Information processing device, cell processing device, method for determining seeding cell amount, and cell processing method

Abstract

To calculate an appropriate seeding volume to obtain the desired number of pluripotent stem cells.SOLUTION: An information processing device according to an embodiment includes an image acquisition unit, an estimation unit, and a calculation unit. The image acquisition unit acquires a bright-field image obtained by imaging a cell group containing multiple types of cells. The estimation unit estimates a specific cell content, which indicates an amount of a specific type of cell contained among the multiple types of cells, based on the bright-field image. The calculation unit calculates a specific cell seeding amount, which indicates a seeding amount of a specific type of cell to be used in a subsequent process, based on the specific cell content.SELECTED DRAWING: Figure 3

Description

[Technical Field]

[0001] The embodiments disclosed in the present specification and drawings relate to an information processing device, a cell processing device, a method for determining the amount of cells to be seeded, and a cell processing method. [Background technology]

[0002] With the advancement of regenerative medicine, a device for producing pluripotent stem cells from CD34+ cells has been proposed. Such a device is required to have a simpler and less expensive manufacturing process and to obtain a stable and constant amount of pluripotent stem cells. Therefore, a system that can accurately estimate the content of CD34+ cells to be seeded and adjust the amount of cells to be seeded is required. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Publication No. 2020-190935 Summary of the Invention [Problem to be solved by the invention]

[0004] One of the problems to be solved by the embodiments disclosed in this specification and the drawings is to calculate an appropriate seeding amount to obtain a desired number of pluripotent stem cells. However, the problems to be solved by the embodiments disclosed in this specification and the drawings are not limited to the above problem. Problems corresponding to the effects of each configuration shown in the embodiments described below can also be positioned as other problems. [Means for solving the problem]

[0005] An information processing device according to an embodiment includes an image acquisition unit, an estimation unit, and a calculation unit. The image acquisition unit acquires a bright-field image of a cell group containing multiple types of cells. The estimation unit estimates a specific cell content, which is related to the amount of a specific type of cell contained among the multiple types of cells, based on the bright-field image. The calculation unit calculates a specific cell seeding amount, which is related to the seeding amount of a specific type of cell to be used in a subsequent process, based on the specific cell content. [Brief explanation of the drawings]

[0006] [Figure 1] FIG. 1 is a diagram showing an example of the configuration of a cell processing apparatus according to the first embodiment. [Figure 2] FIG. 2 is a diagram schematically showing the flow of cell processing according to the first embodiment. [Figure 3] FIG. 3 is a diagram illustrating an example of the configuration of the information processing device according to the first embodiment. [Figure 4] FIG. 4 is a diagram schematically illustrating a method for generating a machine learning model and inputs and outputs according to the first embodiment. [Figure 5] FIG. 5 is a diagram schematically illustrating the flow of calculation of the performance index of the machine learning model according to the first embodiment. [Figure 6] FIG. 6 is a diagram showing a confusion matrix related to calculation of the performance index of the machine learning model according to the first embodiment. [Figure 7] FIG. 7 is a diagram schematically showing the flow of cell treatment of a specific type of cell according to the first embodiment. [Figure 8] FIG. 8 is a diagram showing a schematic flow of calculation of a specific cell seeding amount according to the first embodiment. [Figure 9] FIG. 9 is a diagram illustrating a method for calculating a specific cell seeding amount according to the first embodiment. [Figure 10] FIG. 10 is a diagram showing a display screen according to the first embodiment. [Figure 11] FIG. 11 is a diagram showing a schematic flow of cell treatment of a specific type of cell according to the second embodiment. [Figure 12] FIG. 12 is a diagram schematically illustrating input and output of a machine learning model according to a modified example. DETAILED DESCRIPTION OF THE INVENTION

[0007] (First embodiment) Hereinafter, embodiments of an information processing device, a cell processing device, a method for determining a seeding cell amount, and a cell processing method will be described in detail with reference to the drawings.

[0008] The cell processing device according to this embodiment processes a sample to produce pluripotent stem cells derived from a donor (subject) of the sample from tissue stem cells contained in the sample. The pluripotent stem cells according to this embodiment are pluripotent cells such as embryonic stem cells (ES cells, Embryonic Stem Cells), somatic cell-derived embryonic stem cells (ntES cells, Nuclear Transfer Embryonic Stem Cells), and induced pluripotent stem cells (iPS cells, Induced Pluripotent Stem Cells). In addition, induced pluripotent stem cells are also called induced pluripotent stem cells. Tissue stem cells are multipotent cells such as hematopoietic stem cells, neural stem cells, liver stem cells, kidney stem cells, and skin stem cells. The sample may be any tissue related to the donor, such as blood, bone marrow, or skin. The donor may be human or animal.

[0009] 1 is a diagram showing an example of the configuration of a cell processing device 1 according to this embodiment. The cell manufacturing device 1 includes an information processing device 10, an extraction device 20, an expansion culture device 30, a camera 40, a seeding device 50, a factor introduction device 60, a cell disposal device 70, a pluripotent stem cell culture device 80, and a colony recovery device 90. The cell processing device 1 according to the first embodiment can be implemented as long as it includes at least the information processing device 10, the camera 40, and the seeding device 50.

[0010] The extraction device 20 is a mechanical device that extracts a cell population containing multiple types of cells from a donor's sample. The cell population includes, for example, human peripheral blood mononuclear cells (PBMCs). The extraction device 20 may be, for example, a filter device or a centrifuge.

[0011] The expansion culture device 30 is a mechanical device that cultures a specific type of cells from among multiple types of cells. The specific type of cells is, for example, CD34-positive cells. The specific type of cells may also be other tissue stem cells. The expansion culture device 30 has, for example, a culture vessel and a dispensing mechanism. The dispensing mechanism aspirates a liquid containing the specific type of cells and dispenses it into the culture vessel. Various reagents, such as any medium, are also added to the culture vessel by the dispensing mechanism. The dispensing mechanism may be realized by a pump and a nozzle. The expansion culture device 30 may have multiple culture vessels. The multiple culture vessels may be the same size or different sizes.

[0012] The camera 40 captures a bright-field image of a cell group containing a specific type of cell. A bright-field image is an image in which the sample is placed between the illumination light source and the lens of the camera 40, making the sample appear dark against the background. The camera 40 may capture a bright-field image that allows counting of each cell contained in the cell group via a microscope or the like. However, the camera 40 may also capture a bright-field image that allows counting of each of the multiple types of cells contained in the cell group by zooming in at a high magnification, without using a microscope.

[0013] The seeding device 50 is a mechanical device that seeds a specific type of cells into a culture vessel different from the culture vessel used for expansion culture according to a specific cell seeding amount. The specific cell seeding amount is the amount of seeding solution containing the specific type of cells expanded to seed the specific type of cells, or the number of multiple types of cells contained in the cell population. The seeding solution is a liquid containing the specific type of cells. The seeding device 50 has, for example, a cell counter and a dispensing mechanism. The cell counter may use a cell counting method such as an electrical resistance method, flow cytometry, and / or counting based on bright-field images. The dispensing mechanism dispenses the seeding solution of the specific cell seeding amount into another culture vessel based on the cell counter. The dispensing mechanism appropriately adds various reagents, such as culture medium, to the culture vessel. The dispensing mechanism may be realized by a pump and a nozzle.

[0014] The factor introduction device 60 is a mechanical device that introduces an induction factor into a specific type of cell after expansion culture to establish pluripotent stem cells. The factor introduction device 60 has, for example, a dispensing mechanism. The dispensing mechanism dispenses a liquid containing the induction factor into a culture vessel containing a cell population. The dispensing mechanism may be realized by a pump and a nozzle. The induction factor, also known as a Yamanaka factor, initializes tissue stem cells. Specifically, it is an Oct family gene, a Klf family gene, a Myc family gene, or their respective gene products. As an example, Oct3 / 4 is used as an Oct family gene, Klf4 is used as an Klf family gene, and c-Myc or L-Myc is used as an Myc family gene. The induction factor may also be a Sox family gene or its gene product. Sox2 is used as an example of a Sox family gene. When an induction factor is introduced into a specific type of cell, the specific type of cell is initialized and pluripotent stem cells are established.

[0015] The cell disposal device 70 is a mechanical device that discards expanded and cultured cell populations when predetermined conditions are met. The cell disposal device 70 has, for example, a waste liquid storage container and a liquid delivery mechanism. The liquid delivery mechanism delivers the cell populations to be discarded to the waste liquid storage container. The liquid delivery mechanism may be realized by a pump and a nozzle. The waste liquid storage container is a container that stores liquid containing the discarded cells. Note that the cell disposal device 70 may also discard various liquids other than the cell populations. The cell disposal device 70 discards, for example, plasma, mononuclear cells, etc. separated by the extraction device 20, and / or culture media, reagents, etc. to be provided to the cell populations.

[0016] The pluripotent stem cell culture device 80 is a mechanical device that cultures pluripotent stem cells supplied from the factor introduction device 60. Specifically, the pluripotent stem cell culture device 80 has a culture vessel and a dispensing mechanism. The dispensing mechanism dispenses a liquid containing pluripotent stem cells into the culture vessel. The dispensing mechanism adds various reagents, such as culture medium, to the culture vessel as appropriate. The dispensing mechanism may be realized by a pump and a nozzle. The pluripotent stem cell culture device 80 has at least a first culture vessel. After a predetermined culture period has elapsed, multiple cell masses (colonies) consisting of pluripotent stem cells are produced in the culture vessel.

[0017] The colony recovery device 90 is a mechanical device that recovers pluripotent stem cell colonies cultured in the pluripotent stem cell culture device 80 from a culture vessel. Specifically, the colony recovery device 90 has a storage container and a dispensing mechanism. The dispensing mechanism detaches pluripotent stem cell colonies from the culture vessel and dispenses them into the storage container. The dispensing mechanism adds a liquid containing trypsin or phosphate-buffered saline (PBS) or the like to the culture vessel in order to detach the pluripotent stem cell colonies from the culture vessel. The dispensing mechanism is preferably realized by a pump and a nozzle.

[0018] The information processing device 10 is a computer that acquires a bright-field image, estimates a specific cell content, which is the amount of specific type of cells contained in a cell group based on the bright-field image, and calculates a specific cell seeding amount, which is the seeding amount of specific type of cells to be used in a subsequent process, based on the specific cell content. The specific cell content is, for example, the ratio of the number of specific type of cells to the number of multiple types of cells or the number of specific type of cells.

[0019] Figure 2 is a diagram showing an example of the flow of a pluripotent stem cell manufacturing process. As shown in Figure 2, an extraction device 20 extracts PBMCs from blood, which is a sample derived from a donor. Next, an expansion culture device 30 performs expansion culture to selectively proliferate CD34-positive cells contained in the extracted PBMCs. A factor introduction device 60 introduces an induction factor into the expanded CD34-positive cells, establishing pluripotent stem cells from the CD34-positive cells. A pluripotent stem cell culture device 80 cultures the established pluripotent stem cells for proliferation. A colony recovery device 90 recovers pluripotent stem cell colonies that have adhered to the culture vessel from the culture vessel into a storage vessel.

[0020] Fig. 3 is a diagram showing an example of the configuration of the information processing device 10 of Fig. 1. As shown in Fig. 3, the information processing device 10 has a processing circuit 11, a memory 12, a display 13, an input interface 14, and a communication device 15. The processing circuit 11, the memory 12, the display 13, the input interface 14, and the communication device 15 are connected to each other via a bus so as to be able to communicate with each other.

[0021] The processing circuit 11 has a processor. The processor executes a program related to this embodiment to realize at least one function among an image acquisition function 111, an estimation function 112, a calculation function 113, an allowable amount determination function 114, a discard determination function 115, a performance evaluation function 116, a display control function 117, and a training function 118. The program is stored in a computer-readable recording medium such as the memory 12 or a portable recording medium.

[0022] By implementing the image acquisition function 111, the processing circuitry 11 acquires various images. For example, the processing circuitry 11 acquires a bright-field image of a cell group including multiple types of cells. The bright-field image may be an image of an expanded and cultured cell group.

[0023] By implementing the estimation function 112, the processing circuitry 11 estimates the specific cell content, which is the amount of a specific type of cell among multiple types, based on the bright-field image acquired by the acquisition function 111. Alternatively, the processing circuitry 11 may estimate the specific cell content from the bright-field image using a machine learning model trained to input bright-field images of training data and output classification results for specific types of cells appearing in the bright-field image. The machine learning model may be one of supervised learning methods such as support vector machines, decision trees, ensemble learning, k-nearest neighbors, and logistic regression, or unsupervised learning methods such as clustering and principal component analysis. The machine learning model may be stored in memory 12.

[0024] By implementing the calculation function 113, the processing circuitry 11 calculates a specific cell seeding amount for a specific type of cell to be used in a subsequent process based on the specific cell content. For example, the subsequent process is culturing pluripotent stem cells from the seeded specific type of cells. The processing circuitry 11 also calculates the specific cell seeding amount based on a performance index of the machine learning model. The performance index is a statistical quantity based on the number of correct or incorrect classification results obtained by inputting a bright-field image into the machine learning model and comparing the classification results output with the labels associated with the bright-field image.

[0025] By implementing the allowable quantity determination function 114, the processing circuit 11 determines whether the seeding number is within the allowable seeding number. The allowable seeding number is a range of seeding numbers suitable for culturing pluripotent stem cells in a culture vessel in which a specific type of cell is seeded. The seeding number is the number of cells to be seeded. If the seeding number of a specific type of cell is greater than the allowable seeding number, excessive pluripotent stem cell colonies will be formed in the culture vessel, covering the culture vessel with each colony in an immature state. Furthermore, if the seeding number of a specific type of cell is less than the allowable seeding number, even if the pluripotent stem cell colonies mature, the required number will not be reached.

[0026] By implementing the discard determination function 115, the processing circuit 11 determines whether or not to discard the cell group. For example, when it is determined that the cell group is to be discarded, the processing circuit 11 transmits a signal to the cell discard device 70 via the communication device 15 to indicate that the cell group is to be discarded.

[0027] By implementing the performance evaluation function 116, the processing circuit 11 evaluates the performance index of the machine learning model in order to correct the specific cell seeding amount calculated by the calculation function 113.

[0028] By implementing the display control function 117, the processing circuitry 11 displays various information on the display 13. For example, the processing circuitry 11 displays the specific cell content estimated by the estimation function 112 and the specific cell seeding amount calculated by the calculation function 113. The processing circuitry 11 also displays information regarding the disposal of the cell population discarded by the discard determination function 115.

[0029] By implementing the training function 118, the processing circuitry 11 trains an untrained machine learning model for use in estimating the content of specific cells. For example, the processing circuitry 11 inputs bright-field images of training data and trains the untrained machine learning model to output classification results regarding specific types of cells that appear in the bright-field images.

[0030] The memory 12 is a storage device such as a RAM, a ROM, a hard disk drive (HDD), a solid state drive (SSD), or a semiconductor storage device that stores various types of information. For example, the storage device stores machine learning models and various programs used in the estimation function 112. As hardware, the memory 12 may be a drive device that reads and writes various types of information from and to a portable recording medium such as a CD-ROM drive, a DVD drive, or a flash memory.

[0031] The display 13 displays various information. The display 13 may be, for example, a CRT display, a liquid crystal display, an organic EL display, an LED display, a plasma display, or any other display known in the art. The display 13 may also be a projector.

[0032] The input interface 14 is an interface for inputting various commands from an operator. A keyboard, a mouse, various switches, etc. can be used as the input interface 14. The input interface 14 supplies output signals corresponding to the various commands to the processing circuit 11 via a bus.

[0033] The communication device 15 communicates data via wired or wireless connections (not shown) with the extraction device 20, expansion culture device 30, camera 40, seeding device 50, factor introduction device 60, cell disposal device 70, pluripotent stem cell culture device 80, and / or colony recovery device 90. For example, the communication device 15 receives bright-field images from the camera 40. The communication device 15 also transmits the specific cell seeding amount calculated by the calculation function 113 to the seeding device 50.

[0034] The machine learning model according to the first embodiment will be described in detail below.

[0035] FIG. 4 is a diagram showing a training method and input / output of a machine learning model. The upper part of FIG. 4 shows a training method for an untrained machine learning model 121a. The lower part of FIG. 4 shows the input / output of a trained machine learning model 121b. As shown in the lower part of FIG. 4, the machine learning model 121b receives a bright-field image 411 as input and outputs a classification result 123 regarding a specific type of cell appearing in the bright-field image 411. Specifically, the classification result 123 indicates whether or not the cell appearing in the bright-field image 411 is a specific type of cell. As an example, the classification result 123 is set to "1" if the subject of an input bright-field image 411 is a specific type of cell, and "0" if the subject is not a specific type of cell. As another example, the classification result 123 is set to the number of specific type of cells when the subject of an input bright-field image 411 includes multiple specific type of cells.

[0036] As an example, the machine learning model 121b classifies a single cell captured in a single bright-field image as to whether it is a specific type of cell. The machine learning model 121b classifies a cell as to whether it is a specific type of cell using morphological information and brightness information of the cell captured in the bright-field image 411 as feature quantities. Morphological information is information that represents the outer shape of the cell. Brightness information is information about pixel brightness that represents the thickness of the cell, etc. By using the machine learning model 121b to classify a specific type of cell, it is possible to reduce variability due to the procedure. Furthermore, by not requiring human intervention, it is possible to reduce costs.

[0037] The trained machine learning model may output multiple classification results in response to multiple input bright-field images. Furthermore, the machine learning model may output a specific cell content related to an input bright-field image. More specifically, the machine learning model calculates a classification result for an input bright-field image. The machine learning model outputs the specific cell content based on the calculated classification result. As an example, the machine learning model outputs the number of classification results classified as a specific type of cell as the specific cell content. In this case, the specific cell content indicates the number of cells of a specific type. As another example, the machine learning model outputs the number of classification results classified as a specific type of cell relative to the total number of classification results as the specific cell content. In this case, the specific cell content indicates the ratio of the number of cells of a specific type to the number of cells of multiple types.

[0038] As shown in the upper part of Figure 4, the processing circuitry 11 implements the training function 118 to train parameters that define the output for the input of the untrained machine learning model 121a using supervised learning based on a bright-field image 411a containing a specific type of cell as training data, so as to output a classification result 123 from the bright-field image 411a. The training data includes the bright-field image 411a and a label 412a that indicates whether the bright-field image 411a contains a specific type of cell. The label 412a is associated with the bright-field image 411a using a fluorescent image of the training data, which contains approximately the same cells as those in the bright-field image 411a, but in which the specific type of cell is fluorescently stained.

[0039] Alternatively, the parameters of the untrained machine learning model may be trained using unsupervised learning based on bright-field images containing specific types of cells as training data, in which case processing circuitry 11 trains the parameters of the untrained machine learning model to output specific cell content from bright-field images that do not have associated labels as training data.

[0040] 5 is a diagram illustrating a flow of acquiring the performance index 125 of the machine learning model 121b. As shown in Fig. 5, the processing circuitry 11, by implementing the performance evaluation function 116, calculates the performance index 125 based on a plurality of classification results 123 output by inputting a plurality of bright-field images 411b different from the training data as verification data to the machine learning model 121b, and a plurality of labels 412b respectively associated with the plurality of bright-field images 411b of the verification data.

[0041] For example, multiple classification results 123 are output when multiple bright-field images 411b are input as validation data to the machine learning model 121b and divided into four sets based on multiple labels 412b associated with the multiple bright-field images 411b. The first set is a set in which the bright-field images 411b associated with the labels 412b of specific types of cells are classified as specific types of cells. The second set is a set in which the bright-field images 411b associated with the labels 412b of specific types of cells are classified as cells other than the specific types of cells. The third set is a set in which the bright-field images 411b associated with the labels 412b of cells other than the specific types of cells are classified as specific types of cells. The fourth set is a set in which the bright-field images 411b associated with the labels 412b of cells other than the specific types of cells are classified as cells other than the specific types of cells. The processing circuit 11 calculates a performance index 125 by performing statistical analysis using the number of elements in each of the four sets.

[0042] The performance index is not limited to an index used to evaluate a trained machine learning model, and is obtained depending on a method for classifying a specific type of cell used in the estimation function 112.

[0043] FIG. 6 is a diagram showing a confusion matrix 251 related to the classification of a specific type of cell by a machine learning model. The rows of the confusion matrix 251 shown in FIG. 6 indicate whether or not a cell is a specific type of cell. Whether or not a cell is a specific type of cell may be determined based on the label 412b. The row with "1" indicates the number of cells labeled as a specific type of cell. The row with "0" indicates the number of cells labeled as not a specific type of cell. The columns of the confusion matrix 251 indicate whether or not the machine learning model has classified a cell as a specific type of cell. Whether or not a cell is classified as a specific type of cell may be determined based on the classification result. The "positive" column indicates the number of cells classified as a specific type of cell by the machine learning model. The "negative" column indicates the number of cells classified as not a specific type of cell by the machine learning model.

[0044] The confusion matrix 251 shown in FIG. 6 is divided into four sets: true positives (TP), false negatives (FN), false positives (FP), and true negatives (TN). The number of true positives corresponds to the number of elements in the first set. The number of false negatives corresponds to the number of elements in the second set. The number of false positives corresponds to the number of elements in the third set. The number of true negatives corresponds to the number of elements in the fourth set. The processing circuit 11 calculates a performance index using the four sets of the confusion matrix 251. Examples of the performance index include a positive predictive value (precision, accuracy), a negative predictive value, a true positive rate (recall), a false negative rate, a false positive rate, a true negative rate, accuracy (correctness), an F-measure, an error between a true value and an estimated value, and a deviation. As an example, the processing circuit 11 calculates the positive predictive value as the performance index by calculating TP / (TP+FP). As another example, processing circuitry 11 calculates the negative predictive value as the performance index by calculating TN / (TN+FN). Note that the performance index may include multiple statistics.

[0045] The cell treatment procedure shown in FIG. 2, from expansion of CD34-positive cells to introduction of an inducer, will be described in detail below.

[0046] 7 is a diagram showing the processing procedure for cell processing of a specific type of cell in the cell processing device 1 according to the first embodiment. As shown in FIG. 7, the processing circuit 11 acquires a bright-field image of a cell group including multiple types of cells by implementing the image acquisition function 111 (step S11). The cell group including multiple types of cells includes, for example, PBMCs. The bright-field image according to the first embodiment may be captured by the camera 40, with the cell group expanded and cultured in the expansion culture device 30 as the subject.

[0047] Note that the bright-field image is not limited to being acquired via the camera 40. The bright-field image may be acquired, for example, via the communication device 15 or via the memory 12. For example, the processing circuit 11 acquires a bright-field image showing a plurality of cells, and generates a bright-field image showing a single cell by applying an image analysis method such as object detection to each cell.

[0048] After step S11 is performed, the processing circuit 11, by implementing the estimation function 112, estimates the specific cell content, which is the amount of specific cell types contained, based on the bright-field image acquired in step S11 (step S12). As an example, as described above, the processing circuit 11 inputs multiple bright-field images into a machine learning model, aggregates the output classification results, and estimates the specific cell content. By non-invasively estimating the specific cell content using bright-field images, it is possible to reduce damage to specific cell types compared to using fluorescent images. Furthermore, by not providing a device for fluorescently staining specific cell types, the components of the cell processing device 1 can be simplified, which in turn makes it possible to produce pluripotent stem cells at low cost.

[0049] The machine learning model may input a bright-field image and output the specific cell content. In this case, the machine learning model may perform processing to output the specific cell content estimated using the classification result obtained by inputting the bright-field image.

[0050] After step S12 is performed, the processing circuit 11, by implementing the calculation function 113, calculates a specific cell seeding amount for the specific type of cells to be used in a subsequent process based on the specific cell content estimated in step S12 (step S13). The subsequent process is assumed to be, for example, seeding into a culture vessel of the pluripotent stem cell culture device 80. The seeding liquid is, for example, a cell suspension prepared from a cell population and a culture medium.

[0051] More specifically, the processing circuitry 11 calculates the specific cell seeding amount based on the specific cell content and the performance index of the machine learning model.

[0052] Fig. 8 is a diagram illustrating the flow of a process for calculating the specific cell seeding amount 131. As shown in Fig. 8, the processing circuit 11 calculates the specific cell seeding amount 131 based on the specific cell content 129 and the performance index 125. By calculating the specific cell seeding amount 131 based on the performance index 125 in addition to the specific cell content 129, it is possible to reduce errors resulting from the machine learning model.

[0053] Below, we explain three methods for calculating the specific cell seeding amount using formulas based on the correlation between the ratio of CD34+ cells to the total number of seeded cells and the colony formation efficiency of iPS cells. The colony formation efficiency is the ratio obtained by dividing the number of colonies (described below) by the number of multiple types of cells seeded.

[0054] As a first calculation method, the specific cell seeding amount based on the bright field image is expressed by the following formula (1).

[0055]

number

[0056] Equation (1) calculates the specific cell seeding amount based on the number of pluripotent stem cell colonies, the specific cell content, and the establishment efficiency of pluripotent stem cells. X is the number of pluripotent stem cell colonies. The number of pluripotent stem cell colonies is the number of pluripotent stem cell colonies to be cultured in the cell processing device 1. The number of pluripotent stem cell colonies may be a predetermined value linked to a protocol or the like, or a desired value may be input by the user according to user instructions. Y is the specific cell content estimated by the processing circuit 11 based on the bright-field image. The specific cell content may be the ratio of the number of specific type of cells to the number of multiple types of cells being expanded and cultured. a is the establishment efficiency of pluripotent stem cells. The establishment efficiency of pluripotent stem cells is the ratio of the number of pluripotent stem cells obtained to the number of specific type of cells as a result of introducing an induction factor into the specific type of cells. The establishment efficiency may be determined experimentally, or a known value from literature or the like may be used. N is the specific cell seeding amount as the number of cells of multiple types. By using formula (1), it is possible to easily calculate the specific cell seeding amount according to the number of colonies of pluripotent stem cells to be cultured.

[0057] As a second calculation method, the specific cell seeding amount based on the bright-field image and a performance index including one statistical quantity is expressed by the following formula (2).

[0058]

number

[0059] Formula (2) calculates the specific cell seeding volume based on the number of pluripotent stem cell colonies, the specific cell content, the pluripotent stem cell establishment efficiency, and the positive predictive value. X, Y, and a are the same as in Formula (1). PPV is the positive predictive value. The positive predictive value is one of the performance indicators.

[0060] By using equation (2), it is possible to calculate the specific cell seeding amount corrected by the performance index of the machine learning model.

[0061] As a third calculation method, the specific cell seeding amount based on the bright-field image and the performance index including multiple statistics is expressed by the following formula (3).

[0062]

number

[0063] Equation (3) calculates the specific cell seeding volume based on the number of pluripotent stem cell colonies, the specific cell content, the pluripotent stem cell establishment efficiency, the positive predictive value, and the negative predictive value. X, Y, a, and PPV are the same as in equation (2). PNV is the negative predictive value. The negative predictive value is one of the performance indicators. By using equation (3), correction is made using multiple statistics, making it possible to calculate the specific cell seeding volume with higher accuracy than using equation (2).

[0064] When the specific cell seeding amount is calculated as the amount of seeding solution containing the cell population, the specific cell seeding amount can be calculated by dividing N in formulas (1) to (3) by the cell concentration of the cell population in the sample. Specifically, this is expressed by the following formula (4).

[0065]

number

[0066] N is the number of cells of multiple types to be seeded. For N in formula (4), it is preferable to use N calculated using formulas (1) to (3). V is the specific cell seeding amount calculated as the amount of seeding liquid containing the cell population. c is the cell concentration of the cell population. The cell concentration of the cell population is the number of cells of multiple types relative to the amount of culture liquid, such as the medium, in which the cell population is cultured. The cell concentration may be calculated using a cell counter or based on an acquired bright-field image. By calculating the specific cell seeding amount as the amount of seeding liquid, it is possible to simply seed the cells without having to count the number of cells of a specific type when seeding.

[0067] In addition, the processing circuit 11 may calculate the specific cell seeding amount based on the specific cell content, the number of colonies of pluripotent stem cells to be cultured, and a first allowable seeding number based on the size of the first culture vessel into which the specific type of cells will be seeded.

[0068] FIG. 9 is a diagram showing an example of calculating a specific cell seeding amount 131 based on the specific cell content 129, the number of pluripotent stem cell colonies to be cultured, and the first allowable seeding number. The vertical axis represents the seeded cell number, which is the number of specific type of cells to be seeded. As shown in FIG. 9, the first allowable seeding number is a range of the number of specific type of cells, with the maximum allowable seeding number as the upper limit and the minimum allowable seeding number as the lower limit. For example, the maximum allowable seeding number is determined based on the number of specific type of cells that form excessive colonies on the surface of the culture vessel while the pluripotent stem cell colonies remain immature. The minimum allowable seeding number is determined based on the number of specific type of cells that form fewer pluripotent stem cell colonies than the target number for culture.

[0069] The specific cell seeding amount 131 is calculated based on the specific cell content 129 and a performance index. As an example, as shown in FIG. 9 , the performance index is used as an error bar 171 of the specific cell content 129. More specifically, the error bar 171 extending in the direction of increasing the number of seeded cells for the specific cell content 129 may be determined based on a positive correlation with the false positive value. The error bar 171 extending in the direction of decreasing the number of seeded cells for the specific cell content 129 may be determined based on a positive correlation with the false negative value. The specific cell seeding amount 131 is calculated as the number of seeded cells such that the specific cell content 129 including the error bar 171 is included in the first allowable seeding number. The error bar 171 may be determined using a performance index including one statistical quantity. For example, a performance index including one statistical quantity such as accuracy or precision for the specific cell content 129 may be used to determine the error bar 171. In this case, the error bar 171 is determined to have approximately the same length in the direction of increasing and decreasing the number of seeded cells. By calculating the specific cell seeding amount 131 based on the first allowable seeding number, it is possible to calculate the specific cell seeding amount 131 suitable for the size of the first culture vessel.

[0070] It is also possible to apply the allowable seeding number shown in Fig. 9 to the specific cell content 129, which is the number of specific type of cells calculated by formulas (1) to (3). Also, the specific cell seeding amount 131, which is the amount of seeding solution containing the specific type of cells, may be calculated by applying formula (4) to the specific cell seeding amount 131, which is the number of specific type of cells calculated by the method shown in Fig. 9.

[0071] When step S13 is performed, the processing circuit 11, by implementing the display control function 117, displays the specific cell content estimated in step S12 and / or the specific cell seeding amount calculated in step S13 on the display 13 (step S14).

[0072] FIG. 10 is a diagram showing an example of a display screen I1 showing the specific cell content and the specific cell seeding amount displayed in step S14. The display screen I1 is displayed on the display 13. As shown in FIG. 10, the display screen I1 displays an ID, which is identification information of the sample provider or the sample. The display screen I1 also displays display fields I11, I12, and I13. The display field I1 displays the specific cell content estimated in step S12. The display field I12 displays the specific cell seeding amount calculated in step S13 without using the performance index. The display field I13 displays the specific cell seeding amount calculated in step S13 using the performance index. By displaying the specific cell content or the specific cell seeding amount on the display screen I1, it is possible to notify the user of the output of the information processing device 10. Furthermore, by displaying the specific cell seeding amount calculated without using the performance index and the specific cell seeding amount corrected using the performance index together on the display screen I1, the user can compare whether or not the performance index has been corrected.

[0073] The display field I11 may display the specific cell content as the number of cells of a specific type. The display fields I12 and I13 may display the specific cell seeding amount as the number of cells of a specific type. Furthermore, the display fields I12 and I13 showing the specific cell seeding amount on the display screen I1 in FIG. 10 may be displayed selectably. For example, the specific cell seeding amount is determined to a value selected according to a user's instruction. This allows the user to adjust the specific cell seeding amount. Furthermore, the information displayed on the display screen I1 is not limited to the above. For example, information about the sample before expansion culture may be displayed.

[0074] After step S14 is performed, the seeding device 50 seeds the specific type of cells in the specific cell seeding amount calculated in step S13 from the expansion-cultured cell population (step S15). The seeding device 50, for example, sends a seeding solution containing the specific type of cells in the specific cell seeding amount from the expansion culture device 30 to the culture vessel. By seeding the specific type of cells according to the specific cell seeding amount, it is possible to seed an appropriate number of specific type of cells to obtain the required number of pluripotent stem cell colonies. Note that when the specific cell seeding amount is calculated as the seeding solution amount, the seeding device 50 may send the seeding solution in the specific cell seeding amount from the expansion culture device 30 to the culture vessel.

[0075] After step S15 is performed, the cell processing device 1 processes the specific type of cells seeded in step S15 (step S16). As an example, the cell processing device 1 introduces an induction factor into the seeded specific type of cells via the factor introduction device 60 to establish pluripotent stem cells. For example, a viral vector method or an electroporation method is used to introduce the gene. Note that the method for introducing the gene is not limited to the above methods. The cell processing device 1 can introduce the gene using any method that has little variation in establishment efficiency.

[0076] When step S16 is performed, the cell processing of the specific type of cells according to the first embodiment is completed.

[0077] 7 is an example of a procedure for processing specific types of cells by the cell processing device 1, and various deletions, additions, and / or modifications are possible without departing from the spirit and scope of the invention. For example, the introduction of the induction factor in step S16 may be performed before the seeding of the specific types of cells, in other words, before step S15. In step S15, the cell processing device 1 may culture the established pluripotent stem cells via the pluripotent stem cell culture device 80. Furthermore, the cell processing device 1 may discard the cell population via the cell discard device 70, or may recover colonies of the cultured pluripotent stem cells via the colony recovery device 90, depending on the discard determination.

[0078] Furthermore, the specific cell content, which is the amount of differentiated pluripotent stem cells contained among multiple types of cells, may be estimated. As an example, the processing circuit 11 may calculate the specific cell seeding amount, which is the amount of differentiated pluripotent stem cells to be passaged, by implementing the calculation function 113. This makes it possible to estimate the proportion of undifferentiated pluripotent stem cells among induced-to-differentiate pluripotent stem cells, the number of undifferentiated pluripotent stem cells, and / or the number of differentiated pluripotent stem cells.

[0079] According to the first embodiment, by non-invasively estimating the content of specific cells, it is possible to reduce the loss of specific cell types and thereby control the number of specific cell types as live cells to be seeded. Furthermore, by using a performance index that evaluates the accuracy of estimation using bright-field images, it is possible to seed an appropriate amount of specific cell types to obtain the required number of pluripotent stem cell colonies.

[0080] (Second embodiment) The cell processing device 1 according to the first embodiment is treated as seeding a specific type of cells into one culture vessel. The cell processing device according to the second embodiment seeds a specific type of cells into a culture vessel of a size corresponding to the specific cell content. The cell processing device according to the second embodiment will be described below. However, components having the same functions as those in the first embodiment are given the same reference numerals and will be described only when necessary.

[0081] In the second embodiment, a pluripotent stem cell culture device 80 has, in addition to a first culture vessel, a second culture vessel that is smaller in size than the first culture vessel.

[0082] 11 is a diagram showing the procedure for cell processing of a specific type of cell in the cell processing device 1 according to the second embodiment. Steps S21 to S23 shown in FIG. 11 are the same as steps S11 to S13 shown in FIG. 7, respectively.

[0083] After step S23 is performed, the processing circuit 11 determines whether the specific cell content is within the first allowable seeding number by implementing the allowable amount determination function 114 (step S24). For example, the processing circuit 11 determines whether the specific cell content 129 and error bars 171 shown in Fig. 9 are within the first allowable range. More specifically, if the difference between the maximum value of the specific cell content including the error bars and the maximum seeding number of the first allowable seeding number is negative and the difference between the minimum value of the specific cell content including the error bars and the minimum seeding number of the first allowable seeding number is positive, it is determined that the specific cell content is within the first allowable seeding number.

[0084] If it is determined in step S24 that the cell seeding number is included in the first allowable seeding number (step S24: YES), the processing circuitry 11, by implementing the calculation function 113, calculates the total amount of the cell population as the specific cell seeding amount (step S25). Note that the processing circuitry 11 may calculate the specific cell seeding amount as an amount smaller than the cell population but within the range included in the first allowable seeding number. In this case, the specific cell seeding amount may be calculated in accordance with a user's instruction as an amount smaller than the cell population but within the range included in the first allowable seeding number. For example, by implementing the display control function 117, the processing circuitry 11 displays the first allowable seeding number that can be set by the user before calculating the specific cell seeding amount. The processing circuitry 11 calculates the specific cell seeding amount in accordance with a user's instruction via the input interface 14.

[0085] If it is determined in step S24 that the specific cell content is not included in the first allowable seeding number (step S24: NO), the processing circuit 11 determines whether the specific cell content exceeds the first allowable seeding number by implementing the allowable amount determination function 114 (step S26). For example, if the difference between the maximum specific cell content including the error bar and the maximum seeding number of the first allowable seeding number is positive, it is determined that the specific cell content exceeds the first allowable seeding number.

[0086] If it is determined in step S26 that the seeding number exceeds the first allowable seeding number (step S26: YES), the processing circuit 11, by implementing the calculation function 113, calculates a specific cell seeding amount that is less than the total amount of the cell group so that it falls within the first allowable seeding number (step S27).

[0087] After step S25 or step S27 is performed, the seeding device 50 seeds the specific type of cells according to the specific cell seeding amount into the first culture vessel (step S28). Note that the processing circuit 11 may determine to discard the cell population that was not seeded into the first culture vessel by implementing the discard determination function 115. The cell discard device 70 may discard the cell population that was not seeded into the first culture vessel based on the determination to discard.

[0088] If it is determined in step S26 that the specific cell content does not exceed the first allowable seeding number (step S26: NO), the processing circuit 11 determines whether the specific cell content is included in the second allowable seeding number by implementing the allowable amount determination function 114 (step S29). The second allowable seeding number is a second allowable seeding number corresponding to the second culture vessel. As an example, the second allowable seeding number is set to a smaller maximum allowable seeding number than the first allowable seeding number. The determination may be performed for the second allowable seeding number using the same process as in step S24.

[0089] If it is determined in step S29 that the seeding number is included in the second allowable seeding number (step S29: YES), the processing circuitry 11 calculates the total amount of the cell population as the specific cell seeding amount by implementing the calculation function 113 (step S210). Note that the processing circuitry 11 may calculate the specific cell seeding amount as an amount that is smaller than the cell population but is included in the first allowable seeding number.

[0090] If it is determined in step S29 that the number of cells is not included in the second allowable seeding number (step S29: NO), the processing circuitry 11 determines whether or not the number of cells exceeds the second allowable seeding number by implementing the allowable amount determination function 114 (step S211). As an example, the condition for determining whether or not to discard the cell populations in the cell processing device 1 in the second embodiment is whether or not the number of cells falls below the second allowable seeding number. By implementing the discard determination function 115, the processing circuitry 11 determines to discard the cell populations if the number of cells falls below the second allowable seeding number, in other words, if the number of cells does not exceed the second allowable amount (step S211: NO). Note that the processing circuitry 11 may make the determination to discard the cell populations based on the volume of the culture medium containing the cell populations or a user instruction.

[0091] If it is determined in step S211 that the seeding number exceeds the second allowable seeding number (step S211: YES), the processing circuit 11, by implementing the calculation function 113, calculates a specific cell seeding amount that is less than the total amount of the cell group so that it is included in the second allowable seeding number (step S212).

[0092] After step S210 or step S212 is performed, the seeding device 50 seeds the specific type of cells according to the specific cell seeding amount into the second culture vessel (step S213). This makes it possible to improve the efficiency of producing pluripotent stem cells from a cell population that does not meet the first allowable seeding number. Note that the processing circuit 11 may determine to discard the cell population that was not seeded into the second culture vessel by implementing the discard determination function 115. The cell discard device 70 may discard the cell population that was not seeded into the second culture vessel based on the determination to discard.

[0093] If it is determined in step S211 that the second allowable seeding number is not exceeded (step S211: NO), the cell discard device 70 discards the cell populations (step S214). The cell discard device 70 discards the cell populations, for example, by sending the cell populations from the expansion culture device 30 to a waste liquid storage container of the cell discard device 70. By discarding cell populations that do not meet the conditions suitable for producing pluripotent stem cells, it is possible to improve the efficiency of pluripotent stem cell production.

[0094] When step S214 is performed, the processing circuit 11, by implementing the display control function 117, displays information regarding the disposal of the cell groups on the display 13 (step S215). The information regarding the disposal of the cell groups is a display screen including, for example, the fact that the cell groups have been discarded, the reason for discarding the cell groups, the date and time when the cell groups were discarded, and information that allows the discarded cell groups to be identified. Specifically, the fact that the cell groups have been discarded may be a string such as "The cell groups have been discarded." The reason for discarding the cell groups may be a string such as "Because the second allowable seeding number is not met." The information that allows the discarded cell groups to be identified may be the sample ID, the name of the sample provider, or the like. By displaying the information regarding the disposal of the cell groups on the display 13, it is possible to notify the user of the information regarding the disposal of the cell groups.

[0095] It is also possible to display information regarding the disposal of the cell population before discarding the cell population. In this case, the information regarding the disposal of the cell population may have a selectable display field for the user to decide whether or not to discard the cell population according to their instructions. The display field for deciding whether to discard the cell population may include text such as "Discard the cell population." The display field for deciding whether to continue culturing the cell population may include text such as "Continue culturing the cell population." The decision to discard the cell population may be made according to the user's instructions.

[0096] When step S215 is performed, the cell processing of the specific type of cells according to the second embodiment is completed.

[0097] The processing procedure for processing specific types of cells in the cell processing device 1 shown in FIG. 11 is an example, and various deletions, additions, and / or modifications are possible without departing from the spirit of the invention. For example, the order of steps S24 and S25 and steps S26 and S27 may be interchanged. Furthermore, the order of steps S29 and S210 and steps S211 and S212 may be interchanged. Furthermore, the allowable amount may be determined for only the first culture vessel to determine whether it is within, exceeds, or falls below the allowable seeding number. In this case, steps S29 to S213 shown in FIG. 11 are not performed, and if the first allowable seeding number is not exceeded (step S26: NO), steps S214 and subsequent steps may be performed.

[0098] The second embodiment is also applicable when the pluripotent stem cell culture device 80 has a culture vessel smaller than the second culture vessel. In this case, steps corresponding to steps S29 to S213 can be added for the third culture vessel from "Does not exceed the second allowable seeding number (step S211: NO)" in Figure 11. This makes it possible to seed a specific type of cells at an appropriate seeding amount in three or more culture vessels of different sizes.

[0099] Furthermore, in step S27, if the specific cell content is sufficient to seed multiple first culture vessels, a specific cell seeding amount is calculated so that multiple first culture vessels can be seeded. As an example, if the specific cell content including the error bars is approximately twice or more the minimum allowable seeding number, a specific cell seeding amount is calculated so that multiple first culture vessels can be seeded. In this case, in step S28, the seeding device 50 seeds multiple first culture vessels with the specific cell seeding amount of the specific type of cells. If the maximum allowable seeding number is exceeded, seeding multiple first culture vessels can improve the efficiency of producing pluripotent stem cell colonies and ultimately reduce the number of cells discarded.

[0100] According to the second embodiment, it is possible to calculate an appropriate seeding amount of specific cells depending on the size of the culture vessel and / or the number of culture vessels, and seed the cells.

[0101] Furthermore, in steps subsequent to step S23 in FIG. 11, the processing circuitry 11 may display the specific cell content and / or specific cell seeding amount on the display 13, similarly to the first embodiment.

[0102] (Variation) The machine learning model may also receive input of information other than the bright-field image and the performance index. FIG. 12 is another diagram related to the training method and input / output of the machine learning model. As shown in FIG. 12, the trained machine learning model 121c receives as input a bright-field image 411 and information 413 including donor information, sample information, and / or expansion culture information, and outputs the specific cell content. For example, the donor information includes the donor's gender, height, weight, medical history, etc. The sample information includes the content rate of a specific type of cell before expansion culture, the proportion of blood cells, and a bright-field image of the sample before expansion culture. The expansion culture conditions include the culture time, the medium used, etc. The untrained machine learning model receives as input a bright-field image containing a specific type of cell, a label indicating whether the cell in the bright-field image is a specific type of cell, donor information, sample information, and expansion culture conditions as training data, and trains parameters to output the specific cell content.

[0103] According to a variant example, the processing circuit 11 can estimate the specific cell content using a machine learning model 121c that is further based on donor information, sample information and / or expansion culture conditions, thereby estimating the specific cell content that reflects information before expansion culture.

[0104] The modified example may be applied to either the first embodiment or the second embodiment.

[0105] According to at least one of the embodiments described above, an appropriate seeding amount can be calculated to obtain a desired number of pluripotent stem cells.

[0106] The term "processor" used in the above description refers to a circuit such as a CPU, a GPU, an application specific integrated circuit (ASIC), a programmable logic device (e.g., a simple programmable logic device (SPLD), a complex programmable logic device (CPLD), and a field programmable gate array (FPGA)). A processor realizes its function by reading and executing a program stored in a memory circuit. Note that instead of storing a program in a memory circuit, the program may be directly embedded in the processor circuit. In this case, the processor realizes its function by reading and executing the program embedded in the circuit. On the other hand, if the processor is, for example, an ASIC, the function is directly embedded in the processor circuit as a logic circuit instead of storing the program in a memory circuit. Note that each processor in this embodiment is not limited to being configured as a single circuit for each processor, but may be configured as a single processor by combining multiple independent circuits to realize its function. Furthermore, multiple components in FIGS. 1 and 3 may be integrated into a single processor to realize its function.

[0107] Although several embodiments have been described, these embodiments are presented as examples and are not intended to limit the scope of the invention. These embodiments can be implemented in various other forms, and various omissions, substitutions, modifications, and combinations of embodiments can be made without departing from the spirit of the invention. These embodiments and their modifications are included within the scope and spirit of the invention, as well as within the scope of the invention and its equivalents as defined in the claims. [Explanation of symbols]

[0108] 1. Cell processing equipment 10...Information processing equipment 11...Processing circuit 12...Memory 13...Display 14...input interface 15...Communication equipment 20...Extraction device 30...Expansion culture device 40...camera 50...Seeding device 60...Factor introduction device 70...Cell disposal device 80...Pluripotent stem cell culture device 90...Colony recovery device 111...Image acquisition function 112... Estimation function 113...Calculation function 114 ...Tolerance determination function 115 ...Discard decision function 116...Performance evaluation function 117...Display control function 118...Training function

Claims

1. an image acquisition unit that acquires a bright-field image of a cell group including multiple types of cells; an estimation unit that estimates a specific cell content related to the amount of a specific type of cell contained among the plurality of types based on the bright-field image; a calculation unit that calculates a specific cell seeding amount regarding the seeding amount of the specific type of cells to be used in a subsequent process based on the specific cell content; An information processing device comprising:

2. the content of specific cells is the ratio of the number of the specific type of cells to the number of the plurality of types of cells or the number of the specific type of cells, the specific cell seeding amount is the amount of seeding solution containing the specific type of cells or the number of the multiple types of cells contained in the cell population, the cell population comprises human peripheral blood mononuclear cells; The information processing device according to claim 1 , wherein the specific type of cells is a CD34-positive cell.

3. The information processing device according to claim 1 , wherein the estimation unit estimates the specific cell content from the bright-field image using a machine learning model trained to input a bright-field image of training data and output a classification result of the specific type of cells appearing in the bright-field image.

4. The information processing device according to claim 3 , wherein the calculation unit calculates the specific cell seeding amount further based on a performance index of the machine learning model.

5. 5. The information processing device according to claim 4, wherein the performance index is a positive predictive value, a negative predictive value, a true positive rate, a false negative rate, a precision, and / or a deviation of the machine learning model based on a classification result output when a bright-field image different from the training data is input as validation data and the validation data.

6. 3. The information processing device according to claim 2, wherein the calculation unit calculates the specific cell seeding amount based further on a first allowable seeding number based on the number of colonies of pluripotent stem cells to be cultured and the size of a first culture vessel into which the specific type of cells is seeded.

7. further comprising an allowable amount determination unit that determines whether the specific cell content is included in the first allowable seeding number; The information processing device according to claim 6 , wherein the calculation unit calculates the total amount of the cell population as the specific cell seeding amount when it is determined that the specific cell content is included in the first allowable seeding number.

8. 8. The information processing device according to claim 7, wherein, when it is determined that the specific cell content exceeds the first allowable seeding number, the calculation unit calculates the specific cell seeding amount to be less than the total amount of the cell group so that the specific cell content falls within the first allowable seeding number.

9. the calculation unit calculates the total amount of the cell population as the specific cell seeding amount when the specific cell content is less than the first allowable seeding number and is included in a second allowable seeding number based on a size of a second culture vessel that is smaller than the first culture vessel; 8. The information processing device according to claim 7, wherein, when the content of the specific cells is less than the first allowable seeding number and the content of the specific cells is greater than the second allowable seeding number, the specific cell seeding amount is calculated to be less than the total amount of the cell group so that the content falls within the second allowable seeding number.

10. a discard determination unit that determines whether or not to discard the cell group; The information processing device according to claim 1 , further comprising a display control unit that displays information regarding the disposal of the specific type of cells.

11. 3. The information processing device according to claim 2, wherein the calculation unit calculates the specific cell seeding amount based further on donor information about a donor who provided the cell group as a sample, sample information about a cell amount contained in the sample, and / or expansion culture information about the cell group.

12. an acquisition unit for acquiring a bright-field image of a cell group including a plurality of types of cells; an estimation unit that estimates a specific cell content related to the amount of a specific type of cell contained among the plurality of types by analyzing the bright field image; a calculation unit that calculates a specific cell seeding amount regarding the seeding amount of the specific type of cells to be used in a subsequent process based on the specific cell content; a seeding unit that seeds the specific type of cells from the cell group in a seeding amount corresponding to the specific cell seeding amount; a cell processing unit for processing the specific type of cells; A cell processing device comprising:

13. the cell processing unit cultures pluripotent stem cells from the seeded specific type of cells; The cell processing device according to claim 12 , wherein the bright-field image is a subject of the expanded and cultured cell group.

14. Further provided is a culture unit that cultures the seeded specific type of cells in a first culture vessel, The cell processing device according to claim 13 , wherein the seeding unit seeds the specific type of cells according to the specific cell seeding amount into the first culture vessel when the specific cell content is included in or exceeds a first allowable seeding number based on the size of the first culture vessel.

15. a culture unit having a plurality of culture vessels including a first culture vessel for culturing the seeded cells of the specific type and a second culture vessel smaller than the first culture vessel; 14. The cell processing device according to claim 13, wherein the seeding unit seeds the specific type of cells according to the specific cell seeding amount into the second culture vessel when the specific cell seeding amount is below a first allowable seeding number range based on a size of the first culture vessel and the specific cell seeding amount is within a second allowable seeding number range based on a size of the second culture vessel.

16. a discard determination unit that determines whether or not to discard the cell group; a cell disposal unit that discards the cell population when it is determined that the cell population should be discarded; The cell processing apparatus according to claim 12 , further comprising a display control unit that displays information regarding the disposal of the cell population.

17. a culture unit having a plurality of first culture vessels for culturing the seeded cells of the specific type; The cell processing device according to claim 13 , wherein the seeding unit seeds the specific type of cells according to the specific cell seeding amount into each of the plurality of first culture vessels when the specific cell seeding amount exceeds a first allowable seeding number based on the size of the first culture vessel.

18. The cell processing device according to claim 12 , further comprising a display control unit that displays the specific cell content and / or the specific cell seeding amount.

19. The computer A bright-field image of a cell group containing multiple types of cells is acquired. estimating a specific cell content relating to the amount of a specific type of cell among the plurality of types based on the bright-field image; Calculating a specific cell seeding amount for the seeding amount of the specific type of cells to be used in a subsequent step based on the specific cell content. A method for determining the amount of cells to be seeded, comprising:

20. A bright-field image of a cell group containing multiple types of cells is acquired. By analyzing the bright-field image, a specific cell content relating to the amount of a specific type of cell contained among the plurality of types is estimated, and a specific cell seeding amount relating to the seeding amount of the specific type of cells to be used in a subsequent process is calculated based on the specific cell content; seeding the specific type of cells from the cell group in a seeding amount corresponding to the specific cell seeding amount; treating said specific type of cells; A cell processing method comprising:

Images