KR102423304B1 - Integrated system of electro-stimulation for optimal differentiation of stem cells - Google Patents

Abstract

A driving current control unit configured to provide electrical stimulation according to a predetermined current pattern to the stem cell culture medium contained in the incubator, and a photographing device configured to provide a plurality of photographed images obtained by photographing the stem cell culture medium at a predetermined time interval to the estimator , and a neural network unit, each of the plurality of photographed images being input to an input layer of the neural network unit, and an estimating unit configured to output a series of output values from the neural network unit is disclosed. and to determine an end time of the provision of the electrical stimulation based on a history of the series of output values over time.

Description

Integrated system of electro-stimulation for optimal differentiation of stem cells

The present invention relates to a technology for inducing cell differentiation or functional activity using a microelectric stimulation system without genetic manipulation or biochemical factors. In particular, it relates to an automatic scheduling technology for electrical stimulation for optimal differentiation of stem cells.

Recently, many studies have been conducted on the induction of cell differentiation and reprogramming using electrical stimulation. It has been reported that electrical stimulation plays a special role in cell proliferation and migration and promotes tissue regeneration in studies using cells, tissues, and animals. is known Currently, the establishment of differentiation technology into specific cells using electrical stimulation in companion animals, leisure animals and industrial animals and the application of diseases using the technology are not known.

As an alternative to the conventional treatment of specific growth factors, many studies have been conducted to induce differentiation of stem cells into cells responsible for specific functions, such as neurons, chondrocytes, and osteogenic cells. In this regard, it has been reported that by applying electrical stimulation to human mesenchymal stem cells, differentiation into striated muscle cells expressing myocardial specific markers can be induced. In addition, it has been reported that the human mesenchymal stem cells seeded on the silk-fibroin film succeeded in osteogenic differentiation by applying electrical stimulation. Furthermore, it is known that electrical stimulation can be used not only to differentiate stem cells into specific cell types, but also to cross-differentiate already differentiated specific cells into other types of cells. In this regard, it has been reported that skin-derived fibroblasts can be cross-differentiated into nerve cells using a triboelectric nanogenerator. In addition, Korean Patent Registration No. 1653197 discloses a method of cross-differentiation into chondrocytes by applying electrical stimulation to fibroblasts.

However, the prior art discloses only a method of differentiating into a specific cell by applying a specific electrical stimulation to stem cells or fibroblasts, and does not suggest optimization of electrical stimulation scheduling to more efficiently induce differentiation. have. In particular, it does not suggest an optimal method for improving the chondrogenic markers of any cell differentiated from stem cells by electrical stimulation.

According to the observation by the inventors of the present invention, when electrical stimulation is continuously applied to the stem cell culture medium, the amount of chondrocytes changed from the stem cells increases and then decreases again. In order to mass-differentiate chondrocytes in this way, the first time point at which the amount of differentiated chondrocytes is maximized is determined according to the duration of the electrical stimulation, and after the first time point, the electrical stimulation is stopped, and the differentiated It is necessary to harvest chondrocytes. If the amount of chondrocytes formed during electrical stimulation maintains a maximum value for a certain period of time, the electrical stimulation is stopped at the first time point when the maximum value is reached to optimize the differentiation process into chondrocytes.

An object of the present invention is to provide a technique for determining the end point of electrical stimulation applied to a stem cell culture medium in order to differentiate chondrocytes from stem cells so as to solve the above problems. However, these problems are exemplary, and the scope of the present invention is not limited thereto.

According to an aspect of the present invention, a driving current control unit 30 configured to provide electrical stimulation according to a predetermined current pattern to the stem cell culture medium contained in the incubator 10; a photographing device 40 configured to provide a plurality of photographed images obtained by photographing the stem cell culture medium at predetermined time intervals to the estimator 50; and a neural network unit 510 , wherein each of the plurality of photographed images is input to an input layer of the neural network unit 510 and an estimator 50 is configured to output a series of output values from the neural network unit 510 . Including; and, based on the time history of the series of output values, the electrical stimulation control system can be provided to determine the end time of the provision of the electrical stimulation.

In this case, the neural network unit may be supervised to output the output value as a larger value as the area of the chondrocyte cluster region included in the photographed image input to the neural network unit decreases.

In this case, the end of the electrical stimulation may be determined at a point in time when it is determined that the series of output values do not increase with time.

At this time, the neural network unit, the step of providing electrical stimulation according to a predetermined current pattern to the stem cell culture medium contained in the incubator 10, obtaining a plurality of photographed images obtained by photographing the stem cell culture medium at predetermined time intervals; preparing a set of labels corresponding to the plurality of photographed images in order to train the neural network unit using the plurality of photographed images; and updating an internal parameter of the neural network unit by inputting the selected captured image to the neural network unit to reduce an error between the value output by the neural network unit and the value of the label corresponding to the selected captured image. It is learned by the negative learning method, and the step of preparing a set of labels includes allocating a reference label having a predetermined specific value to a reference photographed image that is a photographed image selected by a user among the plurality of photographed images ; and allocating labels to the other captured images except for the reference captured image among the plurality of captured images according to a predetermined rule.

In this case, the step of allocating the labels according to the predetermined rule includes dividing the selected photographed image among the remaining photographed images into two regions, an outer region including an edge of the incubator and an inner region inside the outer region. ; and determining a label value for the selected photographed image based on the width of the inner region.

In this case, the dividing into the two regions may include: selecting a plurality of outer points among edges of an incubator image representing the incubator among the selected photographed images; selecting, as an inner point, a point at which the image attribute value of the selected photographed image changes most rapidly when observed along a line connecting the center point of the incubator image from the outer point to each of the outer points; determining the inner region by determining a closed curve connecting the plurality of inner points selected for each of the outer points as an outer boundary of the inner region; and determining an outer portion of the closed curve as the outer region.

According to another aspect of the present invention, the step of providing electrical stimulation according to a predetermined current pattern to the stem cell culture medium contained in the incubator 10, and obtaining a plurality of photographed images obtained by photographing the stem cell culture medium at predetermined time intervals ; preparing a set of labels corresponding to the plurality of photographed images in order to train the neural network unit using the plurality of photographed images; and inputting the selected captured image to the neural network unit and updating the internal parameters of the neural network unit to reduce an error between the value output by the neural network unit and the value of the label corresponding to the selected captured image; The preparing of the set of labels may include: allocating a reference label having a predetermined specific value to a reference photographed image selected by a user from among the plurality of photographed images; and allocating labels to the other captured images from among the plurality of captured images according to a predetermined rule, except for the reference captured image.

In this case, the step of allocating the labels according to the predetermined rule includes dividing the selected photographed image among the remaining photographed images into two regions, an outer region including an edge of the incubator and an inner region inside the outer region. ; and determining a label value for the selected photographed image based on the width of the inner region.

In this case, the dividing into the two regions may include: selecting a plurality of outer points among edges of an incubator image representing the incubator among the selected photographed images; selecting, as an inner point, a point at which the image attribute value of the selected photographed image changes most rapidly when observed along a line connecting the center point of the incubator image from the outer point to each of the outer points; determining the inner region by determining a closed curve connecting the plurality of inner points selected for each of the outer points as an outer boundary of the inner region; and determining an outer portion of the closed curve as the outer region.

According to the present invention, it is possible to provide an optimal control technique for determining the end point of electrical stimulation applied to a stem cell culture medium to differentiate chondrocytes from stem cells.

1 is a block diagram showing an electrical stimulation system 100 provided according to an embodiment of the present invention.
2 is a block diagram illustrating an electric stimulation learning system provided according to an embodiment of the present invention.
Figure 3 shows an example of a photographed image observed over time when electrical stimulation is applied to a stem cell culture medium by modeling.
4 is a diagram for explaining a method of dividing an acquired image into two regions according to an embodiment of the present invention.
5 is a flowchart illustrating a method for determining an electrical stimulation end time point using an electrical stimulation system provided according to an embodiment of the present invention.
6 is an example of a graph showing values output by the estimation unit of the electrical stimulation system according to an embodiment of the present invention according to time.

Hereinafter, embodiments of the present invention will be described with reference to the accompanying drawings. However, the present invention is not limited to the embodiments described herein and may be implemented in various other forms. The terminology used in this specification is intended to help the understanding of the embodiment, and is not intended to limit the scope of the present invention. Also, singular forms used hereinafter include plural forms unless the phrases clearly indicate the opposite.

<General configuration of electric stimulation control system>

1 is a block diagram showing an electrical stimulation system 100 provided according to an embodiment of the present invention.

The electrical stimulation system 100 provided according to an aspect of the present invention is an incubator 10 configured to contain a stem cell culture solution, a pair of installed to apply an electric current to the stem cell culture solution contained in the incubator 10 . The electrode 20, the driving current controller 30 for providing electricity to the pair of electrodes 20, the photographing device 40 for photographing the stem cell culture medium, and the photographing apparatus 40 output the output over time. It may include an estimator 50 for estimating and outputting a value related to the differentiation amount of chondrocytes differentiated from the stem cells included in the stem cell culture medium by inputting a plurality of photographed images, respectively. At this time, the driving current controller 30 is configured to cut off the current applied through the pair of electrodes 20 based on the values related to the differentiation amount output by the estimator 50 over time.

The value of the differentiation amount may be normalized so that its maximum and minimum values are, for example, 1 and 0, respectively. When the value of the differentiation amount is 1, it can be considered that the chondrocytes are differentiated as much as possible.

The estimator 50 may include a neural network unit 510 learned by supervised learning.

From the time the driving current control unit 30 starts to provide current to the pair of electrodes 20, the imaging device 40 captures the inside of the incubator 10 to acquire a plurality of photographed images over time. .

The estimator 50 may receive the acquired plurality of photographed images in real time and output an estimated value regarding the differentiation amount of chondrocytes. As time passes, the estimated value output by the estimator 50 may have a tendency to gradually increase with the passage of time, maintain a saturated state for a certain period, and then decrease again.

The driving current control unit 30 monitors the estimated value output by the estimator 50 and blocks the current applied to the pair of electrodes 20 when it is determined that the estimated value will no longer increase. have.

<Learning of the neural network>

The neural network unit of FIG. 1 may be learned by supervised learning.

Hereinafter, a supervised learning method of the neural network unit will be described with reference to FIG. 2 . In particular, a method for determining labels to be used for supervised learning is described.

2 is a block diagram illustrating an electric stimulation learning system provided according to an embodiment of the present invention.

In the electrical stimulation learning system of FIG. 2 , a supervised learning control unit 520 is added to the electrical stimulation system shown in FIG. 1 .

For the supervised learning, the expert (person) observes the plurality of photographed images output by the photographing device 40 in chronological order, and it is determined that the differentiation amount of chondrocytes has reached the maximum value among the plurality of photographed images. A reference label having a specific value may be assigned to the first photographed image (=reference photographed image), which is the first photographed image. The specific value of the reference label may be, for example, 1. That is, the reference label can be associated with the image acquired by the imaging device 40 at the first time point when it is determined that the amount of chondrocytes differentiated by the electrical stimulation has reached the maximum.

In an embodiment, the labels for the other captured images other than the reference captured image among the plurality of captured images may be automatically assigned by a predetermined method described below, rather than being directly assigned by a person.

The plurality of photographed images may have characteristics according to a phenomenon described below.

That is, the stem cells contained in the culture medium before applying the electrical stimulation may be uniformly distributed in the culture medium. However, as the electrical stimulation is started and continued, the stem cells are differentiated into chondrocytes, and the differentiated chondrocytes can form a colony. However, when electrical stimulation is continuously applied, the amount of differentiation of chondrocytes increases and at some point the amount of increase is stagnant, and then the chondrocytes cluster again disperse, and eventually the amount of chondrocytes decreases. This phenomenon can be described in more detail with reference to FIG. 3 .

Figure 3 shows an example of a photographed image observed over time when electrical stimulation is applied to a stem cell culture medium by modeling.

The large circles shown in (a) to (h) of FIG. 3 indicate the shape of the outer edge of the incubator 10 when viewed from the top down in the case where the incubator 10 is a circular culture dish. From Fig. 3 (a) to Fig. 3 (h) shows the result that the electrical stimulation process further progressed with time. Figure 3 (a) shows the start time of the electrical stimulation.

The small circles shown in (b) to (h) of Figure 3 represent the shape of the outer edge of the chondrocyte cluster differentiated by electrical stimulation. In fact, the shape of the chondrocyte population may not be an exact circle, but it can be modeled as an approximate circle. In the small circles shown in (b) to (h) of FIG. 3, not only differentiated chondrocytes but also stem cells may be mixed and included, but nevertheless, since the chondrocytes are dense, it is called a cluster region of chondrocytes. can be considered

Referring to FIG. 3 , in FIG. 3A , since the electrical stimulation is started, a separate chondrocyte cluster is not observed. From Fig. 3 (a) to Fig. 3 (e), it can be observed that the area of the chondrocyte cluster gradually decreases due to the electrical stimulation. Even if the area of the chondrocyte population decreases, the amount of chondrocytes actually present in the chondrocyte population gradually increases with time. When the amount of chondrocytes reaches the maximum value as shown in (e) of FIG. 3, even if additional electrical stimulation is applied, the chondrocytes are not further differentiated as shown in FIG. can be maintained for a period of time. Furthermore, if the electrical stimulation is further proceeded without stopping thereafter, as shown in (g) and (h) of FIG. 3, the area of the chondrocyte cluster starts to increase again, and the amount of actually differentiated chondrocytes decreases. will do Therefore, in order to optimize the electrical stimulation process for differentiating chondrocytes from the stem cell culture medium, it is necessary to block the current provided to the stem cell culture medium at an appropriate time. In the example of FIG. 3, it is preferable to block the current in FIGS. 3 (e) and 3 (f), and even if the current is blocked in FIG. 3 (e), chondrocytes can be obtained as much as possible, and stem cells It has the advantage of minimizing the time for obtaining chondrocytes from the culture medium and reducing the current consumption.

Now, with reference to FIG. 2 again, a method of setting the above-described reference label value will be described.

When the amount (number) of chondrocytes included in the chondrocyte cluster is substantially the maximum, the value of the reference label given to the reference photographed image may be set to a specific value, for example, 1.

Here, the subject that determines that the differentiation amount of the chondrocytes has reached the maximum value is the expert (human). The differentiation amount of the chondrocytes corresponding to the maximum value may be referred to as a first differentiation amount, a reference differentiation amount, or a maximum differentiation amount, and the reference differentiation amount may be normalized to a specific value as described above. For example, it may be suggested that the reference differentiation amount is 1.

Then, the supervised learning control unit 520 provided according to an embodiment of the present invention is a unique label value determined according to a predetermined algorithm for each of the remaining captured images except for the reference captured image among the plurality of photographed images. can be given The label value given to each of the remaining photographed images may be equal to or less than the specific value of the reference label. For example, the label value given to any second photographed image among the remaining photographed images may be a value of 1 or less.

The supervised learning control unit 520 may determine a label value given to each of the remaining photographed images based on the value of the reference label, the reference photographed image, and each of the photographed images. For example, the differentiation amount of chondrocytes estimated from the reference photographed image is referred to as the reference differentiation amount, the differentiation amount of chondrocytes estimated from the second photographed image is referred to as a second differentiation amount, and If the label to be given is the second label, the relationship of Equation 1 can be established.

[Formula 1]

Second differentiation amount/(value of second label)=(standard amount of differentiation)/(value of reference label)

In Equation 1 above, the value of the reference label is a value already assigned by an expert. For example, the value of the reference label may be 1.

In addition, the reference differentiation amount may be a normalized value based on a preset value. In one embodiment of the present invention, regardless of the specific value of the total number of differentiated chondrocytes, the reference differentiation amount, which is the amount of differentiation of the chondrocytes at the time of maximum differentiation of chondrocytes determined by the expert, is 1 You can also define

In addition, the second differentiation amount is a value that can be determined by a method to be described later. Therefore, the value of the second label to be given to the second photographed image may be determined as in [Equation 2].

[Equation 2]

(Value of the second label) = (Value of the reference label)*Second differentiation amount/(Standard differentiation amount)

If Equation 2 is generalized, the value of the kth label for the kth photographed image may be determined as in Equation 3.

[Equation 3]

(Value of the kth label) = (Value of the reference label)*Kth differentiation amount/(Standard differentiation amount)

A method of estimating the differentiation amount of chondrocytes from each of the photographed images may be presented as follows. That is, a method of estimating the kth differentiation amount from the kth photographed image may be presented as follows.

First, the supervised learning control unit 520 may identify the edge of the incubator 10 from the captured image. The incubator 10 may be a circular or rectangular plate. In this case, the edge of the incubator 10 may be, for example, a circular closed curve as shown in FIG. 3 .

Then, the supervised learning control unit 520 may classify the photographed image of the stem cell culture solution present in the incubator 10 into two regions according to a predetermined criterion. The two regions are shown in FIG. 3 .

Among the two regions, the first region (outer region) 110 may be a donut-shaped region having an outer closed curve 111 and an inner closed curve 112 . The outer closed curve 111 may be an outer edge of the incubator 10 . In addition, a second region (inner region) 120 of the two regions may be a region inside the inner closed curve 112 . In an embodiment, the inner closed curve 112 may be modeled and defined in a circular or elliptical shape.

Hereinafter, a method of determining the inner closed curve in an arbitrary captured image according to an embodiment of the present invention will be described with reference to FIG. 4 .

4 is a diagram for explaining a method of dividing an acquired image into two regions according to an embodiment of the present invention.

The method for determining the inner closed curve 112 in an arbitrary photographed image may include the following steps. First, the supervised learning control unit 520 connects the center point 1120 of the incubator 10 from the first outer point 1110, which is a point on the edge of the incubator 10, in the arbitrary captured image. A path P1 may be determined. The path P1 may be a straight line or a curved line. When the length of the path P1 is L1, a second point 1121 that moves from the first outer point to the center point by dL along the path P1 may be defined. As described above, the k+1th point moved from the kth point to the central point by dL may be continuously defined (k is a natural number greater than or equal to 1, dL < L1 ). In this case, a difference value between the image attribute value at the kth point and the image attribute value at the k+1th point may be defined as Dk. The image attribute value may be, for example, attribute values such as brightness, color value, or saturation at each point of the arbitrary captured image. The image attribute value is sufficient according to the criteria for classifying image attributes in the image processing field, and the present invention is not limited by the specific attribute selection.

The largest value among the difference values Dk (k=1, 2, 3, ...) between the image attribute values defined as described above may be selected. For example, if the difference value D3 is the largest value, it can be seen that the image attribute value changes the most between the second point 1121 and the third point 1131 on the path P1 .

Now, the first inner point 1115 constituting the inner closed curve 112 may be determined to exist between the second point 1121 and the third point 1131 .

The process of determining the first inner point 1115 starts with the step of selecting the first outer point of the edge of the incubator 10 . Now, if the process of determining the first inner point is performed starting from various other outer points of the edge of the incubator 10 , a plurality of other inner points constituting the inner closed curve 112 can be determined.

When the plurality of inner points determined in this way are interpolated and connected to each other, the inner closed curve 112 can be completed. As a result, the first region (outer region) 110 and the second region (inner region) 120 can be completely defined.

If the largest value among the difference values Dk (k=1, 2, 3, ...) is smaller than a predetermined value, it is determined that the first inner point 1115 is the first outer point 1110 . may be

In some cases, the second region (inner region) 120 and the first region (outer region) 110 may not exist. Such a situation may occur, for example, in a state in which no electrical stimulation is applied to the stem cell culture medium. For example, the inner region 120 and the outer region 110 cannot be defined in (a) of FIG. 3 .

The above-described method for determining the first inner point includes the second region (inner region) 120 that is approximated in a circular or elliptical shape and the first existing outside the second region (inner region) 120 . It is presented as one of various algorithms for classifying the region (outer region) 110 . That is, the above description is intended to explain the feasibility of dividing the photographed image of the stem cell culture solution present in the incubator 10 into the two regions described above, and the present invention is not limited to this embodiment.

The operation of dividing the photographed image into two regions is performed for each of the plurality of photographed images photographed according to the passage of time during which the electrical stimulation is applied.

When the second region (inner region) 120 is defined as described above, the area SB of the second region (inner region) 120 may be calculated.

Now, when the differentiation amount of chondrocytes estimated from the k-th photographed image is referred to as the k-th differentiation amount, and the area of the second region (inner region) 120 calculated from the k-th photographed image is referred to as the k-th area. , The k-th differentiation amount of chondrocytes estimated from the k-th photographed image may be defined as inversely proportional to the k-th area.

Alternatively, in another embodiment, the k-th differentiation amount of chondrocytes estimated from the k-th photographed image may be defined as inversely proportional to the root value of the k-th area. That is, when the second region (inner region) 120 is modeled as a circle, the k-th differentiation amount of chondrocytes estimated from the k-th photographed image may be defined as inversely proportional to the diameter or radius of the circle. .

However, in some embodiments, the k-th differentiation amount is estimated based on the k-th area, but a rule may be set such that a nonlinear function intervenes in the relationship between the k-th differentiation amount and the k-th area. According to an aspect of the present invention, the k-th differentiation amount is estimated based on the k-th area, but the present invention is not limited by the specific functional relationship.

In addition, although the k-th differentiation amount is estimated based on the k-th area, values of other additional parameters observed from the k-th photographed image may also be further used to estimate the k-th differentiation amount. However, regardless of how the value of the additional parameter is defined, the fact that the k-th differentiation amount is estimated based on the value of the k-th area does not change.

For example, the other additional parameter may be defined as a ratio between the first average brightness of the outer region and the second average brightness of the inner region observed in the k-th photographed image.

As such, when the k-th differentiation amount is estimated from the k-th photographed image, the value of the k-th label can be determined using Equation 3.

Through the above-described process, it is possible to obtain by defining or calculating labels assigned to a series of photographed images obtained by photographing a stem cell culture medium whose state is changed by receiving electrical stimulation.

Now, the supervised learning control unit 520 inputs the k-th photographed image to the input layer of the neural network unit 510, and the value output by the neural network unit 510 is the k-th label corresponding to the k-th photographed image. The internal parameters of the neural network unit 510 may be updated so that an error of the synapse may be reduced.

In an embodiment, the neural network unit 510 may be, for example, a Convolutional Neural Network (CNN). The CNN is a well-known technology and an example thereof will not be separately described herein. Nevertheless, it is not difficult for those skilled in the art to apply any CNN implementation technique to the spirit of the present invention presented herein.

Learning of the neural network unit 510 may be repeated using a plurality of photographed images and differentiated labels for them.

In addition, learning of the neural network may be further repeated using a plurality of images taken while applying electrical stimulation to the skin detail culture medium contained in the plurality of incubators 10 and corresponding labels.

In the above-described neural network learning method, the input data for learning of the neural network is the photographed data, and it can be seen that a feature of the present invention exists in a method of creating the labels corresponding to the correct answers corresponding to each of the learning input data.

<Method for determining the end time of electrical stimulation using electrical stimulation system>

According to the electrical stimulation control method provided in accordance with an aspect of the present invention, it is possible to determine the time point at which the current provided to the stem cell culture medium contained in the incubator 10 is cut off. The electrical stimulation control method may be implemented using the electrical stimulation system 100 shown in FIG. 1 .

5 is a flowchart illustrating a method for determining an electrical stimulation end time point using an electrical stimulation system provided according to an embodiment of the present invention.

First, in step S10 , the driving current controller 30 may apply a current to the incubator 10 containing the stem cell culture solution using a pair of electrodes 20 .

Next, in step S20 , the imaging device 40 may transmit the photographed images obtained by photographing the stem cell culture medium at predetermined time intervals to the estimator 50 .

Next, in step S30 , the estimator 50 may input each transmitted captured image to the input layer of the neural network unit 510 of the estimator 50 . In this case, the estimator 50 may output a scalar value.

Next, in step S40 , the driving current control unit 30 may determine whether to end the provision of the electrical stimulation based on the time history of a series of output values output by the estimation unit 50 . .

For example, the driving current control unit 30 may determine to terminate the application of the current when it is determined that the output value output by the estimator 50 will no longer increase. To this end, for example, the driving current controller 30 observes a moving average value of the output value output by the estimator 50, and when the moving average value starts to decrease, or is saturated for a certain period and does not increase anymore. At a point in time, it may be decided to terminate the application of the current.

Next, the driving current control unit 30 may block the current applied to the incubator 10 containing the stem cell culture medium when the end time is determined.

In a modified embodiment, the function module for determining whether to end the provision of the electrical stimulation based on the time-dependent history of a series of output values output by the estimation unit 50 is provided to the driving current control unit 30 . It may not exist and may exist in the estimator 50 . In this case, the estimator 50 may provide a separate signal instructing the end timing of the electrical stimulation to the driving current controller 30 , and the estimator 50 transmits the output value to the driving current controller 30 . It may not be provided separately.

As described above, a method of blocking the electrical stimulation provided by the driving current controller 30 to the stem cell culture medium may be described with reference to FIG. 6 .

6 is an example of a graph showing values output by the estimation unit of the electrical stimulation system according to an embodiment of the present invention according to time.

The graph of FIG. 6 may show the circular value output by the estimator 50 as it is, or may show the circular value by averaging the circular values over time.

In FIG. 6, the output value of the estimator 50 net increases in the period t0 to t1, the output value of the estimator 50 is maintained in the period t1 to t2, and the output value of the estimator 50 decreases in the period t2 to t2. can In some cases, the time period t1 to t2 does not substantially exist, and the output value of the estimator 50 may start to decrease immediately after t1.

When the curve shown in FIG. 6 is observed in real time over time, ideally the termination of the electrical stimulation should be commanded at time t1, but the output value of the estimator is observed to determine whether the amount of differentiation of chondrocytes has reached the maximum value. Since a certain amount of time delay is required to determine this, the termination of the electrical stimulation can be commanded after the t1 time point.

The present invention described above can be equally applied to the embodiment of differentiating chondrocytes from skin cells, not the embodiment of differentiating chondrocytes from stem cells. Therefore, in the above-described embodiments, the stem cell culture solution may be substituted for the skin cell culture solution.

By using the above-described embodiments of the present invention, those skilled in the art will be able to easily implement various changes and modifications within the scope without departing from the essential characteristics of the present invention. The content of each claim in the claims may be combined with other claims without reference within the scope that can be understood through this specification.

10: incubator
20: a pair of electrodes
30: drive current control unit
50: estimator
40: shooting device
510: neural network
100: electrical stimulation system

Claims (9)

a driving current control unit 30 configured to provide electrical stimulation according to a predetermined current pattern to the stem cell culture medium contained in the incubator 10;
a photographing device 40 configured to provide a plurality of photographed images obtained by photographing the stem cell culture medium at predetermined time intervals to the estimator 50; and
An estimator 50 including a neural network unit 510 and configured to input each of the plurality of photographed images to an input layer of the neural network unit 510 and output a series of output label values from the neural network unit 510 . );
includes,
The neural network unit,
providing electrical stimulation according to a predetermined current pattern to the stem cell culture medium contained in the incubator 10 to obtain a plurality of photographed images obtained by photographing the stem cell culture medium at a predetermined time interval;
preparing a set of labels corresponding to the plurality of photographed images in order to train the neural network unit using the plurality of photographed images; and
inputting the selected photographed image to the neural network unit and updating the internal label value of the neural network unit to reduce an error between the label value output by the neural network unit and the label value corresponding to the selected photographed image;
It is learned by the learning method of the neural network including
The preparing of the set of labels may include: allocating, by the user, a reference label having a predetermined specific value to a reference photographed image that is a photographed image selected by the user from among the plurality of photographed images; and allocating labels according to a predetermined rule to the remaining photographed images except for the reference photographed image among the plurality of photographed images,
and determine an end point of presentation of the electrical stimulation based on a history of the series of output label values over time.
Electrical stimulation control system. The method according to claim 1, wherein the neural network unit is supervised to output the output label value as a larger value as the area of the cluster region of chondrocytes included in the photographed image input to the neural network unit decreases. Electrical stimulation control system. The electrical stimulation control system according to claim 1, arranged to determine the end of the provision of the electrical stimulation at a point in time when it is determined that the set of output label values no longer increases with time. According to claim 1,
Allocating labels according to the predetermined rule comprises:
dividing the selected photographed image among the remaining photographed images into two regions: an outer region including an edge of the incubator and an inner region inside the outer region; and
determining a label value for the selected photographed image based on an area of the inner region;
containing,
Electrical stimulation control system. 5. The method of claim 4,
The value of the label for the selected photographed image is a value obtained by multiplying the value of the reference label having the predetermined specific value by the differentiation amount calculated based on the area of the inner region divided by the reference differentiation amount, ,
The reference differentiation amount is the differentiation amount of chondrocytes estimated from the reference photographed image,
The amount of differentiation calculated based on the area of the inner area is inversely proportional to the area of the inner area,
Electrical stimulation control system. 5. The method of claim 4,
The step of dividing into the two areas is,
selecting a plurality of outer points among edges of an incubator image representing the incubator from among the selected photographed images;
selecting, as an inner point, a point at which the image attribute value of the selected photographed image changes most rapidly when observed along a line connecting the center point of the incubator image from the outer point to each of the outer points;
determining the inner region by determining a closed curve connecting the plurality of inner points selected for each of the outer points to an outer boundary of the inner region; and
determining an outer portion of the closed curve as the outer region;
containing,
Electrical stimulation control system. providing electrical stimulation according to a predetermined current pattern to the stem cell culture medium contained in the incubator 10 to obtain a plurality of photographed images obtained by photographing the stem cell culture medium at predetermined time intervals;
preparing a set of labels corresponding to the plurality of photographed images in order to train the neural network unit using the plurality of photographed images; and
inputting the selected photographed image to the neural network unit and updating an internal label value of the neural network unit to reduce an error between the label value output by the neural network unit and the label value corresponding to the selected photographed image;
includes,
The preparing of the set of labels may include: allocating, by the user, a reference label having a predetermined specific value to a reference photographed image selected by the user from among the plurality of photographed images; and allocating labels according to a predetermined rule to the remaining photographed images except for the reference photographed image among the plurality of photographed images,
Allocating labels according to the predetermined rule comprises:
dividing the selected photographed image among the remaining photographed images into two regions, an outer region including an edge of the incubator and an inner region inside the outer region, and
determining a label value for the selected photographed image based on the area of the inner region;
includes,
The value of the label for the selected photographed image is a value obtained by multiplying the value of the reference label having the predetermined specific value by the differentiation amount calculated based on the area of the inner region divided by the reference differentiation amount, ,
The reference differentiation amount is the differentiation amount of chondrocytes estimated from the reference photographed image,
The amount of differentiation calculated based on the area of the inner area is inversely proportional to the area of the inner area,
The learning method of the neural network. delete 8. The method of claim 7,
The step of dividing into the two areas is,
selecting a plurality of outer points among edges of an incubator image representing the incubator from among the selected photographed images;
selecting, as an inner point, a point at which the image attribute value of the selected photographed image changes most rapidly when observed along a line connecting the center point of the incubator image from the outer point to each of the outer points;
determining the inner region by determining a closed curve connecting the plurality of inner points selected for each of the outer points to an outer boundary of the inner region; and
determining an outer portion of the closed curve as the outer region;
containing,
The learning method of the neural network.

Images