WO2011021391A1 - Dispositif d'évaluation de cellules cultivées, incubateur et programme - Google Patents

Dispositif d'évaluation de cellules cultivées, incubateur et programme Download PDF

Info

Publication number
WO2011021391A1
WO2011021391A1 PCT/JP2010/005119 JP2010005119W WO2011021391A1 WO 2011021391 A1 WO2011021391 A1 WO 2011021391A1 JP 2010005119 W JP2010005119 W JP 2010005119W WO 2011021391 A1 WO2011021391 A1 WO 2011021391A1
Authority
WO
WIPO (PCT)
Prior art keywords
cells
cultured cell
cultured
cell
feature amount
Prior art date
Application number
PCT/JP2010/005119
Other languages
English (en)
Japanese (ja)
Inventor
加藤竜司
本多裕之
山本若菜
名倉良英
Original Assignee
国立大学法人名古屋大学
株式会社ニコン
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 国立大学法人名古屋大学, 株式会社ニコン filed Critical 国立大学法人名古屋大学
Publication of WO2011021391A1 publication Critical patent/WO2011021391A1/fr

Links

Images

Classifications

    • 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
    • C12M41/00—Means for regulation, monitoring, measurement or control, e.g. flow regulation
    • C12M41/46—Means for regulation, monitoring, measurement or control, e.g. flow regulation of cellular or enzymatic activity or functionality, e.g. cell viability

Definitions

  • the present invention relates to a cultured cell evaluation apparatus, an incubator, and a program.
  • Patent Document 1 discloses a cancer cell evaluation method using a transcription factor as a marker.
  • the evaluation test process as described above it is actually difficult to perform an enormous evaluation only for ensuring cell stability. Therefore, the actual situation is that the evaluation of the degree of cell degradation is operated based on empirical and rough judgment criteria based on the number of passages and the number of freezing of cell lines.
  • an object of the present invention is to provide means for evaluating cells to be evaluated based on evaluation attributes by a relatively simple technique.
  • the cultured cell evaluation apparatus includes an image acquisition unit, a feature amount acquisition unit, a storage unit, and an evaluation processing unit.
  • the image acquisition unit acquires a plurality of images obtained by capturing the target cells cultured in the culture container in time series.
  • the feature amount acquisition unit obtains a plurality of types of feature amounts respectively indicating the morphological features of the target cells included in the image, for each image.
  • the storage unit stores a discrimination model for classifying cells having different evaluation attributes.
  • the classification of the discriminant model is performed based on an index selected from a combination of a plurality of types of feature amounts and observation periods.
  • the evaluation processing unit collates the index of the discrimination model with the feature quantity at each observation time of the target cell, and classifies the target cell.
  • the cultured cell evaluation method includes an image acquisition step of acquiring image data of cultured cells to be evaluated, a selection step, a feature amount acquisition step, and an evaluation step.
  • a type of feature amount indicating a morphological feature for classifying cultured cells and a threshold corresponding to the type of feature amount are selected.
  • a feature amount acquisition step a feature amount corresponding to the type selected in the selection step is acquired from the image data acquired in the image acquisition step.
  • the evaluation step the cultured cell is evaluated using the feature amount of the cultured cell acquired in the feature amount acquisition step and the threshold value selected in the selection step.
  • an incubator incorporating the above cultured cell evaluation apparatus, a program and a program storage medium for causing a computer to function as the above cultured cell evaluation apparatus, and an operation of the above cultured cell evaluation apparatus expressed in a method category, This is effective as a specific embodiment of the present invention.
  • the block diagram which shows the structural example of the cultured cell evaluation apparatus which concerns on 1st Embodiment.
  • the figure which shows the example of the change of the cytoskeleton amount per cell of the 4th passage -8th passage Flow chart of an operation example of the construction process of the degradation determination model according to the first embodiment (A)-(o): Diagram showing an overview of each feature value Flow chart showing an example of a construction subroutine for a degradation discrimination model The figure which shows the example of the deterioration discrimination model constructed
  • FIG. 1 Flow chart of an example of cell deterioration degree evaluation processing according to the first embodiment
  • FIG. 1 is a block diagram illustrating a configuration example of the cultured cell evaluation apparatus according to the first embodiment.
  • the cultured cell evaluation apparatus of the first embodiment is configured by a personal computer in which an evaluation processing program for evaluating the degree of deterioration of cultured cells is installed.
  • the cultured cell evaluation apparatus of the first embodiment reads a plurality of microscopic images (target images and teacher images) acquired from time-lapse observation of a culture vessel in which cells are cultured from the outside. Then, the cultured cell evaluation apparatus according to the first embodiment constructs a deterioration determination model that classifies cells having different degrees of deterioration by supervised learning using a teacher image. In addition, the cultured cell evaluation apparatus according to the first embodiment executes the evaluation of the degree of deterioration of the cells included in the target image by applying the above-described deterioration determination model.
  • the 1 includes a data reading unit 12, a storage device 13, a CPU 14, a memory 15, an input / output I / F 16, and a bus 17.
  • the data reading unit 12, the storage device 13, the CPU 14, the memory 15, and the input / output I / F 16 are connected to each other via a bus 17.
  • an input device 18 keyboard, pointing device, etc.
  • a monitor 19 are connected to the computer 11 via an input / output I / F 16.
  • the input / output I / F 16 receives various inputs from the input device 18 and outputs display data to the monitor 19.
  • the data reading unit 12 is used when reading the above-mentioned microscope image data and the above-described evaluation processing program from the outside.
  • the data reading unit 12 communicates with a reading device (such as an optical disk, a magnetic disk, or a magneto-optical disk reading device) that acquires data from a removable storage medium, or an external device in accordance with a known communication standard. It consists of communication devices (USB interface, LAN module, wireless LAN module, etc.) to be performed.
  • the storage device 13 is constituted by a storage medium such as a hard disk or a nonvolatile semiconductor memory, for example.
  • the storage device 13 stores an evaluation processing program and various data necessary for executing the program (for example, data of a deterioration determination model).
  • the storage device 13 can also store the microscope image data read from the data reading unit 12.
  • the CPU 14 is a processor that comprehensively controls each part of the computer 11.
  • the CPU 14 functions as a feature amount acquisition unit 21, a model construction unit 22, and an evaluation processing unit 23 by executing the above evaluation processing program (feature amount acquisition unit 21, model construction unit 22, evaluation processing unit 23, respectively). These operations will be described later).
  • the feature quantity acquisition unit 21 and the model construction unit 22 operate.
  • the feature amount acquisition unit 21 and the evaluation processing unit 23 operate.
  • the memory 15 temporarily stores various calculation results in the evaluation processing program.
  • the memory 15 is composed of, for example, a volatile SDRAM.
  • the observation magnification in the microscope image is 4 times, and the image size is set to 1360 pixels ⁇ 1024 pixels (about 1.4 million pixels).
  • the cultured cell evaluation apparatus in the first embodiment reads and acquires 450 microscopic images (3 ⁇ 5 fields of view ⁇ 6 days ⁇ 5 passages) acquired from the above conditions from the data reading unit 12. And
  • the prediction accuracy of the degree of cell degradation is verified by cross-validation using the above-described 450 microscope images.
  • 450 microscopic images were randomly divided into 10 sample groups. Then, the process of constructing the deterioration determination model is executed using 9 samples (405 sheets) as a teacher image, and the operation of executing the cell deterioration degree evaluation process is repeated 10 times with the remaining samples (45 sheets) by replacing the samples. (10-fold cross validation).
  • FIG. 2 shows an example of changes caused by subculture of human fibroblasts.
  • an image of normal human fibroblasts and each image of human fibroblasts at the 4th to 9th passages are shown.
  • Comparison of the images in FIG. 2 shows that human fibroblasts tend to spread thinly as the number of passages increases, and that the appearance of human fibroblasts changes depending on the number of passages.
  • FIGS. 3 to 5 are diagrams showing the degree of degradation of human fibroblasts by subculture based on conventional experimental methods, respectively.
  • FIG. 3 is a diagram showing an example of changes in the viable cell ratio (Calcein / PI) from the 4th to the 8th passages. According to FIG. 3, it can be seen that the viable cell rate gradually decreases as the number of passages progresses.
  • FIG. 4 is a diagram showing an example of changes in the number of senescent cells ( ⁇ galactosidase / DAPI) from the 4th to the 8th passages. According to FIG. 4, senescent cells were not detected at passages 4-6, but senescent cells were detected at passages 7 and 8.
  • FIG. 5 is a diagram showing an example of changes in cytoskeleton amount (Phaloidin / DAPI) per cell from the 4th passage to the 8th passage.
  • the amount of cytoskeleton gradually decreases as the number of passages progresses. This indicates that as the number of passages progresses, the intracellular order decreases and it becomes difficult to maintain the cell morphology.
  • FIGS. 3 to 5 it can be clearly seen that the degree of cell deterioration increases as the passage number advances.
  • Step S101 The CPU 14 acquires teacher image data. Note that, as described above, the CPU 14 in the first embodiment sets 405 images among the 450 microscope images stored in advance in the storage device 13 as teacher images.
  • Step S102 The CPU 14 designates a calculation target image from among a plurality of teacher images. Note that the CPU 14 in S102 sequentially designates all of the teacher images as calculation targets.
  • the feature quantity acquisition unit 21 extracts cells included in the image of the calculation target teacher image (specified in S102). For example, when a cell is imaged with a phase-contrast microscope, a halo appears in the vicinity of a region with a large change in phase difference, such as a cell wall. Therefore, the feature quantity acquisition unit 21 extracts a halo corresponding to the cell wall by a known edge extraction method, and estimates a closed space surrounded by edges by a contour tracking process as a cell. Thereby, individual cells can be extracted from the microscope image.
  • the feature quantity acquisition unit 21 obtains a feature quantity indicating a morphological feature of each cell extracted from the image in S103.
  • the feature amount acquisition unit 21 in S104 obtains the following 15 types of feature amounts for each cell.
  • Total area is a value indicating the area of the cell of interest.
  • the feature amount acquisition unit 21 can obtain the value of “Total area” based on the number of pixels in the cell area of interest.
  • Hole area is a value indicating the area of Hole in the cell of interest.
  • Hole refers to a portion where the brightness of the image in the cell is equal to or greater than a threshold value due to contrast (a portion that is close to white in phase difference observation).
  • a threshold value due to contrast (a portion that is close to white in phase difference observation).
  • stained lysosomes of intracellular organelles are detected as Hole.
  • a cell nucleus and other organelles can be detected as Hole.
  • the feature amount acquisition unit 21 may detect a group of pixels in which the luminance value in the cell is equal to or greater than the threshold value as a Hole, and obtain the value of “Hole area” based on the number of pixels of the Hole.
  • Perimeter is a value indicating the length of the outer periphery of the cell of interest.
  • the feature amount acquisition unit 21 can acquire the value of “Perimeter” by contour tracking processing when extracting cells.
  • Width is a value indicating the length of the cell of interest in the horizontal direction (X direction) of the image.
  • Height is a value indicating the length of the cell of interest in the image vertical direction (Y direction).
  • Length is a value indicating the maximum value (the total length of the cell) of the lines crossing the cell of interest.
  • “Breadth” is a value indicating the maximum value (lateral width of the cell) of lines orthogonal to “Length”.
  • Fiber Length is a value indicating the length when the target cell is assumed to be pseudo linear.
  • the feature quantity acquisition unit 21 obtains the value of “Fiber Length” by the following equation (1).
  • Fiber Breath is a value indicating a width (a length in a direction orthogonal to Fiber Length) when the target cell is assumed to be pseudo linear.
  • the feature quantity acquisition unit 21 calculates the value of “Fiber Breath” by the following equation (2).
  • Shape Factor is a value indicating the circularity of the cell of interest (cell roundness).
  • the feature quantity acquisition unit 21 obtains the value of “Shape Factor” by the following equation (3).
  • Inner radius is a value indicating the radius of the inscribed circle of the cell of interest.
  • Outer radius is a value indicating the radius of the circumscribed circle of the cell of interest.
  • Mean radius is a value indicating the average distance between all the points constituting the outline of the cell of interest and its center of gravity.
  • Equivalent radius is a value indicating the radius of a circle having the same area as the cell of interest.
  • the parameter “Equivalent radius” indicates the size when the cell of interest is virtually approximated to a circle.
  • the feature quantity acquisition unit 21 may obtain each feature quantity described above by adding an error to the number of pixels corresponding to the cell. At this time, the feature quantity acquisition unit 21 may obtain the feature quantity in consideration of imaging conditions of the microscope image (observation magnification, aberration of the optical system of the microscope, etc.).
  • the feature amount acquisition unit 21 obtains the center of gravity of each cell based on a known center of gravity calculation method. What is necessary is just to obtain
  • Step S105 The feature quantity acquisition unit 21 obtains the average value and the standard deviation within the image of the 15 types of feature quantities (S104) for the teacher image to be calculated. Then, the feature amount acquisition unit 21 records the in-image average value and the in-image standard deviation of each feature amount in the storage device 13.
  • Step S106 The CPU 14 determines whether or not all the teacher images have been processed (a feature amount has been acquired for all the teacher images). If the above requirement is satisfied (YES side), the CPU 14 shifts the process to S107. On the other hand, when the above requirement is not satisfied (NO side), the CPU 14 returns to S102 and repeats the above operation with another unprocessed teacher image as a calculation target.
  • Step S107 The feature amount acquisition unit 22 of the CPU 14 groups the teacher images having the same passage number by the following processes (A1) to (A3), and each feature between two teacher images in the grouped teacher image group. Find the amount of change in quantity.
  • the feature quantity acquisition unit 21 groups the six teacher images having the same cell passage number and different observation periods (from the first day to the sixth day). Although not particularly limited, it is preferable that the teacher images to be grouped are six microscopic images having the same culture container and captured position (field of view).
  • the feature quantity acquisition unit 21 combines two teacher images at different imaging points in the teacher image group grouped in (A1).
  • there are six teacher images in one group there are 15 combinations of two teacher images.
  • the amount of change obtained from one group of teacher images is 450 types (15 feature values ⁇ 2 patterns (average value, standard deviation) ⁇ 15 combinations). Become.
  • the feature amount acquisition unit 21 includes 15 types of change amounts indicating changes in the average value of each feature amount between two teacher images and two teacher images. 15 kinds of change amounts indicating changes in the standard deviation in the image of each feature amount in the meantime are obtained.
  • the model construction unit 22 constructs a deterioration determination model that classifies cells having different degrees of deterioration based on the feature amount obtained in S105 and the change amount of the feature amount obtained in S107.
  • the model construction unit 22 in the first embodiment constructed a model that classifies microscopic images according to the number of passages of cells by a decision tree method (AnswerTree).
  • Step S201 The model construction unit 22 obtains a parameter type (index type) and a parameter value (index value) to be applied when classifying cells having different passage numbers at the root node of the decision tree.
  • the types of the parameters are selected from the feature amounts (180 types) on the first day to the sixth day obtained in S105 and the feature amount change amounts (450 types) obtained in S107.
  • the model construction unit 22 selects a parameter to be calculated from the above 630 types of parameters. At this time, the model construction unit 22 extracts a teacher image group corresponding to the calculation target parameter in advance.
  • the extracted teacher image group includes teacher images having different cell passage numbers.
  • the model construction unit 22 sets a search range (upper limit and lower limit) for the parameter to be calculated, and divides the search range for the parameter to be calculated into a plurality of arbitrary increments.
  • the model construction unit 22 classifies the cells of the teacher image group corresponding to the parameter to be calculated into two sets using each step (parameter value) of the parameter to be calculated as a threshold value. As a result, the classification result of the cells of the teacher image group is obtained at each step of the parameter to be calculated. At this time, the model construction unit 22 obtains the distribution of the number of cells according to the number of passages of cells in each set of classification results.
  • the model construction unit 22 performs the same process for each of the above 630 types of parameters, and acquires the classification result of the teacher image group at each step of each parameter. Then, the model construction unit 22 determines a parameter type (index type) most suitable for classification of cells having different passage numbers and a threshold value (index value) for the parameter among all the classification results.
  • the model construction unit 22 determines a parameter type and an index value that can completely separate cells of any passage number into one set among combinations of parameter types and threshold values. When there are a plurality of combinations that meet the above conditions, the model building unit 22 determines the type and the index value of the above-mentioned index by giving priority to the one that can separate only one cell of any passage number into one set. do it.
  • the model building unit 22 may determine the type of index and the index value in the following manner. For example, although the model construction unit 22 includes two sets of teacher images having the same passage number, one set can extract only one kind of passage number of teacher images, and one set can extract teacher images.
  • the index type and the index value may be determined with priority given to the image having the largest number of images.
  • Step S202 The model construction unit 22 next designates the node to be calculated for obtaining the index type and the index value. For example, the model construction unit 22 designates the left node among the child nodes that branch left and right from the parent node. When the index type and index value have already been obtained in all nodes below the left child node, the model building unit 22 specifies a node that branches from the parent node to the right side.
  • Step S203 The model construction unit 22 determines whether or not the current computation target node is a terminal node that cannot branch further. For example, the model construction unit 22 determines that it is a terminal node when cells of one passage number can be separated at the current computation target node.
  • Step S204 The model construction unit 22 determines whether the calculation is completed. The model construction unit 22 determines that the calculation is completed when the index types and index values have been obtained at all nodes except the terminal node.
  • the model construction unit 22 ends the process of constructing the degradation determination model. Thereby, the process returns to the process of FIG. On the other hand, if the above requirement is not satisfied (NO side), the process proceeds to S205.
  • Step S205 The model construction unit 22 obtains an index type and an index value at the current calculation target node. Note that the processing in S205 is the same as that in S201, and therefore redundant description is omitted. Thereafter, the model construction unit 22 returns to S202 and changes the node to be calculated. Through the loop from S202 to S205, the index type and index value at each node are obtained recursively. This is the end of the description of the subroutine of FIG.
  • Step S109 The model construction unit 22 records the deterioration determination model data constructed in the process of S108 in the storage device 13. Above, description of the flowchart of FIG. 6 is complete
  • FIG. 9 shows an example of the deterioration determination model constructed in the first embodiment.
  • the root node index is “average of the first day after passage (Total area)”, and the root node index value is “716 pixels 2 ” or less.
  • the index of the node A branched to the left from the root node is “average of the long axis on the first day after passage”, and the index value of the node A is “71.6 pixels” or less. Note that all branches from node A are terminal nodes (left: 4th passage, right: 5th passage).
  • the index of the node B branched to the right from the root node is “the average of ellipticity on the first day after the passage”, and the index value of the node B is “3.77” or less. It is.
  • the right branch of this node B becomes a terminal node (passage 8th).
  • the index of the node C branched to the left from the node B is “average area on the fourth day after passage (Total area)”, and the index value of the node C is “793 pixels 2 ” or less. Note that all branches from node C are terminal nodes (left: 6th passage, right: 7th passage).
  • Step S301 The CPU 14 reads data of a plurality of microscope images to be evaluated from the storage device 13.
  • the image to be evaluated is an image obtained by time-lapse observation of cultured cells under the same conditions as those for obtaining the teacher image for one passage.
  • the operation of the degree of cell degradation was verified using 45 images excluding the teacher image among 450 microscope images stored in advance in the storage device 13.
  • Step S302 The CPU 14 reads the data of the deterioration determination model in the storage device 13 (recorded in S109 in FIG. 6).
  • Step S303 The feature amount acquisition unit 21 obtains the feature amount of the image to be evaluated and the change amount of the feature amount by the same processing as S102 to S107 in FIG.
  • Step S304 The evaluation processing unit 23 collates the feature amount of the image of the cultured cell and the change amount of the feature amount (S303) with the deterioration determination model, and classifies the cultured cell included in the evaluation target image. Thereafter, the evaluation processing unit 23 displays the classification result on the monitor 19 or the like. Above, description of FIG. 10 is complete
  • the images to be evaluated include images obtained by time-lapse observation of cultured cells from the 4th to 8th passages.
  • the evaluation processing unit 23 determines whether or not “average area on the first day after passage” is 716 pixels 2 or more in the root node of the deterioration determination model.
  • the index values at the 4th to 5th passages are each 716 pixels 2 or less, so the process proceeds to determination of node A.
  • the index values of the 6th to 8th passages among the evaluation targets are each larger than 716 pixels 2 , the process proceeds to the determination of the node B. Accordingly, the evaluation processing unit 23 can classify the cultured cells at the 4th to 5th passages and the cultured cells at the 6th to 8th passages by determining the root node.
  • the evaluation processing unit 23 determines whether or not “average of major axes on the first day after passage” is 71.6 pixels or less in the node A of the deterioration determination model.
  • the index value at the 4th passage is 71.6 pixels or less, and the index value at the 5th passage is larger than 71.6 pixels, so each belongs to a different node. Therefore, the evaluation processing unit 23 can classify the cultured cell at the 4th passage and the cultured cell at the 5th passage according to the determination of the node A.
  • the evaluation processing unit 23 determines whether or not “average ellipticity on the first day after passage” is 3.77 or less in the node B of the deterioration determination model. Since the index value at the 6th to 7th passages is 3.77 or less, the process proceeds to determination of node C. On the other hand, since the index value at the 8th passage is larger than 3.77, it belongs to another node. Therefore, the evaluation processing unit 23 can classify the cultured cells at the 6th to 7th passages and the cultured cells at the 8th passage according to the determination of the node B.
  • the evaluation processing unit 23 determines whether or not “average area on the fourth day after passage” is equal to or less than 793 pixels 2 in the node C of the deterioration determination model.
  • the index value at the 6th passage is 793 pixels 2 and the index value at the 7th passage is larger than 793 pixels 2 , so each of them belongs to a different node. Therefore, the evaluation processing unit 23 can classify the cultured cell at the sixth passage and the cultured cell at the seventh passage according to the determination of the node C.
  • the evaluation processing unit 23 executes the above-described cell deterioration degree evaluation process using an image group obtained by time-lapse observation of cultured cells of any passage number. But of course it does n’t matter.
  • FIG. 11 shows an example of evaluating the degree of deterioration of the cryopreserved cultured cells using the deterioration discrimination model of FIG.
  • the cultured cells used in the above experimental examples of FIGS. 2 to 10 were separated and stored frozen at the time of passage. Then, each frozen cell from the first generation to the tenth generation was thawed, and time-lapse observation was performed under the same conditions as in the above experimental example to obtain an image to be evaluated.
  • a cell cryopreserved in the nth passage is denoted as “PnC”.
  • the cultured cell evaluation apparatus collates the index of the deterioration determination model constructed by supervised learning with the feature amount at each observation time of the cells obtained from the evaluation target image. Then classify the cells of the image to be evaluated. Therefore, in the first embodiment, the degree of cell degradation can be evaluated easily and accurately from the image alone, and the work of evaluating the degree of cell degradation can be greatly saved.
  • the cultured cell evaluation apparatus of the first embodiment can be used as an evaluation target, it is extremely useful in a process for evaluating cells cultured for pharmaceutical screening or regenerative medicine, for example.
  • the information on the degree of cell degradation obtained in the first embodiment can be applied as means for detecting abnormalities in cultured cells and as means for engineeringly managing the quality of cultured cells.
  • Second Embodiment an example of heterogeneous cell classification evaluation by a cultured cell evaluation apparatus will be described.
  • a classification example of keratinocytes (NHEK) and fibroblasts (NHDF) will be described.
  • the second embodiment is a modification of the first embodiment, and the apparatus configuration is the same as that of the first embodiment.
  • a plurality of culture vessels (6-well plates) in which keratinocytes and fibroblasts were mixed and seeded were prepared.
  • images were continuously acquired every 8 hours from 0 hour to 56 hours.
  • Cell culture and image acquisition were performed by BioStation CT of Nikon Corporation.
  • the observation magnification was 4 times the objective lens, the number of fields of view in one well was 5, and the resolution of the image was set to about 1 million pixels.
  • 19 types of feature quantities are obtained for each sample. Then, using all of the 19 types of feature amounts, a polynomial (discriminant) defining a boundary line that best separates the two groups of cells was obtained.
  • the 19 types of feature values are measured using “relative hole area (hole area / total area value)” and “Pixel area (number of elements present in the cell). Cell area), “Area (area of the cell measured in a unit configured regardless of the number of elements)”, “Orientation (angle between the long axis of the cell and the horizontal axis)” Features are included.
  • the normal distance (Z value) from the boundary line in each sample can be acquired.
  • FIGS. 13A to 13D are histograms obtained by discriminating and classifying cell images (samples) at each observation period from 0h to 24h.
  • (a) to (d) in FIG. 14 are histograms obtained by discriminating and classifying cell images at each observation period from 32h to 56h.
  • Each of FIGS. 13 and 14 shows the frequency distribution of the Z value of the keratinocyte sample and the Z value of the fibroblast sample at each observation period.
  • the vertical axis of FIGS. 13 and 14 indicates the number of samples, and the horizontal axis of FIGS. 13 and 14 indicates the magnitude of the Z value.
  • the histogram of keratinocytes is indicated by a solid line
  • what is necessary is just to obtain
  • classification evaluation of heterogeneous cells was performed using an image of a sample after 24 hours of culture.
  • the cultured cell evaluation apparatus constructed a classification model for different types of cells using an algorithm that was almost the same as the degradation discrimination model construction process (FIGS. 6 and 8) in the first embodiment.
  • FIG. 15 is a diagram showing an example of a heterogeneous cell classification model constructed in the second embodiment.
  • each node in FIG. 15 represents an index type and an index value.
  • a terminal node denoted as “NHEK” indicates a branch on the keratinocyte side
  • a terminal node denoted as “NHDF” indicates a branch on the fibroblast side.
  • the fraction in the terminal node the number on the left indicates the number of NHEKs separated at the node, and the number on the right indicates the number of NHDFs separated at the node.
  • the heterogeneous cell classification model shown in FIG. 15 it is understood that keratinocytes and fibroblasts can be separated by the evaluation process by the cultured cell evaluation apparatus.
  • FIG. 16 is a schematic front view of an incubator according to the third embodiment.
  • FIG. 17 is a block diagram of an incubator according to the third embodiment.
  • the incubator 111 includes an upper casing 112 and a lower casing 113.
  • the upper casing 112 is placed on the lower casing 113.
  • the internal space between the upper casing 112 and the lower casing 113 is vertically divided by a base plate 114.
  • a door for carrying in / out the culture vessel 119 and equipment is provided on the front surface of the incubator 111 (FIG. 16 shows the door opened and the illustration of the door is omitted for the sake of simplicity). ).
  • a temperature-controlled room 115 for culturing cells is formed inside the upper casing 112.
  • the temperature-controlled room 115 is provided with a temperature adjusting device 115a, a humidity adjusting device 115b, and a temperature / humidity sensor 115c.
  • the temperature-controlled room 115 has an environment suitable for cell culture (for example, an atmosphere having a temperature of 37 ° C. and a humidity of 90%). (In FIG. 16, the temperature adjustment device 115a, the humidity adjustment device 115b, and the temperature / humidity sensor 115c are not shown).
  • a stocker 116 In addition, in the temperature-controlled room 115, a stocker 116, a microscope unit 117, and a container transport device 118 are arranged.
  • the stocker 116 is disposed on the left side (left side in FIG. 16) of the temperature-controlled room 115 when viewed from the front of the upper casing 112.
  • the stocker 116 has a plurality of shelves, and each shelf can store a plurality of culture vessels 119.
  • Each culture container 119 contains cells together with the medium.
  • the microscope unit 117 is disposed on the right side of the temperature-controlled room 15 (the right side in FIG. 16) when viewed from the front of the upper casing 112. In this microscope unit 117, time-lapse observation of the cells in the culture vessel 119 can be executed.
  • the microscope unit 117 is installed by being fitted into the opening of the base plate 114 of the upper casing 112.
  • the microscope unit 117 includes a sample stage 121, a stand arm 122 projecting above the sample stage 121, and a main body 123.
  • the sample stage 121 and the stand arm 122 are disposed in the temperature-controlled room 115, while the main body 123 is accommodated in the lower casing 113. With this configuration, it becomes possible to observe cells in the culture vessel 119 with the microscope unit 117 without changing the environmental conditions.
  • the sample stage 121 is made of a translucent material, and the culture vessel 119 can be placed on the upper surface of the sample stage 121. Moreover, the sample stage 121 is configured to be movable in the horizontal direction, and the position of the culture vessel 119 placed on the upper surface can be adjusted.
  • the container transport device 118 is disposed in the center of the temperature-controlled room 115 when viewed from the front of the upper casing 112.
  • the container transport device 118 is configured by further attaching an arm for holding the culture container 119 to a vertical robot having an articulated arm.
  • the container transport device 118 delivers the culture container 119 between the stocker 116 and the sample stage 121.
  • a control device 124 is accommodated in the lower casing 113.
  • the control device 124 is connected to the temperature adjustment device 115a, the humidity adjustment device 115b, the temperature / humidity sensor 115c, the microscope unit 117, and the container transport device 118, respectively, and performs overall control of the incubator 111.
  • control device 124 incorporates the cultured cell evaluation device of the above embodiment, and evaluates the cultured cells using the image captured by the microscope unit 117 as a processing target. According to the incubator of the third embodiment, it is possible to perform the evaluation based on the classification of the cultured cells by the same method as that of the first embodiment or the second embodiment while performing time-lapse observation of the cultured cells.
  • the cultured cell evaluation apparatus of the above embodiment the example in which the evaluation process of the degree of deterioration of the cultured cell and the classification evaluation of the heterogeneous cells are performed independently has been described.
  • the cultured cell evaluation apparatus of the present invention may be configured to sequentially perform the above two processes on the image to be evaluated. For example, when an image obtained by time-lapse observation of a cell whose cell type and degree of deterioration are both subject to evaluation, the cultured cell evaluation device first estimates the cell type by classification evaluation of different cells, and then In addition, by performing the evaluation process of the degree of deterioration of the cultured cells, it is possible to analyze the unknown cell type and the degree of deterioration.
  • the construction of the discriminant model in the above embodiment is an example, and the discriminant model is constructed by an algorithm such as clustering (hierarchical clustering, k-means clustering) or the basis of self-organizing maps (Self-Organizing) Maps). May be.

Landscapes

  • Life Sciences & Earth Sciences (AREA)
  • Chemical & Material Sciences (AREA)
  • Organic Chemistry (AREA)
  • Zoology (AREA)
  • Health & Medical Sciences (AREA)
  • Engineering & Computer Science (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Wood Science & Technology (AREA)
  • Sustainable Development (AREA)
  • Microbiology (AREA)
  • Biotechnology (AREA)
  • Biomedical Technology (AREA)
  • Analytical Chemistry (AREA)
  • Biochemistry (AREA)
  • General Engineering & Computer Science (AREA)
  • General Health & Medical Sciences (AREA)
  • Genetics & Genomics (AREA)
  • Cell Biology (AREA)
  • Measuring Or Testing Involving Enzymes Or Micro-Organisms (AREA)
  • Apparatus Associated With Microorganisms And Enzymes (AREA)

Abstract

Une unité d'acquisition d'images d'un dispositif pour évaluer des cellules cultivées acquiert une pluralité d'images dans lesquelles les cellules cibles cultivées à l'intérieur d'un récipient de culture sont capturées en séries temporelles. Une unité d'acquisition de quantités de caractéristiques trouve une pluralité de types de quantités de caractéristiques indiquant chacun les caractéristiques morphologiques des cellules cibles incluses dans les images provenant de chacune des images. Une unité de stockage stocke un modèle de discrimination pour diviser en classes des cellules ayant différents attributs d'évaluation. La division des cellules en classes par le modèle de discrimination est effectuée sur la base d'un indice choisi parmi une combinaison des différents types de quantités de caractéristiques et de périodes d'observation. Une unité de traitement d'évaluation compare l'indice du modèle de discrimination avec les quantités de caractéristiques des cellules cibles à chacune des périodes d'observation, et divise en classes les cellules cibles.
PCT/JP2010/005119 2009-08-19 2010-08-19 Dispositif d'évaluation de cellules cultivées, incubateur et programme WO2011021391A1 (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
JP2009190130 2009-08-19
JP2009-190130 2009-08-19

Publications (1)

Publication Number Publication Date
WO2011021391A1 true WO2011021391A1 (fr) 2011-02-24

Family

ID=43606850

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/JP2010/005119 WO2011021391A1 (fr) 2009-08-19 2010-08-19 Dispositif d'évaluation de cellules cultivées, incubateur et programme

Country Status (1)

Country Link
WO (1) WO2011021391A1 (fr)

Cited By (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2015533434A (ja) * 2012-10-22 2015-11-24 ゼネラル・エレクトリック・カンパニイ 教師あり形状ランク付けに基づく生物学的単位の識別
WO2016009708A1 (fr) * 2014-07-16 2016-01-21 オリンパス株式会社 Système, procédé et programme de traitement de données d'observation de cellule
JP2016034288A (ja) * 2015-12-04 2016-03-17 株式会社ニコン 培養状態評価装置、細胞培養方法およびプログラム
JP2018061440A (ja) * 2016-10-11 2018-04-19 憲隆 福永 受精判定システム
JP2018108064A (ja) * 2017-01-06 2018-07-12 オリンパス株式会社 細胞観察システム
WO2018128080A1 (fr) 2017-01-06 2018-07-12 オリンパス株式会社 Système d'observation de cellules
WO2018163641A1 (fr) * 2017-03-08 2018-09-13 オリンパス株式会社 Dispositif d'observation, système d'observation, procédé de commande pour dispositif d'observation et support d'enregistrement enregistré avec un programme de commande pour dispositif d'observation
JP2019000026A (ja) * 2017-06-14 2019-01-10 オリンパス株式会社 細胞培養モニタリングシステム
WO2019150755A1 (fr) * 2018-01-31 2019-08-08 ヤマハ発動機株式会社 Système d'imagerie
JP2020005661A (ja) * 2019-10-16 2020-01-16 憲隆 福永 受精判定システム
WO2020039683A1 (fr) * 2018-08-22 2020-02-27 富士フイルム株式会社 Programme d'exploitation de dispositif d'aide à la culture cellulaire, dispositif d'aide à la culture cellulaire et procédé d'exploitation de dispositif d'aide à la culture cellulaire
US10762327B2 (en) 2017-09-28 2020-09-01 Olympus Corporation Image-processing device and cell observation system

Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2009044974A (ja) * 2007-08-16 2009-03-05 Univ Nagoya 細胞の品質を予測する予測モデルの構築法、予測モデルの構築用ブログラム、該プログラムを記録した記録媒体、予測モデルの構築用装置

Patent Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2009044974A (ja) * 2007-08-16 2009-03-05 Univ Nagoya 細胞の品質を予測する予測モデルの構築法、予測モデルの構築用ブログラム、該プログラムを記録した記録媒体、予測モデルの構築用装置

Cited By (23)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2015533434A (ja) * 2012-10-22 2015-11-24 ゼネラル・エレクトリック・カンパニイ 教師あり形状ランク付けに基づく生物学的単位の識別
WO2016009708A1 (fr) * 2014-07-16 2016-01-21 オリンパス株式会社 Système, procédé et programme de traitement de données d'observation de cellule
JP2016023942A (ja) * 2014-07-16 2016-02-08 オリンパス株式会社 細胞観察情報処理システム、細胞観察情報処理方法、細胞観察情報処理プログラム
JP2016034288A (ja) * 2015-12-04 2016-03-17 株式会社ニコン 培養状態評価装置、細胞培養方法およびプログラム
JP2018061440A (ja) * 2016-10-11 2018-04-19 憲隆 福永 受精判定システム
WO2018128080A1 (fr) 2017-01-06 2018-07-12 オリンパス株式会社 Système d'observation de cellules
US11037293B2 (en) 2017-01-06 2021-06-15 Olympus Corporation Cell observation system
CN110099995A (zh) * 2017-01-06 2019-08-06 奥林巴斯株式会社 细胞观察系统
JP2018108064A (ja) * 2017-01-06 2018-07-12 オリンパス株式会社 細胞観察システム
JP7196238B2 (ja) 2017-01-06 2022-12-26 株式会社エビデント 細胞観察システムおよび細胞観察方法
JP2021151257A (ja) * 2017-01-06 2021-09-30 オリンパス株式会社 細胞観察システムおよび細胞観察方法
WO2018163641A1 (fr) * 2017-03-08 2018-09-13 オリンパス株式会社 Dispositif d'observation, système d'observation, procédé de commande pour dispositif d'observation et support d'enregistrement enregistré avec un programme de commande pour dispositif d'observation
JP2019000026A (ja) * 2017-06-14 2019-01-10 オリンパス株式会社 細胞培養モニタリングシステム
US10762327B2 (en) 2017-09-28 2020-09-01 Olympus Corporation Image-processing device and cell observation system
WO2019150755A1 (fr) * 2018-01-31 2019-08-08 ヤマハ発動機株式会社 Système d'imagerie
JPWO2019150755A1 (ja) * 2018-01-31 2020-12-10 ヤマハ発動機株式会社 撮像システム
JP7018078B2 (ja) 2018-01-31 2022-02-09 ヤマハ発動機株式会社 撮像システム
US11367294B2 (en) 2018-01-31 2022-06-21 Yamaha Hatsudoki Kabushiki Kaisha Image capture system
JPWO2020039683A1 (ja) * 2018-08-22 2021-04-30 富士フイルム株式会社 細胞培養支援装置の作動プログラム、細胞培養支援装置、細胞培養支援装置の作動方法
WO2020039683A1 (fr) * 2018-08-22 2020-02-27 富士フイルム株式会社 Programme d'exploitation de dispositif d'aide à la culture cellulaire, dispositif d'aide à la culture cellulaire et procédé d'exploitation de dispositif d'aide à la culture cellulaire
JP2022121560A (ja) * 2019-10-16 2022-08-19 憲隆 福永 受精判定システム
JP2020005661A (ja) * 2019-10-16 2020-01-16 憲隆 福永 受精判定システム
JP7482172B2 (ja) 2019-10-16 2024-05-13 憲隆 福永 受精判定システム

Similar Documents

Publication Publication Date Title
WO2011021391A1 (fr) Dispositif d'évaluation de cellules cultivées, incubateur et programme
JP5816416B2 (ja) 細胞評価装置、インキュベータ、プログラム、および、培養方法
JP5740101B2 (ja) 細胞評価装置、インキュベータ、細胞評価方法、細胞評価プログラムおよび細胞の培養方法
US9488639B2 (en) Cell-based tissue analysis
JP6448129B2 (ja) 細胞評価装置、インキュベータ、細胞評価方法、プログラム、及び細胞の培養方法
US9567560B2 (en) Incubated state evaluating device, incubated state evaluating method, incubator, and program
Chen et al. Machine learning based methodology to identify cell shape phenotypes associated with microenvironmental cues
JP5816415B2 (ja) 細胞評価装置、インキュベータ、プログラム、および、培養方法
Yang Yu et al. Image processing and classification algorithm for yeast cell morphology in a microfluidic chip
Dirvanauskas et al. Embryo development stage prediction algorithm for automated time lapse incubators
US20160055292A1 (en) Methods for quantitative analysis of cell spatial trajectories
Zubairova et al. LSM-W 2: laser scanning microscopy worker for wheat leaf surface morphology
JP6343874B2 (ja) 観察装置、観察方法、観察システム、そのプログラム、および細胞の製造方法
JP2011002995A (ja) 細胞認識装置、インキュベータおよびプログラム
Ronneberger et al. Voxel-wise gray scale invariants for simultaneous segmentation and classification
Candia et al. Understanding health and disease with multidimensional single-cell methods
JP2011229411A (ja) 細胞評価モデル生成装置、細胞評価装置、インキュベータ、プログラム、および、培養方法
CN107194319A (zh) 基于支持向量机排序的有丝分裂定位和识别的方法
Viswanath et al. Grading of mammalian cumulus oocyte complexes using machine learning for in vitro embryo culture
Harder et al. Automated recognition of mitotic patterns in fluorescence microscopy images of human cells
Mazo et al. Automatic recognition of fundamental tissues on histology images of the human cardiovascular system
JP2011229412A (ja) 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
US20230161146A1 (en) Method and device for examining microscope specimens using optical markers
Murphy Automated interpretation of subcellular location patterns
Turley et al. Deep learning for rapid analysis of cell divisions in vivo during epithelial morphogenesis and repair

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: 10809737

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 10809737

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: JP