Cell image analysis method, device, computer equipment and storage medium

Abstract

The application relates to a cell image analysis method and device, computer equipment and a storage medium. The method comprises the following steps: determining an abnormal cell region corresponding to at least one abnormal cell type from a cell image, counting cells in the abnormal cell region corresponding to the at least one abnormal cell type, determining respective abnormal cell count values, acquiring a normal cell region corresponding to a normal cell type in the cell image under the condition that the at least one abnormal cell count value meets a corresponding abnormal count value requirement, counting cells in the normal cell region corresponding to the normal cell type in the cell image, obtaining a normal cell count value of the normal cell type, and recording various cell count values under the condition that the normal cell count value meets a normal count value requirement. The method can improve the accuracy of data analysis.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of image processing, and in particular to a cell image analysis method and device, computer equipment and a storage medium. BACKGROUND

[0002] With the development of medical science and technology, in order to obtain the required cells, for example, to obtain cells capable of expressing specific products, it is usually necessary to analyze the state of the cell pool. For example, in the field of biopharmaceuticals, in order to screen monoclonal cell strains, it is usually necessary to first determine whether the cell pool is suitable for monoclonal cell strain screening, and if it is suitable, to screen monoclonal cell strains from the cell pool.

[0003] In the traditional technology, biological technology is usually used to analyze the data of the state of the cell pool. Since biological technology relies on manual means for subjective judgment, it is affected by subjective factors of biological technology personnel and external observation conditions, resulting in low accuracy of data analysis. SUMMARY

[0004] Therefore, it is necessary to provide a cell image analysis method and device, computer equipment, computer readable storage medium and computer program product capable of improving the accuracy of data analysis.

[0005] In a first aspect, the present application provides a cell image analysis method. The method comprises: determining an image region corresponding to at least one abnormal cell type from a cell image; determining cell statistical values corresponding to the at least one abnormal cell type respectively based on the image region corresponding to the at least one abnormal cell type; in the case that the cell statistical values corresponding to the at least one abnormal cell type respectively all meet the corresponding statistical value requirements, determining a cell statistical value of a normal cell type based on an image region corresponding to the normal cell type in the cell image; and recording various cell statistical values in the case that the cell statistical value of the normal cell type meets the corresponding statistical value requirements.

[0006] In a second aspect, the present application also provides a cell image analysis device. The device comprises: an image processing module configured to determine an image region corresponding to at least one abnormal cell type from a cell image; an abnormal statistical module configured to determine cell statistical values corresponding to the at least one abnormal cell type respectively based on the image region corresponding to the at least one abnormal cell type; a statistical confirmation module configured to determine a cell statistical value of a normal cell type based on an image region corresponding to the normal cell type in the cell image in the case that the cell statistical values corresponding to the at least one abnormal cell type respectively all meet the corresponding statistical value requirements; and an information recording module configured to record various cell statistical values in the case that the cell statistical value of the normal cell type meets the corresponding statistical value requirements.

[0007] In some embodiments, the cell statistical value is a cell proportion, the statistical value requirement is a cell proportion requirement, and the device further comprises an image updating module configured to: in a case where the cell proportion of any of the at least one abnormal cell type does not meet the corresponding cell proportion requirement, acquire a new cell image; and return to the step of determining the image region corresponding to the at least one abnormal cell type from the cell image.

[0008] In some embodiments, the cell image is an image obtained by image acquisition on a cell pool; the at least one abnormal cell type comprises a clumped cell type, and the image updating module is further configured to: in a case where the cell proportion of the clumped cell type does not meet the corresponding cell proportion requirement, determine a first processing mode for the cell pool; acquire a new cell image; and the new cell image is an image obtained by image acquisition on the cell pool processed by the first processing mode.

[0009] In some embodiments, the at least one abnormal cell type further comprises a state difference cell type, and the image updating module is further configured to: in a case where the cell proportion of the clumped cell type meets the corresponding cell proportion requirement, determine whether the cell proportion of the state difference cell type meets the corresponding cell proportion requirement; if not, acquire a new cell image; and the new cell image is an image obtained by image acquisition on a new cell pool.

[0010] In some embodiments, the at least one abnormal cell type further comprises a suspended cell type, and the image updating module is further configured to: in a case where the cell proportion of the state difference cell type meets the corresponding cell proportion requirement, determine whether the cell proportion of the suspended cell type meets the corresponding cell proportion requirement; if not, determine a second processing mode for the cell pool; acquire a new cell image; and the new cell image is an image obtained by image acquisition on the cell pool processed by the second processing mode.

[0011] In some embodiments, the at least one abnormal cell type comprises a clumped cell type; the cell statistical value is a cell proportion; the statistical value requirement is a cell proportion requirement; and the abnormality statistical module is further configured to: for the clumped cell type, statistically determine the area of each image region corresponding to the clumped cell type to obtain a cell image area corresponding to the clumped cell type; and determine the cell proportion of the clumped cell type based on the cell image area corresponding to the clumped cell type.

[0012] In a third aspect, the present application provides a computer device. The computer device comprises a memory and a processor. The memory stores a computer program. The processor executes the computer program to implement the steps of the cell image analysis method.

[0013] In a fourth aspect, the present application provides a computer readable storage medium. The computer readable storage medium stores a computer program. The computer program is executed by a processor to implement the steps of the cell image analysis method.

[0014] In a fifth aspect, the present application provides a computer program product. The computer program product comprises a computer program. The computer program is executed by a processor to implement the steps of the cell image analysis method.

[0015] The cell image analysis method, the cell image analysis device, the computer device, the storage medium and the computer program product determine the image region corresponding to at least one abnormal cell type from the cell image, determine the cell statistical value corresponding to at least one abnormal cell type based on the image region corresponding to at least one abnormal cell type, determine the cell statistical value of the normal cell type based on the image region corresponding to the normal cell type in the cell image in the case that the cell statistical value corresponding to at least one abnormal cell type meets the corresponding statistical value requirement, and record various cell statistical values in the case that the cell statistical value of the normal cell type meets the corresponding statistical value requirement. The cell statistical value of each type is obtained from the image region of the cell image, and the accuracy of data analysis is improved. BRIEF DESCRIPTION OF DRAWINGS

[0016] Figure 1 It is an application environment diagram of the cell image analysis method in one embodiment;

[0017] Figure 2 It is a flowchart of the cell image analysis method in one embodiment;

[0018] Figure 3 It is a schematic diagram of the cell image in one embodiment;

[0019] Figure 4 It is a flowchart of the cell image analysis method in another embodiment;

[0020] Figure 5 It is a structural block diagram of the cell image analysis device in one embodiment;

[0021] Figure 6 It is an internal structure diagram of the computer device in one embodiment;

[0022] Figure 7 It is an internal structure diagram of the computer device in one embodiment. DETAILED DESCRIPTION

[0023] In order to make the purposes, technical solutions and advantages of the present application clearer, further detailed description will be made to the present application in combination with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application, and do not limit the present application.

[0024] The cell image analysis method provided by the embodiments of the present application can be applied in the application environment as shown in Figure 1 The application environment includes a terminal 102 and a server 104. The terminal 102 communicates with the server 104 through a network. The data storage system can store data required to be processed by the server 104, or can store data required to be processed by other devices. The data storage system can be integrated on the server 104, or can be placed on a cloud or other network server.

[0025] Specifically, the terminal 102 can determine an image region corresponding to at least one type of abnormal cell from the cell image, determine cell statistical values corresponding to the at least one type of abnormal cell respectively based on the image region corresponding to the at least one type of abnormal cell, determine a cell statistical value of a normal cell type based on an image region corresponding to the normal cell type in the cell image in a case where the cell statistical values corresponding to the at least one type of abnormal cell respectively all meet corresponding statistical value requirements, and record various cell statistical values in a case where the cell statistical value of the normal cell type meets a corresponding statistical value requirement, facilitating later review and analysis. The various cell statistical values can be used as data for reference by cell research. The terminal 102 can send the recorded various cell statistical values to the server 104, and the server 104 can store the received various cell statistical values, for example, in a data storage system.

[0026] The terminal 102 can be, but is not limited to, a desktop terminal or a mobile terminal. The mobile terminal can be at least one of a mobile phone, a tablet computer, a notebook computer, a smart watch, and the like. The server 104 can be implemented by an independent server or a server cluster composed of multiple servers.

[0027] Those skilled in the art can understand that the application environment shown in Figure 1 is only part of the scene related to the scheme of the present application, and does not constitute a limitation on the application environment of the scheme of the present application.

[0028] In some embodiments, as shown in Figure 2 , a cell image analysis method is provided. The method can be executed by a terminal or a server, and can also be executed by a terminal and a server together. Taking the terminal 102 in Figure 1 as an example, the method includes the following steps:

[0029] Step 202, determining an image region corresponding to at least one abnormal cell type from the cell image.

[0030] The cell image is an image obtained by image acquisition of a cell pool. The cell image can be obtained in any manner, for example, a cell image obtained by a microscope. The cells in the cell image include at least one of normal cells or abnormal cells. The normal cell refers to a cell without rupture, complete, round and clear. The abnormal cell refers to a cell having obvious difference compared with the normal cell, for example, at least one of shape, size, color or cell membrane state of the abnormal cell has obvious difference compared with the normal cell.

[0031] The cell type refers to the type of the cell, and the cell type includes normal cell type and abnormal cell type. The cell type includes but is not limited to at least one of normal cell, clumped cell, poor state cell, dying cell, suspended cell or cell with abnormal shape. The normal cell can also be referred to as a good quality cell. The abnormal cell type is at least one, including but not limited to at least one of clumped cell, poor state cell, dying cell, suspended cell or cell with abnormal shape.

[0032] The image region can be a rectangular frame where the cell is located, or a cell contour figure. The same type of cells are included in the same image region. The image region can be of any shape, including but not limited to a rectangular region or a circular region. For example, in the case of using a rectangular frame to position the image region corresponding to different types of cells, each image region can present a rectangular shape. The image region corresponding to the abnormal cell type is the region where the abnormal cell type is located in the cell image. For each cell type, there can be one or more image regions, and the multiple refers to at least two. As shown in the following table, a cell image is shown, which includes cells of multiple types. The A region includes 3 clumped cells, which can be seen as cells adhered to at least one cell. The B region is a poor state cell, which can be seen as a cell membrane with obvious rupture, small bubbles and small burrs. The C region is a dying cell, which can be seen as a whole black color, and the cell membrane and cytoplasm cannot be distinguished, and the inside of the cell cannot be seen. The D region is a suspended cell, which can be seen as a cell with obvious virtual focus. The E region is a cell with abnormal shape, which can be seen as a cell with abnormal shape. The F region is a normal cell. Figure 3

[0033] ​Specifically, the terminal can store an image processing model, and the image region can be detected by the image processing model. The image processing model has the function of locating different types of cells from the image, for example, the regions where different types of cells are located can be detected from the image. The terminal obtains a cell image obtained by image acquisition of the cell pool, inputs the cell image into the image processing model to detect the image region, and obtains the image region corresponding to each type of cell, i.e., the image region corresponding to each type of cell. Wherein, the image region corresponding to each type of cell can be determined simultaneously or sequentially, which is not limited here.

[0034] In some embodiments, the terminal can obtain a sample cell image, train the image processing model to be trained using the sample cell image, obtain a trained image processing model, and determine the image region corresponding to each type of cell from the cell image using the trained image processing model. Specifically, the terminal can obtain the image region where different types of cells in the sample cell image actually exist, and obtain each real image region. For each type of cell, the real image region refers to the region where the cell actually exists. The sample cell image can be multiple, for example, 100. In the process of training the image processing model using the sample cell image, the sample cell image is input into the image processing model to detect the image region, and the predicted image region corresponding to each type of cell is obtained. For each type of cell, the difference between the corresponding predicted image region and the real image region is determined to obtain an image region difference. A model loss value is generated based on the image region difference. The model loss value and the image region difference have a positive correlation relationship. The model parameters of the image processing model are adjusted in the direction of reducing the model loss value until the model converges, and a trained image processing model is obtained. Wherein, the positive correlation relationship refers to: under the condition that other conditions remain unchanged, the two variables change in the same direction. When one variable changes from large to small, the other variable also changes from large to small.

[0035] In some embodiments, the image processing model can be based on a target detection algorithm. The target detection algorithm is used to locate the image region corresponding to different types of cells by a detection box.

[0036] In some embodiments, the image processing model can be based on an image segmentation algorithm, for example, when the calculation requires pixel-level accuracy, the image processing model can be based on an image segmentation algorithm.

[0037] Step 204, based on the image region corresponding to at least one type of abnormal cell, determine the cell statistical value corresponding to each type of abnormal cell.

[0038] The cell statistics include at least one of a cell number or a cell proportion.

[0039] Specifically, for each abnormal cell type, the terminal can determine the cell statistics of the abnormal cell type based on the image area corresponding to the abnormal cell type. The cell image includes at least one abnormal cell type and a normal cell type, and the cell statistics of each cell type can be calculated simultaneously or sequentially, for example, in the case where the calculated cell statistics meet the corresponding statistical value requirement, the next cell type whose cell statistics need to be calculated is determined. Figure 3 For example, in the cell image in Figure 3 There are clustered cells, poor state cells, dying cells, suspended cells, cells with abnormal shapes, and normal cells. The cell statistics of any one of the abnormal cell types are calculated and compared with the corresponding statistical value requirement. If it meets the requirement, the cell statistics of another abnormal cell type are calculated. If it does not meet the requirement, the statistics are stopped. For example, the cell statistics of the clustered cells can be calculated. In the case where the cell statistics of the clustered cells meet the corresponding statistical value requirement, the cell statistics of the poor state cells are calculated. The statistical value requirement can be set as needed.

[0040] In some embodiments, for each cell type, the terminal can count the number of cells contained in the image area corresponding to the cell type to obtain the cell number of the cell type, and determine the cell statistics of the cell type based on the cell number. For example, the cell number can be determined as the cell statistics of the cell type.

[0041] In some embodiments, for each cell type, there can be one or more image areas, and the number of image areas is at least two. The terminal can calculate the cell number of the cell type based on the number or area of the image area corresponding to the cell type. In some image areas corresponding to some cell types, one image area includes only one cell, such as the poor state cell type, the dying cell, the suspended cell, the cell with abnormal shape, and the normal cell. For these cell types, the number of image areas of the cell type is counted to obtain the corresponding cell number. In some image areas corresponding to some cell types, one image area includes multiple cells, and the number of cells is at least two, such as the clustered cell type. For the clustered cell type, the terminal can determine the cell number of the clustered cell type based on the area of the cell image corresponding to the clustered cell type. The cell type corresponding to the clustered cell type refers to the sum of the areas of the image areas corresponding to the clustered cell type.

[0042] In some embodiments, the terminal determines the cell number of the clustered cell type based on the cell image area corresponding to the clustered cell type and the average area of single cells. The average area of single cells refers to the average value of the area occupied by single cells. For example, if there are five image areas corresponding to the clustered cell type, the terminal sums the areas of the five image areas to obtain the cell image area corresponding to the clustered cell type, calculates the ratio of the cell image area corresponding to the clustered cell type to the average area of single cells, and obtains the cell number of the clustered cell type.

[0043] In some embodiments, the terminal can calculate the average area of single cells by averaging the areas of the image areas of each non-clustered cell type. Specifically, the terminal can calculate the total area of the image areas corresponding to the non-clustered cell types by summing the areas of the image areas of each non-clustered cell type, count the total number of image areas by counting the number of image areas of each non-clustered cell type, and calculate the average area of single cells by calculating the ratio of the total area of the image areas to the total number of image areas. The image areas corresponding to the non-clustered cell types only include one cell, and the non-clustered cell types include at least one of the following: abnormal cells, dying cells, suspended cells, cells with abnormal shapes, and normal cells.

[0044] In some embodiments, the cell statistical value is the cell proportion, and after obtaining the cell number corresponding to each cell type, the terminal can count the cell number of each cell type, i.e., sum the cell number of each cell type, to obtain the total number of cells. For each cell type, the terminal can calculate the ratio of the cell number corresponding to the cell type to the total number of cells to obtain the cell proportion corresponding to the cell type. Taking the abnormal cell type as an example, the terminal can count the number of cells included in the image areas corresponding to the abnormal cell type to obtain the cell number corresponding to the abnormal cell type, and calculate the ratio of the cell number corresponding to the abnormal cell type to the total number of cells to obtain the cell proportion of the abnormal cell type.

[0045] In step 206, when the cell statistical value corresponding to each abnormal cell type meets the statistical value requirement, the terminal determines the cell statistical value of the normal cell type based on the image areas corresponding to the normal cell type in the cell image.

[0046] The statistical value requirement is a condition that the cell statistical value needs to meet, and the statistical value requirement includes but is not limited to any one of the following: the cell statistical value belongs to a preset numerical range, the cell statistical value is less than a preset threshold, or the cell statistical value is greater than a preset threshold. Each cell type can be preconfigured with a statistical value requirement, and the cell type and the statistical value requirement have a one-to-one correspondence. The statistical value requirements of each cell type can be pre-stored in the terminal.

[0047] Specifically, for each abnormal cell type, the terminal can determine whether the cell statistical value of each abnormal cell type meets the corresponding statistical value requirement, and if all meet, the cell statistical value of the normal cell type is determined based on the image region corresponding to the normal cell type in the cell image. The method of calculating the cell statistical value can refer to the above-mentioned method of calculating the cell statistical value, which will not be repeated here.

[0048] In some embodiments, in the case that there is a cell statistical value corresponding to each abnormal cell type that does not meet the corresponding statistical value requirement, a new cell image is obtained and analyzed.

[0049] Step 208, in the case that the cell statistical value of the normal cell type meets the corresponding statistical value requirement, record various cell statistical values.

[0050] The statistical value requirement of the normal cell type is used to limit the condition that the cell statistical value corresponding to the normal cell type needs to meet. When the cell statistical value is the cell ratio, the statistical value requirement can also be referred to as the cell ratio requirement. The cell ratio requirement corresponding to the normal cell type is used to limit the condition that the cell ratio of the normal cell type needs to meet. For example, the cell ratio requirement of the normal cell type is that the cell ratio is greater than a first preset ratio threshold. The first preset ratio threshold can be set according to experience. For example, the first preset ratio threshold can be 50%.

[0051] Specifically, the terminal records various cell statistical values in the case that the cell statistical value of the normal cell type meets the corresponding statistical value requirement, for example, the cell statistical value of the clumped cell, the cell statistical value of the state difference cell and the cell statistical value of the suspended cell can be recorded. The terminal can store various cell statistical values in a document or a database for later reference and analysis.

[0052] In some embodiments, in the case that the cell statistical value corresponding to each abnormal cell type meets the corresponding statistical value requirement, and the cell statistical value of the normal cell type meets the corresponding statistical value requirement, the terminal can determine that the state of the cell pool is good, otherwise, it is determined that the state of the cell pool does not meet the selection condition.

[0053] In the cell image analysis method, an image region corresponding to at least one type of abnormal cell is determined from the cell image; a cell statistical value corresponding to each type of abnormal cell is determined based on the image region corresponding to the at least one type of abnormal cell; a cell statistical value of a normal cell type is determined based on an image region corresponding to the normal cell type in the cell image, if the cell statistical value corresponding to each type of abnormal cell meets a corresponding statistical value requirement; and various cell statistical values are recorded if the cell statistical value of the normal cell type meets a corresponding statistical value requirement. The cell statistical values of various types of cells are obtained from the image region of the cell image, and the accuracy of data analysis is improved.

[0054] The cell image analysis method provided in the application can be applied to determine whether the entire cell pool is suitable for screening of a monoclonal cell strain. In the field of biological pharmaceuticals, in order to screen a monoclonal cell strain, biological technology is usually used to determine whether the entire cell pool is suitable for screening of a monoclonal cell strain, and if suitable, a monoclonal cell strain is screened from the cell pool. For example, a method of labeling by using a fluorescent protein can be used to screen a monoclonal cell strain by using a fluorescence value instead of expression amount, or a microscope image construction algorithm model can be used to screen a high-expression monoclonal cell strain. The cell image analysis method provided in the application can be applied to determine whether the entire cell pool is suitable for screening of a monoclonal cell strain. Specifically, the terminal determines that the cell pool is suitable for screening of a monoclonal cell strain if the cell statistical value corresponding to each type of abnormal cell meets a corresponding statistical value requirement and the cell statistical value of the normal cell type meets a corresponding statistical value requirement, and determines that the cell pool is not suitable for screening of a monoclonal cell strain otherwise. The cell image analysis method provided in the application, when applied to determine whether the entire cell pool is suitable for screening of a monoclonal cell strain, has the advantages of simple analysis mode, high accuracy and strong robustness, and can replace biological technicians to make objective evaluation.

[0055] In some embodiments, the cell statistical value is a cell proportion, the statistical value requirement is a cell proportion requirement, and the cell image analysis method further comprises: if the cell proportion of any type of abnormal cell in the at least one type of abnormal cell does not meet the corresponding cell proportion requirement, obtaining a new cell image; and returning to the step of determining the image region corresponding to the at least one type of abnormal cell from the cell image.

[0056] The cell proportion requirement is used to define a condition required to be met by the cell proportion, and the cell proportion requirement of the abnormal cell type is used to define a condition required to be met by the cell proportion of the abnormal cell type. For example, the cell proportion requirement of the abnormal cell type is that the cell proportion is less than a second preset proportion threshold. The second preset proportion threshold in the cell proportion requirement of different abnormal cell types can be different or the same. For example, the second preset proportion threshold in the cell proportion requirement of the clumped cell is 30%, the second preset proportion threshold in the cell proportion requirement of the poor state cell is 20%, and the second preset proportion threshold in the cell proportion requirement of the suspended cell is 10%. The second preset proportion threshold can be set according to experience, and the second preset proportion threshold can be adjusted as needed.

[0057] The new cell image is an image obtained by re-acquiring an image of the cell pool, or an image obtained by acquiring an image of a new cell pool.

[0058] Specifically, the terminal can sequentially determine whether the cell proportion of each abnormal cell type meets the corresponding cell proportion requirement. If not, a new cell image is acquired, and step 202 is returned to be executed. For example, if the cell proportion of the clumped cell type does not meet the corresponding cell proportion requirement, a new cell image is acquired, and step 202 is returned to be executed.

[0059] In some embodiments, the terminal can compare the sum of the cell proportions of two abnormal cell types with a second preset proportion threshold. If the sum is less than the second preset proportion threshold, the terminal executes the step of determining whether the other abnormal cell type meets the corresponding cell proportion requirement, or determines the cell statistical value of the normal cell type based on the image region corresponding to the normal cell type in the cell image. For example, the second preset proportion threshold corresponding to the poor state cell and the dying cell is 20%. If the sum of the cell proportions of the poor state cell and the dying cell is less than 20%, the terminal executes the step of determining whether the cell proportion of the suspended cell type meets the corresponding cell proportion requirement.

[0060] In this embodiment, a new cell image is acquired when the cell proportion of at least one abnormal cell type does not meet the proportion requirement, so as to obtain statistical data meeting the requirement and improve the efficiency of obtaining statistical data.

[0061] In some embodiments, the cell image is an image obtained by image acquisition on the cell pool; the at least one abnormal cell type includes a clumped cell type, and in a case where the cell proportion of any of the at least one abnormal cell type does not meet the corresponding cell proportion requirement, obtaining a new cell image includes: in a case where the cell proportion of the clumped cell type does not meet the corresponding cell proportion requirement, determining a first processing mode for the cell pool; obtaining a new cell image; the new cell image is an image obtained by image acquisition on the cell pool after the first processing mode.

[0062] The clumped cell refers to a cell adhered to at least one cell, and the clumped cell cannot be separated by a tool in the process of cell screening, and thus cannot be used for cell screening. The first processing mode refers to a processing mode for the cell pool in a case where the cell proportion of the clumped cell does not meet the cell proportion requirement of the clumped cell. For example, the first processing mode can be a processing mode of performing a dispersing operation on the cell pool.

[0063] Specifically, the terminal can determine whether the cell proportion of the clumped cell type meets the corresponding cell proportion requirement of the clumped cell type. If not, the terminal displays a first processing mode for the cell pool. The terminal can obtain an image obtained by image acquisition on the cell pool after the first processing mode, to obtain a new cell image, and return to step 202.

[0064] In some embodiments, in a case where the cell proportion of the clumped cell type meets the corresponding cell proportion requirement, the terminal can perform a step of determining whether other abnormal cell types meet the corresponding cell proportion requirement.

[0065] In the embodiment, in a case where the cell proportion of the clumped cell type does not meet the cell proportion requirement, a decision is automatically made for the next step of execution, and the efficiency of determining the statistical data is improved.

[0066] In some embodiments, the at least one abnormal cell type further includes a state difference cell type, and the cell image analysis method further includes: in a case where the cell proportion of the clumped cell type meets the corresponding cell proportion requirement, determining whether the cell proportion of the state difference cell type meets the corresponding cell proportion requirement; if not, obtaining a new cell image; the new cell image is an image obtained by image acquisition on a new cell pool.

[0067] The state difference cell refers to a cell in which at least one of the following occurs in the cell image: cell membrane rupture, small bubbles, or small burrs. The new cell pool refers to another cell pool selected again in a case where the current cell pool does not meet the requirement.

[0068] Specifically, the terminal determines whether the cell ratio of the state-difference cell type meets the corresponding cell ratio requirement, and displays prompt information for updating the cell image if the cell ratio of the state-difference cell type does not meet the corresponding cell ratio requirement. The prompt information is, for example, "Give up the current cell pool, and please select a new cell pool again". The technical personnel select a new cell pool again, and the terminal can acquire a new cell image obtained by image acquisition of the new cell pool through the microscope, and returns to step 202.

[0069] In some embodiments, if the cell ratio of the state-difference cell type meets the corresponding cell ratio requirement, the terminal can execute the step of determining whether other abnormal cell types meet the corresponding cell ratio requirement.

[0070] In this embodiment, if the cell ratio of the state-difference cell type does not meet the corresponding cell ratio requirement, the next operation is automatically confirmed, and the efficiency of determining the statistical data is improved.

[0071] In some embodiments, the at least one abnormal cell type further includes a suspended cell type, and the cell image analysis method further includes: determining whether the cell ratio of the suspended cell type meets the corresponding cell ratio requirement if the cell ratio of the state-difference cell type meets the corresponding cell ratio requirement; determining a second processing mode for the cell pool if the cell ratio of the suspended cell type does not meet the corresponding cell ratio requirement; and acquiring a new cell image, wherein the new cell image is an image obtained by image acquisition of the cell pool processed by the second processing mode.

[0072] The suspended cell refers to a cell that is obviously out of focus in the cell image. The second processing mode refers to a processing mode for the cell pool if the cell ratio of the suspended cell type does not meet the corresponding cell ratio requirement. The second processing mode can be, for example, a processing mode of placing the cell pool.

[0073] Specifically, the terminal determines whether the cell ratio of the state-difference cell type meets the corresponding cell ratio requirement, and displays prompt information for updating the cell image if the cell ratio of the state-difference cell type does not meet the corresponding cell ratio requirement. The prompt information is, for example, "Give up the current cell pool, and please select a new cell pool again". The technical personnel select a new cell pool again, and the terminal can acquire a new cell image obtained by image acquisition of the new cell pool through the microscope, and returns to step 202.

[0074] In this embodiment, if the cell ratio of the state-difference cell type does not meet the corresponding cell ratio requirement, the next operation is automatically confirmed, and the efficiency of determining the statistical data is improved.

[0075] In some embodiments, the at least one abnormal cell type includes a clumped cell type; the cell statistical value is a cell proportion, and the statistical value requirement is a cell proportion requirement; and step 204 specifically includes: counting areas of image regions corresponding to the clumped cell type to obtain a cell image area corresponding to the clumped cell type; and determining the cell proportion of the clumped cell type based on the cell image area corresponding to the clumped cell type.

[0076] The clumped cell refers to a cell adhered to at least one cell.

[0077] Specifically, the terminal counts areas of image regions corresponding to the clumped cell type in the cell image, and the clumped cell type can correspond to one or more image regions. When the clumped cell type corresponds to multiple image regions, the areas of the multiple image regions are summed to obtain the cell image area corresponding to the clumped cell type. The server calculates a ratio of the cell image area of the clumped cell type to a total cell area, and determines the calculated ratio as the cell proportion corresponding to the clumped cell type. The total cell area refers to a sum of areas of all image regions included in the image regions, and the terminal can sum the areas of all image regions in the cell image to obtain the total cell area. The total cell area can be specifically an area of a detection frame in which the cell is located, or an area of a cell contour graph.

[0078] In some embodiments, the terminal determines a cell number of the clumped cell type based on the cell image area corresponding to the clumped cell type and an average area of single cells. For the clumped cell type, the terminal can calculate a ratio of the cell number corresponding to the clumped cell type to a total cell number to obtain the corresponding cell proportion.

[0079] In this embodiment, the cell proportion is confirmed by counting the areas of image regions corresponding to the clumped cell type, which improves the efficiency of obtaining statistical data and the accuracy of data analysis, and reduces the labor cost.

[0080] In some embodiments, as shown in FIG. 1, Figure 4 A cell image analysis method is provided, which can be executed by a terminal or a server, and can also be executed by the terminal and the server together. Taking the case where the method is applied to the terminal as an example, the method includes the following steps:

[0081] Step 402: determining image regions corresponding to a plurality of abnormal cell types from a cell image; the plurality of abnormal cell types include a clumped cell type, a state difference cell type, and a suspended cell type.

[0082] The cell image is an image obtained by image acquisition on a cell pool.

[0083] Step 404, for each abnormal cell type, based on the image area corresponding to the abnormal cell type, determine the cell proportion corresponding to the abnormal cell type.

[0084] Step 406, determine whether the cell proportion of the clustered cell type meets the cell proportion requirement corresponding to the clustered cell type, if not, execute step 408, if yes, execute step 410.

[0085] Step 408, determine the first processing mode for the cell pool, obtain a new cell image, the new cell image is an image obtained by image acquisition on the cell pool after being processed by the first processing mode, return to step 402.

[0086] Step 410, determine whether the cell proportion of the poor state cell type meets the cell proportion requirement corresponding to the poor state cell type, if not, execute step 412, if yes, execute step 414.

[0087] Step 412, obtain a new cell image; the new cell image is an image obtained by image acquisition on a new cell pool, return to step 402.

[0088] Step 414, determine whether the cell proportion of the suspended cell type meets the cell proportion requirement corresponding to the suspended cell type, if not, execute step 416, if yes, execute step 418.

[0089] Step 416, determine the second processing mode for the cell pool, obtain a new cell image; the new cell image is an image obtained by image acquisition on the cell pool after being processed by the second processing mode, return to step 402.

[0090] Step 418, based on the image area corresponding to the normal cell type in the cell image, determine the cell proportion of the normal cell type.

[0091] Step 420, determine whether the cell proportion of the normal cell type meets the cell proportion requirement corresponding to the normal cell type, if not, execute step 412, if yes, execute step 422.

[0092] Step 422, record various cell proportions.

[0093] The recorded various cell proportions can be used in the field of cell screening, for example, for screening cells with protein expression meeting the set conditions, or for assisting in monoclonal cell strain screening work.

[0094] In this embodiment, by determining the image regions corresponding to the plurality of abnormal cell types from the cell image, for each abnormal cell type, based on the image region corresponding to the abnormal cell type, the corresponding cell proportion is determined, it is judged whether the cell proportion meets the corresponding cell proportion requirement, if not, a new cell image is obtained, if it meets, the cell proportion corresponding to other abnormal cell types is determined, in the case that the cell proportions corresponding to at least one abnormal cell type respectively meet the corresponding cell proportion requirement, based on the image region corresponding to the normal cell type in the cell image, the cell proportion of the normal cell type is determined, in the case that the cell proportion of the normal cell type meets the corresponding cell proportion requirement, the various cell proportions are recorded. By counting the image regions of at least one abnormal cell type and the normal cell type, the cell proportions of various types are obtained, and the accuracy of data analysis is improved.

[0095] It should be understood that, although each step in the flowchart involved in each embodiment as described above is displayed in sequence according to the arrow, these steps are not necessarily executed in sequence according to the order of the arrow. Unless otherwise specified herein, the execution of these steps is not strictly limited in sequence, and these steps can be executed in other orders. Moreover, at least part of the steps in the flowchart involved in each embodiment as described above can include multiple steps or stages, which are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily sequential, but can be executed alternately or alternately with at least part of other steps or steps or stages in other steps.

[0096] Based on the same inventive concept, the embodiments of the present application also provide a cell image analysis device for implementing the above-mentioned cell image analysis method. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme described in the above method, so the specific limitations in one or more cell image analysis device embodiments provided below can refer to the limitations of the cell image analysis method in the above text, which will not be repeated here.

[0097] In one embodiment, as shown in Figure 5 A cell image analysis device is provided, comprising: an image processing module 502, an abnormality statistical module 504, a statistical confirmation module 506 and an information recording module 508, wherein:

[0098] The image processing module 502 is configured to determine the image region corresponding to at least one abnormal cell type from the cell image.

[0099] The abnormality statistical module 504 is configured to determine the cell statistical value corresponding to at least one abnormal cell type based on the image region corresponding to at least one abnormal cell type.

[0100] The statistical confirmation module 506 is configured to determine the cell statistical value of the normal cell type based on the image region corresponding to the normal cell type in the cell image, in a case where the cell statistical value corresponding to each of the at least one abnormal cell type meets the corresponding statistical value requirement.

[0101] The information recording module 508 is configured to record the various cell statistical values in a case where the cell statistical value of the normal cell type meets the corresponding statistical value requirement.

[0102] In some embodiments, the cell statistical value is a cell proportion, and the statistical value requirement is a cell proportion requirement. The device further includes an image updating module configured to: in a case where the cell proportion of any one of the at least one abnormal cell type does not meet the corresponding cell proportion requirement, acquire a new cell image; and return to the step of determining the image region corresponding to the at least one abnormal cell type from the cell image.

[0103] In some embodiments, the cell image is an image obtained by image acquisition on a cell pool; the at least one abnormal cell type includes a clumped cell type; and the image updating module is further configured to: in a case where the cell proportion of the clumped cell type does not meet the corresponding cell proportion requirement, determine a first processing mode for the cell pool; acquire a new cell image; and the new cell image is an image obtained by image acquisition on the cell pool processed by the first processing mode.

[0104] In some embodiments, the at least one abnormal cell type further includes a state-difference cell type; and the image updating module is further configured to: in a case where the cell proportion of the clumped cell type meets the corresponding cell proportion requirement, determine whether the cell proportion of the state-difference cell type meets the corresponding cell proportion requirement; and in a case where the cell proportion of the state-difference cell type does not meet the corresponding cell proportion requirement, acquire a new cell image; and the new cell image is an image obtained by image acquisition on a new cell pool.

[0105] In some embodiments, the at least one abnormal cell type further includes a suspended cell type; and the image updating module is further configured to: in a case where the cell proportion of the state-difference cell type meets the corresponding cell proportion requirement, determine whether the cell proportion of the suspended cell type meets the corresponding cell proportion requirement; in a case where the cell proportion of the suspended cell type does not meet the corresponding cell proportion requirement, determine a second processing mode for the cell pool; acquire a new cell image; and the new cell image is an image obtained by image acquisition on the cell pool processed by the second processing mode.

[0106] In some embodiments, at least one abnormal cell type includes a clustered cell type, the cell statistics value is the cell percentage, and the statistics value requirement is the cell percentage requirement; the abnormal statistics module is also used to perform statistics on the area of ​​each image region corresponding to the clustered cell type to obtain the cell image area corresponding to the clustered cell type; and determine the cell percentage of the clustered cell type based on the cell image area corresponding to the clustered cell type.

[0107] Each module in the aforementioned cell image analysis device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the memory of a computer device as software, so that the processor can call and execute the corresponding operations of each module.

[0108] In one embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as follows: Figure 6 As shown, the computer device includes a processor, memory, and a network interface connected via a system bus. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The database stores relevant data related to the cell image analysis method. The network interface communicates with external terminals via a network connection. When the computer program is executed by the processor, it implements a cell image analysis method.

[0109] In one embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as follows: Figure 7As shown in the figure. The computer device includes a processor, a memory, a communication interface, a display screen and an input device connected by a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used for wired or wireless communication with external terminals. Wireless communication can be achieved through WIFI, mobile cellular network, NFC (near field communication) or other technologies. The computer program is executed by the processor to implement a cell image analysis method. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen. The input device of the computer device can be a touch layer overlaid on the display screen, or a key, trackball or touchpad provided on the shell of the computer device. It can also be an external keyboard, touchpad or mouse, etc.

[0110] Those skilled in the art can understand that, Figure 7 The structure shown in the figure is only a block diagram of part of the structure related to the scheme of the present application, and does not constitute a limitation on the computer device to which the scheme of the present application is applied. A specific computer device can include more or fewer components than those shown in the figure, or combine certain components, or have a different component arrangement.

[0111] In one embodiment, a computer device is provided, including a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the steps of the cell image analysis method described above.

[0112] In one embodiment, a computer readable storage medium is provided, which stores a computer program, and the computer program is executed by a processor to implement the steps of the cell image analysis method described above.

[0113] In one embodiment, a computer program product is provided, including a computer program, and the computer program is executed by a processor to implement the steps of the cell image analysis method described above.

[0114] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in the present application are all information and data authorized by the user or authorized by all parties.

[0115] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer readable storage medium, and when the computer program is executed, the processes of the above-mentioned embodiments of the methods can be included. Any reference to memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (Read-Only Memory, ROM), magnetic tape, floppy disk, flash memory, optical storage, high-density embedded non-volatile memory, resistive memory (ReRAM), magnetoresistive random access memory (Magnetoresistive Random Access Memory, MRAM), ferroelectric memory (Ferroelectric Random Access Memory, FRAM), phase change memory (Phase Change Memory, PCM), graphene memory, etc. Volatile memory can include random access memory (Random Access Memory, RAM) or external cache memory, etc. As an illustration but not limitation, RAM can be in various forms, such as static random access memory (Static Random Access Memory, SRAM) or dynamic random access memory (Dynamic Random Access Memory, DRAM), etc. The database involved in the embodiments provided in the present application can include at least one of a relational database and a non-relational database. The non-relational database can include a distributed database based on a block chain, etc., without being limited thereto. The processor involved in the embodiments provided in the present application can be a general-purpose processor, a central processing unit, a graphics processing unit, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., without being limited thereto.

[0116] Any combination of the technical features of the above embodiments can be made. In order to make the description simple, all possible combinations of the technical features in the above embodiments are not described, however, as long as the combination of the technical features does not exist contradictory, it should be considered as the scope of the present application.

[0117] The above embodiments only express several implementation manners of the present application, and the description is more specific and detailed, but it should not be understood as a limitation on the scope of the patent of the present application. It should be pointed out that for ordinary skilled in the art, without departing from the concept of the present application, a number of modifications and improvements can be made, which are within the scope of protection of the present application. Therefore, the protection scope of the present application should be subject to the appended claims.

Claims

1. A cell image analysis method, characterized in that, The method includes: Identify image regions corresponding to at least one abnormal cell type from cell images; each abnormal cell type corresponds to one or more image regions, and each image region includes one or more cells; For each abnormal cell type, the number of cells contained in the image region corresponding to the abnormal cell type is counted to obtain the cell count corresponding to the abnormal cell type. Based on the cell count corresponding to the abnormal cell type, the cell count value corresponding to the abnormal cell type is determined. Specifically, for an abnormal cell type where an image region contains only one cell, the number of corresponding image regions is counted to obtain the corresponding cell count. For an abnormal cell type where an image region contains multiple cells, the corresponding cell count is determined based on the sum of the areas of the corresponding image regions and the average area of ​​a single cell. If any of the cell statistical values ​​corresponding to the at least one abnormal cell type do not meet the corresponding statistical value requirements, a new cell image is acquired, and the step of determining the image region corresponding to the at least one abnormal cell type from the cell image is returned to continue execution; the new cell image is an image obtained by re-acquiring images of the processed cell pool; the processing methods for the cell pool include the processing method of breaking up the cell pool and the processing method of letting the cell pool stand still; If the cell statistical values ​​corresponding to at least one abnormal cell type all meet the corresponding statistical value requirements, the cell statistical value of the normal cell type is determined based on the image region corresponding to the normal cell type in the cell image. If the cellular statistics of the normal cell type meet the corresponding statistical requirements, record various cellular statistics and determine that the cell pool is suitable for screening monoclonal cell lines.

2. The method according to claim 1, characterized in that, The cell statistics value is the percentage of cells, the statistical value requirement is a cell percentage requirement, and the method further includes: If the proportion of any one of the at least one abnormal cell types does not meet the corresponding cell proportion requirement, a new cell image is acquired. Return to the steps for identifying the image region corresponding to at least one abnormal cell type from the cell image.

3. The method according to claim 2, characterized in that, The cell image is an image obtained by acquiring images of a cell pool; the at least one abnormal cell type includes clumped cell types; When the percentage of any one of the at least one abnormal cell types does not meet the corresponding cell percentage requirement, acquiring a new cell image includes: If the proportion of cells of the clustered cell type does not meet the corresponding cell proportion requirement, a first treatment method is determined for the cell pool; the first treatment method includes a treatment method of breaking up the cell pool. Acquire new cell images; the new cell images are obtained by image acquisition of the cell pool after processing by the first processing method.

4. The method according to claim 3, characterized in that, The at least one abnormal cell type also includes poor-state cell types, where the cell membrane of cells belonging to the poor-state cell type has obvious ruptures, small bubbles, and small spiky appearances. The method further includes: If the percentage of cells in the clustered cell type meets the corresponding cell percentage requirement, determine whether the percentage of cells in the poor state cell type meets the corresponding cell percentage requirement. If the condition is not met, a new cell image is acquired; the new cell image is the image obtained by acquiring images of a new cell pool.

5. The method according to claim 4, characterized in that, The at least one abnormal cell type also includes a suspended cell type, and the method further includes: If the percentage of cells of the poor state cell type meets the corresponding cell percentage requirement, determine whether the percentage of cells of the suspended cell type meets the corresponding cell percentage requirement. If not, a second treatment method is determined for the cell pool; the second treatment method includes a method of letting the cell pool stand still. Acquire new cell images; the new cell images are images obtained by image acquisition of the cell pool after processing by the second processing method.

6. The method according to claim 1, characterized in that, The at least one abnormal cell type includes clustered cell types; the cell statistics value is the cell percentage, and the statistics value requirement is a cell percentage requirement; For an abnormal cell type comprising multiple cells in an image region, the number of corresponding cells is determined based on the sum of the areas of the corresponding image regions and the average area of ​​a single cell, including: The area of ​​each image region corresponding to the clustered cell type is statistically analyzed to obtain the total area, and the total area is used as the cell image area corresponding to the clustered cell type. Based on the cell image area and the average area of ​​a single cell corresponding to the clustered cell type, the number of cells corresponding to the clustered cell type is determined. The step of determining the cell statistics value corresponding to the abnormal cell type based on the cell count corresponding to the abnormal cell type includes: Based on the number of cells corresponding to the clustered cell type, the cell percentage of the clustered cell type is determined.

7. A cell image analysis device, characterized in that, The device includes: An image processing module is used to determine an image region corresponding to at least one abnormal cell type from a cell image; the at least one abnormal cell type corresponds to one or more image regions, and an image region includes one or more cells; The anomaly statistics module is used to count the number of cells contained in the image region corresponding to each abnormal cell type, obtain the cell count corresponding to the abnormal cell type, and determine the cell statistics value corresponding to the abnormal cell type based on the cell count corresponding to the abnormal cell type; wherein, for an abnormal cell type in which an image region contains only one cell, the number of corresponding image regions is counted to obtain the corresponding cell count; for an abnormal cell type in which an image region contains multiple cells, the corresponding cell count is determined based on the sum of the areas of the corresponding image regions and the average area of ​​a single cell; The image update module is used to acquire a new cell image when there are cell statistical values ​​that do not meet the corresponding statistical value requirements for the at least one abnormal cell type, and then return to the step of determining the image region corresponding to the at least one abnormal cell type from the cell image to continue execution; the new cell image is an image obtained by re-acquiring images of the processed cell pool; the processing methods for the cell pool include a processing method of scattering the cell pool and a processing method of leaving the cell pool still; the statistical confirmation module is used to determine the cell statistical value of the normal cell type based on the image region corresponding to the normal cell type in the cell image when the cell statistical values ​​corresponding to the at least one abnormal cell type all meet the corresponding statistical value requirements; The information recording module is used to record various cell statistical values ​​when the cell statistical values ​​of the normal cell type meet the corresponding statistical value requirements, and to determine that the cell pool is suitable for monoclonal cell line screening.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.

Images