JP7000379B2 - Embryo selection system - Google Patents

Description

The present invention relates to an embryo selection system.

In the field of infertility treatment, good embryos suitable for transplantation are selected by evaluating embryos in culture from the viewpoint of improving conception rate and QOL of patients. As a method for evaluating embryos non-invasively, there is a method for evaluating the developmental status of embryos by morphological observation with a microscope.

Japanese Unexamined Patent Publication No. 2012-29686

In the embryo selection system of Patent Document 1, embryos are selected using the number of blastomeres of the embryo corresponding to a specific cleavage stage as one index. However, in the embryo selection system of Patent Document 1, since the image used for embryo selection is extracted using the time zone information corresponding to the cleavage stage stored in advance, it is out of the time zone information. Embryos whose cleavage has progressed at the timing may not be selected as good embryos. In addition, from the image extracted as an image showing a specific cleavage stage based on the stored time zone information, the number of embryo blastomeres at the specific cleavage stage meets the selection criteria. Even if it can be seen, there is a risk that embryos that meet the selection criteria due to fusion (reverse) of at least a part of the embryo blastomere in the stage before the cleavage stage will be selected as good embryos. be. In order to solve such a problem, a technique capable of further improving the selection accuracy of a system for selecting good embryos has been desired.

The present invention has been made to solve at least a part of the above-mentioned problems, and can be realized as the following forms. The first aspect is an aspect as an embryo selection system. This embryo culture system includes an image storage unit that stores images of embryos housed and cultured in a plurality of wells provided in a culture vessel at set time intervals for each well in a time series. The determination unit is provided with a determination unit for determining the state of the embryo by reading the image stored in the image storage unit and analyzing the change in the number of blastomeres of the embryo in the image with time. The part confirmed that in the first egg splitting started after the fertilization process, the number of blastomeres of the embryo directly shifted to the two state, and the first egg started after the fertilization process. In the split, different determinations are made for the embryo depending on the case where the number of blastomeres of the embryo directly shifts to the state of 3 or more without going through the state of 2 blastomeres.
The second aspect is an aspect as a method for selecting embryos. This embryo selection method includes an image storage step of storing images for each well, which are images of embryos housed and cultured in a plurality of wells provided in a culture container at set time intervals, in chronological order. A selection step of reading out the image stored in the image storage step and selecting an embryo by analyzing a change in the number of blastomeres of the embryo in the image with time is provided. In the first cleavage started after fertilization, it was confirmed that the number of blastomere of the embryo directly shifted to the two state, or in the first cleavage started after fertilization. The embryo is selected depending on whether the number of blastomeres of the embryo directly shifts to the state of 3 or more without going through the state of 2 blastomeres.

(1) According to one embodiment of the present invention, an embryo selection system is provided. This embryo selection system analyzes the state of the cultured embryo in an image storage unit that stores images taken at set time intervals and changes in the number of blastomeres of the embryo in the image over time. A determination unit for determining whether the embryo is a good embryo is provided. In such an embodiment, the determination unit can determine whether the embryo is a good embryo by analyzing the change over time in the number of blastomeres of the embryo using the image in which the state of the embryo is photographed. Therefore, for a system that can select good embryos, the accuracy of selecting good embryos can be further improved.

(2) In the embryo selection system in the above form, even if the determination unit learns about the characteristics of the embryo captured in the image by supervised learning and determines whether the embryo is a good embryo based on the learning. good. In such an embodiment, it is possible to determine whether the embryo is a good embryo based on the criteria learned by the supervised learning by the determination unit.

(3) In the embryo selection system in the above embodiment, the determination unit learns about the characteristics of the embryo captured in the image by deep learning using a multi-layer neural network, and the embryo is a good embryo based on the learning. It may be determined whether or not there is. With such an embodiment, it is possible to determine whether the embryo is a good embryo based on the criteria learned by the determination unit by deep learning.

(4) The embryo selection system in the above embodiment may further include a notification unit for notifying the determination image used for determination among the images. In such an embodiment, the user using the embryo selection system can know which image the determination unit used to determine the good embryo.

(5) In the embryo selection system in the above embodiment, the notification unit may notify the determination image and also notify the information on which the determination unit is based in the determination image. In such an embodiment, the user using the embryo selection system can know which image the determination unit used to determine a good embryo, and the determination unit knows the information on which the determination is based. be able to.

(6) According to one embodiment of the present invention, there is provided a method for selecting embryos that are not good embryos. The method for selecting embryos that are not good embryos is an image storage step of storing images of the cultured embryos taken at set time intervals, and a time course of the number of blastomeres of the embryos in the images. It comprises a selection step of selecting embryos that are not good embryos by analyzing changes. In such an embodiment, embryos that are not good embryos can be selected by analyzing changes in the number of blastomeres of the embryos over time using images of the embryo state.

The present invention can also be realized in various forms other than the embryo selection system. For example, the present invention can be realized in the form of an embryo selection device. Further, the present invention is not limited to the above-mentioned embodiments, and it is needless to say that the present invention can be carried out in various embodiments within a range not deviating from the gist of the present invention.

It is explanatory drawing which shows the structure of the embryo selection system in 1st Embodiment. This is an example of an image in which the judgment unit is used in supervised learning. This is an example of an image in which the judgment unit is used in supervised learning. This is an example of an image in which the judgment unit is used in supervised learning. This is an example of an image in which the judgment unit is used in supervised learning. This is a flow showing the image acquisition process executed by the control unit. It is a flow which shows the good embryo determination process performed by a control part. It is explanatory drawing explaining the learning of an image by deep learning.

A. First Embodiment:
FIG. 1 is an explanatory diagram showing the configuration of the embryo selection system 10 in the first embodiment. The embryo selection system 10 is a system for selecting good embryos suitable for transplantation from cultured embryos. The embryo referred to here is an egg that has been treated for fertilization, such as a conventional method in which sperms and eggs are co-cultured, or an intracytoplasmic sperm injection method. The embryo selection system 10 includes a culture unit 110, an image acquisition unit 130, a control unit 140, a user interface 150, and a notification unit 160.

The culture unit 110 is a so-called incubator for culturing embryos. The culture conditions such as temperature, humidity, oxygen concentration, carbon dioxide concentration, and culture time in the culture unit 110 are controlled by the control unit 140 based on the contents input in advance by the user via the user interface 150. The culture unit 110 cultivates embryos in a state where the culture container 200, which is a container for culturing embryos, is fixed in the culture unit 110.

The culture vessel 200 is a well plate having 12 wells in 3 rows and 4 columns. The bottom of each well of the culture vessel 200 is numbered 1 to 12, which is a well number. The culture container 200 is a container for putting one embryo in each well and culturing it.

The culture unit 110 has a container transport unit 115. The container transport unit 115 has a shape extending in the horizontal direction and constitutes a bottom surface portion of the culture unit 110. The container transport unit 115 has a fixing unit (not shown) for fixing the culture container 200 on a surface facing upward in the direction of gravity. The culture section 110 cultivates embryos with the culture vessel 200 fixed to the fixed section.

The container transport unit 115 transports the culture container 200 fixed to the fixed portion by moving the fixed portion to a position on the lower side in the gravity direction of the image acquisition unit 130 in which a part thereof protrudes inside the culture unit 110. .. The container transport unit 115 transports the culture container 200 to the initial position when the image acquisition by the image acquisition unit 130 is completed. In FIG. 1, the position where the culture vessel 200 is shown is the initial position.

The frequency (time interval) of the container transport unit 115 transporting the culture container 200 is controlled by the control unit 140 based on the content set in advance by the user via the user interface 150. The time interval referred to here is a time interval that can capture the change over time in the number of blastomeres of the embryo, which is empirically obtained. In the present embodiment, the container transport unit 115 is controlled to transport the culture container 200 to a position below the image acquisition unit 130 in the direction of gravity every 15 minutes. The frequency of transport may be set to a different time interval than every 15 minutes. The container transport unit 115 transports the culture container 200 to a position below the image acquisition unit 130 in the direction of gravity, and then adjusts the position of the culture container 200 two-dimensionally in the vertical and horizontal directions when viewed from the image acquisition unit 130. , Each well can be arranged at a position where the image acquisition unit 130 can acquire an image. The container transport unit 115 transports the culture container 200 to the initial position when the image acquisition by the image acquisition unit 130 is completed. The step in which the image acquisition unit 130 acquires an image of each well in the culture vessel 200 will be described later.

The image acquisition unit 130 acquires images by photographing the state of the embryos cultured by the culture unit 110 at set time intervals. In the present embodiment, the image acquisition unit 130 captures the state of the embryo each time the container transport unit 115 transports the culture vessel 200, so that a plurality of images for each well in the culture vessel 200 are captured in chronological order. To get to. In another embodiment, the image acquisition unit 130 may acquire images by taking pictures at time intervals directly instructed by the control unit 140. Of the 12 wells of the culture vessel 200, the position of the well from which the image acquisition unit 130 acquires an image is specified in advance by the user via the user interface 150. In the following description, the position of the well specified by the user is referred to as "designated position". In the present embodiment, the image acquisition unit 130 is a CCD camera.

In the present embodiment, the image acquisition unit 130 takes a picture from the upper side in the gravity direction with the cultured culture container 200 illuminated from the lower side in the gravity direction. In another embodiment, the image acquisition unit 130 may be arranged on the lower side in the gravity direction when viewed from the culture container 200 to be transported, and may be photographed in a state of being illuminated from the upper side in the gravity direction.

The control unit 140 is composed of a microcomputer including a central processing unit and a main storage device. The control unit 140 controls each unit of the embryo selection system 10. Further, the control unit 140 controls the culture unit 110, the container transport unit 115, and the image acquisition unit 130 based on the contents input in advance by the user via the user interface 150.

The control unit 140 includes an image storage unit 142 and a determination unit 144.

The image storage unit 142 stores the image acquired by the image acquisition unit 130. In other words, the image storage unit 142 stores images of the state of the cultured embryo at set time intervals. The image storage unit 142 sends the acquired image of each well to the determination unit 144.

The determination unit 144 determines whether the embryo is a good embryo by analyzing the state of the embryo reflected in the image sent from the image storage unit 142. In the present embodiment, the determination unit 144 uses the image of each well acquired by the image acquisition unit 130 at a time interval of 15 minutes during 72 hours after the culture unit 110 starts culturing the embryo, and uses the embryo. Is a good embryo.

The determination unit 144 determines whether the embryo is a good embryo by analyzing the change in the number of blastomeres of the embryo over time. The determination unit 144 determines whether the embryo is a good embryo by analyzing whether the cleavage started after the fertilization process progresses through the two-cell stage.

The determination unit 144 makes a determination using an image that can recognize the number of blastomeres of the embryo in cleavage among a plurality of images acquired at different times. When the determination unit 144 confirms that the number of blastomeres of the embryo has directly shifted to the two state in the first cleavage started after the fertilization process, the determination unit 144 determines that the embryo is a good embryo. In other words, when the embryo (fertilized egg) is one cell, the determination unit 144 determines that the embryo is a good embryo when it directly shifts to the state of two cells in the first cleavage. .. Here, "direct transition to two states" or "direct transition to two-cell state" means one to two states without going through a state in which the number of blastomeres or cells of the embryo is larger than two. It means to move to.

When the determination unit 144 confirms that in the first cleavage, the number of blastomeres of the embryo directly shifts to the state of 3 or more without going through the state of 2 blastomeres, the embryo is good. Judge that it is not an embryo. In other words, in the first cleavage, the determination unit 144 directly transitions from one cell to the state of three or more cells without going through the state of one cell to two cells (fertilized egg). , The embryo is determined not to be a good embryo. Further, the determination unit 144 determines that the embryo is not a good embryo when the embryo (fertilized egg) shifts from one cell to a chaotic state in the first cleavage.

When a cell divides, it usually results from one mother cell dividing into two daughter cells. At this time, if three or more daughter cells are divided from one mother cell, it is highly probable that these daughter cells have an abnormal number of chromosomes. Therefore, as described above, when the embryo (fertilized egg) is one cell and the embryo is transferred to the state of two cells in the first cleavage, the determination unit 144 is a good embryo. Judge that there is.

The determination unit 144 learns about the characteristics of the embryo captured in the image by supervised learning, and determines whether the embryo is a good embryo based on the learning. In the present embodiment, the determination unit 144 learns about the determination of the number of blastomeres in the embryo captured in the image, and determines whether the embryo is a good embryo based on the learning. Therefore, the determination unit 144 can determine whether the embryo is a good embryo based on the determination criterion of the number of blastomeres learned by supervised learning.

2, FIG. 3, FIG. 4 and FIG. 5 are explanatory views showing an example of an image in which the determination unit 144 is used in supervised learning. FIG. 2 is an example of an image labeled as an embryo in a state in which cleavage has not started since fertilization. FIG. 3 is an example of an image labeled as an embryo in which the number of blastomeres has directly transitioned to two states in the first cleavage after fertilization. FIG. 4 is an example of an image labeled as an embryo in which the number of blastomeres directly shifts to the state of 3 in the first cleavage after fertilization without going through the state of 2 blastomeres. be. FIG. 5 is an example of an image labeled as an embryo that has transitioned to a chaotic state in the first cleavage after fertilization.

The user interface 150 exchanges information with the user of the embryo selection system 10. In the present embodiment, the user interface 150 is a touch panel that displays an image and accepts input of an instruction from a user on the image. In another embodiment, the user interface 150 may include a push button that accepts input of instructions from the user.

The notification unit 160 notifies the determination image used for the determination among the images. The notification unit 160 notifies the determination image when the user is viewing the determination result by the determination unit 144 on the screen of the touch panel which is the user interface 150. Here, the image notified as the determination image is an image used for determination by the determination unit 144 as an image capable of recognizing the number of blastomeres of the embryo in cleavage. An example of an image is an image of an embryo in which the number of blastomere is directly transferred to the state of 2 in the first cleavage after fertilization. As an example of the notification format, tagging of an image regarded as a determination image can be mentioned. Therefore, the user who uses the embryo selection system 10 can know which image the determination unit 144 used to determine a good embryo. In the present embodiment, since the acquired time is attached to the image for each acquired image, the user confirms the time attached to the determination image to divide the time from the fertilization process. You can know the correspondence with the number of balls.

Further, the notification unit 160 notifies the information on which the determination unit 144 is the basis of the determination in the determination image. When the user is browsing the notified determination image on the screen of the touch panel which is the user interface 150, the notification unit 160 notifies the information on which the determination unit 144 is the basis of the determination. In the present embodiment, the notification unit 160 notifies the position information about the region portion in the image used by the determination unit 144 to count the number of blastomeres in the determination image. In other words, the notification unit 160 notifies information on which part of the image is counted as one blastomere.

FIG. 6 is a flow showing an image acquisition process executed by the control unit 140. The control unit 140 executes an image acquisition process when the culture vessel 200 is transported to a position below the image acquisition unit 130 in the direction of gravity.

When the image acquisition process is started, the control unit 140 calculates a variable A representing the number of wells designated by the user (step S100). After calculating the variable A representing the number of the designated wells (step S100), the control unit 140 obtains an image of the well with the lowest number among the designated wells that have not been photographed. Let the acquisition unit 130 take a picture (step S110). The number is a well number from 1 to 12 attached to the bottom of each well. The image taken at this time is stored in the image storage unit 142. Images of wells having the same number taken at different times are stored in the image storage unit 142 in chronological order.

In step S110, the image acquisition unit 130 acquires an image of the well in the following steps (1) and (2). (1) The control unit 140 causes the container transport unit 115 to two-dimensionally adjust the position of the culture container 200, and moves the position of the well to a position where the image acquisition unit 130 can perform imaging. (2) The control unit 140 moves the well to a position where the image acquisition unit 130 can take an image, and then causes the image acquisition unit 130 to take an image.

After the image of the well with the smallest number among the designated wells and the wells that have not finished shooting is taken (step S110), the control unit 140 stores the number of the wells that have finished shooting (step). S120). After storing the number of the well that has finished photographing (step S120), the control unit 140 decrements the variable A. (Step S130).

After the variable A is decremented (step S130), the control unit 140 determines whether the variable A has become 0 (step S140). When the variable A becomes 0 (step S140: YES), the control unit 140 ends the image acquisition process of FIG.

If the variable A is not 0 (step S140: NO), the control unit 140 returns to step S110 and repeats the processes of steps S110 to S140 until the variable A becomes 0. When the variable A becomes 0 (step S140: YES), the control unit 140 ends the image acquisition process of FIG.

FIG. 7 is a flow showing a good embryo determination process executed by the control unit 140. The control unit 140 executes a good embryo determination process when 72 hours have passed since the embryo culture was started.

When the good embryo determination process is started, the control unit 140 calculates a variable A representing the number of wells designated by the user (step S200). After calculating the variable A representing the number of the designated wells (step S200), the control unit 140 extracts the image of the well with the lowest number among the designated wells that have not been determined. (Step S210). In the present embodiment, for example, in the good embryo determination process performed 72 hours after the embryo culture is started, the image of the designated well is obtained by the culture unit 110 starting the embryo culture. Since the images are acquired by the image acquisition unit 130 at time intervals of 15 minutes between 72 hours and 72 hours, there are 288 images for each designated well. That is, in the good embryo determination process performed 72 hours after the start of embryo culture, in step S210, the control unit 140 has 288 sheets for one of the designated wells. Extract the image of. In other words, the control unit 140 extracts images of wells having the same number, which are stored in the image storage unit 142 in time series, taken at different times from the image storage unit 142.

After extracting the image of the well with the smallest number among the designated wells and the wells for which the determination has not been completed (step S210), the control unit 140 in the extracted images, the embryos in cleavage. Select an image that can recognize the number of blastomeres (step S220).

After selecting an image that can recognize the number of blastomere of the embryo in the fertilized cleavage (step S220), the determination unit 144 in the control unit 140 analyzes the change in the number of blastomere of the embryo over time. In the first cleavage after the embryo is fertilized, it is determined whether or not the embryo is a good embryo based on whether or not the embryo has directly transitioned to the state where the number of blastomeres is 2. (Step S230).

After determining whether the embryo is a good embryo (step S230), the control unit 140 stores the number of the well that has completed the determination (step S240). After storing the wells for which the determination has been completed (step S240), the control unit 140 decrements the variable A. (Step S250).

After the variable A is decremented (step S250), the control unit 140 determines whether the variable A becomes 0 (step S260). When the variable A becomes 0 (step S260: YES), the control unit 140 ends the good embryo determination process of FIG. 7.

If the variable A is not 0 (step S260: NO), the control unit 140 returns to step S210 and repeats the processes of steps S210 to S260 until the variable A becomes 0. When the variable A becomes 0 (step S260: YES), the control unit 140 ends the good embryo determination process of FIG. 7.

According to the embodiment described above, the determination unit 144 can determine whether the embryo is a good embryo by analyzing the change over time in the number of blastomeres of the embryo using the image in which the state of the embryo is photographed. .. Therefore, for a system that can select good embryos, the accuracy of selecting good embryos can be further improved.

B. Second embodiment:
The configuration of the embryo selection system in the second embodiment is the same as the configuration of the embryo selection system 10 in the first embodiment, except that it includes a determination unit that performs learning different from that of the determination unit 144 in the first embodiment.

The determination unit in the second embodiment learns about the characteristics (number of blastomeres) of the embryo captured in the image by deep learning using the deep neural network 400, which is a multi-layered neural network, and the embryo is good based on the learning. Determine if it is an embryo. Therefore, it is possible to determine whether the embryo is a good embryo based on the criteria learned by the determination unit by deep learning. When the feature amount of the blastomere number of the embryo extracted by deep learning is a feature amount that humans cannot recognize, it is higher than that human beings make a judgment as to whether or not the embryo is a good embryo. It can be done with precision.

FIG. 8 is an explanatory diagram illustrating learning of an image by deep learning. The deep neural network 400 is a network modeled on the learning mechanism in the human cranial nerve system. The deep neural network 400 includes an input layer 410, a plurality of intermediate layers 420, and an output layer 430. The deep neural network 400 in the second embodiment includes four intermediate layers 420.

The input layer 410 is a layer into which information is input. The intermediate layer 420 is a layer for calculating the feature amount based on the information transmitted from the input layer 410. The output layer 430 is a layer that outputs a result based on the information transmitted from the intermediate layer 420.

Image 300 in FIG. 8 is an image showing an embryo. In the image 300, an image labeled as an embryo in a state where cleavage has not been started after fertilization processing, and a state in which the number of blastomeres is 2 in the first cleavage treatment after fertilization processing. An image labeled as a directly transferred embryo, the number of blastomeres is N (N is an integer of 3 or more) without going through the state where the number of blastomeres is 2 in the first cleavage after the embryo is fertilized. ), Images labeled as embryos that have transitioned directly to the state of), images labeled as embryos that have transitioned to a chaotic state in the first cleavage after the embryo was fertilized, etc. are included. ..

The learning method by the deep neural network 400 will be described. The input layer 410 transmits the information to the intermediate layer 420 when the image 300 labeled about the state of the embryo is input. The intermediate layer 420 calculates the feature amount of the number of blastomeres of the embryo based on the information transmitted from the input layer 410. The output layer 430 outputs the feature amount of the number of blastomeres of the embryo calculated based on the information transmitted from the intermediate layer. The determination unit in the second embodiment determines whether the embryo is a good embryo based on the output feature amount.

C. Third embodiment:
In the third embodiment, a method for selecting embryos that are not good embryos will be described. This method for selecting embryos that are not good embryos includes a culture step, an image acquisition step, and a selection step.

The culturing step is a step of culturing the fertilized embryo. The image acquisition step is a step of acquiring a plurality of images by photographing the state of the embryos cultured in the culture step at set time intervals. The selection step is a step of selecting embryos that are not good embryos by analyzing changes in the number of blastomeres of embryos over time in images acquired at different times.

According to the third embodiment described above, embryos that are not good embryos can be selected by analyzing changes in the number of blastomeres of the embryos over time using images taken of the state of the embryos.

D. Other embodiments:
In the first embodiment, the embryo selection system 10 includes a container transport unit 115, but the present invention is not limited to this. For example, the embryo selection system in other embodiments may not include the container transport section 115. In this case, the image acquisition unit 130 may be provided on the upper side of the culture container 200 fixed to the fixed portion in the gravity direction, or the image acquisition unit 130 may be configured to be movable on the upper side of the culture container 200 in the gravity direction. Just do it.

In the first embodiment, the image acquired by the image acquisition unit 130 is stored in the image storage unit 142, but the present invention is not limited to this. For example, the image acquired by the image acquisition unit 130 may be stored in the so-called cloud. In this case, the determination unit 144 acquires an image from the cloud and makes a determination.

In the first embodiment, when the determination unit 144 confirms that in the first cleavage, the embryo has directly shifted to the state where the number of blastomere is 3 or more without going through the state where the number of blastomere is 2. Was determined not to be a good embryo, but the present invention is not limited to this. For example, the determination unit 144 has divided into three or more embryos from the start of cleavage to the lapse of a preset time without going through the state where one blastomere is two. If is confirmed, the embryo may be determined not to be a good embryo. This is because it is highly probable that the number of chromosomes is abnormal even in the cells generated by division in this case. Further, when the determination unit 144 confirms that at least a part of the blastomere of the embryo is fused (reverse) by the time when a preset time elapses from the start of cleavage of the embryo, the embryo is the embryo. May be determined not to be a good embryo.

In the third embodiment, the input image 300 was an image labeled about the state of the embryo, but the invention is not limited to this. For example, the input images are an image showing the state of the embryo in which implantation was confirmed after transplantation and an image showing the state of the embryo in which implantation was not confirmed after transplantation during cleavage. You may.

In the first embodiment, the embryo selection system 10 executes a good embryo determination process 72 hours after the start of embryo culture, but the present invention is not limited to this. For example, the embryo selection system may perform a good embryo determination process when a time shorter or longer than 72 hours has elapsed since the embryo culture was started. In addition, the embryo selection system may repeatedly execute the good embryo determination process at preset time intervals, for example, every hour after the embryo culture is started. The image used for the determination at this time is an image acquired by the image acquisition unit 130 up to that point. In the embryo selection system of such a form, when the embryo is determined to be a good embryo, the subsequent execution of the good embryo determination process may not be repeated.

In the first embodiment, the embryo selection system 10 includes a culture unit 110 and an image acquisition unit 130, but the present invention is not limited to this. For example, in another embodiment, the embryo selection system may not have the culture unit 110 as compared with the embryo selection system 10 of the first embodiment. In such an embryo selection system, a culture vessel containing embryos cultured in an external culture device of the embryo selection system is brought into the embryo selection system at set time intervals to obtain an image acquisition unit. By having 130 acquire an image, the determination unit 144 can determine a good embryo. Further, in another embodiment, the embryo selection system may not have the culture unit 110 and the image acquisition unit 130 as compared with the embryo selection system 10 of the first embodiment. In such an embryo selection system, images of the cultured embryos taken at set time intervals are brought into the embryo selection system from outside the embryo selection system via a recording medium or the Internet. , The determination unit 144 can determine a good embryo.

In the first embodiment, the determination unit 144 learns about the characteristics of the embryo captured in the image by supervised learning, and in the second embodiment, the determination unit is captured in the image by deep learning using the deep neural network 400. The present invention is not limited to this, although learning about the characteristics of the embryo and determining whether the embryo is a good embryo based on the learning. For example, the determination unit may determine whether the embryo is a good embryo by pattern matching using an image showing the state of the embryo whose implantation has been confirmed after transplantation during cleavage.

In the first embodiment, the culture vessel 200 is a well plate provided with 12 wells in 3 rows and 4 columns, but the present invention is not limited to this. For example, the culture vessel 200 may be a well plate having 25 wells in 5 rows and 5 columns, or may be a well plate composed of any row and column.

In the first embodiment, the image acquisition unit 130 takes a picture from the upper side in the gravity direction with the cultured culture container 200 illuminated from the lower side in the gravity direction, but the present invention is not limited to this. For example, the image acquisition unit 130 may take an image from any direction while illuminating from any direction, not limited to the direction of gravity.

The present invention is not limited to the above-described embodiments, examples, and modifications, and can be realized with various configurations within a range not deviating from the gist thereof. For example, the technical features in the embodiments, examples, and modifications corresponding to the technical features in each of the embodiments described in the column of the outline of the invention may be used to solve some or all of the above-mentioned problems. , Can be replaced or combined as appropriate to achieve some or all of the above effects. Further, if the technical feature is not described as essential in the present specification, it can be appropriately deleted.

10 ... Embryo selection system 110 ... Culture unit 115 ... Container transport unit 130 ... Image acquisition unit 140 ... Control unit 142 ... Image storage unit 144 ... Judgment unit 150 ... User interface 160 ... Notification unit 200 ... Culture container 300 ... Image 400 ... Deep Neural network 410 ... Input layer 420 ... Intermediate layer 430 ... Output layer

Claims (6)

It ’s an embryo selection system.
An image storage unit that stores images of embryos housed and cultured in a plurality of wells provided in a culture container in a time-series manner at set time intervals.
A determination unit for determining the state of the embryo by reading out the image stored in the image storage unit and analyzing the change over time in the number of blastomeres of the embryo in the image.
Equipped with
In the first cleavage started after the fertilization process, the determination unit confirms that the number of blastomeres of the embryo has directly shifted to the two state, and the first cleavage process is started after the fertilization process. In cleavage, the embryo selection is performed differently depending on whether the embryo has a blastomere number of 3 or more without going through a state of 2 blastomeres. system. The embryo selection system according to claim 1.
The determination unit is an embryo selection system that learns about the characteristics of the embryo captured in the image by supervised learning and determines the state of the embryo based on the learning. The embryo selection system according to claim 1.
The determination unit is an embryo selection system that learns about the characteristics of the embryo captured in the image by deep learning using a multi-layer neural network and determines the state of the embryo based on the learning. The embryo selection system according to any one of claims 1 to 3, further comprising.
An embryo selection system including a notification unit for notifying a determination image used for determination among the images. The embryo selection system according to claim 4.
The notification unit is an embryo selection system that notifies the determination image and also notifies the information on which the determination unit is based in the determination image. It ’s a method of selecting embryos .
An image storage step of chronologically storing images for each well , in which embryos housed and cultured in a plurality of wells provided in a culture container are imaged at set time intervals,
A selection step of selecting an embryo by reading out the image stored in the image storage step and analyzing a change over time in the number of blastomeres of the embryo in the image.
Equipped with
In the selection step, in the first cleavage started after fertilization, it was confirmed that the number of blastomeres of the embryo directly shifted to the two state, or the first started after fertilization. A method of selecting an embryo according to whether or not the number of blastomeres of the embryo directly shifts to the state of 3 or more without going through the state of 2 blastomeres in the cleavage .

Images