JP7375886B2 - Culture support equipment, observation equipment, and programs - Google Patents

Description

The present invention relates to a culture support device , an observation device, and a program .
This application claims priority based on Japanese Patent Application No. 2018-029336 filed in Japan on February 22, 2018, the contents of which are incorporated herein.

In general, technology for evaluating the culture state of cells has become a fundamental technology in a wide range of fields, including cutting-edge medical fields such as regenerative medicine and drug screening. For example, in the field of regenerative medicine, there is a process of growing and differentiating cells in vitro. In the above-mentioned process, it is required to accurately evaluate the culture state of the cells, such as the success or failure of cell differentiation, the presence or absence of cell canceration or infection. As an example, a method is disclosed in which the culture state of cells is determined by performing image processing on images of cells (see Patent Document 1).

Japanese Patent Application Publication No. 2004-229619

One aspect of the present invention includes a first information acquisition unit that acquires first information regarding a first culture state of the cells in a first period of a cell culture process ; a second information acquisition unit that acquires second information regarding a second culture state of the cells;
A learning result in which a relationship between a culture protocol indicating the culture conditions of the cells in the culture process and a change in the culture state of the cells due to the culture protocol is learned, information regarding the culture state, and a predetermined predetermined value based on the culture protocol. a state prediction unit that repeatedly performs a process of predicting the culture state after the period from the first culture state until reaching the second culture state;
a culture protocol presentation unit that presents the culture protocol used in a series of prediction processes performed by the state prediction unit , and the state prediction unit is configured to change the culture state output by the prediction process to the second culture state. If it has not been reached, the culture support device performs a prediction process based on the information regarding the culture state outputted by the previous prediction process, the culture protocol, and the learning result.
One aspect of the present invention provides a thermostatic chamber capable of accommodating a culture container for culturing the cells and maintaining the interior at predetermined environmental conditions; This is an observation device that includes an imaging device that captures images every time, and the culture support device described above.
One aspect of the present invention includes a first information acquisition step of acquiring, in a computer, first information regarding a first culture state of the cells at a first stage of a cell culture process; and a second stage after the first stage. a second information acquisition step of acquiring second information regarding a second culture state of the cells, a culture protocol indicating the culture conditions of the cells in the culture process, and a relationship between a change in the culture state of the cells due to the culture protocol; A state in which prediction processing of the culture state after a predetermined period based on the learning result of the learned sex, information regarding the culture state, and the culture protocol is repeated until the culture state is reached from the first culture state to the second culture state. A prediction step, wherein the state prediction step is a program for executing a state prediction step related to the culture state output by the immediately preceding prediction process, when the culture state output by the prediction process has not reached the second culture state. This is a program that performs predictive processing based on information, the culture protocol, and the learning results.

FIG. 1 is a block diagram showing an outline of an incubator including a culture support device according to an embodiment of the present invention. 1 is a diagram showing an example of a front view of an incubator according to an embodiment of the present invention. 1 is a diagram showing an example of a plan view of an incubator according to an embodiment of the present invention. It is a figure showing an example of observation operation in an incubator of an embodiment of the present invention. 1 is a diagram showing an example of a functional configuration of a control device according to an embodiment of the present invention. It is a figure showing an example of processing of the learning stage of an embodiment of the present invention. It is an example of the information stored in the storage part of embodiment of this invention. It is a figure showing an example of implementation event information of an embodiment of the present invention. It is a figure showing an example of processing of the application stage of an embodiment of the present invention. FIG. 3 is a diagram showing an example of an image stored in an image storage unit according to an embodiment of the present invention. It is a figure showing an example of an initial information input screen of an embodiment of the present invention. It is a figure showing an example of a termination information input screen of an embodiment of this invention. It is a figure showing an example of processing of culture process analysis of an embodiment of the present invention. It is a figure which shows an example of the process which predicts the image feature-value of the cell image of a final state of embodiment of this invention. It is a figure showing an example of a cultivation mode selection screen of an embodiment of the present invention. It is a figure which shows an example of an analysis result screen of embodiment of this invention. It is a figure showing an example of an event selection screen of an embodiment of the present invention.

[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 11 including a culture support device according to an embodiment. Moreover, FIG.2 and FIG.3 is a figure which shows an example of the front view and top view of the incubator 11 of this embodiment.
This incubator 11 is an example of an observation device.

The incubator 11 of the 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 spaces of the upper casing 12 and the lower casing 13 are partitioned into upper and lower parts by a base plate 14.

First, an outline of the configuration of the upper casing 12 will be explained. A thermostatic chamber 15 for culturing cells is formed inside the upper casing 12. This constant temperature chamber 15 has a temperature adjustment device 15a and a humidity adjustment device 15b, and the inside of the constant temperature chamber 15 is maintained in an environment suitable for culturing cells (for example, an atmosphere with a temperature of 37° C. and a humidity of 90%). Note that illustrations of the temperature adjustment device 15a and the humidity adjustment device 15b in FIGS. 2 and 3 are omitted). In other words, the constant temperature room 15 can maintain the interior under predetermined environmental conditions.

A large door 16, a middle door 17, and a small door 18 are arranged at the front of the constant temperature 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 constant temperature room 15 from the outside environment when the large door 16 is opened. The small door 18 is a door for carrying in and out a culture container 19 for culturing cells, and is attached to the middle door 17. By carrying in and out the culture container 19 through this small door 18, it becomes possible to suppress environmental changes in the thermostatic chamber 15. In addition, the airtightness of the large door 16, the middle door 17, and the small door 18 is maintained by the packing SL1, the packing SL2, and the packing SL3, respectively.

For example, these doors are opened when performing operations such as "medium exchange,""subculture,""cleaning," and "incubator transfer." The types of these operations are selected depending on the culture state of the cells. In the following description, these tasks will also be collectively referred to as "events." Note that "events" include work performed without opening the door, doing nothing, and discontinuing cell culture.
Note that "medium exchange" refers to replacing all or part of the medium in the culture container with a new medium. Furthermore, "passage" refers to collecting the proliferated cells and reseeding them into another culture container. Moreover, "cleaning" means cleaning the inside of the incubator. Cleaning includes disinfecting the surfaces of the incubator and sterilizing the water necessary to maintain humidity within the incubator. Furthermore, "transferring incubators" refers to transferring an incubator to a different incubator when there are multiple incubators.

Further, in the constant temperature room 15, a stocker 21, an observation unit 22, a container transport device 23, and a transport table 24 are arranged. Here, the transport table 24 is arranged in front of the small door 18, and the culture container 19 is carried in and out through the small door 18.

Stocker 21 is arranged on the left side of thermostatic chamber 15 when viewed from the front of upper casing 12 (lower side in FIG. 3). The stocker 21 has a plurality of shelves, and each shelf of the stocker 21 can accommodate a plurality of culture containers 19. Note that each culture container 19 accommodates cells to be cultured together with a medium. In this way, the thermostatic chamber 15 houses a culture container for culturing cells.

The observation unit 22 is arranged on the right side of the thermostatic chamber 15 when viewed from the front of the upper casing 12. This observation unit 22 can perform time-lapse observation of cells within the culture container 19. Here, time-lapse observation is a method of observing time-series changes in a sample by imaging the sample at predetermined time intervals based on a preset imaging schedule. Imaging of the sample may be performed at regular time intervals or at different time intervals.

Here, the observation unit 22 is fitted into the opening of the base plate 14 of the upper casing 12 and arranged. The observation unit 22 includes a sample stage 31, a stand arm 32 projecting above the sample stage 31, and a main body portion 33 incorporating a microscopic optical system for phase contrast observation and an imaging device 34. The sample stage 31 and stand arm 32 are placed in the thermostatic chamber 15, while the main body portion 33 is housed within the lower casing 13.

The sample stage 31 is made of a translucent material, and the culture container 19 can be placed thereon. This sample stage 31 is configured to be movable in the horizontal direction, and the position of the culture container 19 placed on the top surface can be adjusted. Further, the stand arm 32 has a built-in LED light source 35. The imaging device 34 can obtain a microscopic image of the cells by imaging the cells in the culture container 19 that are transmitted and illuminated from above the sample stage 31 by the stand arm 32 through the microscopic optical system. The imaging device 34 images the cells housed in the culture container in the thermostatic chamber 15 at predetermined time intervals.

The container conveyance device 23 is arranged at the center of the thermostatic chamber 15 when viewed from the front of the upper casing 12. This container transport device 23 transfers the culture container 19 between the stocker 21 , the sample stage 31 of the observation unit 22 , and the transport stage 24 .

As shown in FIG. 3, the container transport device 23 includes a vertical robot 38 having a multi-joint arm, a rotation stage 39, a mini stage 36, and an arm portion 37. The rotation stage 39 is attached to the tip of the vertical robot 38 via a rotation shaft 35a so as to be rotatable by 180 degrees in the horizontal direction. Therefore, in the rotation stage 39, the arm portions 37 can be opposed to the stocker 21, the sample stage 31, and the transport stage 24, respectively.

Further, the mini stage 36 is attached to the rotation stage 39 so as to be slidable in the horizontal direction. An arm portion 37 that grips the culture container 19 is attached to the mini stage 36.

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

The control device 41 is connected to the temperature adjustment device 15a, the humidity adjustment device 15b, the observation unit 22, and the container conveyance device 23, respectively. This control device 41 includes a calculation section 42 and a storage section 43, and centrally controls each section of the incubator 11 according to a predetermined program. This control device 41 is an example of a culture support device.

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

[Example of observation behavior]
Next, an example of the observation operation in the incubator 11 will be described with reference to the flowchart in FIG. 4.
FIG. 4 is a diagram showing an example of the observation operation in the incubator 11 of this embodiment. This figure shows an example of an operation in which a culture container 19 carried into a thermostatic chamber 15 is subjected to time-lapse observation according to a registered observation schedule.

Step S101: The calculation unit 42 compares the observation schedule of the management data in the storage unit 43 with the current date and time, and determines whether the observation start time for the culture container 19 has arrived. When the observation start time has come (step S101: YES), the calculation unit 42 moves the process to S102. On the other hand, if it is not the observation time for the culture container 19 (step S101: NO), the calculation unit 42 waits until the time of the next observation schedule.

Step S102: The calculation unit 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 out the instructed culture container 19 from the stocker 21 and places it on the sample stage 31 of the observation unit 22. Note that when the culture container 19 is placed on the sample stage 31, a bird-view camera (not shown) built into the stand arm 32 captures an overall observation image of the culture container 19.

Step S103: The calculation unit 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 container 19, and drives the imaging device 34 to capture a microscopic image of the cells in the culture container 19.

At this time, the imaging device 34 captures a microscope image based on the imaging conditions (magnification of the objective lens, observation point in the container) specified by the user based on the management data stored in the storage unit 43. For example, when observing a plurality of points within the culture container 19, the observation unit 22 sequentially adjusts the position of the culture container 19 by driving the sample stage 31, and captures a microscope image at each point. Note that the data of the microscope image acquired in S<b>103 is read into the control device 41 and recorded in the storage unit 43 under the control of the calculation unit 42 .

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

Through the above-described procedure, time-series image data observed by the incubator 11 is stored in the storage unit 43. In the following description, obtaining time-series image data by the incubator 11 is also referred to as time-lapse imaging.

[Function to present culture protocols and final state prediction according to culture mode]
Next, with reference to FIGS. 5 to 16, a presentation function for predicting the culture protocol and final state according to the culture mode will be described. Here, the culture protocol is information indicating procedures for events to be performed and environmental conditions to be set. The final state is the state of cells obtained at the end of culture.

FIG. 5 is a diagram showing an example of the functional configuration of the control device 41 of this embodiment. As described above, the control device 41 includes the calculation section 42 and the storage section 43.
The calculation unit 42 includes an image acquisition unit 421, a display control unit 422, an operation detection unit 423, a storage control unit 424, a learning unit 425, an analysis information generation unit 426, a culture mode selection unit 427, and a parameter acquisition unit It includes a section 4285 and an analysis result presentation section 428 as its functional sections.
The storage unit 43 includes an image storage unit 431 , an implemented event storage unit 432 , an environment log storage unit 433 , a learning result storage unit 434 , a culture mode storage unit 435 , and a predicted result storage unit 436 .

The image acquisition unit 421 acquires an image P from the imaging device 34. This image P is an image of cells in culture that are imaged at predetermined intervals, for example, based on an imaging schedule. When the image acquisition unit 421 acquires the image P from the imaging device 34, it adds imaging date and time information DT indicating the imaging date and time and stores it in the image storage unit 431.

The display control unit 422 controls the screen display of the display unit 44. Specifically, the display control unit 422 displays the image P stored in the image storage unit 431 and event candidates related to this image P on the display unit 44. The display control unit 422 displays an initial information input screen DI for inputting initial information IS, a termination information input screen DF for inputting termination information FS, a culture mode selection screen DM for selecting a culture mode, and a culture process selection screen DM. An analysis result screen DO showing analysis results and an event selection screen DE for selecting an event to be implemented are displayed.

The operation unit 45 includes a touch panel, a mouse, a keyboard, or the like. Note that when the operation section 45 is a touch panel, the operation section 45 and the display section 44 may be configured as one unit. Further, the operation section 45 and the display section 44 may be configured as a touch panel provided in the upper casing 12 or the lower casing 13.
The observer selects an event to be performed by operating this operation unit 45. In the above-mentioned example, when performing a culture medium exchange operation, the observer operates the operation unit 45 to select "medium exchange" as the event to be performed.
Furthermore, the observer sets the environmental conditions of the thermostatic chamber 15 by operating the operating section 45 .
Further, in the above example, a mode has been described in which the temperature and humidity of the constant temperature room 15 are set as the environmental conditions of the constant temperature room 15, but the present invention is not limited to this. The constant temperature room 15 may have a carbon dioxide concentration adjustment device that adjusts the carbon dioxide concentration, and this carbon dioxide concentration adjustment device may be controlled by the control device 41.

The operation detection unit 423 detects an operation on the operation unit 45. When detecting an operation, the operation detection unit 423 generates implementation event information EV corresponding to this operation. When the observer performs an operation on the operation unit 45 to select “medium exchange”, the operation detection unit 423 detects that “medium exchange” has been selected as the implementation event.
Further, the operation detection unit 423 generates implementation event information EV indicating "medium exchange". Moreover, when the operation detection unit 423 detects an operation for setting the environmental conditions of the constant temperature room 15, it generates environmental log information EL according to this operation. When the observer performs an operation on the operation unit 45 to set the environmental conditions of the constant temperature room 15 to an atmosphere with a temperature of 37°C and a humidity of 90%, the operation detection unit 423 detects that the temperature is 37°C and the humidity is 90%. Detects what has been set as an environmental condition.

The storage control unit 424 controls writing of information to the storage unit 43. Specifically, the storage control unit 424 associates the image acquired by the image acquisition unit 421 with the implemented event information EV indicating the event related to cell culture at the timing when the image was captured, and stores the image in the implemented event storage unit 432. to be memorized. The storage control unit 424 stores the image acquired by the image acquisition unit 421 in the environmental log storage unit 433 in association with the environmental log information EL indicating the environmental conditions of the constant temperature room 15 at the timing when the image was captured.

Furthermore, the storage control unit 424 may add information regarding the date and time when the event was performed to the implemented event information EV and store the information. In this case, the implemented event information EV includes information regarding the date and time when the event was implemented.
Further, the storage control unit 424 may add information regarding the date and time when the environmental log was acquired to the environmental log information EL and store the environmental log information EL. In this case, the environmental log information EL includes information regarding the date and time when the environmental log was acquired.

The learning unit 425 learns the relationship between the image stored in the image storage unit 431, the implemented event information EV associated with this image, and the environmental log information EL associated with this image. . The learning unit 425 learns the relationships between these pieces of information using various known methods. The learning unit 425 stores the learned result in the learning result storage unit 434 as a learning result LR.

The analysis information generation unit 426 generates each piece of information that the analysis result presentation unit 428 uses for analysis. The analysis information generation section 426 includes an initial information generation section 4261, a current information generation section 4262, an end information generation section 4264, and an intermediate information generation section 4263.

The initial information generation unit 4261 acquires, from among the images P stored in the image storage unit 431, images P acquired from the start of the culture process to the first medium exchange. The initial information generating unit 4261 acquires the implemented event information EV for the implemented event detected from the start of the culture process to the first culture medium exchange from the implemented event information EV stored in the implemented event storage unit 432. The initial information generation unit 4261 acquires the environmental log information EL detected from the start of the culture process to the first medium exchange from among the environmental log information EL stored in the environmental log storage unit 433. Here, the start of the culture process is, for example, immediately after seeding in the cell culture process.
The initial information generation unit 4261 supplies the acquired image P, implemented event information EV, and environment log information EL to the analysis result presentation unit 428 as initial information IS.

The current information generation unit 4262 acquires the images P that have been acquired from immediately after seeding to the present among the images P stored in the image storage unit 431. The current information generating unit 4262 acquires the implemented event information EV for the implemented event detected from immediately after sowing to the present among the implemented event information EV stored in the implemented event storage unit 432. The current information generation unit 4262 acquires the environmental log information EL detected from immediately after sowing to the present among the environmental log information EL stored in the environmental log storage unit 433.
The current information generation unit 4262 supplies the acquired image P, the implemented event information EV, and the environment log information EL to the analysis result presentation unit 428 as current information PS.

The intermediate information generation unit 4263 acquires the intermediate information MS from the operation detection unit 423 and supplies it to the analysis result presentation unit 428. The midway information MS is input from the operation unit 45.
Note that the intermediate information generation unit 4263 may not be provided.

The termination information generation unit 4264 acquires the termination information FS from the operation detection unit 423 and supplies it to the analysis result presentation unit 428. Here, the termination information FS is input from the operation unit 45.

The termination information FS is information selected according to the purpose or goal of culture, such as expansion culture, medicinal efficacy, transplantation, biological material production, cell experimentation, and improvement of culture processes. The termination information FS includes, for example, the amount of cells, the name of the cell/organ/organ, the sample image of the cell you want to obtain by culturing, the name/paper of the differentiation induction method, the drug/procedure/conditions you want to use, the transplant surgery to transplant the cells. name of the surgical procedure, name of the disease/condition or age/sex/height/weight or medical record of the patient to be transplanted, name/component of the drug to be tested for pharmacological efficacy, name of the disease to be elucidated, biological material/protein to be obtained by culture, and This includes the types of cell experiments in which you would like to utilize cells obtained through culture. Note that the amount of cells is specified by the target increase in cells in expansion culture, the area, the number of passages after culture, and the like.
A sample image of cells desired to be obtained by culturing in the end information FS is called a end image PF. The end information FS other than the end image PF is called non-image end information CF.

The culture mode selection unit 427 selects culture mode CM. The culture mode CM is information indicating a set of weights W indicating which of the setting values V used by the analysis result presentation unit 428 to analyze the culture protocol is given priority over other setting values. . Therefore, the culture mode CM is information indicating a predetermined set of weights W. Further, the weight W is used to select a culture protocol indicating conditions for cell culture.

Here, the setting value V is, for example, past culture results, predicted cell amount, predicted type of cultured cells, prediction accuracy (guaranteed accuracy), amount of money/period calculated from the culture setting value, etc. These include culture costs, consumption of culture media and equipment calculated from culture settings, process and degree of cell growth, and culture work time. The set value V may be a value specifying an upper limit value or a lower limit value of these quantities.
The weight W is a weight associated with each setting value V. Note that the weight W may be associated with a plurality of setting values V.

The culture mode CM includes, for example, a quality-oriented mode, a production amount-oriented mode, and a speed mode. The quality emphasis mode is a culture mode in which prediction accuracy among the set values V is given more importance than other set values of the set values V. The production amount emphasis mode is a culture mode in which the predicted cell quantity of the set value V is given more importance than other set values of the set value V. The speed mode is a culture mode in which the culture cost of the set value V is given more importance than other set values of the set value V.

The culture mode selection unit 427 selects a culture mode CM in response to an operation from the operation unit 45. Here, the culture mode CM is stored in advance in the culture mode storage unit 435. That is, the culture mode selection unit 427 selects a culture mode CM from one or more culture mode CMs stored in advance in the culture mode storage unit 435.

In addition, although the above-mentioned example demonstrated the aspect in which the weight W which the culture mode selection part 427 acquires is determined by the culture mode CM selected by the culture mode selection part 427, it is not limited to this. The culture mode selection unit 427 may acquire the weight W input from the operation unit 45. When the weights W are input from the operation unit 45, the observer inputs each of the weights W from the operation unit 45.

Further, the culture mode CM may be information indicating one or more sets of setting values V instead of a set of weights W. Further, the culture mode CM may include information indicating a set of a weight W and a set of one or more setting values V. The quality emphasis mode may include prediction accuracy as a predetermined value, for example. The production amount emphasis mode may include, for example, the predicted amount of cells as a predetermined value. The speed mode may include, for example, the length of the culture period as a predetermined value.

The analysis result presentation unit 428 presents a culture protocol indicating conditions for cell culture. The analysis result presentation section 428 includes an initial information acquisition section 4281, a current information acquisition section 4282, an intermediate information acquisition section 4283, an end information acquisition section 4284, a parameter acquisition section 4285, a feature extraction section 4286, and a culture protocol. It includes a presentation section 4287 and a state prediction section 4288.

The initial information acquisition unit 4281 acquires the initial information IS supplied by the initial information generation unit 4261. Here, the initial information IS is information regarding the culture state of the cells from the start of the culture process to the first medium exchange. That is, the initial information generation unit 4261 acquires initial information IS regarding the culture state of the cells from the start of the culture process to the first medium exchange.

The current information acquisition unit 4282 acquires the current information PS supplied by the current information generation unit 4262. Here, the current information PS is information regarding the cell culture state from immediately after seeding to the present in the cell culture process. That is, the current information acquisition unit 4282 acquires current information PS regarding the culture state of cells from the start of the culture process to the present.

The intermediate information acquisition unit 4283 acquires the intermediate information MS supplied by the intermediate information generation unit 4263. Here, the intermediate information MS is information regarding the state of cell culture between the start of the culture process and the end of the culture process. That is, the intermediate information acquisition unit 4283 acquires intermediate information MS regarding the culture state of cells at a time between the start of the culture process and the end of the culture process.

The termination information acquisition unit 4284 acquires the termination information FS supplied by the termination information generation unit 4264. Here, the end information FS is information regarding the cell culture state at the end of the cell culture process. That is, the termination information generation unit 4264 acquires termination information FS regarding the culture state of the cells at the time of termination after the period from the start of the culture process to the first medium exchange.

The parameter acquisition unit 4285 acquires a parameter PM used to select a culture protocol indicating conditions for culturing cells. Here, the parameter PM is the weight W indicated by the culture mode CM selected by the culture mode selection unit 427 and the set value V supplied from the operation detection unit 423. The set value V is input by the observer from the operation unit 45.

The feature extraction unit 4286 extracts the image feature FP from the image P included in the acquired initial information IS using a known machine learning method. The feature extraction unit 4286 extracts the image feature FP from the image P included in the acquired current information PS using a known machine learning method.

Here, the image features FP include, for example, the growth state (single, colony-formed, sheet-like), number of cells, cell size, external shape characteristics of cells (spherical, bubbly, jagged), adhesion between cells. nature, neighbor connectivity, number of nuclei, shape of nucleus, size of nucleus, number of nucleoli, size of nucleolus, concentration of nucleolus, amount of cytoplasmic granules, brightness of cytoplasmic granules, empty space. These include the size of the vacuole, the number of vacuoles, the shape (number, length, and thickness) of cytoplasmic projections, the occupied area, and the density. Further, the image feature amount FP includes a feature amount regarding a change in the image P over time.

The feature amount extraction unit 4286 extracts the non-image feature amount F from the implementation event information EV and the environment log information EL included in the acquired initial information IS. The feature amount extraction unit 4286 extracts the non-image feature amount F from the implemented event information EV and the environment log information EL included in the acquired current information PS.

The non-image feature amount F is a feature amount other than the image feature amount FP from immediately after seeding until the first culture medium exchange. Non-image feature values F include, for example, passage history (culture history of undifferentiated cells), coating agent, amount and type of medium, type of cell line, name of culture protocol, method of seeding, method of freezing work, Reference papers, etc. Note that the non-image feature amount F may include culturer information indicating the registered culturer ID, the number of years of culture experience of the culturer, and the like. The cultivator information may be input from the operation unit 45.

The feature extraction unit 4286 supplies the extracted image feature FP and non-image feature F to the culture protocol presentation unit 4287 and state prediction unit 4288.
The culture protocol presentation unit 4287 calculates the culture protocol based on the image feature amount FP and the non-image feature amount F, the termination information FS, the weight W and the set value V, and the learning result LR. Here, the culture protocol presentation unit 4287 acquires the learning result LR from the learning result storage unit 434.
The state prediction unit 4288 predicts the final state of culture based on the image feature amount FP and the non-image feature amount F, the end information FS, the weight W and the setting value V, and the learning result LR. Here, the state prediction unit 4288 acquires the learning result LR from the learning result storage unit 434.

The analysis result presentation section 428 supplies the display control section 422 with a culture protocol EVC indicating the culture protocol calculated by the culture protocol presentation section 4287 and a predicted final state PFS indicating the final state of the culture predicted by the state prediction section 4288. , is displayed on the display unit 44. Furthermore, the analysis result presentation unit 428 causes the learning result storage unit 434 to store the final state prediction PFS indicating the final state predicted by the state prediction unit 4288.

In other words, the analysis result presentation unit 428 uses the parameters acquired by the parameter acquisition unit 4285, the initial information IS acquired by the initial information generation unit 4261, the termination information FS acquired by the termination information generation unit 4264, and the cell information according to the culture protocol. The culture protocol is presented based on the culture result and the learning result in which the relationship between the culture protocol and the culture protocol has been learned.

The processing performed by the control device 41 will be explained. The processing performed by the control device 41 includes learning stage processing and application stage processing. The control device 41 performs the application stage process based on the result of the learning stage process.

[Learning stage]
Here, the learning stage processing performed by the control device 41 will be described with reference to FIGS. 6 to 8. FIG. 6 is a diagram illustrating an example of processing in the learning stage of this embodiment.

Step S200: The learning unit 425 acquires a plurality of data in which time-series cell images, implementation events, and environmental logs are linked from the storage unit 43 over the culture process. Here, the learning unit 425 acquires images P1 to Pn and imaging date and time information DT1 to imaging date and time information DTn added to each of these images P1 to Pn from the image storage unit 431 as time-series cell images. do. The learning unit 425 acquires the executed event information EV1 to the executed event information EVn from the executed event storage unit 432.
Here, referring to FIG. 7, a plurality of pieces of data that the learning unit 425 acquires from the storage unit 43 will be described.
FIG. 7 is an example of information stored in the storage unit 43 of this embodiment. In the example shown in the figure, the storage unit 43 stores the culture progress in the culture sequence seq1. In this culture sequence seq1, images P are captured at time t1, time t2, . . . , time t3, respectively. As described above, these images P are stored in the image storage unit 431 in chronological order in association with the imaging date and time information DT.
Further, each of these images P is associated with event information EV. In this example, "medium exchange,""immediateimplementation," and "half amount exchange" are associated with image P1 as implementation event information EV. As described above, these implemented event information EV are stored in the implemented event storage section 432.
Furthermore, each of these images P is associated with environmental log information EL. In this example, the image P1 is associated with a temperature of "37° C." and a humidity of "90%" as environmental log information EL. As described above, these environmental log information EL are stored in the environmental log storage section 433.

Here, the implemented event information EV will be explained in more detail.
FIG. 8 is a diagram showing an example of implementation event information EV of this embodiment. In the implemented event information EV, events are classified into hierarchies. In this example, events are hierarchically divided into three levels.
As an example shown in the figure, the events (layer 1) include "medium exchange,""subculture,""cleaning," and so on. Events (layer 2) regarding "medium exchange" include "immediate execution", "execution after a predetermined time", and so on. Although not shown, information on observers who perform each event may also be displayed as event information.

Returning to FIG. 6, the explanation of the learning process of the learning unit 425 will be continued.
Step S201: The learning unit 425 divides the plurality of data acquired from the storage unit 43 into predetermined periods. Here, as an example, the learning unit 425 divides the plurality of data by the type of event indicated by the event information EV. The learning unit 425 may divide the plurality of data into each predetermined length of time. Each of the plurality of divided data includes one or more sets of an image capturing date and time, an image, an environmental log, and an implemented event.

Step S202: The learning unit 425 extracts the feature amount of the cell image in each period. The learning unit 425 extracts the feature amount of the cell image for each data segmented in step S201. When the cell images in a certain period are images P-i (i=1, 2, ..., N: N is the number of images included in a certain period), the learning unit 425 calculates the A feature quantity fi (i=1, 2, . . . , N: N is the number of images included in a certain period) is extracted. When calculating the feature quantity fi, in addition to the corresponding image P-i, previous and subsequent images P-(i-1), P-(i+1) and images P-j (j=1, 2, ..., N:N is the number of images included in a certain period) may be used together.

The learning unit 425 extracts the morphological feature amount as the feature amount fi using known image processing. Here, the morphological features include, for example, the area, circumference, and dispersion of the cells captured in the image Pi. The learning unit 425 may extract the feature amount fi using a known machine learning method. Machine learning here is, for example, deep learning. When using deep learning to extract the feature amount fi, the learning unit 425 uses previously acquired learning data for deep learning. For example, ideal cell area values are used for this learning data. When using deep learning to extract the feature amount fi, the learning unit 425 may extract a value output from an intermediate layer of a neural network used for deep learning as the feature amount fi.
The learning unit 425 converts the representative value of each component of the extracted feature quantity fi (i=1, 2, . . . , N: N is the number of images included in a certain period) into a feature of images in a certain period. Quantity. Here, the representative value is an average value or a median value.

Step S203: The learning unit 425 learns a model that reproduces the feature amount of cell images in each period by regression analysis based on the feature amount of past cell images, the environment log, and the implementation event. Here, the feature amount of the past cell image is the feature amount extracted from the image of the period before each period. The model is a function that outputs a value of 1 or more when the feature amounts of past cell images, environmental logs, and implementation events are input. The number of values of 1 or more is equal to the number of components of the feature amount of the cell image in each period. This model includes one or more model parameters that are values that characterize this model. The learning unit 425 determines that when the feature values of past cell images, environmental logs, and implementation events are input to this model, the value of 1 or more output by the model is close to the feature value of cell images in each period. Adjust the model parameters so that

Note that, before learning the model, the learning unit 425 may extract a heuristic value from the environmental log of each period and perform learning of the model after using the environmental log of each period. Here, heuristic values include average, variance, maximum value, minimum value, etc.
Further, the learning unit 425 may also use a deep learning architecture that automatically performs feature extraction in the process of step S203.
The learning unit 425 supplies the learned model to the analysis result presentation unit 428 as a learning result LR. Here, when the learning unit 425 uses deep learning, the learning result LR is a result obtained by deep learning.

[Application stage]
The application stage processing performed by the control device 41 will be described with reference to FIGS. 9 to 17.
FIG. 9 is a diagram illustrating an example of processing in the application stage of this embodiment. The processing shown in FIG. 9 is performed after the learning stage processing shown in FIG. 6 is completed and the learning section 425 supplies the learning result LR to the analysis result presentation section 428.

Step S300: The initial information acquisition unit 4281 acquires initial information IS. The initial information IS includes images P0 to Pn acquired immediately after seeding until the first culture medium exchange, implementation event information EV, and environmental log information EL. The initial information acquisition unit 4281 supplies the acquired initial information IS to the culture protocol presentation unit 4287 and the state prediction unit 4288.

Here, referring to FIG. 10, images P0 to Pn acquired by the initial information acquisition unit 4281 from the image storage unit 431 will be described.
FIG. 10 is a diagram showing an example of an image P stored in the image storage unit 431 of this embodiment. In this example, the imaging device 34 captures images at each time: time t0, time t1, . . . time tn-1, time tn, and time tn+1. For example, image P0 is an image captured at time t0. When the image acquisition unit 421 acquires the image P0 from the imaging device 34 at time t0, it stores the image P0 in the image storage unit 431 with the addition of imaging date and time information DT indicating time t0. Similarly, for images P1 to Pn+1, the image acquisition unit 421 adds imaging date and time information DT to each image P and stores it in the image storage unit 431.

At time tE between time tn and time tn+1, medium exchange is performed as an implementation event. The initial information generation unit 4261 acquires, from among the images P stored in the image storage unit 431, images P0 to Pn acquired from time t0 immediately after seeding to time tE when the first culture medium exchange is performed. .

When the initial information acquisition unit 4281 acquires the image Pn+1, the display control unit 422 causes the display unit 44 to display the initial information input screen DI. Here, image Pn+1 is a cell image taken after the first medium exchange was performed immediately after seeding. The initial information input screen DI will be explained with reference to FIG. 11.

FIG. 11 is a diagram showing an example of the initial information input screen DI of this embodiment. The display unit 44 displays an initial information input screen DI. In this example, the initial image PI is displayed in the area AR1 of the initial information input screen DI. This initial image PI is image Pn+1 in FIG. Implemented event information EV and environment log information EL are displayed in area AR2 of the initial information input screen DI. In this example, the history of passage, the amount and type of culture medium, the type of cell line, and the procedure are displayed as the non-image feature amount F.

Note that in this example, a mode has been described in which the initial information acquisition unit 4281 acquires the initial information IS from the initial information generation unit 4261, but the present invention is not limited to this. The initial information acquisition unit 4281 may acquire the initial information IS from the operation detection unit 423. Further, the initial information acquisition unit 4281 may acquire the initial information IS from both the storage unit 43 and the operation detection unit 423.

Returning to FIG. 9, the description of the application stage processing will be continued.
Step S301: The termination information acquisition unit 4284 acquires the termination information FS supplied by the operation detection unit 423. The termination information acquisition unit 4284 supplies the acquired termination information FS to the analysis result presentation unit 428. Here, the end information FS includes at least one of the end image PF and the non-image end information CF.

Now, with reference to FIG. 12, the termination information input screen DF will be explained.
FIG. 12 is a diagram showing an example of the termination information input screen DF of this embodiment. A termination information input screen DF is displayed on the display unit 44. In this example, the end image PF is displayed in the area AR3 of the end information input screen DF. An input form for inputting non-image end information CF is displayed in area AR4 of the end information input screen DF. The end image PF and non-image end information CF are input by the viewer from the operation unit 45.

In this example, the termination information acquisition unit 4284 acquires the termination information FS from the current information generation unit 4262, but the present invention is not limited to this. The termination information acquisition unit 4284 may acquire the termination information FS from the image P stored in the storage unit 43. This image P is, for example, a cell image stored in the image storage unit 431 during the learning stage of the control device 41.

Returning to FIG. 9, the description of the application stage processing will be continued.
Step S302: The analysis result presentation unit 428 analyzes the culture process. Here, with reference to FIG. 13, the culture process analysis process will be described. However, in the process of step S302, the current state is immediately after the first culture medium exchange is performed immediately after seeding.

FIG. 13 is a diagram illustrating an example of the culture process analysis process of this embodiment.
Step S400: The feature extraction unit 4286 extracts the image feature FP from the current image P. Here, the feature amount extraction unit 4286 extracts image feature amounts FP0 to FPn from images P0 to Pn included in the initial information IS, respectively. The feature amount extraction unit 4286 extracts image feature amounts FP0 to image feature amounts FPn using a known machine learning method. The image feature amounts FP0 to FPn extracted by the feature amount extraction unit 4286 may be selected depending on the type of cell. Further, the feature amount extracting unit 4286 extracts feature amounts regarding temporal changes of images P0 to Pn, and includes them in image feature amounts FP0 to image feature amounts FPn.
The feature extraction unit 4286 supplies the extracted image feature quantities FP0 to FPn to the culture protocol presentation unit 4287 and the state prediction unit 4288.

Note that the feature amount extracting unit 4286 may extract morphological features from images P0 to Pn as image feature amounts FP0 to FPn using known image processing. Here, the morphological features include, for example, the area, circumference, and dispersion of the cells imaged in images P0 to Pn, respectively. The feature extraction unit 4286 uses morphological features extracted using image processing as image features FP0 to image features instead of image features FP0 to FPn extracted using machine learning techniques. FPn may be used, or the image feature amount FP0 to image feature amount FPn may be a combination of the feature amount extracted using a machine learning method and the morphological feature amount extracted using image processing.

Step S401: The feature extracting unit 4286 sets a series of environmental logs and implemented events based on the environmental log information EL and implemented event information EV. Here, the feature amount extraction unit 4286 sets a series of environmental logs and implementation events, which means that the non-image feature amount F is extracted from the environmental logs and implementation events from immediately after seeding to the present, and the culture protocol presentation unit 4287 and state prediction unit 4288.

Step S402: The analysis result presentation unit 428 performs a process of predicting the image feature amount FP of the cell image in the final state obtained by culturing. Here, with reference to FIG. 14, the process of predicting the image feature amount FP of the cell image in the final state will be described.

FIG. 14 is a diagram illustrating an example of a process for predicting the image feature amount FP of a cell image in the final state according to the present embodiment.
Step S500: The state prediction unit 4288 obtains the image feature amount FP and the non-image feature amount F supplied by the feature amount extraction unit 4286. Here, the image feature amount FP supplied by the feature amount extraction unit 4286 is a feature amount extracted from the current image P. The non-image feature amount F supplied by the feature amount extraction unit 4286 is a feature amount extracted from a set series of environmental logs and implementation events.

Step S501: The state prediction unit 4288 calculates the image feature amount FP extracted from the current image, the non-image feature amount F extracted from the given environment log and event, and the learned model (learning result LR). is used to predict the image feature amount FP of the cell image in the next period. The state prediction unit 4288 sets the predicted image feature amount FP of the cell image and the non-image feature amount F as a set as a prediction result PR.

Step S502: The state prediction unit 4288 uses the non-image feature amount F extracted from the environmental log and event of the next period, the prediction result PR, and the learned model (learning result LR) to predict the next period. The image feature amount FP of the cell image is predicted.
Each time the state prediction unit 4288 performs the process of step S502, the state prediction unit 4288 calculates the image feature amount FP of the cell image predicted in the prediction process of step S502, and the environmental log and event of the next period used in the prediction process of step S502. , and the non-image feature amount F extracted from the above are combined and added to the current prediction result PR.

Step S503: The state prediction unit 4288 determines whether the cell image has reached the final state. Here, the state prediction unit 4288 determines that the cell image has reached the final state, for example, when the culture sequence has a predetermined length or more. Note that when the end image PF is included in the end information FS, the state prediction unit 4288 determines that the distance between the image feature amount FP of the predicted cell image and the image feature amount FP extracted from the end image PF is less than or equal to a predetermined value. In this case, it may be determined that the cell image has reached its final state. Here, the distance between the image feature quantities FP is, for example, the distance between one or more values indicating the image feature quantities FP. For this distance, Euclidean distance or the like is used.

If the state prediction unit 4288 determines that the cell image has reached the final state (step S503: YES), the process ends. On the other hand, when determining that the cell image has not reached the final state (step S503: NO), the state prediction unit 4288 repeats the process shown in step S502.

Returning to FIG. 13, the explanation of the culture process analysis process will be continued.
Step S403: The state prediction unit 4288 stores the prediction result PR in the prediction result storage unit 436.

Returning to FIG. 9, the description of the application stage processing will be continued.
Step S303: The parameter acquisition unit 4285 acquires the setting value V from the operation detection unit 423. The parameter acquisition unit 4285 supplies the acquired setting value V to the culture mode selection unit 427. Note that the parameter acquisition unit 4285 may use a pre-stored predetermined value as the set value V.

Step S304: The culture mode selection unit 427 presents a culture mode CM. Here, the culture mode selection unit 427 acquires the culture mode CM from the culture mode storage unit 435. The culture mode selection unit 427 acquires the prediction result PR from the prediction result storage unit 436. The culture mode selection unit 427 acquires the setting value V from the parameter acquisition unit 4285.

The culture mode selection unit 427 selects an environmental log and an event based on the prediction result PR and the setting value V for each acquired culture mode CM. Here, the culture mode selection unit 427 makes a prediction corresponding to the set value V when the final state is reached, based on the environmental log and events from the initial state to the selected final state. Predict values. The predicted value corresponding to the set value V is, for example, a predicted value of the period required for culture, cost, and success rate. The culture mode selection unit 427 selects environmental logs and events whose predicted values satisfy the conditions corresponding to the set value V. However, the culture mode selection unit 427 determines which condition to prioritize among the conditions corresponding to the set value V based on the culture mode CM.

The culture mode selection unit 427 supplies the culture mode CM and the predicted value corresponding to the culture mode CM to the display control unit 422. The display control unit 422 causes the display unit 44 to display the culture mode CM supplied by the culture mode selection unit 427 and the predicted value as a culture mode selection screen DM.

Here, with reference to FIG. 15, the culture mode selection screen DM will be explained.
FIG. 15 is a diagram showing an example of the culture mode selection screen DM of this embodiment. A culture mode selection screen DM is displayed on the display unit 44. In this example, quality emphasis mode information CM1, production volume emphasis mode information CM2, and speed mode information CM3 are displayed as culture mode CMs. Quality emphasis mode information CM1 is displayed together with predicted values in area AR5 of the culture mode selection screen DM. In the area AR6 of the culture mode selection screen DM, production amount emphasis mode information CM2 is displayed together with predicted values. Speed mode information CM3 is displayed together with predicted values in area AR6 of culture mode selection screen DM.
The observer selects one of the culture mode CMs displayed on the culture mode selection screen DM from the operation unit 45 depending on the culture purpose.

Returning to FIG. 9, the description of the application stage processing will be continued.
Step S305: The culture mode selection unit 427 selects culture mode CM. Here, the culture mode selection unit 427 acquires information indicating the selected culture mode CM, which is supplied by the operation detection unit 423. The culture mode selection unit 427 selects a culture mode CM based on the acquired information indicating the selected culture mode CM. The culture mode selection unit 427 supplies the set of weights W indicated by the selected culture mode CM to the parameter acquisition unit 4285. The parameter acquisition unit 4285 supplies the weight W supplied by the culture mode selection unit 427 and the setting value V supplied by the operation detection unit 423 to the culture protocol presentation unit 4287.

Step S306: The analysis result presentation unit 428 presents the culture protocol EVC and final state prediction PFS according to the culture mode CM. Here, the analysis result presentation unit 428 acquires the prediction result PR from the prediction result storage unit 436.

The culture protocol presentation unit 4287 selects the culture protocol EVC based on the setting value V, the weight W, the current information PS, the end information FS, and the prediction result PR. The culture protocol presentation unit 4287 predicts a predicted value corresponding to the set value V when the final state is reached, based on the environmental log and events from the current state to the selected final state. The culture protocol presentation unit 4287 selects the environment log and event whose predicted value satisfies the condition corresponding to the set value V as the culture protocol EVC.

However, based on the weight W, the culture protocol presentation unit 4287 determines which of the conditions corresponding to the set value V should be prioritized. That is, the culture protocol presentation unit 4287 selects the culture protocol EVC according to the culture mode CM. Note that the culture protocol presentation unit 4287 may select the culture protocol EVC without using the weight W.

The culture protocol presentation unit 4287 supplies the selected culture protocol EVC to the display control unit 422. The display control unit 422 displays the culture protocol EVC supplied by the culture protocol presentation unit 4287 on the display unit 44 as an analysis result screen DO.

Note that the culture protocol presentation unit 4287 may select a plurality of culture protocols EVC. When the culture protocol presentation section 4287 selects a plurality of culture protocols EVC, the display control section 422 causes the display section 44 to display an analysis result screen DO including the plurality of culture protocols EVC provided by the culture protocol presentation section 4287. The observer may select any one of the plurality of culture protocols EVC from the analysis result screen DO.

The state prediction unit 4288 predicts the final state based on the current information PS, the culture protocol EVC selected by the culture protocol presentation unit 4287, and the prediction result PR.
Here, the prediction result PR includes the non-image feature amount F extracted from environmental logs and events in a certain period, the prediction result PR, and the learned model (learning result LR) in steps S501 and S502 shown in FIG. ) is the result predicted by the state prediction unit 4288. That is, the prediction result PR is a result predicted based on the learning result LR. Therefore, the state prediction unit 4288 predicts the culture state of the cells based on the current information PS acquired by the current information acquisition unit 4282, the culture protocol EVC presented by the culture protocol presentation unit 4287, and the learning result LR.

The state prediction unit 4288 supplies the final state prediction PFS indicating the predicted final state to the display control unit 422. The state prediction unit 4288 causes the display unit 44 to display the predicted final state PFS supplied by the state prediction unit 4288 as the analysis result screen DO.

Here, the analysis result screen DO will be explained with reference to FIG.
FIG. 16 is a diagram showing an example of the analysis result screen DO of this embodiment. The display unit 44 displays an analysis result screen DO. In this example, speed mode information CM3 is displayed together with the predicted value in area AR8 of analysis result screen DO.
The culture protocol EVC is displayed in area AR9 of the analysis result screen DO. In this example, the culture protocol EVC indicates instructions for medium replacement, matters to be aware of, and conditions under which culture should be discontinued.
The predicted final state PFS is displayed in area AR10 of the analysis result screen DO. The final state prediction PFS includes the predicted end image PF. In this example, the final state prediction PFS indicates cell number, quality, and undifferentiated cell rate.

Returning to FIG. 9, the description of the application stage processing will be continued.
Step S307: The operation detection unit 423 detects the viewer's event selection operation on the operation unit 45. The observer selects an event to be performed from the event selection screen DE displayed on the display unit 44.

In addition, in the process shown in step S306 described above, the culture protocol presentation unit 4287 creates the culture protocol EVC based on the setting value V, the weight W, the current information PS, the end information FS, and the prediction result PR. Although the mode of selection has been described, it is not limited thereto. The culture protocol presentation unit 4287 selects the culture protocol EVC based on the setting value V, the weight W, the current information PS, the end information FS, the prediction result PR, and also the intermediate information MS. Good too.

In other words, the culture protocol presentation unit 4287 outputs the weight W acquired by the parameter acquisition unit 4285, the current information PS acquired by the current information acquisition unit 4282, the termination information FS acquired by the termination information generation unit 4264, and the intermediate information generation unit The culture protocol EVC may be presented based on the intermediate information MS acquired by 4263 and the learning result LR.

In this case, the culture protocol presentation unit 4287 selects the culture protocol EVC for passing through the intermediate state indicated by the intermediate information MS in the process of reaching the final state corresponding to the end image PF indicated by the end information FS.

In addition, in the process shown in step S306 described above, the culture protocol presentation unit 4287 selects the environment log and event information based on the setting value V, the weight W, the current information PS, the end information FS, and the prediction result PR. Although the mode of selecting EVC as the culture protocol has been described, it is not limited thereto. The culture protocol presentation unit 4287 may generate an environment log and an event based on the setting value V, the weight W, the current information PS, the end information FS, and the prediction result PR, and use it as the culture protocol EVC. That is, the culture protocol presentation unit 4287 may generate the culture protocol EVC based on the learning result LR.

The event selection screen DE will now be described with reference to FIG. 17.
FIG. 17 is a diagram showing an example of the event selection screen DE of this embodiment. An event selection screen DE is displayed on the display unit 44. In this example, the current image Px is displayed in the area AR11 of the event selection screen DE along with the imaging date and time. Presentation event REV and candidate event OEV are displayed in area AR12 of event selection screen DE. The presentation event REV is an event indicated by the culture protocol EVC presented by the culture protocol presentation section 4287. The text “(recommended)” is added to the presentation event REV, indicating that it is an event indicated by the culture protocol EVC.
Note that the observer may select a candidate event OEV other than the presentation event REV indicated by the culture protocol EVC.

Returning to FIG. 9, the description of the application stage processing will be continued.
Step S308: The current information acquisition unit 4282 acquires the current information PS. The current information PS includes an image P acquired from immediately after sowing to the present, implementation event information EV, and environmental log information EL. The current information acquisition unit 4282 supplies the acquired current information PS to the analysis result presentation unit 428.

Step S309: The state prediction unit 4288 determines whether the image P included in the current information PS has reached the final state. Here, the state prediction unit 4288 determines that the cell image has reached the final state, for example, when the length of the culture sequence is equal to or longer than a predetermined length. Note that the state prediction unit 4288 determines that the cell image is a cell image when the distance between the image feature amount FP of the image P included in the current information PS and the image feature amount FP extracted from the finished image PF is less than or equal to a predetermined value. It may be determined that the final state has been reached.

Step S310: The analysis result presentation unit 428 analyzes the culture process. Comparing the process of analyzing the culture process in step S310 and the process of analyzing the culture process in step S302, it is found that in step S310, the analysis result presentation unit 428 performs the analysis based on the current information PS, whereas in step S302 The difference is that the analysis result presentation unit 428 performs analysis based on the initial information IS. The other processing contents in step S310 are the same as in step 302, so the explanation will be omitted.

In addition, in the process shown in step S304 of FIG. 9, if the culture mode selection unit 427 cannot select an environment log and an event whose predicted value satisfies the condition corresponding to the set value V, the culture mode selection unit 427 selects a cell from the cell indicated by the initial image PI. may supply the display control unit 422 with warning information AL0 indicating that it is predicted that a final state that satisfies the set conditions will not be obtained. The display control section 422 may cause the display section 44 to display the warning information AL supplied by the culture mode selection section 427.

In addition, in the process shown in step S306 of FIG. 9, if the culture protocol presentation unit 4287 cannot select an environmental log and an event whose predicted value satisfies the condition corresponding to the set value V, the culture protocol presentation unit 4287 displays the image P of the current information PS. The indicated cell may supply the display control unit 422 with warning information AL1 indicating that it is predicted that a final state that satisfies the set conditions will not be obtained. The display control unit 422 may cause the display unit 44 to display the warning information AL1 provided by the culture protocol presentation unit 4287.

In the above-described embodiment, the termination information generation unit 4264 acquires the termination information FS from the operation detection unit 423, that is, the termination information FS is input from the operation unit 45. However, the present invention is not limited to this. do not have. The termination information generation unit 4264 may obtain one or more of the termination information FSM-1 to FSM-n from the storage unit 43. When the termination information generation unit 4264 acquires the termination information FSM-1 to FSM-n from the storage unit 43, the storage unit 43 stores the termination information FSM-1 to FSM-n.

The termination information generation unit 4264 acquires the termination information FSM-1 to FSM-n from the storage unit 43 and supplies them to the feature amount extraction unit 4286. The culture protocol presentation unit 4287 selects the culture protocol EVCM-1 to culture protocol EVCM-n for each of the termination information FSM-1 to FSM-n supplied by the termination information generation unit 4264. The display control unit 422 causes the display unit 44 to display the analysis result screen DO including the culture protocols EVCM-1 to EVCM-n selected by the culture protocol presentation unit 4287.

In this example, even if the purpose or goal of culture is not input from the operation unit 45 as the end information FS, the control device 41 temporarily sets a plurality of purposes or goals for culture, and adjusts the purpose or goal for each culture. Culture protocols EVCM-1 to EVCM-n can be presented accordingly. For example, when the end information FSM-1 to end information FSM-n stored in the storage unit 43 include the amount of cells, the control device 41 controls the culture protocol EVCM-1 to culture protocol EVCM-n for each amount of cells. can be presented as a list of protocols.
Note that, after the application stage process is completed, the control device 41 may execute the learning stage process using the information obtained in the application stage process. In this way, the control device 41 can always obtain the best model by executing the learning stage process every time information about the application stage process is obtained.

As explained above, the culture support device (control device 41) according to the present embodiment includes a first information acquisition section (initial information acquisition section 4281 or current information acquisition section 4282) and a second information acquisition section (end information acquisition section 4281 or current information acquisition section 4282). acquisition section 4284), parameter acquisition section 4285, and culture protocol presentation section 4287.
The first information acquisition unit (initial information acquisition unit 4281 or current information acquisition unit 4282) acquires first information (initial information IS or current information PS) regarding the culture state of cells at the first stage of the cell culture process. .
The second information acquisition unit (completion information acquisition unit 4284) acquires second information (completion information FS) regarding the culture state of cells in a second period after the first period.
The parameter acquisition unit 4285 acquires a parameter (set value V or weight W) used to select a culture protocol EVC indicating conditions for cell culture.
The culture protocol presenting unit 4287 displays the parameters (setting value V or weight W) acquired by the parameter acquiring unit 4285 and the first information (the initial information acquiring unit 4281 or the current information acquiring unit 4282) acquiring relationship between the initial information IS or current information PS), the second information (finish information FS) acquired by the second information acquisition unit (finish information acquisition unit 4284), the cell culture results according to the culture protocol EVC, and the culture protocol EVC A culture protocol EVC is presented based on the learned learning result LR.

With this configuration, in the culture support device (control device 41) according to the present embodiment, in the first period of the cell culture process, based on the learning result LR, the culture support device (control device 41) performs a process to obtain the cell culture state indicated by the second information. Since the culture protocol EVC can be presented, culture techniques and environmental conditions can be successively fine-tuned while checking the culture status according to the culture purpose and goal.

Further, in the culture support device (control device 41) according to the present embodiment, the learning result LR is a result obtained by deep learning.
With this configuration, the culture support device (control device 41) according to the present embodiment can present the culture protocol EVC based on a learning result that is more accurate than when deep learning is not used.

Furthermore, the culture support device (control device 41) according to this embodiment further includes a state prediction unit 4288. The state prediction unit 4288 uses the first information (initial information IS or current information PS), the first information (initial information IS or current information PS) acquired by the second information acquisition unit (end information acquisition unit 4284), and the culture The cell culture state is predicted based on the culture protocol EVC presented by the protocol presentation unit 4287 and the learning result LR.

With this configuration, the culture support device (control device 41) according to the present embodiment can predict the cell culture state indicated by the second information based on the learning result LR in the first period of the cell culture process. This allows the observer to make fine adjustments one by one while confirming the predicted culture state.

Furthermore, the culture support device (control device 41) according to this embodiment further includes an intermediate information acquisition section 4283. The interim information acquisition unit 4283 acquires interim information MS regarding the culture state of cells in a period between the first period and the second period.
The culture protocol presenting unit 4287 displays the parameters (setting value V or weight W) acquired by the parameter acquiring unit 4285 and the first information (the initial information acquiring unit 4281 or the current information acquiring unit 4282) acquiring initial information IS or current information PS), second information (finish information FS) acquired by the second information acquisition unit (finish information acquisition unit 4284), intermediate information MS acquired by the intermediate information acquisition unit 4283, and learning results. We present a culture protocol EVC based on LR.

With this configuration, in the culture support device (control device 41) according to the present embodiment, in the first period of the cell culture process, based on the learning result LR, the first period and the second period indicated by the intermediate information MS are Since it is possible to present a culture protocol EVC for obtaining the cell culture state indicated by the second information via the cell culture state at the time between It can be performed.

The culture support device (control device 41) according to this embodiment further includes a culture mode storage section 435 and a culture mode selection section 427. The culture mode storage unit 435 stores in advance one or more culture mode CMs that are information indicating a predetermined set of parameters. The culture mode selection unit 427 selects a culture mode CM from among the one or more culture mode CMs stored in the culture mode storage unit 435. The parameter acquisition unit 4285 acquires the parameter (set value V or weight W) indicated by the culture mode CM selected by the culture mode selection unit 427.
With this configuration, the culture support device (control device 41) according to the present embodiment does not need to sequentially specify the parameters (setting value V or weight W) used for presenting the culture protocol EVC. The parameters (setting value V or weight W) used for this can be easily specified.

Further, the first period may be the start of the culturing process, and the second period may be the end of the culturing process.
With this configuration, in the culture support device (control device 41) according to the present embodiment, at the start of the cell culture process, based on the learning result LR, the culture support device (control device 41) performs the culture to obtain the cell culture state at the end of the culture process. Since the protocol EVC can be presented, the observer can successively fine-tune the culture techniques and environmental conditions while checking the culture status from the start to the end of the cell culture process. Note that the first time is not limited to the start of the culture process, but may be a later time. Further, the second time is not limited to the end of the culture process, but may be a timing before the end of the culture process.

The observation device according to this embodiment includes a thermostatic chamber 15, an imaging device 34, and a culture support device (control device 41). The thermostatic chamber 15 can accommodate a culture container 19 for culturing cells, and can maintain the interior at predetermined environmental conditions. The imaging device 34 images the cells housed in the culture container 19 in the thermostatic chamber 15 at predetermined time intervals.

[Modified example]
As a modification of the above-described embodiment, a case will be described in which there are a plurality of incubators 11-1 to 11-n. In this modification, even if it is predicted that the cells cultured in one of the incubators 11-i will not be able to reach the target final state, the cells cultured in the other incubator 11-j This method can be applied to cells that can reach the final state indicated by the termination information FS.

The culture system S includes a management device AD and a plurality of incubators 11-1 to 11-n. Incubators 11-1 to 11-n each include control devices 41-1 to 41-n.
The management device AD communicates with each of the control devices 41-1 to 41-n. The management device AD and the control devices 41-1 to 41-n each include a communication module and communicate with each other through wired or wireless communication.

Among the control devices 41-1 to 41-n, the control device 41-i determines that the predicted value corresponds to the set value V in the process shown in step S304 and the process shown in step S306 in FIG. If an environmental log or event that satisfies the conditions cannot be selected, warning information AL (warning information AL0 or warning information AL1) is supplied to the management device AD.

When the management device AD acquires the warning information AL supplied by the control device 41-i, the management device AD acquires the setting value V and the termination information FS from the control device 41-i. Here, any one of the control devices 41-1 to 41-n other than the control device 41-i is designated as a representative control device 41-j. The management device AD supplies the control device 41-j with the setting value Vi and termination information FS-i acquired from the control device 41-i.

The control device 41-j, based on the setting value Vi obtained from the control device 41-i, the current information PS-j of the own device, and the termination information FS-i obtained from the control device 41-i, It is determined whether the final state indicated by the end information FS-i can be reached from the state of the cell image indicated by the current information PS-j. When the control device 41-j determines that the final state indicated by the end information FS-i can be reached from the state of the cell image indicated by the current information PS-j, the control device 41-j determines whether the cells cultured in the incubator 11-j have reached the final state. The culturability information PC indicating what can be done is supplied to the management device AD.

The management device AD supplies culturability information PC supplied by the control device 41-j to the control device 41-i. The control device 41-i causes the display unit 44-i of its own device to display the culturability information PC supplied by the management device AD.
Note that instead of the culture system S including the management device AD, direct communication may be performed between the control devices 41-1 to 41-n.

In this modification, even if it is predicted that the cells cultured in one incubator 11-i will not be able to reach the final state indicated by the termination information FS-i, the observer It can be seen that the cells cultured in the other incubators 11-j of S are predicted to reach the final state indicated by the termination information FS-i.

Note that some of the control device 41 in the embodiment described above, for example, the image acquisition section 421, the display control section 422, the operation detection section 423, the storage control section 424, the learning section 425, the analysis information generation section 426, and the culture mode selection section 427 and the analysis result presentation unit 428 may be realized by a computer. In that case, a program for realizing this control function may be recorded on a computer-readable recording medium, and the program recorded on the recording medium may be read into a computer system and executed. Note that the "computer system" herein refers to a computer system built into the control device 41, and includes hardware such as an OS and peripheral devices. Furthermore, the term "computer-readable recording medium" refers to portable media such as flexible disks, magneto-optical disks, ROMs, and CD-ROMs, and storage devices such as hard disks built into computer systems. Furthermore, a "computer-readable recording medium" refers to a medium that dynamically stores a program for a short period of time, such as 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, it may also include a device that retains a program for a certain period of time, such as a volatile memory inside a computer system that is a server or a client. Further, the above-mentioned program may be one for realizing a part of the above-mentioned functions, or may be one that can realize the above-mentioned functions in combination with a program already recorded in the computer system.
Moreover, a part or all of the control device 41 in the embodiment described above may be realized as an integrated circuit such as an LSI (Large Scale Integration). Each functional block of the control device 41 may be made into a processor individually, or some or all of them may be integrated into a processor. Further, the method of circuit integration is not limited to LSI, but may be implemented using a dedicated circuit or a general-purpose processor. Further, if an integrated circuit technology that replaces LSI emerges due to advances in semiconductor technology, an integrated circuit based on this technology may be used.

Although one embodiment of the present invention has been described above in detail with reference to the drawings, the specific configuration is not limited to that described above, and various design changes etc. may be made without departing from the gist of the present invention. It is possible to

DESCRIPTION OF SYMBOLS 11... Incubator (observation device), 41... Control device (culture support device), 43... Storage section, 44... Display section, 45... Operation section, 421... Image acquisition section, 422... Display control section, 423... Operation detection section , 424...Storage control section, 425...Learning section, 426...Analysis information generation section, 427...Culture mode selection section, 428...Analysis result presentation section

Claims (12)

a first information acquisition unit that acquires first information regarding a first culture state of the cells in a first period of the cell culture process;
a second information acquisition unit that acquires second information regarding a second culture state of the cells in a second period after the first period ;
A learning result in which a relationship between a culture protocol indicating the culture conditions of the cells in the culture process and a change in the culture state of the cells due to the culture protocol is learned, information regarding the culture state, and a predetermined predetermined value based on the culture protocol. a state prediction unit that repeatedly performs a process of predicting the culture state after the period from the first culture state until reaching the second culture state;
a culture protocol presentation unit that presents the culture protocol used in the series of prediction processes performed by the state prediction unit ;
Equipped with
If the culture state output by the prediction process has not reached the second culture state, the state prediction unit applies information on the culture state output by the immediately previous prediction process, the culture protocol, and the learning result. Perform prediction processing based on
Culture support equipment. The culture protocol includes replacing the medium for culturing the cells, passage of the cells, cleaning the incubator storing the cell culture container, and transferring the cell culture container to a different incubator. , including at least one working condition
The culture support device according to claim 1. The culture protocol includes environmental conditions during the culture process.
The culture support device according to claim 1 or 2. The learning results are results obtained by deep learning.
The culture support device according to any one of claims 1 to 3. further comprising an intermediate information acquisition unit that acquires intermediate information regarding the culture state of the cells in a period between the first period and the second period,
The culture protocol presentation unit may pass through a culture state indicated by the intermediate information before reaching the second culture state, among the plurality of culture protocols that can reach the second culture state from the first culture state. We present the culture protocol described above.
The culture support device according to any one of claims 1 to 4. further comprising a condition setting value acquisition unit that acquires condition setting values set according to the purpose of culture,
The culture protocol presentation unit presents the culture protocol that satisfies the conditions indicated by the condition setting values, among the plurality of culture protocols that can reach the second culture state from the first culture state.
The culture support device according to any one of claims 1 to 5. a culture mode storage unit that stores in advance one or more culture modes indicating the predetermined set of the condition setting values;
a culture mode selection unit that receives instructions from an observer and selects the culture mode according to the purpose of culture from among the culture modes stored in the culture mode storage unit;
Furthermore,
The culture protocol presentation unit presents the culture protocol that satisfies the condition setting value indicated by the culture mode selected by the culture mode selection unit.
The culture support device according to claim 6. The first period is the start of the culture process.
The culture support device according to any one of claims 1 to 7. The first period is a period after the cells are cultured according to the culture protocol presented by the culture protocol presentation unit.
The culture support device according to any one of claims 1 to 7. The second period is the end of the culture process.
The culture support device according to any one of claims 1 to 9. a thermostatic chamber capable of accommodating a culture container for culturing the cells and maintaining the interior at predetermined environmental conditions;
an imaging device that images the cells housed in the culture container in the thermostatic chamber at predetermined time intervals;
The culture support device according to any one of claims 1 to 10,
An observation device equipped with. to the computer,
a first information acquisition step of acquiring first information regarding a first culture state of the cells in a first period of the cell culture process;
a second information acquisition step of acquiring second information regarding a second culture state of the cells in a second period after the first period;
A learning result in which a relationship between a culture protocol indicating the culture conditions of the cells in the culture process and a change in the culture state of the cells due to the culture protocol is learned, information regarding the culture state, and a predetermined predetermined value based on the culture protocol. a state prediction step of repeatedly performing a process of predicting the culture state after the period from the first culture state until reaching the second culture state;
A program that executes
In the state prediction step, if the culture state output by the prediction process has not reached the second culture state, the state prediction step includes information regarding the culture state output by the immediately previous prediction process, the culture protocol, and the learning result. Perform prediction processing based on
program.

Images