[go: up one dir, main page]

WO2020148964A1 - Dispositif, procede et programme d'aide a la generation de cellules - Google Patents

Dispositif, procede et programme d'aide a la generation de cellules Download PDF

Info

Publication number
WO2020148964A1
WO2020148964A1 PCT/JP2019/042067 JP2019042067W WO2020148964A1 WO 2020148964 A1 WO2020148964 A1 WO 2020148964A1 JP 2019042067 W JP2019042067 W JP 2019042067W WO 2020148964 A1 WO2020148964 A1 WO 2020148964A1
Authority
WO
WIPO (PCT)
Prior art keywords
information
cell
cells
measurement
generated
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Ceased
Application number
PCT/JP2019/042067
Other languages
English (en)
Japanese (ja)
Inventor
兼太 松原
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Fujifilm Corp
Original Assignee
Fujifilm Corp
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Fujifilm Corp filed Critical Fujifilm Corp
Priority to JP2020566110A priority Critical patent/JP7289854B2/ja
Publication of WO2020148964A1 publication Critical patent/WO2020148964A1/fr
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/0464—Convolutional networks [CNN, ConvNet]
    • C—CHEMISTRY; METALLURGY
    • C12—BIOCHEMISTRY; BEER; SPIRITS; WINE; VINEGAR; MICROBIOLOGY; ENZYMOLOGY; MUTATION OR GENETIC ENGINEERING
    • C12M—APPARATUS FOR ENZYMOLOGY OR MICROBIOLOGY; APPARATUS FOR CULTURING MICROORGANISMS FOR PRODUCING BIOMASS, FOR GROWING CELLS OR FOR OBTAINING FERMENTATION OR METABOLIC PRODUCTS, i.e. BIOREACTORS OR FERMENTERS
    • C12M1/00—Apparatus for enzymology or microbiology
    • C—CHEMISTRY; METALLURGY
    • C12—BIOCHEMISTRY; BEER; SPIRITS; WINE; VINEGAR; MICROBIOLOGY; ENZYMOLOGY; MUTATION OR GENETIC ENGINEERING
    • C12M—APPARATUS FOR ENZYMOLOGY OR MICROBIOLOGY; APPARATUS FOR CULTURING MICROORGANISMS FOR PRODUCING BIOMASS, FOR GROWING CELLS OR FOR OBTAINING FERMENTATION OR METABOLIC PRODUCTS, i.e. BIOREACTORS OR FERMENTERS
    • C12M1/00—Apparatus for enzymology or microbiology
    • C12M1/34—Measuring or testing with condition measuring or sensing means, e.g. colony counters
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N20/00—Machine learning
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G06N3/09—Supervised learning
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods

Definitions

  • the technology of the present disclosure relates to a cell generation support device, method, and program.
  • pluripotent stem cells such as ES (Embryonic Stem) cells and iPS (Induced Pluripotent Stem) cells have the ability to differentiate into cells of various tissues, and are useful in regenerative medicine, drug development, disease elucidation, etc. It is attracting attention as a cell that can be applied. For example, when it is desired to generate a desired number of desired cells by differentiating iPS cells, cells such as blood cells 41 or skin cells 42 are collected from a cell donor 40 as shown in FIG.
  • ES Embryonic Stem
  • iPS Induced Pluripotent Stem
  • expansion culture culturing the generated iPS cells 43
  • the initialization process T1 and the culture process T2 require a total of about 2 months
  • the differentiation process T3 requires a period of about 2 to 3 months.
  • the culturing step T2 there is an operation called "passage" in which the medium is removed from the culture container containing the iPS cells 43 and the iPS cells 43 are transferred to a new medium.
  • the proliferated iPS cells 43 are uniformly seeded in a plurality of culture vessels at a predetermined size and density, and cell division is performed.
  • the person in charge of the work should visually observe cells that may proliferate while maintaining the undifferentiated state. Have been selected by.
  • the person in charge selects cells, for example, by continuously culturing iPS cells 44 having a well-shaped cell line and removing iPS cells 45 having a non-well-shaped cell line.
  • iPS cells 44 having a well-shaped cell line
  • iPS cells 45 having a non-well-shaped cell line.
  • differentiation induction from iPS cells is not successful. If differentiation induction is not successful, it will be difficult to generate the target number of cells to be differentiated, which is an obstacle to industrialization.
  • the differentiation induction is always successful and the target cells are generated.
  • the number of cells that can possibly become the cells to be generated is determined at the end of the culture step T2. For example, when it is found that the number of cells that can possibly become the cells to be generated is smaller than the target number of cells after entering the differentiation step T3, new cells are generated from scratch due to the insufficient amount. This is time consuming and costly. For example, when using cells collected from a healthy person as a drug discovery tool, it is desired to generate the target number of cells to be generated in the shortest possible time.
  • the present disclosure has been made in view of the above circumstances, and an object of the present disclosure is to enable acquisition of information as to whether or not a desired number of cells can be generated.
  • the cell generation support device includes an information acquisition unit that acquires history information indicating a history of cells to be used and cell information of cells to be generated, and history information, cell information, and cells acquired by the information acquisition unit. Generated for each cell measurement based on the measurement information related to the measurement when measuring the cell in any of the initialization step, the cell culture step, and the cell differentiation induction step.
  • a generation possibility information acquisition unit for acquiring information on whether or not a desired cell can be generated.
  • the generative information acquisition unit derives information about whether or not a desired cell can be generated based on the history information and the cell information acquired by the information acquisition unit, and the measurement information. It may include a first derivation unit that does.
  • the first derivation unit, the history information indicating the history of the cells to be used, the cell information of the cells to be generated, the initialization step of initializing the cells, and the cells are cultured.
  • a first set of information including measurement information related to measurement when measuring cells and a set of the first information are provided.
  • the first learned model that has been machine-learned by using the learning information including a plurality of information sets including the information indicating whether the corresponding cells to be generated can be generated may be included.
  • the measurement information may be at least one of information related to the measurement unit and information indicating the measurement result obtained by the measurement by the measurement unit.
  • the information related to the measurement means includes information indicating one of the method used for measurement and the person in charge of measurement, and the information indicating the measurement result is measured.
  • the information may include any one or more of a cell state, a medium state, and the presence or absence of bacteria.
  • the measured cell state includes cell shape, cell color, cell number, cell size, cell odor, cell gene expression, cell metabolite.
  • the information of any one or more of the type and the protein of the cell may be included.
  • the history information is the name of the cell donor who is the holder of the cells to be used, the sex of the cell donor, the blood type of the cell donor, the race of the cell donor,
  • the information may include any one or more of the age of the cell donor, the disease history of the cell donor, the immune information of the cell donor, and the disease history of the relatives of the cell donor.
  • the cell information is any one or more of the types of cells to be generated, the number of cells to be generated, the state of cells to be generated, and the number of days to be completed. May be included.
  • the cell generation support device may include a notification unit that notifies information about whether or not a cell to be generated can be generated.
  • the generative information acquisition unit acquires generative information, culture conditions for culturing cells based on the history information and the cell information acquired by the information acquisition unit. It may further include a culture condition acquisition unit for acquiring.
  • the culture condition acquisition unit may be used in any one of an initialization step of initializing cells, a culture step of culturing cells, and a differentiation step of inducing differentiation of cells.
  • the updated culture condition updated based on the measurement information related to the measurement when measuring cells may be acquired as the culture condition.
  • the culture condition acquisition unit updates the culture condition acquisition unit based on the measurement information and the second derivation unit that derives the culture condition based on the history information and the cell information acquired by the information acquisition unit.
  • a third derivation unit that derives the updated culture condition as the culture condition may be included.
  • the second derivation unit includes a second information set including history information indicating the history of cells to be used and cell information of cells to be generated, and the second information.
  • the second derivation model includes a second trained model machine-learned using learning information including a plurality of information sets with culture conditions corresponding to the set, and the third derivation unit initializes the cell, In any one of the culturing step of culturing and the differentiating step of inducing differentiation of cells, a third set of information including measurement information and culturing conditions related to measurement when measuring cells, and this third set
  • the third learned model machine-learned using learning information including a plurality of information sets with updated culture conditions corresponding to the information set of
  • the second learned model and the third learned model may be configured by one learned model.
  • the culture conditions include the type of cells used, the number of cells used, the type of container used, the type of medium used, the type of additive used, the timing of treatment, Also, any one or more of the information regarding the person in charge may be included.
  • the processing timing is any one of seeding timing, passage timing, medium replacement timing, additive addition timing, and cell inspection timing. It may include one or more timings.
  • history information indicating the history of cells to be used and cell information of cells to be generated are acquired, and history information, cell information, and an initialization step of initializing cells, and culturing cells Whether or not the desired cell can be generated for each cell measurement, based on the measurement information related to the measurement when measuring the cell in any one of the culture step and the differentiation step of inducing the differentiation of cells Get information.
  • the cell generation support method according to the present disclosure may be provided as a program that causes a computer to execute the method.
  • Another cell generation support device includes a memory that stores instructions to be executed by a computer, and a processor configured to execute the stored instructions, the processor indicating a history of cells to be used. Acquiring history information and cell information of cells to be generated, history information, cell information, and any one of an initialization step of initializing cells, a culture step of culturing cells, and a differentiation step of inducing differentiation of cells Based on the measurement information related to the measurement when measuring the cells in the process, a process of acquiring information on whether or not the desired cell can be generated is executed for each measurement of the cell.
  • the flowchart which shows the process performed in the cell production assistance apparatus of the 1st Embodiment of this indication.
  • the figure for demonstrating the trained model by 1st Embodiment of this indication The figure which shows the schematic structure of the cell production assistance apparatus by 2nd Embodiment of this indication.
  • the figure for demonstrating the trained model by 2nd Embodiment of this indication The figure for demonstrating the 2nd derivation
  • the flowchart which shows the process performed in the cell production assistance apparatus of the 2nd Embodiment of this indication.
  • FIG. 1 is a diagram showing a schematic configuration of a cell generation support device according to the first embodiment of the present disclosure.
  • FIG. 1 shows that the cell generation support program is installed in the non-volatile memory 12.
  • the cell generation support program may be installed in the storage 13.
  • the memory 12 may be a volatile memory such as a DRAM (Dynamic Random Access Memory) or an SRAM (Static Random Access Memory).
  • the cell generation support program called from the CPU 12 is temporarily stored in the memory 12 May be stored and executed.
  • the cell generation support device includes the learned model. Therefore, only the cell generation support device is shown in FIG. As shown in FIG.
  • the cell generation support device 1 includes a CPU (Central Processing Unit) 11, a memory 12, and a storage 13 as a standard computer configuration. Further, the cell generation support device 1 is connected to a notification unit 14 for notifying a culture condition C, which will be described later, and an input device (hereinafter referred to as an input unit) 15 such as a keyboard and a mouse.
  • a CPU Central Processing Unit
  • a memory 12 for storing data
  • a storage 13 as a standard computer configuration
  • the cell generation support device 1 is connected to a notification unit 14 for notifying a culture condition C, which will be described later, and an input device (hereinafter referred to as an input unit) 15 such as a keyboard and a mouse.
  • an input unit 15 such as a keyboard and a mouse.
  • the notification unit 14 includes, for example, a display that visually displays the culture condition C and the information F indicating whether or not a desired cell can be generated.
  • the notification unit 14 includes a display for visually displaying a message and the like, a sound reproducing device for audibly displaying when a sound is output, a printer for recording on a recording medium such as paper and the like for permanent visual display, a communication means such as an email or a telephone, and the like. It means an indicator light or the like, and may be a combination of at least two or more of the display, the audio reproducing device, the printer, the communication means, and the display light.
  • the notification unit 14 is an external device of the cell generation support device 1, but the technology of the present disclosure is not limited to this, and the notification unit 14 is included in a part of the cell generation support device 1. It may be.
  • the storage 13 comprises a storage device such as a hard disk or SSD (Solid State Drive).
  • the storage 13 stores various information including history information A indicating the history of cells to be used and information necessary for the process of the cell generation support device 1, acquired from an external data server (not shown) via the network.
  • the memory 12 stores a cell generation support program and a learned model.
  • the cell generation support program as processing to be executed by the CPU 11, information acquisition processing for acquiring history information indicating the history of cells to be used and cell information of cells to be generated, and history information, cell information, and an initial stage of initializing cells.
  • Cells to be generated for each cell measurement based on measurement information related to measurement when measuring cells in any one of the process of culturing cells, the step of culturing cells, and the step of differentiating cells Defines a generation possibility information acquisition process for acquiring information on whether or not generation is possible.
  • the computer functions as the information acquisition unit 21 and the creatable information acquisition unit 23 by the CPU 11 executing these processes according to the cell generation support program.
  • the CPU 11 executes the function of each unit by the cell generation support program.
  • a programmable logic device which is a processor whose circuit configuration can be changed after manufacture of an FPGA (Field Programmable Gate Array) or the like, can be used.
  • the processing of each unit may be executed by a dedicated electric circuit or the like, which is a processor having a circuit configuration specifically designed for executing a specific processing such as an ASIC (Application Specific Integrated Circuit).
  • the memory 12 is a volatile memory
  • the cell generation support program called by the CPU 12 and the learned model may be temporarily stored in the memory 12 and executed.
  • One processing unit may be configured by one of these various processors, or may be a combination of two or more processors of the same type or different types (for example, a plurality of FPGAs or a combination of CPU and FPGA). It may be configured. Further, the plurality of processing units may be configured by one processor. As an example of configuring a plurality of processing units by one processor, firstly, as represented by a computer such as a client and a server, one processor is configured by a combination of one or more CPUs and software. There is a form in which the processor functions as a plurality of processing units.
  • SoC system on chip
  • a processor that realizes the function of the entire system including a plurality of processing units by one IC (Integrated Circuit) chip is used.
  • IC Integrated Circuit
  • the various processing units are configured by using one or more of the above various processors as a hardware structure.
  • the information acquisition unit 21 acquires history information A indicating the history of cells to be used and cell information B of cells to be generated. As an example, when the identification information written on the container in which the cells to be used are stored is input from the input unit 15, the information acquisition unit 21 outputs the history information A of the cell provider corresponding to the input identification information. , Get from external server.
  • FIG. 2 is a diagram showing an example of the history information A according to the first embodiment of the present disclosure.
  • the history information A is information indicating the history of the cells used.
  • the history information A is, for example, as shown in FIG. 2, the name of the cell donor who is the holder of the cells to be used, the sex of the cell donor, the blood type of the cell donor, the race of the cell donor, and the cell donor.
  • the relatives of the cell donor are, for example, relatives within the third degree of relatives of the cell provider himself.
  • the technology of the present disclosure is not limited to this, and may include, for example, a blood relative farther than the third degree relative.
  • the history information A indicates the information illustrated in FIG. 2.
  • the technology of the present disclosure is not limited to this, and any one or more of the information illustrated in FIG. The information may be included.
  • FIG. 3 is a diagram showing an example of the cell information B according to the first embodiment of the present disclosure.
  • the cell information B is information on cells to be generated.
  • the cell information B includes information on the type B1 of cells to be generated, the target cell number B2, and the state B3 of cells to be generated.
  • the cell type B1 is information on the types of cells to be generated, such as iPS cells, cardiomyocytes, and nerve cells.
  • the target cell number B2 is information indicating the number of cells to be generated, such as 100,000 cells and 100 cells.
  • the cell state B3 is information indicating what one wants to do with the cell, such as wanting to culture and differentiating.
  • the cell type B1 and the target cell number B2 are set in advance, they are not changed until the initialization step T1, the culture step T2, and the differentiation step T3 shown in FIG. 19 are all completed.
  • the cell state B3 is "I want to initialize” in the initial step T1, "I want to expand culture” and “I want to sort” in the culture step T2, and "I want to differentiate” in the differentiation step T3. It is changed by the person in charge for each process.
  • the cell information B is information indicating the cell type B1, the target cell number B2, the cell state B3, and the number of days B4 at which generation is desired to be completed.
  • the technology of the present disclosure is not limited to this, and the cell information B may be information including any one or more of these pieces of information.
  • the generable information acquiring unit 23 includes the history information A acquired by the information acquiring unit 21, the cell information B, an initialization step T1 for initializing the cells, a culturing step T2 for culturing the cells, and a differentiation step for inducing differentiation of the cells. Based on the measurement information D related to the measurement when measuring the cell in any step of T3, the information F indicating whether or not the desired cell can be generated is acquired for each measurement of the cell.
  • FIG. 4 is a diagram showing an example of the measurement information D according to the first embodiment of the present disclosure.
  • the measurement information D is information related to the measurement when measuring the cells in the inspection of the cells.
  • the measurement information D1 is information D1 and the information D2 indicating the measurement result obtained by the measurement by the measurement means. is there.
  • the information D1 on the measuring means includes information on the method used for the measurement and information on the person in charge of the measurement.
  • the method used for the measurement there is information on the type of the measuring device and the presence/absence of use of the measuring device, and there are a phase contrast microscope, a bright field microscope, visual inspection, and the like.
  • the information of the person in charge of measurement there are information such as the names of the respective measurers such as the measurer A and the measurer B and the mature years of the measurement.
  • the information D2 indicating the measurement result obtained by the measurement includes information on the measured cell state, medium state, and presence/absence of bacteria.
  • the measured cell state is the inspection value of the cell, and the shape of the cell, the color of the cell, the number of cells, the size of the cell, the odor of the cell, the gene expression of the cell, the kind of the metabolite of the cell, the type of the cell.
  • cell protein information is information on whether or not a protein is synthesized, and cell gene expression refers to a process in which gene information is converted into structure and function in the cell.
  • a protein is measured using a fluorescent probe, and gene expression is measured using a gene amplification agent of a target obtained by grinding cells. Note that the present disclosure is not limited to this, and a known measurement method can be used.
  • the state of the medium includes information such as the color of the medium, metabolites of cells contained in the medium, and the concentration of gas dissolved in the medium.
  • the color of the medium By measuring the color of the medium, the amount of carbon dioxide dissolved in the medium can be measured.
  • the gas concentration for example, the carbon concentration and nitrogen concentration in the medium are measured. This makes it possible to detect whether or not the cells have been normally cultured.
  • the presence/absence of the bacterium is information such as whether the cell has the bacterium, the medium has the bacterium, the cells and the medium have the bacterium, and the bacterium does not have the bacterium.
  • the information illustrated in FIG. 4 is the measurement information D as one embodiment, but the technology of the present disclosure is not limited to this, and the measurement information D includes any one or more of the information illustrated in FIG. 4. Any information can be included.
  • a method used for the measurement is, for example, a phase contrast microscope. That is, in the initialization step T1, blood cells 41 and skin cells 42 are perforated, and a drug is introduced into the perforated holes. In this case, the cells may not be successfully initialized unless the holes are formed in the size, shape, and depth necessary for containing the drug. Therefore, for example, the size of the hole is measured from the image obtained by imaging the perforated cell 41 and the skin cell 42 with a phase contrast microscope.
  • the method used for measurement in the initialization step T1 is not limited to the phase-contrast microscope, and any method may be used as long as it can measure holes.
  • a method used for the measurement performed when selecting the iPS cells there is, for example, a method using a phase contrast microscope.
  • An iPS cell 43 is imaged using a phase-contrast microscope to acquire a captured image, and the size and shape of the iPS cell 43 in the acquired captured image are measured to form an iPS having a well-shaped shape, that is, a differentiation-inducible shape.
  • the iPS cell 44 is the cell 44, the iPS cell 44 is expanded and continuously cultivated.
  • the iPS cell 44 has an irregular shape, that is, the iPS cell 44 has a shape that cannot induce differentiation
  • the cells are sorted.
  • the method of using the iPS cells 43 for measurement is not limited to the phase contrast microscope, and may be the visual observation of the measurer or any other method.
  • FIG. 5 is a diagram showing a schematic configuration of the createable information acquisition unit 23 according to the first embodiment of the present disclosure.
  • the generable information acquisition unit 23 includes a first derivation unit 29, as shown in FIG.
  • the first derivation unit 29 derives, based on the history information A and the cell information B, and the measurement information D, the information F indicating whether or not a desired cell can be generated for each cell measurement.
  • the first derivation unit 29 includes a learned model M that has been machine-learned using learning information.
  • FIG. 6 is a diagram for explaining the learned model M according to the first embodiment of the present disclosure.
  • the learned model M corresponds to the history information A indicating the history of the cells to be used, the cell information B of the cells to be generated, the information set Q of the measurement information D, and the information set Q.
  • Machine learning is performed using learning information including a plurality of information sets J with the information F indicating whether or not cells to be generated can be generated. That is, the learned model M is machine-learned so as to output information F indicating whether or not a desired cell can be generated based on the history information A and the cell information B, and the measurement information D.
  • the learned model M is, for example, a target number of cells to be generated when generating cells of the cell information B from cells of the cell provider X having the information set Q of the cell provider X, that is, the history information A.
  • the model for obtaining the trained model M is also trained together with the result of whether or not it has been generated.
  • the history information A and the cell information B and the measurement information D are input to the learned model M, the cells to be generated can be generated for the history information A and the cell information B and the measurement information D. Learning is performed so that the information F indicating whether or not it is output.
  • a machine learning algorithm in the learned model M can use, for example, a neural network (NN (Neural Network)) on which deep learning (deep learning) is performed.
  • NN Neurological Network
  • the technology of the present disclosure is not limited to this, and examples thereof include a support vector machine (SVM), a convolutional neural network (CNN), a convolutional neural network (CNN), and a recurrent.
  • SVM support vector machine
  • CNN convolutional neural network
  • CNN convolutional neural network
  • CNN convolutional neural network
  • RNN Recurrent Neural Network
  • FIG. 7 is a diagram for explaining the first derivation unit 29 according to the first embodiment of the present disclosure.
  • the first derivation unit 29 has, as an example, the learned model M described above.
  • the learned model M described above.
  • the learned model M may output the probability that a desired cell can be generated for each number of cells.
  • the number of cells that exceeds a threshold of a predetermined probability is output as the number of cells that can be generated, and the number of cells that is less than or equal to the threshold of the probability is a cell that is insufficient to reach the target number of cells. May be output as the number of
  • FIG. 8 is a diagram for explaining processing performed in the cell generation supporting apparatus 1 according to the first embodiment of the present disclosure
  • FIG. 9 shows processing performed in the cell generation supporting apparatus 1 according to the first embodiment of the present disclosure. It is a flowchart shown.
  • the information acquisition unit 21 acquires history information A indicating the history of cells to be used and cell information B of cells to be generated (step ST1).
  • the measurement of cells is determined in advance in each step of an initialization step T1 for initializing cells, a culture step T2 for culturing cells, and a differentiation step T3 for inducing differentiation of cells.
  • Timing that is, cell inspection timing.
  • the CPU 11 determines a predetermined timing in each step of the initialization step T1 for initializing cells, the culture step T2 for culturing cells, and the differentiation step T3 for inducing differentiation of cells, that is, the determination.
  • the determination timing can be set based on the cell inspection timing, and the determination timing can be set between a certain cell inspection timing and the next cell inspection timing.
  • step ST2 When it is determined in step ST2 that the generable information acquisition unit 23 has not acquired new measurement information D (step ST2; NO), the CPU 11 shifts the processing to step ST6, and all steps are completed. It is determined whether or not (step ST6).
  • step ST3 when the CPU 11 determines in step ST2 that the new measurement information D has been acquired (step ST2; YES), the producible information acquisition unit 23 acquires the new measurement information D as shown in FIG. Based on the history information A, the cell information B, and the measurement information D output by inputting to the learned model M, the information F indicating whether or not the desired cell can be generated is acquired (step ST3).
  • the CPU 11 determines whether or not the cells to be generated can be generated (step ST4). If it can be generated (step ST4; YES), the notification unit 14 notifies that it can be generated, and the cell culture is continued. Specifically, the notification unit 14 displays on the display that cells can be generated (step ST5). The notification unit 14 may display the number of cells that are still insufficient.
  • step ST6 determines whether or not all steps have been completed.
  • step ST6; NO the CPU 11 shifts the processing to step ST2 and performs the subsequent processing. That is, based on the timing determined in advance, it is determined whether or not the generatable information acquisition unit 23 has acquired new measurement information D related to measurement when measuring cells (step ST2).
  • step ST6; YES the cell generation support device 1 ends the series of processes.
  • step ST4 when the generation is not possible (step ST4; NO), the notification unit 14 notifies the culture stop and stops the cell culture. Specifically, the notification unit 14 displays the culture stop on the display (step ST7). Then, the cell generation support device 1 ends the series of processes.
  • the history information A indicating the history of the cells to be used and the cell information B of the cells to be generated are acquired, and the history information A and the cell information are acquired.
  • B based on measurement information D related to measurement when measuring cells in any one of an initialization step of initializing cells, a culture step of culturing cells, and a differentiation step of inducing differentiation of cells.
  • the information F indicating whether or not the cells to be generated can be generated is acquired for each cell measurement, it is possible to acquire the information regarding whether or not the desired number of cells can be generated.
  • the person in charge of generating the cell is notified of the fact that the cell can be generated when the cell is notified that the cell can be generated.
  • the culture can be continued, and when it is notified that the cells cannot be generated, the cell culture can be stopped and restarted from the beginning, or the generation of an insufficient number of cells can be started.
  • unnecessary time can be shortened and unnecessary culture and differentiation induction can be eliminated as compared with the conventional case, so that cost loss can be prevented.
  • the creatable information acquisition unit 23 acquires the information F indicating whether or not the desired cell can be created, based on the history information A, the cell information B, and the new measurement information D.
  • the generative information acquisition unit 23 wants to generate based on the history information A, the cell information B, and all the measurement information D acquired from the start of the culture until the new measurement information D is acquired.
  • the information F indicating whether or not cells can be generated may be acquired.
  • FIG. 10 is a diagram showing a schematic configuration of a cell generation support device 1-2 according to the second embodiment of the present disclosure.
  • FIG. 10 is realized by installing a cell generation support program.
  • the cell generation support apparatus 1-2 according to the second embodiment of the present disclosure is the cell generation support apparatus 1 according to the first embodiment described above.
  • the same components as those of the above are given the same reference numerals, and the description thereof will be omitted. Only different points will be described in detail.
  • the cell generation support device 1-2 further includes a culture condition acquisition unit 22 in addition to the cell generation support device 1 of FIG.
  • the culture condition acquisition unit 22 acquires a culture condition C for culturing cells based on the history information A and the cell information B.
  • FIG. 11 is a diagram showing an example of the culture condition C according to the second embodiment of the present disclosure.
  • the culture condition C is a culture condition for producing a desired number of cells to be produced.
  • the "cells to be generated" are cells having a target quality. Therefore, in the present embodiment, the culturing condition C is a culturing condition for producing the desired number of cells to be produced with a desired quality.
  • the culture condition C indicates which cells are used, how many cells are used, which medium is used, which medium is used, which additive is added to generate the cells, and the desired number of cells can be generated. .. Specifically, the culture condition C is, as shown in FIG. 11 as an example, the type of cells used, the number of cells used, the type of container used, the type of medium used, the type of additive used, and the treatment. Includes information about the timing of, and the person in charge.
  • culture condition C includes the use of liver cells as cells A and vascular cells as cells B. Also, cell number, 10 5 cells A, 10 6 cells of cell B, and cell 10 5 A and a cell B 10 6 cells, etc., the number of specific uses for the cells contained in the culture condition C Be done.
  • the type of container used is, for example, a petri dish, n well plates having 6 wells, m well plates having 24 wells, and 1 T75 flask. And are included in culture condition C.
  • the culture conditions C include, as an example, the type of medium to be used, such as medium M1, medium M2, or a mixture of medium M1 and medium M2.
  • the culture condition C is set including the mixing ratio.
  • the type of the additive to be used includes, for example, the additive C1, the additive C2, or the mixture of the additive C1 and the additive C2 in the culture condition C.
  • the culture condition C is set including the mixing ratio.
  • the timing of the treatment is, for example, the timing of seeding, the timing of subculture, the timing of exchanging the medium, the timing of adding additives, and the timing of inspecting cells.
  • the culture condition C includes which treatment should be performed at which timing.
  • the culture condition C includes information about the person in charge, such as who is in charge of the person A and person B. For example, the person A who is good at fine work and the person B who is not good at fine work may have different effects on cell generation even if the same process is performed. Therefore, the culture condition C includes which person in charge and which process should be performed.
  • the condition shown in FIG. 11 as the embodiment is the culture condition C, but the technique of the present disclosure is not limited to this, and the culture condition C includes any one or more of the information shown in FIG. 11. Any information will do.
  • FIG. 12 is a diagram showing a schematic configuration of the culture condition acquisition unit 22 according to the second embodiment of the present disclosure.
  • the culture condition acquisition unit 22 includes a second derivation unit 30 and a third derivation unit 31.
  • the second derivation unit 30 derives the culture condition C based on the history information A and the cell information B.
  • the second derivation unit 30 includes a learned model M that has been machine-learned using learning information.
  • FIG. 13 is a diagram for explaining the learned model M according to the second embodiment of the present disclosure.
  • the learned model M includes a history information A indicating the history of cells to be used and an information set P of cell information B of cells to be generated, and a culture condition C corresponding to the information set P.
  • Machine learning is performed using learning information including a plurality of information sets S. That is, the learned model M is machine-learned so as to output the culture condition C based on the history information A and the cell information B.
  • the learned model M is cultured under the culture condition C when the cells of the cell information B are generated from the cells of the cell provider X having the history information A, that is, the information set P of the cell provider X.
  • the model for obtaining the learned model M is also trained with the result of success or failure.
  • the learned model M outputs the culture condition C capable of generating the cell indicated by the cell information B, with respect to the history information A and the cell information B. Learning is done to do.
  • FIG. 14 is a diagram for explaining the second derivation unit 30 according to the second embodiment of the present disclosure.
  • the second derivation unit 30 has the learned model M shown in FIG. 13 described above as an example.
  • the culture condition exceeding the threshold value is output as the culture condition C suitable for the cells to be generated.
  • the culture condition C is, as shown in FIG. 11, the type of cells used, the number of cells used, the type of container used, the type of medium used, the type of additive used, the timing of treatment, and the charge. It includes at least one of the information about the person.
  • the learned model M has the target quality for each number of cells to be used. , And outputs the probability that a target number of cells can be generated, and the culture condition acquisition unit 22 uses a cell number that has the target quality and the highest probability that the target number of cells can be produced. It may be obtained as the number, that is, as the culture condition C most suitable for the cells to be generated.
  • the culture condition acquisition unit 22 further performs measurement when measuring cells in any one of the initialization step T1, the culture step T2, and the differentiation step T3 shown in FIG.
  • the updated culture condition E which is an update of the culture condition C at the time when the measurement information D is acquired, is acquired as a new culture condition C based on the measurement information D related to.
  • FIG. 15 is a diagram for further explaining the learned model M according to the second embodiment of the present disclosure shown in FIG. 13.
  • the learned model M includes a set G of measurement information D and a culture condition C related to measurement when measuring cells, and an updated culture condition E corresponding to the set G of information.
  • Machine learning is performed using learning information including a plurality of information sets R. That is, the learned model M is machine-learned so as to output the updated culture condition E based on the measurement information D and the culture condition C at the time when the measurement information D was acquired.
  • the learned model M has already been learned together with the result of whether or not the culture was successful when the cell of the cell information B was generated from the cell of the cell provider X and the culture was performed under the updated culture condition E.
  • the model to obtain model M.
  • the cell information B indicates the new measurement information D.
  • Learning is performed so as to output the updated culture condition E capable of generating cells.
  • the learned model M illustrated in FIG. 13 and the learned model M illustrated in FIG. 15 are the same model, but the technique of the present disclosure is not limited to this, and the technique illustrated in FIG.
  • the learned model M shown may be a second learned model and the learned model M shown in FIG. 15 may be a third learned model.
  • the learned model M shown in FIG. 6 the learned model M shown in FIG. 13 and the learned model M shown in FIG. 15 may be the same model, or the learned model shown in FIG.
  • the model may be a trained model and may be different from the above model.
  • a machine learning algorithm in the learned model M can use, for example, a deep learning (NN) neural network (NN (Neural Network)).
  • NN deep learning
  • the technology of the present disclosure is not limited to this, and examples thereof include a support vector machine (SVM), a convolutional neural network (CNN), a convolutional neural network (CNN), and a recurrent.
  • SVM support vector machine
  • CNN convolutional neural network
  • CNN convolutional neural network
  • CNN convolutional neural network
  • RNN Recurrent Neural Network
  • FIG. 16 is a diagram for explaining the third derivation unit 31 according to the second embodiment of the present disclosure.
  • the third derivation unit 31 has the learned model M shown in FIG. 15 described above as an example.
  • the measurement information D measured at each measurement of the cells and the measurement information D are obtained.
  • the culture condition C at the time of acquisition is input, the culture condition exceeding a predetermined threshold value is output as the renewed culture condition E suitable for the cells to be generated.
  • the updated culture condition E is, for example, when the number of cells to be used is the updated culture condition E, the measurement information D and the culture condition C at the time when the measurement information D is acquired are input to the learned model M.
  • the learned model M outputs the probability that a target number of cells can be generated for each number of cells to be used, and the culture condition acquisition unit 22 outputs the target quality with the target quality.
  • the number of cells having the highest probability of generating the number of cells may be acquired as the number of cells to be used, that is, the updated culture condition E most suitable for the cells to be generated.
  • FIG. 17 is a flowchart showing a process performed by the cell generation support device 1-2 of the second embodiment of the present disclosure
  • FIG. 18 is a process performed by the cell generation support device 1-2 of the second embodiment of the present disclosure. It is a figure for explaining.
  • the information acquisition unit 21 acquires history information A indicating the history of cells to be used and cell information B of cells to be generated (step ST21).
  • the culture condition acquisition unit 22 inputs the history information A and the cell information B acquired by the information acquisition unit 21 to the learned model M to set the culture condition C for culturing the cells, as shown in FIG. It is acquired (step ST22).
  • the person in charge starts the work of generating cells.
  • the person in charge collects cells based on the culture condition C from the cell donor 40, and the initialization step T1 of the collected cells is started.
  • the CPU 11 sets a predetermined timing in each step of an initialization step T1 for initializing cells, a culture step T2 for culturing cells, and a differentiation step T3 for inducing differentiation of cells, That is, based on the determination timing, it is determined whether or not the culture condition acquisition unit 22 has acquired new measurement information D related to measurement when measuring cells (step ST23).
  • the determination timing can be set based on the cell inspection timing, and the determination timing can be set between a certain cell inspection timing and the next cell inspection timing.
  • step ST23 determines in step ST23 that the new measurement information D has not been acquired (step ST23; NO)
  • the CPU 11 shifts the processing to step ST30 and completes all the steps. It is determined whether or not (step ST30).
  • step ST23 when it is determined in step ST23 that the culture condition acquisition unit 22 has acquired the new measurement information D (step ST23; YES), the creatable information acquisition unit 23 acquires the newly acquired information as shown in FIG. Based on the history information A and the cell information B and the measurement information D, which is output by inputting various measurement information D into the learned model M, the information F indicating whether or not the desired cell can be generated is acquired ( Step ST24).
  • the CPU 11 determines whether or not the cells to be generated can be generated (step ST25).
  • the notification unit 14 notifies that it can be generated, and the cell culture is continued.
  • the notification unit 14 displays on the display that cells can be generated (step ST26).
  • the notification unit 14 may display the number of cells that are still insufficient.
  • step ST25 when the generation is not possible (step ST25; NO), the notification unit 14 notifies the stop of the culture and stops the culture of the cells. Specifically, the notification unit 14 displays the culture stop on the display (step ST27). Then, the cell generation support device 1 ends the series of processes.
  • step ST26 when it is displayed on the display that cells can be generated, the culture condition acquisition unit 22 then acquires the new measurement information D and the new measurement information as shown in FIG.
  • the updated culture condition E output from the learned model M is acquired as a new culture condition C by inputting the culture condition C at the time when D is acquired to the learned model M (step ST28).
  • the notification unit 14 notifies the culture condition C newly acquired by the culture condition acquisition unit 22. Specifically, the culture condition C is displayed on the display (step ST29).
  • step ST30 determines whether or not all steps have been completed.
  • step ST30 determines whether or not all steps have been completed.
  • step ST30 determines whether or not all steps have been completed.
  • step ST30 determines whether or not the steps are not completed (step ST30; NO)
  • the CPU 11 shifts the processing to step ST23 and performs the subsequent processing. That is, based on the cell inspection timing of the updated culture condition C, it is determined whether or not the culture condition acquisition unit 22 has acquired new measurement information D related to measurement when measuring cells (step ST23). ..
  • step ST30 YES
  • the cell generation support device 1 ends the series of processes.
  • the history information A indicating the history of the cell to be used and the cell information of the cell to be generated.
  • B is acquired, and a culture condition C for culturing cells is acquired based on the acquired history information A and cell information B, and further initialization step T1 for initializing cells, culture step T2 for culturing cells,
  • the culture condition C at the time when the measurement information D is acquired is updated based on the measurement information D related to the measurement when measuring the cells. Since the updated culture condition E is acquired as the culture condition C, it is possible to acquire a more optimal culture condition C for generating the target number of cells to be generated each time the cells are measured.
  • the optimum culture condition C can be acquired for each measurement at the cell inspection timing based on the culture condition C. Therefore, the person in charge of generating the cell generates the cell based on the optimum culture condition C. It is possible to improve the possibility that the desired number of cells to be generated can be generated as compared with the conventional method.
  • the first derivation unit 29, the second derivation unit 30, and the third derivation unit 31 include the learned model M, but the technique of the present disclosure is not limited to this. Not limited. If the first derivation unit 29 can derive the information F indicating whether or not the desired cell can be generated based on the history information A, the cell information B, and the measurement information D, the first derivation unit 29 uses machine learning. Alternatively, a correspondence table between the history information A and the cell information B, the measurement information D, and the information F indicating whether or not the information can be generated, and a calculation formula may be used.
  • the second derivation unit 30 can derive the culture condition C based on the history information A and the cell information B, the history information A and the cell information B and the culture condition can be obtained without using machine learning. You may use the correspondence table with C, a calculation formula, etc.
  • the third derivation unit 31 also derives the updated culture condition E based on the measurement information D and the culture condition C acquired when the measurement information D was acquired. If possible, any one of the correspondence table and the calculation formula may be used.
  • the culture condition acquisition unit 22 of the above-described embodiment may further acquire, as the culture condition C, the updated culture condition E that is updated by adding weighting based on the information D1 regarding the measuring means.
  • the person A who is good at fine work and the person B who is not good at fine work may have different effects on cell generation even if the same process is performed.
  • the influence on the generation of cells may differ between the visual inspection by the person in charge and the measurement using the measuring device. Therefore, the weighting based on the information D1 regarding the measuring means, that is, the weighting based on the information D1 regarding the measuring means, which is more accurate in the measurement result, is added to the updated renewed culture condition E.
  • the more optimal culture condition C can be obtained as compared with the above-described embodiment.
  • the learned model M of the second embodiment described above has new measurement information D and the updated culture condition E derived from the culture condition C acquired at the time of acquisition of this measurement information D, and the target.
  • the learning is performed so as to output the probability that a target number of cells can be generated and the output, but the present invention is not limited to this, and instead of the culture condition C, the history information A and the cell information B are included.
  • the updated culture condition E may be derived from the information obtained.
  • the notification unit 14 of the above-described embodiment displays that cells can be generated in the first embodiment, displays that cells can be generated, and culture condition C in the second embodiment.
  • the probability that the cell indicated by the cell information B can be generated, the history information A, the cell information B, the acquired measurement information D, that is, the information D1 regarding the measurement means and the measurement information are obtained. You may make it display the information D2 which shows a measurement result, and the successive change etc. of the information D2 which shows the measurement result obtained by measurement.
  • cell generation support device 1 which is an embodiment of the technique of the present disclosure can be appropriately modified in design without departing from the gist of the technique of the present disclosure.

Landscapes

  • Engineering & Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Chemical & Material Sciences (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • General Engineering & Computer Science (AREA)
  • Zoology (AREA)
  • Wood Science & Technology (AREA)
  • Software Systems (AREA)
  • Biotechnology (AREA)
  • General Health & Medical Sciences (AREA)
  • Biomedical Technology (AREA)
  • General Physics & Mathematics (AREA)
  • Organic Chemistry (AREA)
  • Data Mining & Analysis (AREA)
  • Evolutionary Computation (AREA)
  • Artificial Intelligence (AREA)
  • Mathematical Physics (AREA)
  • Computing Systems (AREA)
  • Biochemistry (AREA)
  • Molecular Biology (AREA)
  • Medicinal Chemistry (AREA)
  • Microbiology (AREA)
  • Sustainable Development (AREA)
  • Computational Linguistics (AREA)
  • Biophysics (AREA)
  • Genetics & Genomics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Analytical Chemistry (AREA)
  • Medical Informatics (AREA)
  • Apparatus Associated With Microorganisms And Enzymes (AREA)
  • Measuring Or Testing Involving Enzymes Or Micro-Organisms (AREA)

Abstract

Grâce à l'utilisation du dispositif, du procédé et du programme d'aide à la génération de cellules selon l'invention, des informations concernant la possibilité de générer ou non uniquement un nombre cible de cellules que l'on veut générer sont acquises. Plus spécifiquement, des informations de parcours indiquant le parcours des cellules utilisées ainsi que des informations de cellules des cellules que l'on veut générer sont acquises, puis, par la mise en oeuvre soit d'un processus d'initialisation qui permet d'initialiser les informations de parcours, les informations de cellules et les cellules, soit d'un processus de culture qui permet la culture des cellules, soit par un processus de différenciation qui permet d'induire la différentiation des cellules, sur la base d'informations de mesures des cellules, des informations concernant la possibilité de générer ou non les cellules que l'on veut générer sont acquises.
PCT/JP2019/042067 2019-01-18 2019-10-25 Dispositif, procede et programme d'aide a la generation de cellules Ceased WO2020148964A1 (fr)

Priority Applications (1)

Application Number Priority Date Filing Date Title
JP2020566110A JP7289854B2 (ja) 2019-01-18 2019-10-25 細胞生成支援装置、方法、及びプログラム

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
JP2019-007373 2019-01-18
JP2019007373 2019-01-18

Publications (1)

Publication Number Publication Date
WO2020148964A1 true WO2020148964A1 (fr) 2020-07-23

Family

ID=71613596

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/JP2019/042067 Ceased WO2020148964A1 (fr) 2019-01-18 2019-10-25 Dispositif, procede et programme d'aide a la generation de cellules

Country Status (2)

Country Link
JP (1) JP7289854B2 (fr)
WO (1) WO2020148964A1 (fr)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2024523057A (ja) * 2021-10-25 2024-06-26 コリア ユニバーシティ リサーチ アンド ビジネス ファウンデーション 人工知能を利用した細胞判別方法および装置
WO2024210652A1 (fr) * 2023-04-07 2024-10-10 (주)그래디언트 바이오컨버전스 Dispositif de sortie de conditions de milieu de culture, procédé de fourniture en sortie de conditions de milieu de culture de cellules tumorales et programme informatique

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2004013278A (ja) * 2002-06-04 2004-01-15 Olympus Corp 手術日決定支援装置及びその方法並びにプログラム
JP2011229412A (ja) * 2010-04-23 2011-11-17 Nagoya Univ 細胞評価装置、インキュベータ、プログラム、培養方法、手技評価装置、および、細胞評価モデル構築装置
JP2016189702A (ja) * 2015-03-30 2016-11-10 国立大学法人名古屋大学 細胞分析モデル生成装置及び細胞分析モデル生成方法、細胞分析装置及び細胞分析方法、並びにプログラム
JP2018019685A (ja) * 2016-08-04 2018-02-08 ファナック株式会社 幹細胞製造システム、幹細胞情報管理システム、細胞輸送設備、及び幹細胞冷凍保存設備
WO2018101004A1 (fr) * 2016-12-01 2018-06-07 富士フイルム株式会社 Système d'évaluation d'image de cellule et programme de commande d'évaluation d'image de cellule
WO2018142702A1 (fr) * 2017-01-31 2018-08-09 株式会社ニコン Dispositif d'aide à la culture, dispositif d'observation, et programme

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2004013278A (ja) * 2002-06-04 2004-01-15 Olympus Corp 手術日決定支援装置及びその方法並びにプログラム
JP2011229412A (ja) * 2010-04-23 2011-11-17 Nagoya Univ 細胞評価装置、インキュベータ、プログラム、培養方法、手技評価装置、および、細胞評価モデル構築装置
JP2016189702A (ja) * 2015-03-30 2016-11-10 国立大学法人名古屋大学 細胞分析モデル生成装置及び細胞分析モデル生成方法、細胞分析装置及び細胞分析方法、並びにプログラム
JP2018019685A (ja) * 2016-08-04 2018-02-08 ファナック株式会社 幹細胞製造システム、幹細胞情報管理システム、細胞輸送設備、及び幹細胞冷凍保存設備
WO2018101004A1 (fr) * 2016-12-01 2018-06-07 富士フイルム株式会社 Système d'évaluation d'image de cellule et programme de commande d'évaluation d'image de cellule
WO2018142702A1 (fr) * 2017-01-31 2018-08-09 株式会社ニコン Dispositif d'aide à la culture, dispositif d'observation, et programme

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
SATO KAZUKI: "A machine learning algorithm for the automatic and non invasive quality assessment of confluent cells", IEICE TECHNICAL REPORT, vol. 116, no. 393 (MI2016-98), 11 January 2017 (2017-01-11), JP, pages 101 - 106, XP009522563, ISSN: 0913-5685 *

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2024523057A (ja) * 2021-10-25 2024-06-26 コリア ユニバーシティ リサーチ アンド ビジネス ファウンデーション 人工知能を利用した細胞判別方法および装置
JP7612952B2 (ja) 2021-10-25 2025-01-15 コリア ユニバーシティ リサーチ アンド ビジネス ファウンデーション 人工知能を利用した細胞判別方法および装置
WO2024210652A1 (fr) * 2023-04-07 2024-10-10 (주)그래디언트 바이오컨버전스 Dispositif de sortie de conditions de milieu de culture, procédé de fourniture en sortie de conditions de milieu de culture de cellules tumorales et programme informatique

Also Published As

Publication number Publication date
JP7289854B2 (ja) 2023-06-12
JPWO2020148964A1 (ja) 2021-10-21

Similar Documents

Publication Publication Date Title
Chavez-Badiola et al. Embryo Ranking Intelligent Classification Algorithm (ERICA): artificial intelligence clinical assistant predicting embryo ploidy and implantation
Unadkat et al. An algorithm-based topographical biomaterials library to instruct cell fate
EP2682455B1 (fr) Appareil et procédé de commande d'affichage, appareil et procédé de traitement d'image, et programme
Burova et al. Mathematical and computational models for bone tissue engineering in bioreactor systems
JP7034354B2 (ja) 生存細胞の画像解析のための解析方法
Piotrowski et al. Deep-learning-based multi-class segmentation for automated, non-invasive routine assessment of human pluripotent stem cell culture status
Schu et al. Scanning electron microscopy preparation of the cellular actin cortex: A quantitative comparison between critical point drying and hexamethyldisilazane drying
AU2019355222A1 (en) Systems and methods for identifying bioactive agents utilizing unbiased machine learning
Wu et al. Particle tracking microrheology of cancer cells in living subjects
Jernigan et al. Toward an integrative science of the developing human mind and brain: focus on the developing cortex
JP2013039113A (ja) 細胞品質管理方法及び細胞の生産方法
WO2020148964A1 (fr) Dispositif, procede et programme d'aide a la generation de cellules
JP7282809B2 (ja) 細胞生成支援装置、方法、及びプログラム
CN110688985A (zh) 体外培养胚胎的自动化监控
James et al. Quantifying trophoblast migration: in vitro approaches to address in vivo situations
WO2022168774A1 (fr) Dispositif d'estimation, dispositif d'apprentissage, dispositif d'optimisation, procédé d'estimation, procédé d'apprentissage et procédé d'optimisation
WO2016088243A1 (fr) Dispositif de détermination, système d'observation, procédé d'observation, programme associé, procédé de fabrication de cellule, et cellule
EP4361243A1 (fr) Dispositif de traitement d'informations, procédé de traitement d'informations et programme
EP3808834A1 (fr) Dispositif de traitement d'informations, procédé de dérivation et programme de dérivation
WO2023285461A1 (fr) Quantification et analyse d'organoïdes à partir d'images numériques
JP2020166711A (ja) 計数装置、計数方法、計数プログラムおよび記録媒体
CN117612161A (zh) 一种基于无标记影像和深度学习的细胞表型分析方法与应用
Van Blerkom et al. Design and development of simplified, low-cost technologies for clinical IVF: applications in high-and low-resource settings
Elschner et al. Assessing agreement between preclinical magnetic resonance imaging and histology: An evaluation of their image qualities and quantitative results
WO2025250610A1 (fr) Système et procédé d'évaluation d'objet biologique, de sélection de clone et de gestion de processus

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 19909896

Country of ref document: EP

Kind code of ref document: A1

ENP Entry into the national phase

Ref document number: 2020566110

Country of ref document: JP

Kind code of ref document: A

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 19909896

Country of ref document: EP

Kind code of ref document: A1