a schematic diagram of the structure of an electronic device provided by an embodiment of this specification;

[0069] Fig.10 It is a schematic diagram of the structure of a visual detection device for cell growth status provided by an embodiment of the present specification;

[0070] Fig.11 It is a schematic diagram of an embodiment of a visual detection method of cell growth status provided by an embodiment of this specification, in a scenario example. DETAILED DESCRIPTION

[0071] In order to enable those skilled in the art to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below in conjunction with the drawings in the embodiments of this specification. Obviously, the described embodiments are only part of the embodiments of this specification, not all of the embodiments. Based on the embodiments in this specification, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of this specification.

[0072] See also Figure 1 As shown, the embodiment of this specification provides a method for visually detecting the growth state of cells. The method is specifically applied to one side of a cell culture experimental device. When implemented specifically, the method may include the following contents:

[0073] S101: Determine the cell type of target cells;

[0074] S102: Determine a matching target focusing strategy according to the cell type of the target cell; wherein the target focusing strategy at least includes a plurality of matching reference positions and a matching target evaluation rule;

[0075] S103: According to the target focusing strategy, the matching target acquisition position is determined by automatically focusing the microscope lens;

[0076] S104: controlling the microscope head to acquire a target image including target cells based on the target acquisition position;

[0077] S105: Determine the growth status of the target cells by processing the target image according to the matched target processing rule.

[0078] The target cells may be cells that are currently being cultured in a transparent cell culture vessel.

[0079] Among them, the above-mentioned visual inspection can be specifically understood as a non-contact, digital inspection method based on visual images, which has the advantages of high precision, high efficiency and intelligence.

[0080] Before specific implementation, the original cell culture experimental equipment can be modified to add a cell growth detection module that supports autofocus and automatically monitors the cell growth status.

[0081] Specifically, the above-mentioned cell culture experimental equipment may at least include: a cell culture vessel, a cell growth detection module, a cell culture control module, a processor and other structures.

[0082] The cell culture vessel is specifically used for containing cells to be cultured. The cell culture vessel can be a closed vessel made of transparent material.

[0083] The cell culture control module may specifically include: operation units such as a fluid replenishment unit and a subculture unit, which are used to adjust and control specific culture operations in the cell culture process, such as fluid replenishment operations and subculture operations.

[0084] See also Figure 2 As shown, the cell growth detection module may at least include: a translation stage (eg, a precision translation stage), an illumination light source, a connecting plate, a microscope lens, a camera and other structures.

[0085] The above-mentioned translation stage can be connected to a connecting plate; a camera and a microscope lens are arranged on the connecting plate from bottom to top. Figure 2 As shown, the camera and the microscope lens can be located below the cell culture vessel. Correspondingly, the displacement stage can drive the microscope lens disposed on the connecting plate to move along the optical axis through the connecting plate.

[0086] The above-mentioned illumination light source can be specifically located above the cell culture vessel. Specifically, the above-mentioned illumination light source can be arranged above the cell culture vessel through a light source bracket. The above-mentioned illumination light source can effectively assist the microscope lens and camera arranged at the lower position to acquire a relatively high-quality cell image.

[0087] In addition, the cell growth detection module may further include a light source control module, wherein the light source control module is connected to the illumination light source and is used to control the illumination light source.

[0088] The processor is electrically connected to the cell growth detection module and the cell culture control module respectively.

[0089] In a specific implementation, first, the processor can determine a target focusing strategy that matches the cell type of the target cells in the cell culture vessel; then, based on the target focusing strategy, by controlling the movement of the translation stage in the cell growth detection module, the microscope lens is automatically focused to determine a suitable target acquisition position, and the microscope lens is set at the target acquisition position.

[0090] Next, the processor can use the camera in the cell growth detection module to capture a target image with a good focusing effect containing the target cells in the cell culture vessel based on the target acquisition position of the microscope lens; and then perform specific image processing on the target image according to the matching target processing rules to determine the growth status of the target cells.

[0091] Finally, the processor can adjust and control the cell culture of the target cells in a timely manner through operating units such as the rehydration unit and the subculture unit in the cell culture control module according to the growth status of the target cells, so as to better cultivate cells that meet the requirements.

[0092] Based on the above embodiment, by using the modified cell culture experimental equipment that at least includes a cell growth detection module, it is possible to first determine and determine a matching target focusing strategy based on the cell type of the target cell to be observed; then, according to the target focusing strategy, automatic focusing of the microscope lens is achieved to determine a target acquisition position suitable for acquiring an image; the microscope lens is controlled to acquire a target image with a better effect based on the target acquisition position; and then, according to the matching target processing rules, the growth state of the target cell can be accurately determined by processing the target image.

[0093] In some embodiments, the target focusing strategy may specifically include multiple reference positions and matching target evaluation rules, wherein different reference positions are spaced at different distances from the target cell along the optical axis.

[0094] Before specific implementation, a large number of focus operation records before growth status detection of cells of different cell types can be collected; then, for cells of different cell types, based on the focus operation records of the cells of the cell type, a preset number (for example, the top 5) of lens positions with the highest frequency of use in the focus operation records of the cells of the cell type are screened out through data statistics as multiple reference positions; at the same time, for cells of different cell types, clustering processing is performed on the operation records involving lens position setting, lens position change, etc. in the focus operation records of the cells of the cell type, as well as the images captured by the lens, so as to extract evaluation features for the cell type and combine them to obtain corresponding evaluation rules; and then the above-mentioned multiple reference positions and rating rules are combined to obtain a preset focus strategy for the cell type.

[0095] Through the above method, a plurality of preset focus strategies respectively matching a plurality of different cell types can be pre-determined to construct a preset focus strategy set, wherein each preset focus strategy corresponds to a cell type.

[0096] In some embodiments, during specific implementation, the cell culture experimental device can be configured to trigger automatic detection of the cell growth status after continuously running for a preset period of time.

[0097] Specifically, for example, the cell culture experimental equipment can trigger the method provided in this specification to automatically detect the cell growth status of the target cells in the cell culture vessel at intervals of a preset time period.

[0098] The preset time period may be a time period set by the user, or a time period in which the cell growth state is likely to change, determined by the cell culture experiment device after learning and collating a large number of cell culture history records.

[0099] In some embodiments, when the detection of the cell growth state is triggered, the cell type of the target cell can be determined first. Specifically, a data tag (e.g., NFD tag) containing basic attribute information related to the cultured target cells, such as cell type, can be set on the cell culture vessel; accordingly, the cell culture experimental equipment can determine the cell type of the target cell by scanning and according to the data tag on the cell culture vessel.

[0100] In addition, the cell culture experimental device can also receive a detection instruction set by the user regarding the growth state of the target cell through a connected input device; wherein the detection instruction can carry the cell type of the target cell set by the user. Accordingly, the cell culture experimental device can receive and respond to the detection instruction, trigger the detection of the cell growth state, and determine the cell type of the target cell according to the detection instruction.

[0101] In some embodiments, based on the growth characteristics of cells, the cell types of the target cells may specifically include: adherent cells, or suspended cells, etc.;

[0102] Correspondingly, the matching target evaluation rules include: an evaluation rule based on maximum boundary clarity and an evaluation rule based on maximum number of clear cells.

[0103] Specifically, on the one hand, the microscope lens itself has the characteristics of small field of view and small depth of field, which increases the difficulty of focusing; on the other hand, due to the large differences in the presentation states of cells of different cell types in cell culture vessels, the same microscope lens will also have differences when focusing based on cells of different cell types, further increasing the difficulty of focusing.

[0104] This manual takes the above situation into consideration. When performing autofocus, not only the influence of the microscope lens itself will be considered, but also the differences in cell conditions of different cell types, so that a matching focusing strategy with higher focusing efficiency and better focusing accuracy can be pre-built.

[0105] Specifically, for example, considering that adherent cells are usually close to the bottom of the cell culture vessel, and suspended cells are usually present as multiple layers of cells close to the bottom of the cell culture vessel, for the above situation, an evaluation rule based on maximum boundary clarity and an evaluation rule based on maximum clear cell number can be used in combination as a matching target evaluation rule. Based on the above matching target rules, the cell boundaries and cell numbers in the field of view can be focused on at the same time, thereby improving the automatic focusing efficiency and focusing accuracy for the above cell types.

[0106] Specifically, based on the differences in cell growth characteristics, adherent cells are basically all attached to the bottom of the cell culture vessel; and due to their own gravity, most of the suspended cells will settle to the bottom of the cell culture vessel. Therefore, based on the corresponding evaluation rules, first, there is a focus plane with a theoretical maximum number of cells at the bottom of the cell vessel (i.e., the maximum amount of clear cell data), and the cell growth state data in the cell microscopic image collected in this plane is more accurate. Secondly, the average diameter of the cell is usually 5 to 10um, that is, the depth of field along the optical axis is also 5 to 10um. Then, based on the above-mentioned focus plane with a theoretical maximum number of cells, the image acquisition also needs to make the cell boundaries of cells with a diameter of 5-10um in the image present the maximum clarity. Therefore, it is also necessary to collect multiple focus planes and calculate the corresponding contrast or gradient variance, and then screen out the image with the largest contrast or gradient variance as the maximum boundary clarity image (i.e., maximum boundary clarity).

[0107] Of course, it should be noted that the cell types and evaluation rules listed above are only schematic illustrations. In specific implementation, according to specific application scenarios and processing requirements, the cell types mentioned above may also include other cell types, and accordingly, the evaluation rules mentioned above may also include other evaluation rules corresponding to other cell types. This specification does not limit this.

[0108] In some embodiments, see Figure 3 As shown, according to the target focusing strategy, the matching target acquisition position is determined by automatically focusing the microscope lens. When implemented specifically, the following contents may be included:

[0109] S1: According to the target focusing strategy, multiple reference positions for the microscope lens are determined; wherein different reference positions are spaced at different distances from the target cell along the optical axis;

[0110] S2: controlling the microscope head to collect images containing target cells based on the multiple reference positions respectively, to obtain multiple corresponding reference images;

[0111] S3: Evaluate the multiple reference images according to the target evaluation rule to obtain corresponding multiple evaluation results;

[0112] S4: Determine a matching target acquisition position according to the multiple evaluation results.

[0113] Based on the above embodiments, by distinguishing different cell types and adopting matching target focusing strategies, auto-focus processing is performed efficiently and specifically to effectively improve focusing efficiency and focusing accuracy.

[0114] When implementing it, refer to Figure 2 As shown, the processor can control the movement of the translation stage according to the target focusing strategy, drive the microscope lens and the camera on the connecting plate to reach multiple different reference positions respectively, and collect images containing target cells at different reference positions to obtain corresponding multiple reference images.

[0115] Furthermore, the processor can evaluate the image quality of the above-mentioned multiple reference images according to the target evaluation rule, and obtain corresponding multiple evaluation results. Then, the processor can determine the most suitable target acquisition position according to the multiple evaluation results to achieve automatic focusing.

[0116] Specifically, for example, based on multiple evaluation results, it is detected whether there is an evaluation result greater than a preset evaluation score threshold; when it is determined that there is an evaluation result greater than the preset evaluation score threshold, the reference position corresponding to the evaluation result is determined as the matching target acquisition position. When it is determined that there is no evaluation result greater than the preset score threshold, the reference positions corresponding to the two evaluation results with the smallest difference from the preset evaluation score threshold are selected from the multiple evaluation results as pending reference positions; and the difference between the above two evaluation results and the preset evaluation score threshold is calculated; according to the difference value, a weighted calculation is performed on multiple pending reference positions to obtain a new position located between the two pending reference positions as the target acquisition position.

[0117] In some embodiments, during specific implementation, the microscope lens can be controlled to cooperate with the camera to acquire an image containing target cells based on the target acquisition position as the target image.

[0118] Among them, the above-mentioned microscope lens can replace the combination of traditional eyepiece and objective lens.

[0119] Before controlling the microscope lens to acquire the target image, the microscope lens and the camera may be firstly calibrated with internal parameters at the target acquisition position.

[0120] Specifically, a micro chessboard target plate can be used as a target; the microscope lens can be controlled to cooperate with the camera to collect a calibration image of the target based on the target collection position; and then the physical pixels of the calibration image are obtained and used to calculate the corresponding intrinsic parameter matrix. Subsequently, the acquired target image can be corrected using the intrinsic parameter matrix to obtain a target image with higher accuracy and better quality.

[0121] In specific implementation, the corresponding internal parameter matrix can be calculated according to the following formula:

[0122]

[0123] Among them, K represents the internal parameter matrix, f represents the focal length, d x d y Represents the length and width of a single pixel, P x , P y Represents the length and width of the actual pixels in the image respectively.

[0124] In some embodiments, after acquiring a target image containing target cells, the method may further include: performing backup processing on the target image to obtain a backup image of the target image; and storing the backup image of the target image in a preset backup database for subsequent backtracking queries. The preset backup database may specifically include a blockchain-based database. Furthermore, the preset backup database may also store the image acquisition time of the target image corresponding to the backup image.

[0125] In some embodiments, after controlling the microscope lens to acquire a target image containing target cells based on the target acquisition position, the method may further include: removing the cell culture vessel containing the target cells, controlling the microscope lens to acquire an image based on the same target acquisition position, and acquiring a target background image corresponding to the target image. The target background image may be subsequently used for background noise reduction processing of the target image.

[0126] This is because the diameter of the target cells to be observed is generally 5 to 10um, and the depth of field of the microscope lens used is 12um. Although a relatively clear cell image can be seen in the field of view of the microscope lens under normal circumstances, it may still appear more or less due to the influence of the background of the cell culture vessel, which will affect the subsequent processing. Therefore, the target background image can be collected synchronously so that the target background image can be used later for targeted background noise reduction processing.

[0127] In some embodiments, see Figure 4As shown, the above-mentioned determination of the growth state of the target cells by processing the target image according to the matched target processing rule may include the following contents during specific implementation:

[0128] S1: preprocessing the target image according to the target processing rule to obtain a preprocessed target image;

[0129] S2: Based on the preprocessed target image, edge detection is performed to obtain an image edge detection result;

[0130] S3: According to the image edge detection result, a closed area is determined in the preprocessed target image; and the closed area is filled accordingly to obtain a corresponding filled area;

[0131] S4: Based on the filling area, determining the growth status of the target cells.

[0132] Based on the above embodiment, by distinguishing different image situations and using matching target processing rules to process the target image, the growth status of the target cells is accurately detected and determined.

[0133] Before specific implementation, the image characteristics of cell images containing cells of different cell types under different light environments can be analyzed in advance, and a plurality of preset image processing rules corresponding to the combinations of different light environments and cell types can be configured.

[0134] In specific implementation, the current light environment may be determined first; and then the current light environment and cell type may be combined to determine a matching preset image processing rule from a plurality of preset image processing rules as a target processing rule.

[0135] In some embodiments, the target image is preprocessed according to the target processing rule to obtain the preprocessed target image. When specifically implemented, the following contents may be included:

[0136] S1: According to the target processing rules, the target image is converted into the corresponding target grayscale image;

[0137] S2: Using the target background image to perform background noise reduction on the target grayscale image to obtain a denoised target grayscale image;

[0138] S3: performing adaptive binarization processing on the denoised target grayscale image to obtain a preprocessed target image.

[0139] In specific implementation, the target image can be grayed to obtain a corresponding target grayscale image. Obtaining the target grayscale image through conversion can reduce the interference of other imaging factors on the target cells in the target image during the target image acquisition process.

[0140] In specific implementation, since the target images containing target cells are mostly bright field images obtained by collecting transparent cell culture vessels in a closed state, and the above-mentioned transparent cell culture vessels and other impurities will affect the image quality, resolution, etc., and thus cause errors in subsequent processing and recognition. Therefore, the non-cell images in the image or the cell images that are not on the same focal plane can be first subjected to background noise reduction processing to further eliminate image errors. Specifically, the target image is subjected to background noise reduction processing using the target background image according to the following formula:

[0141] I (i,j) =Image1 (i,j) -Image2 (i,j)

[0142] Among them, I (i,j) Represents the pixel value of the pixel point with position coordinates (i, j) in the target grayscale image after denoising, Image1 (i,j) Represents the pixel value of the pixel point with position coordinates (i, j) in the target grayscale image, Image2 (i,j) Represents the pixel value of the pixel with position coordinates (i, j) in the target background image.

[0143] Furthermore, an adaptive operator may be used to perform adaptive binarization processing on the target grayscale image after noise reduction, so that the cells and the background in the image can be better distinguished, and a pre-processed target image with a relatively better effect can be obtained.

[0144] In some embodiments, during specific implementation, the Sobel edge detection algorithm can be used to obtain image edge data (which can be denoted as G) including cell edges by performing edge detection based on the preprocessed target image; then the image edge data is compared with a reference threshold (Gmax), and according to the comparison result, image edge data (corresponding to cell edges) greater than or equal to the reference threshold is further screened out from the image edge data as the image edge detection result. The Sobel edge detection algorithm can specifically refer to an edge detection algorithm based on image gradients, which mainly uses the grayscale value of pixels in the image to detect image edges.

[0145] After obtaining the image edge detection result, the image edge detection result may be subjected to noise detection, and the detected noise may be eliminated to obtain an image edge with better accuracy.

[0146] After obtaining the image edge detection result, the image edge can be traversed based on the image edge detection result, and the image edges (boundaries) within the neighborhood of 2 pixels in the 9-grid are connected to form multiple connected domains and obtain multiple closed areas.

[0147] After obtaining multiple closed areas, further, binary effective pixels can be used to fill the closed areas to obtain a filling area that meets the requirements. Specifically, "1" can be used as a binary effective pixel to indicate a solid cell, and "0" can be used to indicate the background.

[0148] In some embodiments, see Figure 5 As shown, after obtaining the corresponding filling area, the method may further include the following contents when implemented:

[0149] S1: Check whether the area of ​​the filling area is less than or equal to the lower limit of the preset area threshold (for example, S min );

[0150] S2: When it is determined that the area of ​​the filling region is less than or equal to a lower limit value of a preset area threshold, the filling region is determined as noise data.

[0151] In specific implementation, the area of ​​each filled area can be calculated; then, by traversing all the filled areas, it is detected whether the area of ​​the filled area is less than or equal to the lower limit of the preset area threshold, and the noise data with too small area is detected and identified; and the above noise data is removed from the filled area to avoid error interference in subsequent processing.

[0152] In some embodiments, after obtaining the corresponding filling area, the method may further include the following when implemented:

[0153] S1: Check whether the area of ​​the filling area is greater than the upper limit of the preset area threshold (for example, S max );

[0154] S2: When it is determined that the area of ​​the filling region is greater than an upper limit value of a preset area threshold, performing boundary fitting on the filling region to obtain a filling region after boundary fitting;

[0155] S3: Based on the filling area after boundary fitting, multi-arc segmentation is performed to obtain the corresponding arc segmentation result;

[0156] S4: According to the arc segmentation result, the filling area is divided into multiple sub-filling areas.

[0157] The upper limit value and the lower limit value of the preset area threshold value may be determined by statistically analyzing the area of ​​cell regions in a large number of related historical cell images.

[0158] In a specific implementation, when it is detected that the area of ​​the filling region is greater than the upper limit of the preset area threshold, it can be determined that there is a high probability that a plurality of sub-filling regions are adhered to form a large filling region in the filling region.

[0159] In this case, the connected filling area can be segmented in the above manner to separate multiple sub-filling areas. Further, it is also possible to determine whether the sub-filling area is noise data by detecting whether the area of ​​the separated sub-filling area is less than or equal to the lower limit of the preset area threshold.

[0160] Based on the above method, the filled areas in the image whose area is greater than the lower limit of the preset area threshold and less than or equal to the upper limit of the preset area threshold can be further screened out as qualified filled areas with a relatively high probability of belonging to cells, so that the growth status of the target cells can be subsequently analyzed and detected based on the above-mentioned qualified filled areas, further reducing processing errors.

[0161] In some embodiments, see Figure 6 As shown, the above-mentioned determination of the growth state of the target cells based on the filling area may include the following contents during specific implementation:

[0162] S1: Obtain the roundness characteristic parameters of the filling area;

[0163] S2: Detect whether the roundness characteristic parameter of the filling area is greater than or equal to a preset roundness characteristic reference value;

[0164] S3: when it is determined that the roundness characteristic parameter of the filling area is greater than or equal to a preset roundness characteristic reference value, obtaining a shape characteristic of the filling area;

[0165] S4: According to the shape characteristics of the filling area, the growth stage of the target cell corresponding to the filling area is determined by querying a preset cell morphology library.

[0166] The above roundness characteristic parameter (or roundness) may specifically refer to the degree to which a region is close to a theoretical circle.

[0167] In a specific implementation, when it is determined that the roundness characteristic parameter of the filling area is less than the preset roundness characteristic reference value, it can be determined that the filling area is most likely not a living cell. At this time, in order to reduce the overall data processing amount, the growth stage of the cell corresponding to the filling area may not be further determined.

[0168] On the contrary, when it is determined that the roundness characteristic parameter of the filling area is greater than or equal to the preset roundness characteristic reference value, the shape characteristics of the filling area can be obtained and retrieved and matched by querying the preset cell morphology library, and the growth stage of the target cells corresponding to the filling area can be determined based on the matched reference cell morphology.

[0169] The growth stage of the target cells may specifically include one of the following: early stage, middle stage, and mature stage.

[0170] The preset cell morphology library may specifically store reference cell morphologies corresponding to different growth stages of cells of different cell types.

[0171] Based on the above embodiments, the growth stage of the target cells can be accurately detected and determined by using the preset cell morphology library.

[0172] In some embodiments, see Figure 7 As shown, based on the filling area, the growth state of the target cells is determined. When implemented specifically, the following contents may also be included:

[0173] S1: extracting a local image containing a filling area from the preprocessed target image;

[0174] S2: performing fixed binarization processing on the local image to obtain a processed local image;

[0175] S3: Detect whether the processed local image contains a circular ring area;

[0176] S4: when it is determined that the processed local image includes a circular ring region, performing boundary fitting on the circular ring region;

[0177] S5: Obtain and determine the survival status of the target cells corresponding to the circular area according to the circular characteristic parameters of the circular area after the boundary fitting.

[0178] In the specific implementation, combined with a large amount of historical cell image processing experience, considering that living cells often appear to have transparent centers and smooth shapes in the field of vision, and dead cells often appear to have black centers and occasional irregular deformations in the field of vision. Therefore, we can first detect whether the processed local image contains a circular area. For local images that do not contain a circular area, for example Figure 8 The center of the local image is filled with black, and it can be directly determined that the target cells contained in the local image are dead cells.

[0179] For the local image containing the annular region, the boundary fitting can be further performed, and according to the roundness characteristic parameter of the annular region after the boundary fitting, it is judged whether the boundary of the annular region is distorted. For the local image with distortion (for example, the roundness characteristic parameter is less than or equal to 0.95), for example Figure 8 In the local image with boundary distortion 1 and boundary distortion 2, it can be directly determined that the target cells contained in the local image are dead cells.

[0180] Accordingly, the target cells contained in the local image containing the annular region and having no distortion at the boundary of the annular region can be finally determined as living cells.

[0181] Based on the above embodiments, the survival status of target cells in the target image can be accurately determined.

[0182] In some embodiments, in addition to detecting the growth stage and survival status of target cells in a cell culture vessel, the visual detection method for cell growth status provided in this specification can further detect other types of growth status such as size, fusion degree, density, etc. of target cells based on the target image, so as to conduct a more comprehensive observation of the growth of the target cells.

[0183] In some embodiments, after determining the growth status of the target cells, the method may further include the following when implemented:

[0184] S1: Determine statistical data of the target cells according to the growth state of the target cells; wherein the statistical data of the target cells include at least one of the following: density of the target cells, survival rate of the target cells, proportion of growth stages of the target cells, and total amount of the target cells;

[0185] S2: Determine the rehydration time and / or subculture time of the target cells according to the growth status and statistical data of the target cells;

[0186] S3: Perform corresponding cell culture experiments on the target cells in the cell culture vessel according to the rehydration time and / or subculture time during the culture of the target cells.

[0187] In specific implementation, the culture status of the target cells can be monitored according to the growth status and statistical data of the target cells, and culture operations such as fluid replenishment and subculture can be performed in a timely manner when necessary to better complete cell culture experiments or cell culture production.

[0188] Specifically, for example, the current growth state of the target cells can be detected at preset time intervals (for example, every 1 hour), and the current statistical data (for example, cell density, cell survival rate, number of live cells, average cell size, cell fusion degree, etc.) can be calculated based on the detection results; and the current statistical data can be used to update the cell culture data monitoring chart, which can be referred to as Fig.11 As shown; according to the cell culture data monitoring chart, by analyzing the relevant statistical data and the changing trend of the statistical data, it is possible to more accurately grasp the culture status of the target cells and perform more targeted and detailed operational control on the cell culture of the target cells.

[0189] In some embodiments, during specific implementation, it is also possible to determine whether the target cells are contaminated based on the growth status and statistical data of the target cells; if it is determined that the target cells are contaminated, a contamination risk warning is generated; and the contamination risk warning is sent to a user terminal held by the user to promptly prompt the user so that the user can take corresponding measures as soon as possible to reduce the contaminated cells and reduce losses.

[0190] The user terminal may specifically include a front end applied to the user side and capable of realizing functions such as data collection and data transmission. Specifically, the user terminal may be, for example, an electronic device such as a desktop computer, a tablet computer, a laptop computer, a smart phone, etc. Alternatively, the user terminal may also be a software application that can be run in the above electronic devices.

[0191] By using the visual detection method of cell growth status provided in this specification, firstly, rapid detection and data quantification of cell growth status can be achieved, effectively solving the problems of large detection errors, easy contamination and low efficiency of existing manual operations and multiple single means; secondly, the degree of process intelligence can be greatly improved, which has important practical application value for forming a high-precision, high-efficiency and traceable cell medicine production system; in addition, by using a cell growth detection module including a microscope lens and a camera to replace traditional microscope equipment, the use space is effectively saved, and it also has a large size advantage when integrated on other equipment that requires detection or closed-loop feedback.

[0192] As can be seen from the above, the visual detection method of the cell growth state provided in the embodiment of this specification can be configured with matching focus strategies and processing rules for different cell types before specific implementation. During specific implementation, the matching target focus strategy can be determined first and based on the cell type of the target cell; wherein the target focus strategy at least includes a plurality of matching reference positions and a matching target evaluation rule; then, according to the target focus strategy, the matching target acquisition position is determined by automatically focusing the microscope lens; the microscope lens is controlled to acquire a target image containing target cells based on the target acquisition position; according to the matching target processing rule, the growth state of the target cell is determined by processing the target image. Thus, the automatic focusing of the microscope lens can be realized intelligently and efficiently, and the matching target acquisition position can be determined; and based on the target acquisition position, a target image with smaller error and better effect can be acquired; and then, according to the matching target processing rule, the growth state of the target cell can be accurately detected and identified by processing the target image, effectively reducing the cell detection error and improving the cell detection accuracy.

[0193] See also Fig. 9 As shown, an embodiment of this specification also provides a specific electronic device, wherein the electronic device includes a network communication port 901, a processor 902 and a memory 903, and the above structures are connected through internal cables so that each structure can perform specific data interaction.

[0194] Wherein, the network communication port 901 can be specifically used to receive a detection trigger instruction;

[0195] The processor 902 can be specifically used to respond to the detection trigger instruction and determine the cell type of the target cell; determine a matching target focus strategy based on the cell type of the target cell; wherein the target focus strategy at least includes a plurality of matching reference positions and a matching target evaluation rule; determine a matching target acquisition position by automatically focusing the microscope lens according to the target focus strategy; control the microscope lens to acquire a target image containing the target cell based on the target acquisition position; and determine the growth state of the target cell by processing the target image according to the matching target processing rule.

[0196] The memory 903 may be specifically used to store corresponding instruction programs.

[0197] In this embodiment, the network communication port 901 can be a virtual port that is bound to different communication protocols so that different data can be sent or received. For example, the network communication port can be a port responsible for web data communication, a port responsible for FTP data communication, or a port responsible for email data communication. In addition, the network communication port can also be a physical communication interface or communication chip. For example, it can be a wireless mobile network communication chip, such as GSM, CDMA, etc.; it can also be a Wifi chip; it can also be a Bluetooth chip.

[0198] In this embodiment, the processor 902 may be implemented in any appropriate manner. For example, the processor may take the form of a microprocessor or processor and a computer-readable medium storing a computer-readable program code (such as software or firmware) executable by the (micro)processor, a logic gate, a switch, an application specific integrated circuit (ASIC), a programmable logic controller, and an embedded microcontroller, etc. This specification does not limit this.

[0199] In this embodiment, the memory 903 may include multiple levels. In a digital system, anything that can store binary data can be a memory; in an integrated circuit, a circuit with a storage function that has no physical form is also called a memory, such as RAM, FIFO, etc.; in a system, a storage device with a physical form is also called a memory, such as a memory stick, TF card, etc.

[0200] The embodiments of the present specification also provide a computer-readable storage medium based on the visual detection method of the cell growth state mentioned above, wherein the computer-readable storage medium stores computer program instructions, and when the computer program instructions are executed, the following steps are implemented: determining the cell type of the target cell; determining a matching target focus strategy based on the cell type of the target cell; wherein the target focus strategy includes at least a plurality of matching reference positions and a matching target evaluation rule; determining a matching target acquisition position by performing autofocus processing on the microscope lens according to the target focus strategy; controlling the microscope lens to acquire a target image containing the target cell based on the target acquisition position; and determining the growth state of the target cell by processing the target image according to the matching target processing rule.

[0201] In this embodiment, the storage medium includes, but is not limited to, a random access memory (RAM), a read-only memory (ROM), a cache, a hard disk (HDD), or a memory card. The memory may be used to store computer program instructions. The network communication unit may be an interface for network connection communication set in accordance with the standard specified by the communication protocol.

[0202] In this embodiment, the functions and effects specifically implemented by the program instructions stored in the computer-readable storage medium can be explained in comparison with other implementations and will not be described in detail here.

[0203] See also Fig.10 As shown, at the software level, the embodiment of this specification also provides a visual detection device for cell growth status, which may specifically include the following structural modules:

[0204] The first determination module 1001 may be specifically used to determine the cell type of the target cell;

[0205] The second determination module 1002 may be specifically used to determine a matching target focusing strategy according to the cell type of the target cell; wherein the target focusing strategy at least includes a plurality of matching reference positions and a matching target evaluation rule;

[0206] The third determination module 1003 may be specifically used to determine a matching target acquisition position by performing auto-focus processing on the microscope lens according to the target focusing strategy;

[0207] The acquisition module 1004 may be specifically used to control the microscope lens to acquire a target image containing target cells based on the target acquisition position;

[0208] The fourth determination module 1005 may be specifically configured to determine the growth status of the target cells by processing the target image according to the matched target processing rule.

[0209] In some embodiments, when the third determination module 1003 is implemented, the matching target acquisition position can be determined by automatically focusing the microscope lens according to the target focus strategy in the following manner: according to the target focus strategy, multiple reference positions for the microscope lens are determined; wherein different reference positions are spaced at different distances from the target cells along the optical axis; the microscope lens is controlled to respectively acquire images containing the target cells based on the multiple reference positions to obtain corresponding multiple reference images; the multiple reference images are evaluated according to the target evaluation rules to obtain corresponding multiple evaluation results; and the matching target acquisition position is determined according to the multiple evaluation results.

[0210] In some embodiments, the cell types of the target cells may specifically include: adherent cells, or suspended cells, etc.; accordingly, the matching target evaluation rules include: an evaluation rule based on maximum boundary clarity and an evaluation rule based on a maximum number of clear cells.

[0211] In some embodiments, when the fourth determination module 1005 is implemented, the growth state of the target cells can be determined by processing the target image according to the matching target processing rules in the following manner: preprocessing the target image according to the target processing rules to obtain a preprocessed target image; performing edge detection based on the preprocessed target image to obtain an image edge detection result; determining a closed area in the preprocessed target image according to the image edge detection result; and performing corresponding filling processing on the closed area to obtain a corresponding filled area; and determining the growth state of the target cells based on the filled area.

[0212] In some embodiments, when the fourth determination module 1005 is implemented, the target image can be preprocessed according to the target processing rules in the following manner to obtain a preprocessed target image: according to the target processing rules, the target image is converted into a corresponding target grayscale image; the target grayscale image is subjected to background noise reduction processing using the target background image to obtain a denoised target grayscale image; the denoised target grayscale image is subjected to adaptive binarization processing to obtain a preprocessed target image.

[0213] In some embodiments, after obtaining the corresponding filling area, the above-mentioned fourth determination module 1005 can also be used in specific implementation to: detect whether the area of ​​the filling area is less than or equal to the lower limit value of the preset area threshold; when it is determined that the area of ​​the filling area is less than or equal to the lower limit value of the preset area threshold, the filling area is determined as noise data.

[0214] In some embodiments, after obtaining the corresponding filling area, the above-mentioned fourth determination module 1005 can also be used in specific implementation to: detect whether the area of ​​the filling area is greater than the upper limit value of the preset area threshold; when it is determined that the area of ​​the filling area is greater than the upper limit value of the preset area threshold, perform boundary fitting on the filling area to obtain the filling area after boundary fitting; perform multi-arc segmentation based on the filling area after boundary fitting to obtain the corresponding arc segmentation result; and according to the arc segmentation result, split the filling area into multiple sub-filling areas.

[0215] In some embodiments, when the fourth determination module 1005 is implemented, the growth state of the target cells can be determined based on the filling area in the following manner: obtaining roundness characteristic parameters of the filling area; detecting whether the roundness characteristic parameters of the filling area are greater than or equal to a preset roundness characteristic reference value; obtaining the shape characteristics of the filling area when it is determined that the roundness characteristic parameters of the filling area are greater than or equal to the preset roundness characteristic reference value; and determining the growth stage of the target cells corresponding to the filling area by querying a preset cell morphology library based on the shape characteristics of the filling area.

[0216] In some embodiments, when the fourth determination module 1005 is implemented, the growth status of the target cells can be determined based on the filled area in the following manner: a local image including the filled area is captured from the preprocessed target image; a fixed binary processing is performed on the local image to obtain a processed local image; it is detected whether the processed local image contains a circular ring area; if it is determined that the processed local image contains a circular ring area, the boundary of the circular ring area is fitted; and the survival status of the target cells corresponding to the circular ring area is determined based on the circularity characteristic parameters of the circular ring area after boundary fitting.

[0217] In some embodiments, after determining the growth status of the target cells, the device can also be used, when implemented, to: determine statistical data of the target cells based on the growth status of the target cells; wherein the statistical data of the target cells include at least one of the following: the density of the target cells, the survival rate of the target cells, the proportion of the growth stages of the target cells, and the total number of target cells; determine the rehydration time and / or subculture time during the culture of the target cells based on the growth status and statistical data of the target cells.

[0218] It should be noted that the units, devices or modules described in the above embodiments can be implemented by computer chips or entities, or by products with certain functions. For the convenience of description, the above devices are described separately by functions divided into various modules. Of course, when implementing this specification, the functions of each module can be implemented in the same or more software and / or hardware, or the modules that implement the same function can be implemented by a combination of multiple sub-modules or sub-units. The device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0219] As can be seen from the above, the visual detection device for the cell growth state provided by the embodiment of this specification can be configured with matching focus strategies and processing rules for different cell types before specific implementation. During specific implementation, the matching target focus strategy can be determined first and based on the cell type of the target cell; wherein the target focus strategy at least includes a plurality of matching reference positions and a matching target evaluation rule; then, according to the target focus strategy, the matching target acquisition position is determined by automatically focusing the microscope lens; the microscope lens is controlled to acquire a target image containing target cells based on the target acquisition position; according to the matching target processing rule, the growth state of the target cell is determined by processing the target image. Thus, the automatic focusing of the microscope lens can be realized intelligently and efficiently, and the matching target acquisition position can be determined; and based on the target acquisition position, a target image with smaller error and better effect can be acquired; and then, according to the matching target processing rule, the growth state of the target cell can be accurately detected and identified by processing the target image, effectively reducing the cell detection error and improving the cell detection accuracy.

[0220] Although the present specification provides method operation steps as described in the embodiments or flow charts, more or less operation steps may be included based on conventional or non-creative means. The order of steps listed in the embodiments is only one way of executing the order of many steps, and does not represent a unique execution order. When the device or client product in practice is executed, it can be executed in sequence or in parallel according to the method shown in the embodiments or the drawings (for example, a parallel processor or a multi-threaded processing environment, or even a distributed data processing environment). The term "include", "include" or any other variant thereof is intended to cover non-exclusive inclusion, so that the process, method, product or device including a series of elements includes not only those elements, but also includes other elements that are not explicitly listed, or also includes elements inherent to such a process, method, product or device. In the absence of more restrictions, it is not excluded that there are other identical or equivalent elements in the process, method, product or device including the elements. The first, second, etc. words are used to represent the name, and do not represent any particular order.

[0221] Those skilled in the art also know that, in addition to implementing the controller in a purely computer-readable program code, the controller can be made to implement the same function in the form of logic gates, switches, application-specific integrated circuits, programmable logic controllers, and embedded microcontrollers by logically programming the method steps. Therefore, such a controller can be considered as a hardware component, and the devices for implementing various functions included therein can also be considered as structures within the hardware component. Or even, the devices for implementing various functions can be considered as both software modules for implementing the method and structures within the hardware component.

[0222] This specification may be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, classes, etc. that perform specific tasks or implement specific abstract data types. This specification may also be practiced in distributed computing environments where tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules may be located in local and remote computer-readable storage media including storage devices.

[0223] Although the present specification is described through embodiments, those skilled in the art will appreciate that there are many modifications and changes to the present specification without departing from the spirit of the present specification, and it is intended that the appended claims include these modifications and changes without departing from the spirit of the present specification.

Claims

1. A method for visually detecting cell growth status, characterized in that: Applied to cell culture experimental equipment, including: Determining the cell type of the target cell; wherein the cell type of the target cell includes: adherent cells or suspension cells; According to the cell type of the target cell, a matching target focus strategy is determined from a plurality of preset focus strategies; wherein the target focus strategy at least includes a plurality of matching reference positions and a matching target evaluation rule; the target evaluation rule includes: an evaluation rule based on maximum boundary clarity and an evaluation rule based on the maximum number of clear cells; the preset focus strategy is constructed in advance based on the influence of the microscope lens itself and the differences in cell conditions of different cell types; According to the target focusing strategy, a matching target acquisition position is determined by automatically focusing the microscope lens; specifically, the method includes: determining a plurality of reference positions for the microscope lens according to the target focusing strategy; wherein different reference positions are spaced at different distances from the target cells along the optical axis; controlling the microscope lens to respectively acquire images containing the target cells based on the plurality of reference positions to obtain a plurality of corresponding reference images; evaluating the plurality of reference images according to the target evaluation rule to obtain a plurality of corresponding evaluation results; and determining a matching target acquisition position according to the plurality of evaluation results; Controlling the microscope head to acquire a target image containing target cells based on the target acquisition position; Determining the growth state of the target cells by processing the target image according to the matched target processing rule; Among them, according to the matching target processing rules, the growth status of the target cells is determined by processing the target image, including: according to the target processing rules, preprocessing the target image to obtain a preprocessed target image; based on the preprocessed target image, performing edge detection to obtain an image edge detection result; based on the image edge detection result, determining a closed area in the preprocessed target image; and performing corresponding filling processing on the closed area to obtain a corresponding filled area; based on the filled area, determining the growth status of the target cells.

2. The method according to claim 1, characterized in that According to the target processing rule, the target image is preprocessed to obtain a preprocessed target image, including: According to the target processing rules, the target image is converted into a corresponding target grayscale image; Using the target background image to perform background noise reduction on the target grayscale image, and obtaining a target grayscale image after noise reduction; Adaptively binarize the denoised target grayscale image to obtain a preprocessed target image.

3. The method according to claim 1, characterized in that After obtaining the corresponding filling area, the method further includes: Detect whether the area of ​​the filling area is less than or equal to the lower limit of the preset area threshold; When it is determined that the area of ​​the filling region is less than or equal to a lower limit value of a preset area threshold, the filling region is determined as noise data.

4. The method according to claim 1, characterized in that: After obtaining the corresponding filling area, the method further includes: Detect whether the area of ​​the filling area is greater than the upper limit value of the preset area threshold; When it is determined that the area of ​​the filling region is greater than the upper limit of the preset area threshold, performing boundary fitting on the filling region to obtain a filling region after boundary fitting; Based on the filling area after boundary fitting, multiple arc segmentation is performed to obtain the corresponding arc segmentation results; According to the arc segmentation result, the fill area is divided into multiple sub-fill areas.

5. The method according to claim 1, characterized in that Based on the filling area, determining the growth status of the target cell includes: Get the roundness characteristic parameters of the filling area; Detecting whether the roundness characteristic parameter of the filling area is greater than or equal to a preset roundness characteristic reference value; When it is determined that the roundness characteristic parameter of the filling area is greater than or equal to a preset roundness characteristic reference value, obtaining the shape characteristic of the filling area; According to the shape characteristics of the filling area, the growth stage of the target cell corresponding to the filling area is determined by querying a preset cell morphology library.

6. The method according to claim 1, characterized in that Determining the growth state of the target cells based on the filling area also includes: Extracting a local image including a filling area from the preprocessed target image; Performing fixed binarization processing on the local image to obtain a processed local image; Detect whether the processed local image contains a circular ring area; When it is determined that the processed local image contains a circular ring region, performing boundary fitting on the circular ring region; The circularity characteristic parameters of the circular area after boundary fitting are obtained and the survival status of the target cells corresponding to the circular area is determined.

7. The method according to claim 1, characterized in that After determining the growth status of the target cells, the method further comprises: Determine the statistical data of the target cells according to the growth state of the target cells; wherein the statistical data of the target cells include at least one of the following: the density of the target cells, the survival rate of the target cells, the proportion of the growth stages of the target cells, and the total amount of the target cells; Determine the rehydration time and / or subculture time of target cells according to the growth status and statistical data of the target cells; According to the rehydration time and / or subculture time during the culture of the target cells, corresponding cell culture experiments are performed on the target cells in the cell culture vessel.

8. A visual detection device for cell growth status, characterized in that: Applied to cell culture experimental equipment, including: A first determination module is used to determine the cell type of the target cell; wherein the cell type of the target cell includes: adherent cells or suspended cells; The second determination module is used to determine a matching target focus strategy from a plurality of preset focus strategies according to the cell type of the target cell; wherein the target focus strategy at least includes a plurality of matching reference positions and a matching target evaluation rule; the target evaluation rule includes: an evaluation rule based on maximum boundary clarity and an evaluation rule based on a maximum number of clear cells; the preset focus strategy is constructed in advance based on the influence of the microscope lens itself and the differences in cell conditions of different cell types; The third determination module is used to determine the matching target acquisition position by automatically focusing the microscope lens according to the target focusing strategy; An acquisition module, used for controlling the microscope lens to acquire a target image containing target cells based on the target acquisition position; a fourth determination module, configured to determine the growth state of the target cells by processing the target image according to the matched target processing rule; The third determination module is specifically used to: determine multiple reference positions for the microscope lens according to the target focus strategy; wherein different reference positions are spaced at different distances from the target cells along the optical axis; control the microscope lens to collect images containing target cells based on the multiple reference positions respectively, and obtain corresponding multiple reference images; evaluate the multiple reference images according to the target evaluation rule, and obtain corresponding multiple evaluation results; determine the matching target acquisition position according to the multiple evaluation results; The fourth determination module is specifically used for: preprocessing the target image according to the target processing rules to obtain a preprocessed target image; performing edge detection based on the preprocessed target image to obtain an image edge detection result; determining a closed area in the preprocessed target image according to the image edge detection result; and performing corresponding filling processing on the closed area to obtain a corresponding filled area; and determining the growth status of the target cells based on the filled area.

9. A computer-readable storage medium, characterized in that: Computer instructions are stored thereon, and when the instructions are executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images