JP2011229411A - Cell valuation model production apparatus, cell evaluation device, incubator, program, and culture method - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide a cell evaluation model production device which can obtain the remaining number of cell divisions by a relatively simple method on the evaluation of cells.SOLUTION: The cell evaluation model production device includes an input portion for inputting a plurality of images obtained by picturing a plurality of cells cultured in the same culture container at different times and information showing the remaining number of the divisions of the cells, a characteristic quantity calculation portion for outputting characteristic quantities expressing the morphological characteristics of the cells in the images, and a remaining number calculation model building portion for building a calculation model for calculating the remaining numbers for the cells, wherein the remaining number calculation model building portion builds the calculation model by a multiple regression analysis using the characteristic quantities as variables.

Description

  The present invention relates to a cell evaluation model generation device, a cell evaluation device, an incubator, a program, and a culture method.

  The technology for evaluating the culture state of cells has become a basic technology in a wide range of fields including advanced medical fields such as regenerative medicine and drug screening. For example, in the field of regenerative medicine, there are processes for growing and differentiating cells in vitro. And in said process, in order to manage the success or failure of cell differentiation, the canceration of a cell, or the presence or absence of infection, it is indispensable to evaluate the culture state of a cell accurately. As an example, Patent Document 1 discloses a cancer cell evaluation method using a transcription factor as a marker.

JP 2007-195533 A

  However, the above-described conventional technique is very complicated because an experiment for confirming the expression of a transcription factor in each cell to be evaluated is required. Therefore, it is still required to accurately evaluate cells by a relatively simple method.

  By the way, for example, when evaluating cells, it is necessary to perform cell culture and to secure the number of cells used for the experiment. Unlike the case of using established cancer cells for experiments, the number of cell divisions is limited when primary cultured cells are used for experiments. Therefore, when culturing primary cultured cells, the cells may not be appropriately cultured unless the remaining number of divisions of the cells is sufficient.

  The present invention has been made in view of such circumstances, and the object thereof is a cell evaluation model generation device, a cell evaluation device, an incubator, which can obtain the remaining number of times a cell is divided by a relatively simple technique. It is to provide a program and a culture method.

  The present invention has been made to solve the above-described problems, and a plurality of images obtained by imaging a plurality of cells cultured in the same culture vessel at different times and the remaining number of times the cells are divided. An input unit to which information indicating the morphological characteristics of the cells in the image is input, a feature amount calculation unit that outputs a morphological feature of the cell in the image, the feature amount corresponding to each image and the remaining number of times A remaining number calculation model building unit that builds a calculation model for calculating the remaining number of times for the cell based on the information indicating the remaining number calculation model building unit A cell evaluation model generation device characterized in that the calculation model is constructed by multiple regression analysis.

  Further, according to the present invention, the feature amount calculation unit outputs a frequency distribution indicating a feature amount indicating a morphological feature of the cell and a number of the cells having the feature amount in each of the images. The cell evaluation model generation device according to the above, further comprising: a calculation unit, wherein the remaining number calculation model construction unit constructs the calculation model using the frequency distribution output from the frequency distribution calculation unit It is.

  The present invention also includes a temperature-controlled room capable of storing a culture container for culturing cells and maintaining the interior in a predetermined environmental condition, and an imaging device for capturing an image of the cell contained in the culture container in the temperature-controlled room And a cell evaluation model generation device or a cell evaluation device as described above.

  In addition, the present invention is a program that causes a computer to function as the cell evaluation model generation device or the cell evaluation device described above.

  The present invention is also a cell culturing method characterized by changing the culture conditions of the cells cultured in the culture vessel based on the remaining number of times calculated by the cell evaluation apparatus described above.

  According to this invention, the remaining number of times that a cell divides can be obtained by a relatively simple technique.

It is a block diagram which shows the outline | summary of the incubator by 1st Embodiment of this invention. It is a front view of the incubator of FIG. It is a top view of the incubator of FIG. It is a figure which shows an example of the number of remaining doubling. It is a figure which shows the change of the number of remaining doubling with respect to a procedure. It is a flowchart which shows an example of the observation operation | movement by the incubator of FIG. It is a flowchart which shows an example of a process in case CPU42 of the incubator by 1st Embodiment produces | generates a calculation model. It is a figure which shows the outline | summary of each feature-value used by this embodiment. It is a figure which shows the outline | summary of ANN. It is a figure which shows the outline | summary of FNN. It is a figure which shows the sigmoid function in FNN. It is a flowchart which shows an example of the process in case CPU42 of the incubator by 1st Embodiment evaluates a cell. It is a block diagram which shows the outline | summary of the incubator by 2nd Embodiment of this invention. It is a flowchart which shows an example of a process in case CPU42 of the incubator by 2nd Embodiment produces | generates a calculation model. It is a histogram which shows the example of the time-dependent change of a feature-value. It is a figure which shows the microscope image which observed the time-lapse observation of the normal cell group. It is a figure which shows the microscope image which observed the time-lapse observation of the cell group which mixed the cancer cell in the normal cell. It is a flowchart which shows an example of the process in case CPU42 of the incubator by 2nd Embodiment evaluates a cell. It is a figure which shows the culture state example of a myoblast. It is a figure which shows the histogram which shows a time-dependent change of "Shape Factor" at the time of culture | cultivation of a myoblast. It is a figure which shows the histogram which shows a time-dependent change of "Shape Factor" at the time of culture | cultivation of a myoblast. It is a figure which shows the graph which shows the prediction result of each sample in the 1st prediction model of an Example. It is a figure which shows the graph which shows the prediction result of each sample in the 2nd prediction model of an Example. It is a figure explaining the relationship between the estimated number of remaining doublings and the number of remaining doublings actually measured. It is a flowchart which shows the culture | cultivation method of the cell using the cell evaluation apparatus by this embodiment.

<First Embodiment>
Embodiments of the present invention will be described below with reference to the drawings. FIG. 1 is a block diagram showing an overview of an incubator including a cell evaluation apparatus according to the first embodiment. 2 and 3 are a front view and a plan view of the incubator according to the first embodiment.

  The incubator 11 of the first embodiment has an upper casing 12 and a lower casing 13. In the assembled state of the incubator 11, the upper casing 12 is placed on the lower casing 13. Note that the internal space between the upper casing 12 and the lower casing 13 is vertically divided by a base plate 14.

  First, an outline of the configuration of the upper casing 12 will be described. A constant temperature chamber 15 for culturing cells is formed inside the upper casing 12. The temperature-controlled room 15 includes a temperature adjusting device 15a and a humidity adjusting device 15b, and the temperature-controlled room 15 is maintained in an environment suitable for cell culture (for example, an atmosphere having a temperature of 37 ° C. and a humidity of 90%) ( 2 and 3, the illustration of the temperature adjusting device 15a and the humidity adjusting device 15b is omitted.

  A large door 16, a middle door 17 and a small door 18 are arranged on the front surface of the temperature-controlled room 15. The large door 16 covers the front surfaces of the upper casing 12 and the lower casing 13. The middle door 17 covers the front surface of the upper casing 12 and isolates the environment between the temperature-controlled room 15 and the outside when the large door 16 is opened. The small door 18 is a door for carrying in and out a culture vessel 19 for culturing cells, and is attached to the middle door 17. It is possible to suppress environmental changes in the temperature-controlled room 15 by carrying the culture container 19 in and out of the small door 18. The large door 16, the middle door 17, and the small door 18 are maintained airtight by the packings P1, P2, and P3, respectively.

  In the temperature-controlled room 15, a stocker 21, an observation unit 22, a container transfer device 23, and a transfer table 24 are arranged. Here, the conveyance stand 24 is disposed in front of the small door 18, and carries the culture container 19 in and out of the small door 18.

  The stocker 21 is disposed on the left side of the temperature-controlled room 15 when viewed from the front surface of the upper casing 12 (the lower side in FIG. 3). The stocker 21 has a plurality of shelves, and each shelf of the stocker 21 can store a plurality of culture vessels 19. Each culture container 19 contains cells to be cultured together with a medium.

  The observation unit 22 is disposed on the right side of the temperature-controlled room 15 when viewed from the front surface of the upper casing 12. The observation unit 22 can execute time-lapse observation of cells in the culture vessel 19.

  Here, the observation unit 22 is disposed by being fitted into the opening of the base plate 14 of the upper casing 12. The observation unit 22 includes a sample stage 31, a stand arm 32 protruding above the sample stage 31, and a main body portion 33 containing a microscopic optical system for phase difference observation and an imaging device (34). The sample stage 31 and the stand arm 32 are disposed in the temperature-controlled room 15, while the main body portion 33 is accommodated in the lower casing 13.

  The sample stage 31 is made of a translucent material, and the culture vessel 19 can be placed thereon. The sample stage 31 is configured to be movable in the horizontal direction, and the position of the culture vessel 19 placed on the upper surface can be adjusted. The stand arm 32 includes an LED light source 35. And the imaging device 34 can acquire the microscope image of a cell by imaging the cell of the culture container 19 permeate | transmitted and illuminated by the stand arm 32 from the upper side of the sample stand 31 via a microscopic optical system.

  The container transport device 23 is disposed in the center of the temperature-controlled room 15 when viewed from the front surface of the upper casing 12. The container transport device 23 delivers the culture container 19 between the stocker 21, the sample table 31 of the observation unit 22, and the transport table 24.

  As shown in FIG. 3, the container transport device 23 includes a vertical robot 34 having an articulated arm, a rotary stage 35, a mini stage 36, and an arm unit 37. The rotary stage 35 is attached to the tip of the vertical robot 34 via a rotary shaft 35a so as to be capable of rotating 180 ° in the horizontal direction. Therefore, the rotary stage 35 can make the arm portions 37 face the stocker 21, the sample table 31, and the transport table 24.

  The mini stage 36 is attached to the rotation stage 35 so as to be slidable in the horizontal direction. An arm part 37 that holds the culture vessel 19 is attached to the mini stage 36.

  Next, the outline of the configuration of the lower casing 13 will be described. Inside the lower casing 13, the main body portion 33 of the observation unit 22 and the control device 41 of the incubator 11 are accommodated.

  The control device 41 is connected to the temperature adjustment device 15a, the humidity adjustment device 15b, the observation unit 22, and the container transport device 23, respectively. The control device 41 comprehensively controls each part of the incubator 11 according to a predetermined program.

  As an example, the control device 41 controls the temperature adjustment device 15a and the humidity adjustment device 15b, respectively, to maintain the inside of the temperature-controlled room 15 at a predetermined environmental condition. The control device 41 controls the observation unit 22 and the container transport device 23 based on a predetermined observation schedule, and automatically executes the observation sequence of the culture vessel 19. Furthermore, the control device 41 executes a culture state evaluation process for evaluating the culture state of the cells based on the image acquired in the observation sequence.

<Relationship between number of remaining doublings and procedure>
Here, the relationship between the number of remaining doublings and the procedure will be described with reference to FIGS. 4 and 5. FIG. 4 is a graph showing the relationship between the number of passages and the number of remaining cells that divide (number of cells remaining doubling). In FIG. 4, the horizontal axis represents the number of passages, and the vertical axis represents the average number (number of cells / flask (culture vessel 19)) of the remaining number of cells dividing (number of cells remaining doubling).

  As shown in FIG. 4, as the number of passages increases to P3, P4... P9, extrinsic stress due to the incubation time and passage technique accumulates, so the remaining number of times that the cells divide (cells The average number of remaining doublings) gradually decreases. Then, when a cell is subjected to a certain degree of deterioration stress for a certain period of time (in this case, the number of passages corresponding to P10 and repetition of the procedure), the average number of remaining divisions (number of cells remaining doubling) Decreases rapidly. Therefore, if the culture time exceeds a certain level or the stress of the passage technique exceeds the capacity of the cell, even if this cell is cultured, the average number of times that the cell can subsequently divide is reduced. Therefore, the number of cells obtained by culture is reduced.

  So, for example, if the user is culturing this cell to obtain the desired number of cells, if the user is cultivating without knowing what degradation stress (elapsed time or extrinsic stress of the procedure) the user is The desired number of cells will not be obtained. Although the elapsed time is one measure as the deterioration stress, if the extrinsic stress of the procedure is large, a desired number of cells cannot be obtained even if the elapsed time is short. Even if the extrinsic stress of the procedure is small, if the elapsed time is too long, the desired number of cells cannot be obtained. Since how much this affects cell degradation depends on the type and state of the cells, it is not usually possible to clarify the main factors of stress.

  And if the cell shape matches the shape of a cell with a certain remaining doubling number in the sample data, what kind of cell culture is needed to obtain the desired number of cells? It is possible to estimate whether the cell has the remaining number of doublings, and it is conceivable to determine whether or not to culture the target cell according to the estimation result. For example, if the cell morphological information approximates the shape of a cell with a large number of remaining doublings, it is estimated that the number of remaining doublings will be large, and the cells are cultured, and approximated to cells with a small number of remaining doublings. In the case of the cell shape information, it is conceivable that the remaining doubling number is estimated to be small and it is determined that the cell is not cultured. If it is determined that the cells are not to be cultured, an operational process that approaches the desired number of cells, such as newly culturing other cells or supplementing nutrients by adding additional factors, is performed. It is also possible to do this.

  Thus, when culturing cells, the user can obtain a desired number of cells by determining whether to cultivate cells based on the number of remaining doublings.

Next, the relationship between the procedure and the passage number will be described with reference to FIG.
FIG. 5 shows the case where the cells were freeze-stocked once and then reincubated and cultured normally, when cultured as usual (with or without freezing), and with trypsin treatment at the time of passage. The number of cells over time (h: time) for each of the cases where there was a defect and the cells were damaged, and when trypsin treatment was performed as usual (in the case of enzyme damage and normal procedure) A graph showing changes in cells / field of view is shown for each cell that has passed a predetermined passage number. Here, the graph about the cell of passage number P4, P7, and P10 is shown as a cell which passed the predetermined passage number.

In the case of “with freezing”, the cell is placed in −80 ° C. by the usual method of stocking the cell, and then thawed again and cultured, that is, the cell is damaged. Say. The case of “no freezing” refers to a state in which cells are cultured without damaging cells, as compared to the case of “with freezing”.
The case of “with enzyme damage” refers to the case where the primary cultured cells are treated with trypsin, and the treatment time and the amount of trypsin are not appropriate and the cells are damaged. The case of “no enzyme damage” refers to a state where the trypsin treatment is appropriately performed and the cells are cultured without damaging the cells. Thus, since passage of primary cultured cells requires skill in trypsin treatment, if the technique is immature, it will cause extra damage to the cells.

  The upper left graph of FIG. 5 is a graph in the case of no freezing and in the case of no enzyme damage. The lower left graph in FIG. 5 is a graph in the case of freezing and in the absence of enzyme damage. The graph in the upper right of FIG. 5 is a graph when there is no freezing and when there is enzyme damage. The lower right graph in FIG. 5 is a graph in the case of freezing and in the case of enzyme damage.

  From the graph shown in FIG. 5, in the case of the graph at the upper left of FIG. 5, the lower left of FIG. 5, and the upper right of FIG. 5, the number of cells with respect to time (h: time) (cells / field of view) Even if the passage number is different from P4, P7, and P10, there is no significant difference. In either case, the number of cells (cells / field of view) increases with time (h: time).

  In the lower right graph of FIG. 5, the change in the number of cells (cells / field of view) with respect to time (h: time) is shown in the upper left of FIG. 5 when the passage numbers are P4 and P7. As in the case of the lower left in FIG. 5 and the upper right in FIG. 5, there is no significant difference.

  However, in the lower right graph of FIG. 5, the change in the number of cells (cells / field of view) over time (h: time) decreases rapidly when the passage number is P10. ing. Specifically, in the case of the lower right graph of FIG. 5, the number of cells (cells / field of view) increases with the passage of time (h: time), but the rate of increase is shown in the upper left of FIG. In the case of the lower left in FIG. 5, the upper right in FIG. 5, and the lower right in FIG. 5, the number of passages is reduced as compared with the cases of P4 and P7.

  That is, in this case, only in the case of freezing and in the case of enzyme damage, when the passage number exceeds a certain passage number (in this case, the passage number is P10), the increase rate of the cells decreases. . And when only one of freezing or enzyme damage is “Yes”, or when both are “No”, even if the passage number is P10, it is a case of freezing, and In contrast to the case where there is enzyme damage, the rate of increase in cells does not decrease.

  That is, in the case of freezing and the cell having passage number P10 with enzyme damage, as shown in FIG. 4, it was contrary to expectation as compared with the condition with only freezing and the condition with only enzyme damage. Since the remaining number of doublings is estimated to be very small and a great deal of damage has been accumulated in the cells, it is considered that good cell growth cannot be obtained, and it can be determined that the cells are not cultured.

  In this way, even if the culture time and the number of passages are the same, the remaining doubling number of the cell is greatly influenced by the combination of the stress of technical skill and time and the stress of passage, and the rate of increase of cells May be unpredictable.

  Therefore, when cultivating cells, when deciding whether to cultivate cells, it is more appropriate to determine whether to cultivate cells based not only on the number of remaining doublings but also on the procedure. It can be determined whether or not the cells are cultured. Thereby, the user can obtain a desired number of cells.

  In addition, if there is enzyme damage, even if a sufficient number of cells can be cultured, the cultured cells have enzyme damage. Therefore, the cultured cells may not be suitable for cell evaluation. There is. Therefore, as a technique, it is conceivable that cells cultured when there is enzyme damage are not used for the subsequent cell evaluation process.

  Returning to the description of FIG. 1, the configuration of the control device 41 will be described. The control device 41 includes a CPU 42 and a storage unit 43.

  The storage unit 43 is configured by a hard disk, a nonvolatile storage medium such as a flash memory, or the like. The storage unit 43 stores management data related to each culture vessel 19 stored in the stocker 21 and data of a microscope image captured by the imaging device. Further, the storage unit 43 stores a program executed by the CPU 42.

  The management data includes (a) index data indicating individual culture containers 19, (b) the storage position of the culture container 19 in the stocker 21, and (c) the type and shape of the culture container 19 (well plate, (Dish, flask, etc.), (d) type of cells cultured in culture vessel 19, (e) observation schedule of culture vessel 19, (f) imaging conditions during time-lapse observation (magnification of objective lens, observation in vessel) Point, etc.). In addition, for the culture container 19 that can simultaneously culture cells in a plurality of small containers such as a well plate, management data is generated for each small container.

  The CPU 42 includes an input unit 4201, a feature amount calculation unit 4202, an image reading unit 4203, a technique evaluation calculation model construction unit (determination reference creation unit) 4211, a technique evaluation unit (image determination unit) 4212, and a cell evaluation calculation. A model construction unit (remaining frequency calculation model construction unit) 4221 and a cell evaluation unit (remaining frequency calculation unit) 4222 are provided. The CPU 42 is, for example, a processor that executes various arithmetic processes of the control device 41. Note that the CPU 42 executes an input unit 4201, a feature amount calculation unit 4202, an image reading unit 4203, a technique evaluation calculation model construction unit 4211, a technique evaluation unit 4212, and a cell evaluation calculation model construction unit 4221 by executing the program. And may function as the cell evaluation unit 4222, respectively.

  The input unit 4201 reads from the storage unit 43 a plurality of images in which a plurality of cells cultured in the culture container are imaged in time series. In addition, when the input unit 4201 reads an image from the storage unit 43, the input unit 4201 also reads (or inputs) information about a cell captured in the image. The information about the cell is information to be learned, for example, information indicating a technique corresponding to each image or information indicating the number of remaining doublings corresponding to each image.

  That is, the input unit 4201 receives an image in which a plurality of cells cultured in a culture vessel are imaged and information indicating a procedure when the cells are cultured. The input unit 4201 indicates a plurality of images obtained by imaging a plurality of cells cultured in the same culture container at different times, and the remaining number of times that the cells are divided (the number of remaining doublings). Information is entered.

  The “information indicating the procedure” is, for example, identification information predetermined for each of the four procedures described with reference to FIG. Note that the “information indicating a procedure” is not limited to the four procedures described with reference to FIG. 5, and the conditions for identification may be arbitrary, and the number of procedures to be identified is also arbitrary. May be.

  The feature amount calculation unit 4202 outputs the feature amount of the cell shown in the image from the image read by the input unit 4201 or the image reading unit 4203. Further, the feature amount calculation unit 4202 obtains a plurality of different feature amounts indicating a plurality of morphological features of different cells for each cell included in the image, and outputs the obtained feature amount.

  The image reading unit 4203 reads an image in which cells cultured in the culture container are imaged. That is, the image reading unit 4203 reads an image in which cells to be evaluated are captured. The image reading unit 4203 is input with an image of a cell to be evaluated, in which a plurality of cells cultured in the culture container are captured in time series.

  For example, an image in which cells to be evaluated are captured may be stored in the storage unit 43 in advance, and the image reading unit 4203 may read an image in which cells to be evaluated are captured from the storage unit 43. Further, the image reading unit 4203 may read an image in which a cell to be evaluated is captured through a communication network such as the Internet.

  The procedure evaluation calculation model construction unit 4211 creates a criterion for the cell feature amount based on the cell evaluation data and the cell feature amount captured in the image. The “evaluation data of cells and feature quantities of cells shown in the image” are feature quantities output from the feature quantity computation unit 4202. Further, the “evaluation data of the cell imaged in the image” is information regarding the procedure performed on the cell. Further, the “determination criterion for the feature amount of the cell” is a determination criterion for determining a procedure when the cell is cultured, and is a criterion for the feature amount of the cell. In addition, the reference may be a reference for each feature quantity or a reference for a feature quantity in which a plurality of feature quantities are combined.

  For example, the technique evaluation calculation model construction unit 4211 constructs a technique evaluation calculation model for evaluating a technique when cells are cultured based on the feature amount of the cell in the image and information indicating the technique. The “feature amount of cells in the image” is a feature amount output from the feature amount calculation unit 4202. The “information indicating a technique” refers to “information indicating a technique” input to the input unit 4201. The “procedure evaluation calculation model” is a calculation model for determining each procedure shown in FIG. 5 as an example.

  The technique evaluation unit 4212 constructs a cell evaluation calculation model for evaluating cells from the feature amount of the cell copied in the newly input image based on the determination criterion created by the technique evaluation calculation model construction unit 4211. Therefore, it is determined whether it is applicable as usage data.

  For example, the technique evaluation unit 4212 inputs the feature amount obtained by the feature amount calculation unit 4202 to the calculation model constructed by the procedure evaluation calculation model construction unit 4211, thereby converting the image inputted to the image reading unit 4203. The procedure is evaluated when the imaged cells (cells to be evaluated) are cultured.

  The cell evaluation calculation model construction unit 4221 constructs a cell evaluation calculation model for performing cell evaluation based on the morphological feature amount obtained by the feature amount calculation unit 4202. In addition, the cell evaluation calculation model construction unit 4221 uses the image determined to be applicable by the technique evaluation unit 4212 and performs cell evaluation based on the morphological feature amount obtained by the feature amount calculation unit 4202. Build a calculation model. The “morphological feature amount obtained by the feature amount calculation unit 4202 using the image determined to be applicable by the technique evaluation unit 4212” refers to the image determined to be applicable by the technique evaluation unit 4212. The morphological feature amount obtained by the feature amount calculation unit 4202.

  For example, the cell evaluation calculation model construction unit 4221 calculates a cell evaluation calculation model for calculating the number of remaining times (the number of remaining doublings) for the cells based on the feature amount corresponding to each image and the information indicating the number of remaining times. To construct. Further, as the evaluation value, various evaluation values may be output in addition to the remaining number of possible cell divisions. In the present embodiment, the “feature amount corresponding to each image” is a feature amount output from the feature amount calculation unit 4202. The “information indicating the remaining number of times” is “information indicating the remaining number of times that the cell divides” input to the input unit 4201.

  As an example, the cell evaluation calculation model construction unit 4221 obtains a cell evaluation calculation model by supervised learning, for example. In addition, this cell evaluation calculation model outputs the result of having evaluated the characteristic in a cell as evaluation information. This “characteristic in the cell” is, for example, a sign or index indicating the type or state of the cell, or the number of remaining doublings.

  In addition, the cell evaluation calculation model construction unit 4221 displays the result of the technique evaluated by the technique evaluation unit 4212 among the feature amounts obtained by the feature amount calculation unit 4202 for the image input to the image reading unit 4203. The cell evaluation calculation model is constructed based on the feature amount determined to be appropriate when constructing the cell evaluation calculation model for evaluating the cells captured in the image read by the image reading unit 4203.

  Whether or not the result of the technique evaluated by the technique evaluation unit 4212 is appropriate when constructing a cell evaluation calculation model for evaluating cells captured in the image read by the image reading unit 4203. Is executed by determining whether or not the procedure is a predetermined procedure as a result of the procedure evaluated by the procedure evaluation unit 4212.

  As an example, when the result of the technique evaluated by the technique evaluation unit 4212 is a technique with enzyme damage as described with reference to FIG. 5 (in the upper right and lower right in FIG. 5), the cell The evaluation calculation model construction unit 4221 determines that the image cultured by this technique is not appropriate when constructing the cell evaluation calculation model.

  When the result of the technique evaluated by the technique evaluation unit 4212 is a technique that does not cause enzyme damage as described with reference to FIG. 5 (in the case of the upper left and lower left in FIG. 5), the cell evaluation calculation model The construction unit 4221 determines that the image cultured by this technique is appropriate when constructing the cell evaluation calculation model.

  The cell evaluation unit 4222 calculates the evaluation information by inputting the feature amount output from the feature amount calculation unit 4202 to the cell evaluation calculation model constructed by the cell evaluation calculation model construction unit 4221, and the calculated evaluation information Is output. Note that the evaluation information calculated and output by the cell evaluation unit 4222 is information indicating the number of remaining doublings of cells to be evaluated, for example. In this way, the cell evaluation unit 4222 evaluates the cells of the image read by the image reading unit 4203.

  The technique evaluation device includes the input unit 4201, the feature amount calculation unit 4202, and the technique evaluation calculation model construction unit 4211 described above. The technique evaluation device may further include an image reading unit 4203 and a technique evaluation unit 4212. The cell evaluation model construction device includes the technique evaluation device and the cell evaluation calculation model construction unit 4221.

  The cell evaluation calculation model device includes the input unit 4201, the feature amount calculation unit 4202, and the technique evaluation calculation model construction unit 4211 described above.

  The cell evaluation apparatus includes the above-described image reading unit 4203, feature amount calculation unit 4202, and cell evaluation unit 4222. The cell evaluation apparatus may further include an input unit 4201 and a technique evaluation calculation model construction unit 4211. Further, this cell evaluation apparatus may be configured to include a cell evaluation calculation model construction unit 4221 and a cell evaluation unit 4222.

Note that the cell evaluation unit 4222 uses the feature amount calculation unit 4202 that is also used to acquire the feature amount of the cell used when the cell evaluation calculation model construction unit 4221 constructs the cell evaluation computation model. Have gained. By doing in this way, it is the apparatus structure which can perform both cell evaluation calculation model construction and cell evaluation with few structures.
However, the configuration for outputting the feature amount of the cell (feature amount calculation unit 4202) may be configured differently in correspondence with the cell evaluation calculation model construction unit 4221 and the cell evaluation unit 4222. For example, a cell evaluation calculation model device including the cell evaluation calculation model construction unit 4221 includes a feature amount calculation unit 4202, and a cell evaluation device including the cell evaluation unit 4222 is similar to the feature amount calculation unit 4202. The number-of-remaining-number calculating feature amount calculation unit having the above-described configuration may be provided.
Further, the input unit 4201 and the image reading unit 4203 may be configured integrally.

<Example of Observation Operation in First Embodiment>
Next, an example of the observation operation in the incubator 11 in the first embodiment will be described with reference to the flowchart of FIG. FIG. 6 shows an operation example in which the culture container 19 carried into the temperature-controlled room 15 is time-lapse observed according to a registered observation schedule.

  Step S101: The CPU 42 compares the observation schedule of the management data in the storage unit 43 with the current date and time to determine whether or not the observation start time of the culture vessel 19 has come. When it is the observation start time (YES side), the CPU 42 shifts the process to S102. On the other hand, when it is not the observation time of the culture vessel 19 (NO side), the CPU 42 waits until the next observation schedule time.

  Step S102: The CPU 42 instructs the container transport device 23 to transport the culture container 19 corresponding to the observation schedule. Then, the container transport device 23 carries the instructed culture container 19 out of the stocker 21 and places it on the sample stage 31 of the observation unit 22. Note that, when the culture vessel 19 is placed on the sample stage 31, an entire observation image of the culture vessel 19 is captured by a bird view camera (not shown) built in the stand arm 32.

  Step S103: The CPU 42 instructs the observation unit 22 to take a microscopic image of the cell. The observation unit 22 turns on the LED light source 35 to illuminate the culture vessel 19 and drives the imaging device 34 to take a microscopic image of the cells in the culture vessel 19.

  At this time, the imaging device 34 captures a microscopic image based on the imaging conditions specified by the user (magnification of the objective lens, observation point in the container) based on the management data stored in the storage unit 43. For example, when observing a plurality of points in the culture container 19, the observation unit 22 sequentially adjusts the position of the culture container 19 by driving the sample stage 31 and picks up a microscope image at each point. The microscopic image data acquired in S103 is read by the control device 41 and recorded in the storage unit 43 under the control of the CPU.

  Step S104: The CPU 42 instructs the container transport device 23 to transport the culture container 19 after the observation schedule is completed. Then, the container transport device 23 transports the designated culture container 19 from the sample stage 31 of the observation unit 22 to a predetermined storage position of the stocker 21. Thereafter, the CPU 42 ends the observation sequence and returns the process to S101.

  With the explanation using the flowchart of FIG. 6, time-series image data observed by the incubator 11 is stored in the storage unit 43.

<Culture state evaluation process in the first embodiment>
Next, an example in which the control device 41 constructs a technique evaluation calculation model and a cell evaluation calculation model using the image data stored in the storage unit 43 by the process of FIG. 6 described above will be described with reference to FIG.

  Here, as an example, a case will be described in which the control device 41 estimates the number of remaining doublings for cells in the cultured cells of the culture container 19 using a plurality of microscopic images obtained by time-lapse observation of the culture container 19. To do.

  Here, in the process of FIG. 6, the time-lapse observation of the culture vessel 19 is performed every 0.33 days until the 13.67th day, with the first 0.33 days (8 hours) after the start of the culture. It is assumed that it is In addition, here, it is assumed that the plurality of culture vessels 19 are each observed in time lapse, and the microscopic image of the sample is stored in the storage unit 43. Note that the control device 41 treats a plurality of microscope images obtained by photographing a plurality of points (for example, five-point observation or the whole culture container 19) of the same culture container 19 in the same observation time period as an image for one time-lapse observation. It may be.

  It is assumed that the technique has been known for the cells observed in the time lapse. For example, a procedure may be determined in advance for cells that have been time-lapse observed in the culture vessel 19.

  Further, it is assumed that the number of remaining doublings is known for the cells observed in the time lapse. For example, the number of remaining doublings may be examined by an arbitrary experiment on cells that have been time-lapse observed in the culture vessel 19. This arbitrary experiment may be an experiment performed after the time-lapse observation according to the present embodiment is completed.

  Then, it is assumed that an image of a cell for each culture vessel 19 and information indicating a procedure are input to the control device 41 for each culture vessel 19. Further, it is assumed that an image of a cell for each culture container 19 and information indicating the number of remaining doublings of the cells cultured in the culture container 19 are input to the control device 41 for each culture container 19. The information indicating the procedure and the information indicating the number of remaining doublings of the cells may be stored in the storage unit 43 for each culture vessel 19 in association with the time-series image data observed by the incubator 11.

  Step S <b> 201: The CPU 42 reads from the storage unit 43 microscopic image data of a sample prepared in advance. Note that the CPU 42 in step S201 acquires information indicating a technique corresponding to each image and information indicating the number of remaining doublings at this time.

  Step S202: The CPU 42 designates an image to be processed from the above-described sample microscopic image (step S201). Here, it is assumed that the CPU 42 in step S202 sequentially designates all the sample microscope images prepared in advance as processing targets.

  Step S203: The feature amount calculation unit 4202 of the CPU 42 extracts cells included in the processing target microscope image (step S202). For example, when a cell is imaged with a phase-contrast microscope, a halo appears in the vicinity of a region with a large phase difference change such as a cell wall. Therefore, the feature amount calculation unit 4202 extracts a halo corresponding to the cell wall by a known edge extraction method, and estimates a closed space surrounded by edges by a contour tracking process as a cell. Thereby, individual cells can be extracted from the above-mentioned microscopic image.

  Step S204: The feature amount calculation unit 4202 of the CPU 42 obtains, from the image, a plurality of different feature amounts indicating a plurality of morphological features of different cells for each cell extracted from the image in step S203. In step S204, the feature amount calculation unit 4202 of the CPU 42 obtains 16 types of feature amounts for each of the cells extracted from the image in step S203 as the plurality of different feature amounts described above.

  Step S205: The feature value calculation unit 4202 of the CPU 42 records the 16 types of feature values (step S204) of each cell in the storage unit 43 for the microscope image to be processed (step S202).

  Step S206: The CPU 42 determines whether or not all the microscopic images have been processed (a state in which the feature amount of each cell has been acquired from the microscopic images of all the samples). If the above requirement is satisfied (YES side), the CPU 42 shifts the process to step S209. On the other hand, if the above requirement is not satisfied (NO side), the CPU 42 returns to step S202 and repeats the above operation with another unprocessed microscope image as a processing target.

  Step S209: The procedure evaluation calculation model construction unit 4211 of the CPU 42 evaluates a procedure when cells are cultured based on the feature amount of the cell in the image read from the storage unit 43 and information indicating the procedure. Build an evaluation calculation model.

  Step S210: The technique evaluation calculation model construction unit 4211 of the CPU 42 obtains information on the technique evaluation calculation model constructed and obtained in step S209 (information indicating each index used in the calculation formula, coefficient value corresponding to each index in the calculation formula Are recorded in the storage unit 43.

Step S211: The technique evaluation unit 4212 calculates the feature quantity obtained by the feature quantity calculation unit 4202 from the technique evaluation calculation model read from the storage unit 43 (or the calculation constructed by the technique evaluation calculation model construction unit 4211 in step S209). By inputting into the model), a technique when cells (cells to be evaluated) captured in the image input into the image reading unit 4203 are cultured is evaluated. At this time, the technique evaluation unit 4212 first evaluates the technique for each cell and calculates the average of the techniques for each culture vessel 19.
Next, the technique evaluation unit 4212 may evaluate the technique for each culture container 19 based on the calculated result. Next, the cell evaluation calculation model construction unit 4221 extracts an image for constructing the cell evaluation calculation model based on the evaluation of the technique. This extracted image may be an image extracted for each culture vessel 19.

  Step S212: The cell evaluation calculation model construction unit 4221 constructs a cell evaluation calculation model based on the image extracted in step S211 and the feature amount corresponding to the image (feature amount read from the storage unit 43).

  Step S213: The cell evaluation calculation model construction unit 4221 of the CPU 42 obtains information on the cell evaluation calculation model constructed and obtained in Step S212 (information indicating each index used in the calculation formula, coefficient value corresponding to each index in the calculation formula Are recorded in the storage unit 43. Above, description of FIG. 7 is complete | finished.

  In the description of FIG. 7, the case where the control device 41 constructs a technique evaluation calculation model and a cell evaluation calculation model has been described. However, the control device 41 does not have to construct a technique evaluation calculation model in advance. Good. For example, when a pre-constructed technique evaluation calculation model is stored in the storage unit 43, the control device 41 omits steps S209 and S210 in FIG. 7 and reconstructs the technique evaluation calculation model. A cell evaluation calculation model can be constructed without doing so. Moreover, when constructing only the technique evaluation calculation model, the control device 41 may end the process in step S210.

<Step S204 in FIG. 7: Details of Processing by Feature Quantity Calculation Unit 4202 of CPU 42>
Next, with reference to FIG. 8, the processing by the feature amount calculation unit 4202 of the CPU 42 in step S204 of FIG. 7 will be described in detail. The feature amount calculation unit 4202 obtains the following 16 types of feature amounts for each cell.

  Total area (see (a) of FIG. 8) “Total area” is a value indicating the area of the cell of interest. For example, the feature amount calculation unit 4202 can obtain the value of “Total area” based on the number of pixels in the cell area of interest.

  Hole area (see FIG. 8B) “Hole area” is a value indicating the area of Hole in the cell of interest. Here, Hole refers to a portion where the brightness of the image in the cell is equal to or greater than a threshold value due to contrast (a portion that is close to white in phase difference observation). For example, stained lysosomes of intracellular organelles are detected as Hole. Further, depending on the image, a cell nucleus and other organelles can be detected as Hole. Note that the feature amount calculation unit 4202 may detect a group of pixels in which the luminance value in the cell is equal to or greater than the threshold as Hole, and obtain the value of “Hole area” based on the number of pixels of the Hole.

  • relative hole area (see (c) of FIG. 8) “relative hole area” is a value obtained by dividing the value of “Hole area” by the value of “Total area” (relative hole area = Hole area / Total) . The “relative hole area” is a parameter indicating the ratio of the organelle in the cell size, and the value varies depending on, for example, enlargement of the organelle or deterioration of the shape of the nucleus.

  Perimeter (see FIG. 8D) “Perimeter” is a value indicating the length of the outer periphery of the cell of interest. For example, the feature amount calculation unit 4202 can acquire the value of “Perimeter” by contour tracking processing when extracting cells.

  Width (see (e) of FIG. 8) “Width” is a value indicating the length of the cell of interest in the horizontal direction (X direction) of the image.

  Height (see (f) in FIG. 8) “Height” is a value indicating the length of the cell of interest in the image vertical direction (Y direction).

  Length (refer to (g) in FIG. 8) “Length” is a value indicating the maximum value (the total length of the cell) of the lines crossing the cell of interest.

  -Breadth (refer to (h) of FIG. 8) "Breadth" is a value indicating the maximum value (lateral width of the cell) among the lines orthogonal to "Length".

  Fiber Length (see (i) of FIG. 8) “Fiber Length” is a value indicating the length when the target cell is assumed to be pseudo linear. The feature amount calculation unit 4202 obtains a value of “Fiber Length” by the following equation (1).

  However, in the formula of this specification, “P” indicates the value of Perimeter. Similarly, “A” indicates the value of Total Area.

  Fiber Blade (see (j) of FIG. 8) “Fiber Breath” is a value indicating a width (a length in a direction perpendicular to Fiber Length) when the target cell is assumed to be pseudo linear. The feature amount calculation unit 4202 obtains the value of “Fiber Breath” by the following equation (2).

  Shape Factor (see (k) of FIG. 8) “Shape Factor” is a value indicating the circularity (cell roundness) of the cell of interest. The feature amount calculation unit 4202 obtains the value of “Shape Factor” by the following equation (3).

  Elliptical form factor (see (l) in FIG. 8) “Elliptical form factor” is a value obtained by dividing the value of “Length” by the value of “Breadth” (Elliptical form Factor = Length / Breadth) This is a parameter indicating the degree of cell slenderness.

  Inner radius (see (m) of FIG. 8) “Inner radius” is a value indicating the radius of the inscribed circle of the cell of interest.

  Outer radius (see (n) in FIG. 8) “Outer radius” is a value indicating the radius of the circumscribed circle of the cell of interest.

  Mean radius (see (o) of FIG. 8) “Mean radius” is a value indicating an average distance between all the points constituting the outline of the cell of interest and its center of gravity.

  Equivalent radius (see (p) of FIG. 8) “Equivalent radius” is a value indicating the radius of a circle having the same area as the cell of interest. The parameter “Equivalent radius” indicates the size when the cell of interest is virtually approximated to a circle.

  Here, the feature amount calculation unit 4202 of the CPU 42 may obtain each feature amount described above by adding an error to the number of pixels corresponding to the cell. At this time, the feature amount calculation unit 4202 may obtain the feature amount in consideration of the imaging condition of the microscope image (imaging magnification, aberration of the microscopic optical system, etc.). Note that when calculating “Inner radius”, “Outer radius”, “Mean radius”, and “Equivalent radius”, the feature amount calculation unit 4202 determines the center of gravity of each cell based on a known center of gravity calculation method. What is necessary is just to obtain | require each parameter on the basis of a gravity center point.

<Step S212 of FIG. 7: Details of Processing by Cell Evaluation Calculation Model Building Unit 4221 of CPU 42>
Next, the processing by the cell evaluation calculation model construction unit 4221 of the CPU 42 in step S212 of FIG. 7 will be described in detail with reference to FIGS.

  In the present embodiment, for example, in time-series feature quantities, all time-series feature quantities can be used in the cell evaluation calculation model, and some time-series feature quantities are expressed in cells. It can also be used in an evaluation calculation model. This “feature amount of a part of time in the time series” is, for example, the value of the feature amount “Eliptical form Factor” is the value of the 3.00th day, and the feature amount of “Eliptical form Factor” is the number of days elapsed. 3.33th day value: The value of the characteristic amount of “Eliptical form Factor” is the 13.67th day value and each value. Here, “a feature amount of a part of time in time series” will be described as an “index”. In other words, the value of each feature value for each elapsed number of days is an index.

  Here, a case will be described in which the cell evaluation calculation model construction unit 4221 obtains the above-described cell evaluation calculation model by fuzzy neural network (FNN) analysis.

  In addition, here, a case where the cell evaluation calculation model construction unit 4221 obtains a cell evaluation calculation model when obtaining the number of cancer cells (predicted value) in each set of microscopic images based on the feature amount will be described. To do. Here, a case has been described in which the cell evaluation calculation model construction unit 4221 constructs a cell evaluation calculation model in the case of obtaining the number of cancer cells (predicted value), but in the case of estimating the number of remaining doublings. Even when the cell evaluation calculation model is constructed, the method for constructing the cell evaluation calculation model is the same.

  FNN is a method in which an artificial neural network (ANN) and fuzzy inference are combined. In this FNN, an ANN is incorporated in fuzzy inference to automatically determine the membership function, which is a drawback of fuzzy inference.

  ANN (see FIG. 9), which is one of the learning machines, is a mathematical model of a neural network in a biological brain and has the following characteristics. The learning in the ANN uses learning data (input value: X) having a target output value (teacher value), and uses a back propagation (BP) method to calculate the teacher value and the output value (Y). This is a process of constructing a model so that the coupling load in the circuit connecting the nodes (shown by circles in FIG. 9) is changed so that the error becomes small, and the output value approaches the teacher value. Using this BP method, the ANN can automatically acquire knowledge by learning. Finally, by inputting data that is not used for learning, the versatility of the model can be evaluated.

  Conventionally, membership function determination has relied on human senses, but by incorporating ANN as described above into fuzzy inference, membership function can be automatically identified. This is FNN. In the FNN, like the ANN, the input / output relationship given to the network by using the BP method can be automatically identified and modeled by changing the coupling weight. FNN has a feature that it can acquire knowledge as a linguistic rule that is easy for humans to understand like fuzzy reasoning (see the balloon at the lower right in FIG. 10 as an example) by analyzing the model after learning. In other words, the FNN automatically determines the optimal combination of fuzzy reasoning in the combination of variables such as numerical values representing the morphological characteristics of the cell from its structure and characteristics, and estimates the prediction target and the feature quantity effective for the prediction. A rule indicating a combination of (index) can be generated simultaneously.

  The structure of the FNN is “input layer”, “membership function part (preceding part)” that determines parameters Wc and Wg included in the sigmoid function, Wf is determined, and the relationship between input and output is taken out as a rule It consists of four possible layers of “fuzzy rule part (consequent part)” and “output layer” (see FIG. 10). There are Wc, Wg, and Wf as bond loads that determine the model structure of FNN. The combined load Wc determines the center position of the sigmoid function used for the membership function, and Wg determines the inclination at the center position (see FIG. 11). In the model, the input value is expressed by a fuzzy function with flexibility close to human sensation (see the balloon at the lower left in FIG. 10 as an example). The combined load Wf represents a contribution to the estimation result of each fuzzy region, and a fuzzy rule can be derived from Wf. That is, the structure in the model can be deciphered later and written as a rule (see the balloon at the lower right in FIG. 10 as an example).

  A Wf value, which is one of the coupling loads, is used to create a fuzzy rule in the FNN analysis. If the Wf value is positive and large, the unit contributes greatly to being determined to be “effective for prediction”, and the index applied to the rule is determined to be “effective”. If the Wf value is negative and small, the unit has a large contribution to being determined as “invalid for prediction”, and the index applied to the rule is determined as “invalid”.

  As an example, the cell evaluation calculation model construction unit 4221 in step S209 obtains the above cell evaluation calculation model by the following processes (A) to (H).

  (A) The cell evaluation calculation model construction unit 4221 selects one index from a plurality of indices.

  (B) The cell evaluation calculation model construction unit 4221 obtains the number of cancer cells (predicted value) in each set of microscopic images by a calculation formula using the index selected in (A) as a variable.

  Assuming that the calculation formula for obtaining the number of cancer cells from one index is “Y = αX1” (where “Y” is a calculated value of cancer cells (for example, a value indicating the increased number of cancer cells), “X1”. Is a value of the selected index and “α” is a coefficient value corresponding to X1). At this time, the cell evaluation calculation model construction unit 4221 assigns an arbitrary value to α and assigns a value in each set to X1. Thereby, the calculated value (Y) of the cancer cell in each set is obtained.

  (C) The cell evaluation calculation model construction unit 4221 obtains an error between the calculated value Y obtained in (B) and the actual number of cancer cells (teacher value) for each set of microscope images. Note that the above-described teacher value is obtained by the cell evaluation calculation model construction unit 4221 based on the information on the number of cancer cells read in step S201.

  Then, the cell evaluation calculation model construction unit 4221 corrects the coefficient α of the above calculation formula by supervised learning so that the error of the calculation value in each set of microscope images becomes smaller.

  (D) The cell evaluation calculation model construction unit 4221 repeats the processes (B) and (C), and obtains a model of a calculation formula that minimizes the average error of the calculated values for the index (A). .

  (E) The cell evaluation calculation model construction unit 4221 repeats the processes (A) to (D) for each index of the plurality of indices. Then, the cell evaluation calculation model construction unit 4221 compares the average error of the calculated values in each index, and uses the index having the lowest average error for generation of the evaluation information (the cell evaluation calculation model for calculating the evaluation information is used). The first index used for construction).

  (F) The cell evaluation calculation model construction unit 4221 obtains a second index to be combined with the first index obtained in (E) above. At this time, the cell evaluation calculation model construction unit 4221 pairs the first index and the remaining 127 indices one by one. Next, the cell evaluation calculation model construction unit 4221 obtains a cancer cell prediction error using a calculation formula in each pair.

  Assuming that the calculation formula for calculating the number of cancer cells from two indices is “Y = αX1 + βX2” (where “Y” is the calculated value of cancer cells, “X1” is the value of the first index, and “α” is The coefficient value corresponding to X1, “X2” represents the value of the selected index, and “β” represents the coefficient value corresponding to X2.) Then, the cell evaluation calculation model construction unit 4221 obtains the values of the coefficients α and β so that the average error of the calculated values is minimized by the same processing as the above (B) and (C).

  Thereafter, the cell evaluation calculation model construction unit 4221 compares the average error of the calculated values obtained for each pair, and obtains the pair having the lowest average error. Then, the cell evaluation calculation model construction unit 4221 sets the pair index having the lowest average error as the first and second indices used for generating the evaluation information.

  (G) The cell evaluation calculation model construction unit 4221 ends the calculation process when a predetermined end condition is satisfied. For example, the cell evaluation calculation model construction unit 4221 compares the average error by each calculation formula before and after increasing the index. Then, the cell evaluation calculation model construction unit 4221 determines that the average error based on the calculation formula after increasing the index is higher than the average error based on the calculation formula before increasing the index (or if the difference between the two is within the allowable range). Ends the calculation process of step S209.

  (H) On the other hand, when the termination condition is not satisfied in (G), the cell evaluation calculation model construction unit 4221 further increases the number of indices by one and repeats the same processing as in (F) and (G) above. . Thereby, when obtaining the above-described cell evaluation calculation model, the index is narrowed down by step-wise variable selection.

  In this way, the cell evaluation calculation model construction unit 4221 can obtain a cell evaluation calculation model by FNN analysis, for example.

  Here, the case where the cell evaluation calculation model construction unit 4221 obtains the above-described cell evaluation calculation model by FNN analysis has been described, but the method of obtaining the cell evaluation calculation model is not limited to FNN analysis. For example, the cell evaluation calculation model construction unit 4221 may construct the cell evaluation calculation model by any type of multivariate analysis for evaluating the characteristics of the cells using the above-described plurality of feature quantities as explanatory variables. This multivariate analysis may be multiple regression analysis, discriminant analysis, logistic regression analysis, principal component analysis, or the like.

<Step S209 in FIG. 7: Details of processing by the procedure evaluation calculation model construction unit 4211 of the CPU 42>
Next, processing by the procedure evaluation calculation model construction unit 4211 of the CPU 42 in step S209 of FIG. 7 will be described in detail.

  This procedure evaluation calculation model construction unit 4211 constructs a procedure evaluation calculation model in the same manner as the cell evaluation calculation model construction unit 4221 described above with reference to FIGS. The difference is a difference of objects to be evaluated as described below.

  First, the cell evaluation calculation model construction unit 4221 constructs, as an object to be evaluated, a cell evaluation calculation model that evaluates cell characteristics such as the number of remaining doublings by combining a plurality of indices. On the other hand, the technique evaluation calculation model construction unit 4211 constructs a technique evaluation calculation model that evaluates a technique for culturing cells as a target to be evaluated by combining a plurality of indices.

  The cell evaluation calculation model construction unit 4221 and the technique evaluation calculation model construction unit 4211 are different in evaluation target, but are similar in that a calculation model for estimating an evaluation target is constructed by combining the plurality of indicators. is there.

  Therefore, the technique evaluation calculation model construction unit 4211 selects, as an object to be evaluated, a technique evaluation calculation model for evaluating a technique in the case of culturing cells by combining a plurality of indices, like the cell evaluation calculation model construction part 4221. Build by any form of multivariate analysis such as analysis, multiple regression analysis, discriminant analysis, logistic regression analysis, or principal component analysis.

  Note that the cell evaluation calculation model construction unit 4221 and the technique evaluation calculation model construction unit 4211 may construct a calculation model for estimating each evaluation target by an analysis method of a different format based on the index. For example, the cell evaluation calculation model construction unit 4221 may construct a cell evaluation calculation model by FNN analysis, and the technique evaluation calculation model construction unit 4211 may construct a technique evaluation calculation model by multiple regression analysis.

(Example of processing when evaluating cells)
Next, processing when the cell evaluation apparatus according to the first embodiment evaluates a cell to be evaluated will be described using the flowchart of FIG. Here, a description will be given assuming that data of a plurality of microscope images to be evaluated are stored in the storage unit 43. The microscopic image to be evaluated is acquired by time-lapse observation of the same visual field using the incubator 11 under the same imaging conditions in the culture vessel 19 in which the cell group is cultured. In addition, in this case, the time-lapse observation is performed every 0.33 days (8 hours) every 0.33 days (8 hours) after the lapse of 0.33 days (8 hours) from the start of the culture in order to align the conditions with the example of FIG. It is assumed that it is carried out until the 67th day.

  Step S301: The CPU 42 reads data of a plurality of microscope images to be evaluated from the storage unit 43 via the image reading unit 4203.

  Step S302: The feature amount calculation unit 4202 of the CPU 42 applies a plurality of features to the read data of a plurality of microscope images to be evaluated, as in Steps S203, S204, and Step S205 of FIG. Extract quantity (index).

  Step S303: The technique evaluation unit 4212 of the CPU 42 reads information on the technique evaluation calculation model (recorded in step S210 of FIG. 7) from the storage unit 43.

  Step S305: The technique evaluation unit 4212 of the CPU 42 inputs a plurality of feature amounts (a plurality of indices) extracted by the feature amount calculation unit 4202 in step S302 to the technique evaluation calculation model read in step S303. Thereby, the technique evaluation unit 4212 of the CPU 42 evaluates the technique in culture for the cells captured in the data of a plurality of microscope images to be evaluated input in step S301.

  If the result of the evaluation for the procedure in step S305 is appropriate, the CPU 42 advances the process to step S306. If not, the CPU 42 advances the process to step S309. Here, “when the result of the evaluation on the procedure is appropriate” is, for example, the case where the procedure is at the upper left or lower left in FIG. 5 as described with reference to FIG. On the other hand, “when the result of the evaluation of the procedure is not appropriate” means, for example, when the procedure is in the upper right or lower right of FIG. 5 as described with reference to FIG.

  Step S306: The cell evaluation unit 4222 of the CPU 42 reads information of the cell evaluation calculation model (recorded in step S213 of FIG. 7) from the storage unit 43.

  Step S307: The cell evaluation unit 4222 of the CPU 42 performs a calculation by substituting the plurality of feature amounts (a plurality of indexes) obtained in Step S302 into the cell evaluation calculation model read out in Step S306.

  Step S308: The cell evaluation unit 4222 of the CPU 42 generates evaluation information indicating the evaluation of the microscope image to be evaluated based on the calculation result in step S307. Thereafter, the cell evaluation unit 4222 of the CPU 42 displays and outputs this evaluation information on a monitor or the like (not shown). Moreover, CPU42 may output the information which shows the technique evaluated by the technique evaluation part 4212 of CPU42 by step S305 with evaluation information.

  Step S309: The technique evaluation unit 4212 of the CPU 42 displays information indicating that the data of the plurality of microscope images to be evaluated input in step S310 cannot be evaluated by the present cell evaluation apparatus on a monitor (not shown) or the like. Output. Further, the description of FIG. 12 is finished.

  In this way, the cell evaluation apparatus according to the present embodiment can estimate the procedure in which the cells are cultured and the number of remaining doublings of the cells based only on the cell images. Therefore, the cell evaluation apparatus according to the present embodiment can evaluate a procedure and cells by a relatively simple method.

  Further, the cell evaluation calculation model construction unit 4221 according to the present embodiment constructs a cell evaluation calculation model based on the image information of the cell for which the procedure is appropriate, as described in step S211 of FIG.

  Here, it is assumed that the cell evaluation calculation model is constructed based on the image information of the cell in which the procedure is not appropriate or the image information of the cell in which the procedure is not appropriate and the image information of the cell in which the procedure is appropriate. Suppose. In this case, if this cell is evaluated with respect to the image information of the cell for which the procedure is appropriate using this cell evaluation calculation model, the evaluation performance may be reduced.

  In contrast, in the present embodiment, as described in step S211 of FIG. 7, the cell evaluation calculation model construction unit 4221 uses the cell image information determined by the procedure evaluation unit 4212 to determine that the procedure is appropriate. Based on this, a cell evaluation calculation model is constructed. Therefore, this cell evaluation calculation model can appropriately evaluate the cell with respect to the image information of the cell for which the procedure is appropriate.

  In addition, as described with reference to FIG. 12, when evaluating a cell with respect to image information of a cell to be evaluated, the technique evaluation unit 4212 is to be evaluated as described in step S <b> 305 in FIG. 12. It is determined whether or not the cell procedure is appropriate for the cell image information. Only the image for which the procedure is determined to be appropriate by the procedure evaluation unit 4212 is evaluated by the cell evaluation unit 4222 in step S307 of FIG.

  In step S307, as described with reference to FIG. 7, the cell evaluation unit 4222 performs cell evaluation calculation that can appropriately evaluate the cell with respect to the image information of the cell for which the procedure is appropriate. Based on the model, cells that have been determined to be appropriate for the cell procedure are evaluated. Therefore, the cell evaluation unit 4222 can appropriately evaluate the cells.

  Therefore, the cell evaluation apparatus according to the present embodiment can appropriately evaluate cells by a relatively simple method even when operations necessary for cell culture such as passage operations are not technically appropriate. . Further, since the cell evaluation calculation model is constructed so that the remaining doubling number can be calculated from the image of the cell, the cell evaluation unit 4222 uses a relatively simple method to determine the remaining number of times that the cell divides (the remaining doubling number). ) Can be calculated. Therefore, the user can obtain the remaining number of times that the cell divides by a relatively simple method.

  Moreover, according to this embodiment, the control apparatus 41 can evaluate a cell accurately based on a feature-value using the microscope image acquired by the time lapse observation. Moreover, since the control apparatus 41 of this embodiment can make a cell as an evaluation object, it is very useful, for example, when evaluating the cell cultured by the use of a pharmaceutical screening or a regenerative medicine.

  In the present embodiment, an example in which cells are evaluated from a microscopic image has been described. For example, the control device 41 is used to evaluate the mixture ratio of cancer cells from a microscopic image, or an embryonic stem cell (ES Cell) and induced pluripotent stem cells (iPS cells). In addition, the evaluation information obtained in the present embodiment includes the abnormality detection means such as differentiation / dedifferentiation / tumorization / activity degradation / cell contamination in the cultured cell group to be evaluated, and the quality of the cultured cell group to be evaluated. It can be used as a means for engineering management.

  By the way, when culturing embryonic stem cells (ES cells) or induced pluripotent stem cells (iPS cells), for example, from the colonies of these cells, some cells of the colonies are excised, and the excised cells are cultured. May proliferate. And it is not limited to once that cells are cut out from the colony, but there may be multiple times. In this case, the “procedure” of cutting cells from the colony is performed a plurality of times.

  Therefore, in such a case, the “procedure” may become inappropriate in any case in a plurality of procedures. If the “procedure” is inappropriate, even if the cells are cultured, they may not be suitable for use in experiments.

  On the other hand, according to the above-described cell evaluation apparatus, the “procedure” for the cell can be estimated by a simple method. Therefore, it can be easily determined that the cell is not suitable for use in an experiment or the like.

  Also, in the above case, the goal is to culture and proliferate the cells, but if the number of remaining doublings of these cells is very small, even if the cells are cultured, the original appropriate number of cells Or, the cells may not be allowed to grow to the desired number of cells.

  On the other hand, according to the cell evaluation apparatus described above, the “remaining doubling number” for the cell can be estimated by a simple method. Therefore, the user can proliferate cells up to the original appropriate number of cells or the desired number of cells.

  Thus, the cell evaluation apparatus according to the present embodiment is suitable when a plurality of procedures are involved. Therefore, the cell evaluation apparatus according to the present embodiment is suitable for conducting experiments by culturing embryonic stem cells (ES cells) or induced pluripotent stem cells (iPS cells). Similarly, the cell evaluation apparatus according to this embodiment is also suitable for the development of cosmetics and pharmaceuticals.

  Moreover, the cell evaluation apparatus according to the present embodiment estimates the procedure and the number of remaining doublings based on the images. Therefore, the cell evaluation apparatus according to the present embodiment can estimate the procedure and the number of remaining doublings non-invasively with respect to the cells. Therefore, while culturing the cell, the technique for the cell and the number of remaining doublings can be estimated based on the image of the cell itself. Therefore, the cell evaluation apparatus according to the present embodiment is suitable for cell culture.

  In the above description, the cell evaluation calculation model construction unit 4221 constructs a cell evaluation calculation model for calculating the remaining number of times (remaining doubling number) for the cell, and the cell evaluation unit 4222 is constructed. The case where the number of remaining doublings is calculated based on the cell evaluation calculation model and the number of remaining doublings of cells is evaluated has been described.

  However, the present invention is not limited to this, and the cell evaluation calculation model construction unit 4221 is based on a feature amount corresponding to each image and an arbitrary characteristic (known characteristic) predetermined for the cell, You may build the cell evaluation calculation model which calculates the arbitrary characteristics predetermined with respect to the cell. Then, the cell evaluation unit 4222 may calculate an arbitrary characteristic determined in advance based on the cell evaluation calculation model constructed as described above, and may evaluate the arbitrary characteristic for the cell.

  Also in this case, the cell evaluation calculation model construction unit 4221 constructs a cell evaluation calculation model based on the image evaluated by the technique evaluation unit 4212. Therefore, the cell evaluation calculation model construction unit 4221 can construct the cell evaluation calculation model more stably and accurately. In addition, since the cell evaluation calculation model is constructed more stably and accurately, the cell evaluation unit 4222 can evaluate any characteristic of the cell more stably and accurately.

<Second Embodiment>
Next, the configuration of the incubator including the cell evaluation apparatus according to the second embodiment of the present invention will be described with reference to FIG. In the figure, portions corresponding to the respective portions in FIG. Here, the case where the number of cancer cells (predicted value) is obtained will be described, but the same applies to the case where the number of remaining doublings is estimated as in the first embodiment.

  Here, a case where the cell evaluation calculation model construction unit 4221 constructs a cell evaluation calculation model will be described. Note that, as described in the first embodiment, when the technique evaluation calculation model construction unit 4211 constructs a technique evaluation calculation model, it is the same as when the cell evaluation calculation model construction unit 4221 constructs a cell evaluation calculation model. It is.

  The incubator including the cell evaluation apparatus according to the second embodiment illustrated in FIG. 13 further includes a frequency distribution calculation unit 4204 compared to the incubator including the cell evaluation apparatus according to the first embodiment illustrated in FIG. It has.

  The frequency distribution calculation unit 4204 generates a frequency distribution of feature amounts corresponding to each image for each type of a plurality of feature amounts with respect to the feature amounts extracted by the feature amount calculation unit 4202. Then, the frequency distribution calculation unit 4204 outputs the frequency distribution of the feature amount to the cell evaluation calculation model construction unit 4221 as the feature amount. For example, the frequency distribution calculation unit 4204 outputs the frequency distribution of the feature amount to the cell evaluation calculation model construction unit 4221 as an index. The frequency distribution calculation unit 4204 may normalize the frequency classification in each frequency distribution using the standard deviation for each type of feature amount.

  Then, the cell evaluation calculation model construction unit 4221 uses the feature quantity obtained by the feature quantity computation unit 4202 described in the first embodiment and the frequency distribution obtained by the frequency distribution computation unit 4204 as indices, respectively. Build a cell evaluation calculation model. That is, the cell evaluation calculation model construction unit 4221 uses the index of the feature amount obtained by the feature amount computation unit 4202 described in the first embodiment and the indicator of the frequency distribution obtained by the frequency distribution computation unit 4204. A cell evaluation calculation model is constructed by combining them arbitrarily.

  Note that the cell evaluation calculation model construction unit 4221 may construct a cell evaluation calculation model based on a change in the frequency distribution between images. In addition, the cell evaluation calculation model construction unit 4221 may construct a cell evaluation calculation model using the difference in the frequency distribution between images. In addition, the cell evaluation calculation model construction unit 4221 may construct a cell evaluation calculation model based on the information on the change in the frequency distribution generated for each type of the plurality of feature amounts.

  In addition, the cell evaluation calculation model construction unit 4221 extracts a combination of frequency distributions used for construction of the cell evaluation calculation model from a plurality of combinations of frequency distributions having different image capturing times and different types of feature amounts. An evaluation calculation model may be constructed.

Note that the cell evaluation unit 4222 evaluates a cell to be evaluated from the frequency distribution calculation unit 4204 that is also used to acquire the frequency distribution of the feature amount of the cell used when the cell evaluation calculation model construction unit 4221 constructs the cell evaluation calculation model. The frequency distribution of feature quantities is obtained. By doing in this way, it is the apparatus structure which can comprise both a cell evaluation calculation model construction and a cell evaluation apparatus with few structures.
However, the configuration (frequency distribution calculation unit 4204) that outputs the frequency distribution of the feature amount of the cell may be configured differently according to the cell evaluation calculation model construction unit 4221 and the cell evaluation unit 4222. For example, a cell evaluation calculation model device including the cell evaluation calculation model construction unit 4221 includes a frequency distribution calculation unit 4204, and a cell evaluation device including the cell evaluation unit 4222 is similar to the frequency distribution calculation unit 4204. The frequency distribution calculating unit for calculating the remaining number of times may be provided.

  Next, the operation of the cell evaluation apparatus according to the second embodiment will be described with reference to FIG. In the figure, the same steps as those of the cell evaluation apparatus according to the first embodiment described with reference to FIG. 7 are denoted by the same step numbers, description thereof is omitted, and only differences are described. .

  The operation of the cell evaluation apparatus according to the second embodiment shown in FIG. 14 is compared with the operation of the cell evaluation apparatus according to the first embodiment shown in FIG. 7 in steps S206 and S209. In the meantime, steps S207 and S208 are further added.

  Here, the time lapse observation of the culture vessel 19 will be described for a case where the first time is 8 hours after the start of the culture and the time is 72 hours every 8 hours. Therefore, the cell evaluation apparatus acquires nine sets (8h, 16h, 24h, 32h, 40h, 48h, 56h, 64h, 72h) as one set for the microscopic images of the samples having the same culture container 19 and observation point. It will be. Here, it is assumed that a plurality of culture vessels 19 are time-lapse observed, and a plurality of sets of microscopic images of the sample are stored in the storage unit 43 in advance.

  In the case of FIG. 14, in step S <b> 206, the CPU 42 determines whether or not all the microscopic images have been processed (a state in which the feature amount of each cell has been acquired in the microscopic images of all samples). If the above requirement is satisfied (YES side), the CPU 42 shifts the processing to step S207. On the other hand, if the above requirement is not satisfied (NO side), the CPU 42 returns to step S202 and repeats the above operation with another unprocessed microscope image as a processing target.

  Step S207: The frequency distribution calculation unit 4204 obtains the frequency distribution of the feature amount for each type of feature amount for each microscope image. Therefore, the frequency distribution calculation unit 4204 in step S207 obtains frequency distributions of 16 types of feature amounts with respect to a microscope image acquired in one observation.

  Step S208: The frequency distribution calculation unit 4204 (or the cell evaluation calculation model construction unit 4221) obtains the change in the frequency distribution over time for each type of feature amount.

  In step S208, the frequency distribution calculation unit 4204 (or the cell evaluation calculation model construction unit 4221) has the same type of feature amount in the frequency distribution (9 × 16) acquired from the microscope image for one set and the imaging time. Two different frequency distributions are combined. As an example, the frequency distribution calculation unit 4204 (or the cell evaluation calculation model construction unit 4221), for nine frequency distributions with the same feature type and different shooting times, Frequency distribution at 8th and 24th hours, frequency distribution at 8th and 32th hours, frequency distribution at 8th and 40th hours, frequency distribution at 8th and 48th hours, and 8 hours The frequency distribution at the first and 56th hours, the frequency distribution at the 8th and 64th hours, and the frequency distribution at the 8th and 72th hours are combined. That is, when attention is paid to one type of feature amount in one set, a total of eight combinations are generated for the frequency distribution of the feature amount.

  Then, the frequency distribution calculation unit 4204 (or the cell evaluation calculation model construction unit 4221) calculates the amount of change in the frequency distribution (the absolute value of the difference in frequency distribution between images) by the following equation (4) for the above eight combinations. (Integrate the values).

  However, in Expression (4), “Control” indicates the frequency (number of cells) for one section in the initial frequency distribution (8th hour). “Sample” indicates the frequency of one section in the frequency distribution to be compared. “I” is a variable indicating a frequency distribution interval.

  The frequency distribution calculation unit 4204 (or the cell evaluation calculation model construction unit 4221) performs the above calculation for each type of feature amount, and thereby can acquire eight types of change amounts of the frequency distribution for all feature amounts. That is, with respect to one set of microscope images, it is possible to take combinations of 128 frequency distributions in 16 types × 8 ways. Here, one of the combinations of the frequency distributions is simply expressed as “index”. Note that the frequency distribution calculation unit 4204 (or the cell evaluation calculation model construction unit 4221) in step S208 obtains the change amount of 128 frequency distributions corresponding to each index in a set of a plurality of microscope images. Not too long.

  Step S211: The cell evaluation calculation model construction unit 4221 designates one or more indices out of 128 indices that well reflect the cell culture state by multivariate analysis. In addition to the nonlinear model equivalent to a fuzzy neural network described later, the use of a linear model is also effective in selecting the combination of indices according to the complexity of the cell and its form. Along with the selection of such a combination of indices, the cell evaluation calculation model construction unit 4221 obtains a cell evaluation calculation model for deriving the number of cancer cells from the microscopic image using one or more of the specified indices.

<Example of Step S207>
Next, an example of step S207 will be described in detail.
In step S207, the frequency distribution calculation unit 4204 obtains the frequency distribution of the feature amount for each type of feature amount for each microscope image as described above. Therefore, the frequency distribution calculation unit 4204 in step S207 obtains frequency distributions of 16 types of feature amounts with respect to a microscope image acquired in one observation.

  Here, the frequency distribution calculation unit 4204 calculates the number of cells corresponding to each segment of the feature amount as a frequency (%) in each frequency distribution. Further, the frequency distribution calculation unit 4204 in step S207 normalizes the frequency classification in the frequency distribution using the standard deviation for each type of feature amount.

  Here, as an example, a case will be described in which a division in the frequency distribution of “Shape Factor” is determined.

  First, the frequency distribution calculation unit 4204 calculates a standard deviation of all “Shape Factor” values obtained from each microscope image. Next, the frequency distribution calculation unit 4204 substitutes the standard deviation value into the Fisher equation to obtain a reference value for the frequency classification in the frequency distribution of “Shape Factor”. At this time, the frequency distribution calculation unit 4204 divides the standard deviation (S) of all “Shape Factor” values by 4 and rounds off the third decimal place to obtain the above-described reference value. Note that the frequency distribution calculation unit 4204 in the present embodiment causes a monitor or the like to draw a section for 20 series when the frequency distribution is illustrated as a histogram.

  As an example, when the standard deviation S of “Shape Factor” is 259, the reference value is “64.75” from 259/4 = 64.750. When calculating the frequency distribution of the “Shape Factor” of the image of interest, the frequency distribution calculation unit 4204 classifies the cells into each class set from 0 to 64.75 in accordance with the value of “Shape Factor”. Then, the number of cells in each class may be counted.

  As described above, the frequency distribution calculation unit 4204 normalizes the distribution of frequency distributions with the standard deviation for each type of feature quantity, so that the tendency of the frequency distribution can be roughly approximated between different feature quantities. Therefore, in the present embodiment, it is relatively easy to obtain the correlation between the cell culture state and the change in the frequency distribution between different feature amounts.

  Here, FIG. 15A is a histogram showing a change with time of “Shape Factor” when the initial mixing ratio of cancer cells is 0%. FIG. 15B is a histogram showing the change with time of “Shape Factor” when the initial mixing ratio of cancer cells is 6.7%. FIG. 15C is a histogram showing the change with time of “Shape Factor” when the initial mixing ratio of cancer cells is 25%.

  FIG. 15D is a histogram showing the change with time of “Fiber Length” when the initial mixing ratio of cancer cells is 0%. However, in this figure, for ease of understanding, the histogram is omitted up to Fiber Length = 323. FIG. 15E is a histogram showing the change with time of “Fiber Length” when the initial mixing ratio of cancer cells is 6.7%. FIG. 15 (f) is a histogram showing the change with time of “Fiber Length” when the initial mixing ratio of cancer cells is 25%.

  Here, the reason why attention is paid to the change over time in the frequency distribution in this embodiment will be described. FIG. 16 shows microscope images when normal cell groups (initial mixing ratio of cancer cells 0%) are cultured in the incubator 11 and time-lapse observation is performed. A histogram showing the frequency distribution of “Shape Factor” obtained from each microscope image of FIG. 16 is shown in FIG.

  In this case, in each image of FIG. 16, the number of cells increases with time, but in the “Shape Factor” histogram shown in FIG. 15A, the frequency distribution corresponding to each image is almost the same. It keeps its shape.

  On the other hand, FIG. 17 shows a microscopic image when a normal cell group previously mixed with 25% cancer cells is cultured in the incubator 11 and time-lapse observed. In addition, the histogram which shows the frequency distribution of "Shape Factor" calculated | required from each microscope image of FIG. 17 is shown in FIG.15 (c).

  In this case, in each image in FIG. 17, the ratio of cancer cells (rounded cells) having different shapes from normal cells increases with time. Accordingly, in the “ShapeFactor” histogram shown in FIG. 15C, a large change appears in the shape of the frequency distribution corresponding to each image as time passes. Therefore, it turns out that the time-dependent change of frequency distribution has a strong correlation with mixing of cancer cells. Based on the above findings, the present inventors evaluate the state of cultured cells from information on changes over time in the frequency distribution.

<Example of Step S212>
Here, an example of the process executed in step S212 of FIG. 14 in the second embodiment will be described. In this case, the cell evaluation calculation model construction unit 4221 in step S212 obtains the above-described cell evaluation calculation model by the following processes (A) to (H). Here, a case will be described in which the above-described information on the change over time in the frequency distribution is used as an index. That is, a case where 128 indexes are used will be described.

  (A) The cell evaluation calculation model construction unit 4221 selects one index from among 128 indices.

  (B) The cell evaluation calculation model construction unit 4221 calculates the number of cancer cells in each set of microscopic images (predicted value) using a calculation formula using the amount of change in the frequency distribution according to the index selected in (A) as a variable. )

  Assuming that the calculation formula for obtaining the number of cancer cells from one index is “Y = αX1” (where “Y” is a calculated value of cancer cells (for example, a value indicating the increased number of cancer cells), “X1”. Is a change amount of the frequency distribution corresponding to the selected index (obtained in step S208), and “α” is a coefficient value corresponding to X1). At this time, the cell evaluation calculation model construction unit 4221 assigns an arbitrary value to α, and also assigns the amount of change in the frequency distribution in each set to X1. Thereby, the calculated value (Y) of the cancer cell in each set is obtained.

  (C) The cell evaluation calculation model construction unit 4221 obtains an error between the calculated value Y obtained in (B) and the actual number of cancer cells (teacher value) for each set of microscope images. Note that the above-described teacher value is obtained by the cell evaluation calculation model construction unit 4221 based on the information on the number of cancer cells read in step S201.

  Then, the cell evaluation calculation model construction unit 4221 corrects the coefficient α of the above calculation formula by supervised learning so that the error of the calculation value in each set of microscope images becomes smaller.

  (D) The cell evaluation calculation model construction unit 4221 repeats the processes (B) and (C), and obtains a model of a calculation formula that minimizes the average error of the calculated values for the index (A). .

  (E) The cell evaluation calculation model construction unit 4221 repeats the processes (A) to (D) for 128 indices. Then, the cell evaluation calculation model construction unit 4221 compares the average errors of the calculated values of the 128 indices, and sets the index with the lowest average error as the first index used for generating the evaluation information.

  (F) The cell evaluation calculation model construction unit 4221 obtains a second index to be combined with the first index obtained in (E) above. At this time, the cell evaluation calculation model construction unit 4221 pairs the first index and the remaining 127 indices one by one. Next, the cell evaluation calculation model construction unit 4221 obtains a cancer cell prediction error using a calculation formula in each pair.

  Assuming that the calculation formula for calculating the number of cancer cells from two indices is “Y = αX1 + βX2” (where “Y” is a calculated value of cancer cells, and “X1” is a change in the frequency distribution corresponding to the first index. The amount, “α” is a coefficient value corresponding to X1, “X2” is a change amount of the frequency distribution corresponding to the selected index, and “β” is a coefficient value corresponding to X2.) Then, the cell evaluation calculation model construction unit 4221 obtains the values of the coefficients α and β so that the average error of the calculated values is minimized by the same processing as the above (B) and (C).

  Thereafter, the cell evaluation calculation model construction unit 4221 compares the average error of the calculated values obtained for each pair, and obtains the pair having the lowest average error. Then, the cell evaluation calculation model construction unit 4221 sets the pair index having the lowest average error as the first and second indices used for generating the evaluation information.

  (G) The cell evaluation calculation model construction unit 4221 ends the calculation process when a predetermined end condition is satisfied. For example, the cell evaluation calculation model construction unit 4221 compares the average error by each calculation formula before and after increasing the index. Then, the cell evaluation calculation model construction unit 4221 determines that the average error based on the calculation formula after increasing the index is higher than the average error based on the calculation formula before increasing the index (or if the difference between the two is within the allowable range). Ends the calculation process of step S212.

  (H) On the other hand, when the termination condition is not satisfied in (G), the cell evaluation calculation model construction unit 4221 further increases the number of indices by one and repeats the same processing as in (F) and (G) above. . Thereby, when obtaining the above-described cell evaluation calculation model, the index is narrowed down by step-wise variable selection.

  Thereby, similarly to the case of the first embodiment, the cell evaluation calculation model can also be constructed in the second embodiment by using the change amount of the frequency distribution corresponding to the index. In the second embodiment, the cell evaluation calculation model is constructed using the amount of change in the frequency distribution corresponding to the index. Therefore, the accuracy of the cell evaluation calculation model according to the second embodiment can be made higher than that of the cell evaluation calculation model according to the first embodiment.

  As described above, according to the second embodiment, as an index of the above-described cell evaluation calculation model, “the combination of frequency distributions at the 8th hour and the 72th hour of“ Shape Factor ”” and “8 hours of“ Perimeter ” When the combination of “the combination of the frequency distribution at the 24th hour” and “the combination of the frequency distribution at the 8th hour and the 72th hour” of “Length” is used, the prediction accuracy of the cancer cell is 93.2. % Cell evaluation calculation model was obtained.

  In addition, as an index of the above-mentioned cell evaluation calculation model, “the combination of frequency distributions at 8th and 72th hours of“ Shape Factor ”” and “frequency distribution of 8th and 56th hours of“ Fiber Breath ”” “Combination”, “Combination of frequency distributions at 8th and 72th hours of“ relative hole area ””, “Combination of frequency distributions at 8th and 24th hours of“ Shape Factor ””, and “Breadth” When using the “combination of frequency distributions at 8th and 72th hours” and “combination of frequency distributions at 8th and 64th hours” of “Breadth”, the prediction accuracy of cancer cells It was possible to obtain a cell evaluation calculation model with 95.5%.

In the process of step S207 in FIG. 14 described above, the frequency distribution calculation unit 4204 obtains eight types of indices for one type of feature value with reference to the eighth hour, and 16 types of feature values. In total, 128 indices (16 types × 8 patterns) were obtained. However, the index is not limited to this, and the evaluation information generation unit 46 performs the 8th, 16th, 24th, 32th, 40th, 48th, 56th, and 64th hours. 36 (= 9 × 8/2) indicators are obtained for one type of feature value based on each of eyes and 72 hours, and a total of 576 (16 types) is obtained for 16 types of feature values. (X36 types) of indicators may be obtained.
By using such indexes with different reference times, the cell evaluation calculation model construction unit 4221 can construct a cell evaluation calculation model with higher prediction accuracy.

  In addition, as an index, you may combine arbitrarily the information of the time-dependent change of the frequency distribution demonstrated in 2nd Embodiment, and the value of the feature-value for every time demonstrated in 1st Embodiment. Thereby, the cell evaluation calculation model construction unit 4221 can construct a cell evaluation calculation model with higher prediction accuracy.

  Next, processing when the cell evaluation apparatus according to the second embodiment evaluates a cell to be evaluated will be described using the flowchart of FIG. Here, only the difference from the process in the case where the cell evaluation apparatus according to the first embodiment described with reference to FIG. 12 evaluates a cell to be evaluated will be described.

  In the flowchart of FIG. 18, step S303 is added between step S302 and step S304 with respect to the flowchart of FIG. In step S303, the frequency distribution calculation unit 4204 (or the cell evaluation calculation model construction unit 4221) obtains the change in the frequency distribution over time for each type of feature amount. This is the same processing as that described above in step S208 of FIG. However, the target image is different between step S303 and step S208.

  Thereafter, in step S307 of FIG. 18, the cell evaluation unit 4222 of the CPU 42 reads out the plurality of feature amounts obtained in step S301 and the temporal change in the frequency distribution obtained in step S303, and read the cell evaluation calculation in step S306. Substitute into the model and perform the operation. Thereby, the cell evaluation unit 4222 of the CPU 42 according to the second embodiment can evaluate the cells using the plurality of feature amounts and the temporal change of the frequency distribution as indices.

  Similar to the cell evaluation unit 4222 of the CPU 42, the technique evaluation unit 4212 of the CPU 42 can evaluate the technique using a plurality of feature amounts and changes over time in the frequency distribution as indices.

  In the description of FIG. 13, the frequency distribution calculation unit 4204 has been described as being provided in the CPU 42. However, the frequency distribution calculation unit 4204 may be included in the feature amount calculation unit 4202. Further, the frequency distribution calculation unit 4204 and the feature amount calculation unit 4202 may be configured integrally. The frequency distribution calculation unit 4204 may be included in the cell evaluation calculation model construction unit 4221 or the cell evaluation calculation model construction unit 4221.

<Example>
Hereinafter, an example of myoblast differentiation prediction will be described as an example of the first or second embodiment described above. This myoblast differentiation prediction is expected to be applied in, for example, quality control in myoblast sheet transplantation, which is performed as one of heart disease treatments, and quality control in muscle tissue regeneration therapy.

  When the components of the medium are changed by lowering the serum concentration during myoblast culture, differentiation from myoblasts to myotube cells occurs and muscle tissue can be created. FIG. 19 (a) shows an example of the myoblast culture state, and FIG. 19 (b) shows an example of the myoblast differentiated state.

  FIG. 20 and FIG. 21 are histograms showing the change over time of “Shape Factor” during culture of myoblasts. FIG. 20 shows the frequency distribution of “Shape Factor” at 0 hours and 112 hours when differentiation is observed in myoblasts (serum 4%). FIG. 21 shows the frequency distributions of “Shape Factor” at 0 hours and 112 hours when differentiation is not observed in myoblasts (high serum state). In FIGS. 20 and 21, the frequency distribution at the 0th hour is indicated by a broken line, and the frequency distribution at the 112th hour is indicated by a solid line.

  When the two histograms in FIG. 20 are compared, the shapes of both show a large change. On the other hand, when the two histograms of FIG. 21 are compared, there is no significant change in the shape of the two. Therefore, it can be seen that the histogram also changes according to the change in the degree of differentiation of myoblasts (mixing rate of differentiating myoblasts).

  Here, in the Examples, the time-lapse observation was performed on the 72 samples of myoblasts up to the fifth day at 8 hour intervals by the incubator of the first or second embodiment. And the control apparatus (cell evaluation apparatus) performed the differentiation prediction of the myoblast by the following two steps of processes.

  In the first stage, in accordance with the cell evaluation calculation model generation process described above, the control device generates a two-group determination model that alternatively determines the presence or absence of myoblast differentiation. As an example, the control device selects a first index from among all indices obtained from microscopic images from the 8th to the 32nd hour after the start of observation, and obtains the degree of differentiation of myoblasts. A second determination model was constructed that discriminates the presence or absence of differentiation using a threshold value from the degree of differentiation obtained from the determination model. And the control apparatus classified 72 samples into two groups according to the presence or absence of differentiation by discriminant analysis by said 1st determination model and 2nd determination model. As a result, the control device was able to correctly determine the presence or absence of differentiation in 72 samples.

  In the second stage, in accordance with the generation process of the cell evaluation calculation model described above, a prediction model that predicts the degree of differentiation of myoblasts on the fifth day (120 hours) was generated by the control device. In the embodiment, of the 72 samples, only 42 samples determined to be “differentiated” in the first stage processing are used, and two types of prediction models (first prediction model, first 2 prediction models).

  The first prediction model includes “a combination of frequency distributions at the 8th and 48th hours of“ Breadth ””, “a combination of frequency distributions at the 8th and 32nd hours of“ Breadth ””, and “Inner "Radius" 8th and 24th frequency distribution combinations "," Length "8th and 104th frequency distribution combinations" and "Hole area" 8th and 96th hours This is a prediction model using five indices, “combination of eye frequency distribution”.

  FIG. 22 is a graph illustrating a prediction result of each sample in the first prediction model in the example. The vertical axis in FIG. 22 indicates the degree of differentiation of the sample on the fifth day predicted by the first prediction model. The horizontal axis of FIG. 22 shows the value (apparent differentiation degree) that the expert evaluated the differentiation degree of the sample at the time of the fifth day. In FIG. 22, one point is plotted on the graph for each sample. In FIG. 22, the more the point is plotted near the straight line extending from the upper right to the lower left of the graph, the higher the prediction accuracy. In this first prediction model, the prediction accuracy (correct answer rate) of differentiation was 90.5% (error ± 5%).

  The second prediction model includes “a combination of frequency distributions at the 8th and 48th hours of“ Breadth ””, “a combination of frequency distributions at the 8th and 32nd hours of“ Breadth ””, and “ “Combination of frequency distributions at 8th and 24th hours of“ Inner radius ””, “Combination of frequency distributions at 8th and 16th hours of“ Orientation (cell orientation) ””, and “Modified Orientation ( This is a prediction model using five indices, “the combination of frequency distributions at the 8th hour and the 24th hour” of “the degree of variation in cell orientation”.

  The “Orientation” is a feature amount indicating an angle formed by the long axis of each cell and the horizontal direction (X axis) of the image. If this “Orientation” value is the same, the cells are oriented in the same direction. Further, the “Modified Orientation” is a feature value obtained by calculating the variation by digitizing the angle of each cell in a state where the cells in the image are deformed by filtering. The value of “Modified Orientation” has a characteristic that the value becomes larger as the angle of the cell is varied.

  FIG. 23 is a graph illustrating a prediction result of each sample in the second prediction model in the example. The way of viewing FIG. 23 is the same as that of FIG. In the second prediction model, differentiation was predicted based on the observation results up to the second day (48 hours), and the prediction accuracy was 85.7% (error ± 5%). Therefore, according to the second prediction model in this example, it is possible to quantitatively predict the differentiation of myocytes, which is usually very difficult, with high accuracy based on the observation results up to the second day.

  Next, the relationship between the number of remaining doublings predicted according to the present embodiment and the number of remaining doublings actually measured will be described with reference to FIG. Here, as shown in FIG. 24A, it is assumed that an experiment is performed in which a cell is imaged every 24 hours (24h) and a phase difference image obtained by this imaging is used. In this experiment, the medium is changed every three days. In addition, this cultured cell passes 1 passage about every 6 days. Here, as a procedure, an experiment is performed in each of the cases where there is no freezing (for example, in the case of the upper left in FIG. 5) and in the case of freezing (for example, in the case of the lower left in FIG. 5). Yes.

  FIG. 24 (b) shows the case where there is no freezing (for example, the case of the upper left in FIG. 5) with the remaining doubling number obtained by this experiment as the horizontal axis, and the remaining doubling number predicted by the present embodiment as the vertical axis. The symbol “◯” is plotted for each experimental result on the axis. In this figure, when the experimental result and the predicted result are completely coincident with each other, the plotted symbol “◯” is plotted on a straight line having an inclination 1 passing through the origin shown in FIG.

  Here, the cell evaluation calculation model construction unit 4221 constructs a cell evaluation calculation model by multiple regression analysis (MRA). Then, the cell evaluation unit 4222 calculates and predicts the number of remaining doublings using a cell evaluation calculation model constructed by multiple regression analysis (MRA).

  In the case of FIG. 24 (b), as indices, “48th and 24th hours of“ Shape Factor ””, “72nd and 24th hours of“ Fiber Length ””, and “Fiber Breath”. A cell evaluation calculation model is constructed by multiple regression analysis (MRA) using the five indexes “24 hours”.

  FIG. 24C shows a graph similar to FIG. 24B in the case of freezing (for example, the case of the lower left in FIG. 5).

  In the case of FIG. 24C, as indices, “the difference between the 24th and 96th hours of“ Fiber Length ””, “the 96th hour of“ Fiber Length ””, and ““ Fiber Breath ””. A cell evaluation calculation model is constructed by multiple regression analysis (MRA) using three indexes of “the difference between the 48th hour and the 96th hour”.

In the case of FIG. 24B, the correlation coefficient (R ² ) is 0.976, and the standard error is 1.63. In the case of FIG. 24C, the correlation coefficient (R ² ) is 0.958, and the standard error is 1.60. As described above, in both cases of freezing and freezing, the cell evaluation calculation model construction unit 4221 calculates the number of remaining doublings with high accuracy when the cell evaluation calculation model is constructed by multiple regression analysis (MRA). it can.

  Note that, as described with reference to FIGS. 24B and 24C, the index (or cell evaluation calculation model) used for the cell evaluation calculation model for calculating the remaining doubling number varies depending on the procedure. The prediction accuracy may be higher.

  Accordingly, when building a cell evaluation calculation model, the cell evaluation calculation model construction unit 4221 may construct a cell evaluation calculation model for each procedure (FIG.). Then, the cell evaluation calculation model construction unit 4221 stores the constructed cell evaluation calculation model in the storage unit 41 in association with information indicating the procedure.

  Thereafter, when evaluating a cell to be evaluated, the cell evaluation unit 4222 reads from the storage unit 41 a cell evaluation calculation model corresponding to a procedure when the cell to be evaluated is cultured. And the cell evaluation part 4222 evaluates the cell used as evaluation object based on this read cell evaluation calculation model.

  In the present embodiment, by constructing the cell evaluation calculation model for each procedure as described above, as described with reference to FIGS. 24B and 24C, the accuracy can be further improved.

  Here, the “procedure” may be a “procedure” calculated by the procedure evaluation unit 4212. In addition, when the “procedure” is known, the “procedure” here may be the input known “procedure”. In the case of the “procedure” calculated by the technique evaluation unit 4212, even if the technique is not known in advance, the cell evaluation calculation model construction unit 4221 can construct a cell evaluation calculation model for each technique, and The cell evaluation unit 4222 can more accurately predict characteristics such as the number of remaining doublings for cells based on the cell evaluation calculation model constructed for each procedure.

  FIG. 25 is a flowchart for explaining a cell culture method using the cell evaluation apparatus of this embodiment. In this flowchart, it is assumed that the culture container 19 in which desired cells to be grown are cultured is stored in one of a plurality of shelves of the stocker 21 of the incubator 11.

  First, in step S1201, the CPU 42 controls the temperature adjusting device 15a and the humidity adjusting device 15b so as to culture cells under predetermined culture conditions (for example, predetermined temperature, humidity, etc.). After elapse of the predetermined period, in step S1202, the CPU 42 executes the cell evaluation program according to the embodiment of the present invention read from the storage unit 43, and evaluates the cells. The “result of cell evaluation (cell evaluation result)” may be a procedure or the number of remaining doublings of the cell.

  Next, in step S1203, the CPU 42 determines whether to stop the culture, change the culture conditions, or continue the culture under the current culture conditions based on the evaluation result of the cells.

Next, when it is determined in step S1204 that the CPU 42 stops the culture (YES in step S1204), the CPU 42 displays information indicating the suspension of the culture on a monitor or the like (not shown) and ends the process.
On the other hand, when the CPU 42 does not determine that the culture is to be stopped (NO in step S1204), the CPU 42 proceeds to the process of step S1205.

Next, when it is determined in step S1205 that the CPU 42 changes the culture condition (YES in step S1205), the CPU 42 changes to the culture condition (for example, predetermined temperature, humidity, etc.) associated with the evaluation result of the cell state. The temperature adjusting device 15a and the humidity adjusting device 15b are controlled so as to be performed (step S1206). Thereafter, the CPU 42 returns the process to step S1202.
On the other hand, if the CPU 42 determines to continue culturing under the current culturing conditions (NO in step S1205), the CPU 42 advances the process to step S1207.

  Next, in step S1207, the CPU 42 extracts, for each cell, an area of the image in which the cell is imaged from the image captured by the imaging device 34 for each elapse of a predetermined time, and the extracted cell. Is counted the number of areas of the image in which is picked up, that is, the number of cells.

Next, in step S1208, when the counted number of cells has not reached the predetermined number of cells (NO in step S1208), after the time corresponding to the counted number of cells has elapsed, the CPU 42 performs a process in step S1202. return.
On the other hand, when the counted number of cells has reached a predetermined number (YES in step S1208), the CPU 42 displays information indicating that the culture of the cells has been completed on a monitor (not shown) or the like. Above, this flowchart is complete | finished.

  As described above, if the cell culture method of the present invention is used, the culture conditions can be dynamically changed based on the evaluation of the cells, so that desired cells can be easily proliferated.

  In the process of FIG. 25, the CPU 42 may display the determined result on a display unit or the like. And a user inputs the information which changes culture conditions etc. into CPU42 via an input part according to the result displayed on this display part. In this way, the CPU 42 may change the culture conditions and the like based on information input by the user.

<Supplementary items of the embodiment>
(1) In the first or second embodiment, the example in which the cell evaluation device is incorporated in the control device 41 of the incubator 11 has been described. However, the cell evaluation device of the present invention acquires a microscope image from the incubator 11. It may be configured by an external independent computer that performs analysis (in this case, illustration is omitted).

(2) The cell evaluation apparatus of the present invention combines a plurality of cell evaluation calculation models, and generates final evaluation information by majority (or weighted average) of calculation results based on these cell evaluation calculation models. Also good. In this case, for example, the MRA is strong in some cases, and the FNN is strong in other cases, so that one cell evaluation calculation model can cover a low-accuracy situation with another model, and the evaluation information Accuracy can be further increased.

(3) When the cell evaluation apparatus obtains a cell evaluation calculation model of evaluation information, the cell evaluation apparatus may first calculate a calculation result by combining a plurality of indexes, and increase or decrease the indexes by a variable increase / decrease method. . Further, all indicators may be used if the accuracy of the data is high.

(4) In the second embodiment, the example in which the amount of change in the frequency distribution is obtained using the sum of absolute values of the differences between the two frequency distributions has been described. However, the frequency is calculated based on the square sum of the differences between the two frequency distributions. You may obtain | require the variation | change_quantity of distribution. Moreover, the calculation formula shown in the first or second embodiment is merely an example, and may be, for example, an n-order equation of second or higher order.

(5) The feature quantities shown in the above-described embodiments and examples are merely examples, and it is of course possible to employ other feature quantity parameters according to the type of cells to be evaluated.

  The above (1) to (5) are the same not only for the cell evaluation calculation model but also for the technique evaluation calculation model.

1 or 13 may be implemented by dedicated hardware, or may be implemented by a memory and a microprocessor.
1 or 13 may be realized by dedicated hardware, and each configuration provided in the control device 41 may include a memory and a CPU (central processing unit). The program may be realized by loading a program for realizing the function of each component included in the control device 41 into a memory and executing the program.

  Further, a program for realizing the function of each component included in the control device 41 in FIG. 1 or FIG. 13 is recorded on a computer-readable recording medium, and the program recorded on the recording medium is read into a computer system, By executing, the processing by each configuration provided in the control device 41 may be performed. Here, the “computer system” includes an OS and hardware such as peripheral devices.

Further, the “computer system” includes a homepage providing environment (or display environment) if a WWW system is used.
The “computer-readable recording medium” refers to a storage device such as a flexible medium, a magneto-optical disk, a portable medium such as a ROM and a CD-ROM, and a hard disk incorporated in a computer system. Furthermore, the “computer-readable recording medium” dynamically holds a program for a short time like a communication line when transmitting a program via a network such as the Internet or a communication line such as a telephone line. In this case, a volatile memory in a computer system serving as a server or a client in that case, and a program that holds a program for a certain period of time are also included. The program may be a program for realizing a part of the functions described above, and may be a program capable of realizing the functions described above in combination with a program already recorded in a computer system.

  In the cell evaluation apparatus according to the present embodiment, a cell evaluation calculation model construction unit (cell evaluation calculation model construction apparatus) and a cell evaluation unit (cell evaluation apparatus) for performing cell evaluation are incorporated in the same apparatus. However, the present invention is not limited to such a configuration. For example, a cell evaluation model construction device having a function necessary for constructing a cell evaluation calculation model, a cell evaluation unit in which a cell evaluation calculation model created by the cell evaluation model construction device is introduced, and a cell feature amount A cell evaluation apparatus having a function necessary for cell evaluation, such as a calculation unit, may be provided separately. Similarly to the cell evaluation calculation model construction device or the cell evaluation device, the technique evaluation device may be configured as a device different from these devices.

  From the above detailed description, features and advantages of the embodiments will become apparent. It is intended that the scope of the claims extend to the features and advantages of the embodiments as described above without departing from the spirit and scope of the right. Further, any person having ordinary knowledge in the technical field should be able to easily come up with any improvements and modifications, and there is no intention to limit the scope of the embodiments having the invention to those described above. It is also possible to use appropriate improvements and equivalents within the scope disclosed in.

  DESCRIPTION OF SYMBOLS 11 ... Incubator, 15 ... Constant temperature chamber, 19 ... Culture container, 22 ... Observation unit, 34 ... Imaging device, 41 ... Control device, 42 ... CPU, 43 ... Memory | storage part, 4201 ... Input part, 4202 ... Feature-value calculating part, 4203 ... Image reading unit, 4204 ... Frequency distribution calculation unit, 4211 ... Procedure evaluation calculation model construction unit (determination reference creation unit), 4212 ... Procedure evaluation unit (image judgment unit), 4221 ... Cell evaluation calculation model construction unit (remaining number of times) Calculation model construction unit), 4222... Cell evaluation unit (remaining frequency calculation unit)

Claims (7)

A plurality of images obtained by imaging a plurality of cells cultured in the same culture container at different times, and an input unit for inputting information indicating the remaining number of times the cells are divided;
A feature amount calculation unit that outputs a feature amount indicating a morphological feature of the cell in the image;
A remaining number calculation model construction unit for constructing a calculation model for calculating the remaining number for the cell based on the feature amount corresponding to each of the images and the information indicating the remaining number;
With
The remaining number calculation model construction unit
Constructing the calculation model by multiple regression analysis with the feature quantity as a variable;
A cell evaluation model generation device characterized by the above. The feature amount calculation unit includes a frequency distribution calculation unit that outputs a frequency distribution indicating a feature amount indicating the morphological feature of the cell and the number of the cells having the feature amount in each of the images,
The remaining number calculation model construction unit
The cell evaluation model generation device according to claim 1, wherein the calculation model is constructed using the frequency distribution output from the frequency distribution calculation unit. An image reading unit that reads an image in which cells cultured in a culture vessel are imaged;
The feature amount calculation unit, from the image read by the image reading unit, a remaining number calculation feature amount calculation unit for outputting the feature amount of the cells copied in the image,
3. The feature amount output from the remaining number calculation feature amount calculation unit is input to a calculation model constructed by the cell evaluation calculation model construction unit of the cell evaluation model generation device according to claim 1 or 2. A remaining number calculating unit that calculates the remaining number of times that the cells of the image read into the image reading unit divide,
A cell evaluation apparatus comprising: The remaining number calculation feature quantity calculation unit is a frequency indicating the feature quantity indicating the morphological feature of the cell and the number of the cell having the feature quantity that are copied in the image read by the image reading unit. It has a frequency distribution calculation unit for calculating the remaining number of times to output the distribution,
The remaining number calculation unit
Calculating the remaining number of times by inputting the frequency distribution output from the remaining number calculating frequency distribution calculating unit to the calculation model;
The cell evaluation apparatus according to claim 3. A temperature-controlled room that accommodates a culture container for culturing cells, and that can maintain the inside in a predetermined environmental condition, and an imaging device that captures an image of the cell contained in the culture container in the temperature-controlled room;
The cell evaluation model generation device according to claim 1 or claim 2, or the cell evaluation device according to claim 3 or claim 4,
An incubator comprising:   A program for causing a computer to function as the cell evaluation model generation device according to claim 1 or 2, or the cell evaluation device according to claim 3 or 4.   A method for culturing cells, comprising changing the culture conditions of cells cultured in the culture vessel based on the remaining number of times calculated by the cell evaluation apparatus according to claim 3 or 4.