WO2019225176A1 - 制御装置、制御方法、およびプログラム - Google Patents
制御装置、制御方法、およびプログラム Download PDFInfo
- Publication number
- WO2019225176A1 WO2019225176A1 PCT/JP2019/015202 JP2019015202W WO2019225176A1 WO 2019225176 A1 WO2019225176 A1 WO 2019225176A1 JP 2019015202 W JP2019015202 W JP 2019015202W WO 2019225176 A1 WO2019225176 A1 WO 2019225176A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- display
- culture
- control device
- cleavage
- control unit
- Prior art date
Links
Images
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/20—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
-
- C—CHEMISTRY; METALLURGY
- C12—BIOCHEMISTRY; BEER; SPIRITS; WINE; VINEGAR; MICROBIOLOGY; ENZYMOLOGY; MUTATION OR GENETIC ENGINEERING
- C12M—APPARATUS FOR ENZYMOLOGY OR MICROBIOLOGY; APPARATUS FOR CULTURING MICROORGANISMS FOR PRODUCING BIOMASS, FOR GROWING CELLS OR FOR OBTAINING FERMENTATION OR METABOLIC PRODUCTS, i.e. BIOREACTORS OR FERMENTERS
- C12M1/00—Apparatus for enzymology or microbiology
- C12M1/34—Measuring or testing with condition measuring or sensing means, e.g. colony counters
-
- 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
-
- 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
- C12M41/48—Automatic or computerized control
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/14—Digital output to display device ; Cooperation and interconnection of the display device with other functional units
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N5/00—Computing arrangements using knowledge-based models
- G06N5/04—Inference or reasoning models
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T11/00—2D [Two Dimensional] image generation
- G06T11/20—Drawing from basic elements, e.g. lines or circles
- G06T11/206—Drawing of charts or graphs
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0012—Biomedical image inspection
- G06T7/0014—Biomedical image inspection using an image reference approach
- G06T7/0016—Biomedical image inspection using an image reference approach involving temporal comparison
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20036—Morphological image processing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20076—Probabilistic image processing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30004—Biomedical image processing
- G06T2207/30024—Cell structures in vitro; Tissue sections in vitro
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30004—Biomedical image processing
- G06T2207/30072—Microarray; Biochip, DNA array; Well plate
Definitions
- the present disclosure relates to a control device, a control method, and a program.
- Patent Document 1 discloses a technique for estimating a stage related to division of a cell to be cultured.
- the present disclosure proposes a new and improved control device, control method, and program capable of effectively visualizing the culture state related to a plurality of culture objects.
- a dynamic state related to a culture state of a culture target including cells having mitotic potential, estimated along a time series by morphological analysis using a learned model generated based on a machine learning algorithm.
- a control device that includes a display control unit that controls display, and the display control unit controls comparative display of the culture state related to the plurality of culture objects.
- the culture state of a culture target including cells having mitotic ability which is estimated along a time series by a morphological analysis using a learned model generated based on a machine learning algorithm
- a control method is provided, further comprising: controlling the display of the culturing status related to a plurality of the culture objects. .
- the culture state of a culture object including cells having mitotic potential estimated along a time series by a morphological analysis using a learned model generated based on a machine learning algorithm
- a display control unit that controls the dynamic display according to the program, and the display control unit provides a program for functioning as a control device that controls the comparative display of the culture status of the plurality of culture objects Is done.
- FIG. 5 is an example of a user interface controlled by a display control unit according to an embodiment of the present disclosure. It is a block diagram which shows the function structural example of the control system which concerns on the same embodiment. It is a figure for demonstrating the comparison display control of the culture condition which concerns on the culture
- a technique for photographing a culture target such as a cell in time series (also referred to as time-lapse photography) and observing a change with time of the cell has been widely used.
- time-lapse photography as described above, a large number of fertilized eggs, such as 1000 to 2000, may be observed and evaluated at the same time, so that an embryo cultivator can perform re-evaluation and shipment judgment on all fertilized eggs. This required a high workload and a long time. Also, not only in the field of livestock, but also in fields such as infertility treatment and regenerative treatment, time lapse photography has been performed for a long time, but it is very easy to intuitively grasp the culture situation related to a large amount of culture subjects. It was difficult.
- the control device 20 that realizes the control method according to an embodiment of the present disclosure includes a division that is estimated along a time series by morphological analysis using a learned model generated based on a machine learning algorithm.
- the display control part 240 which controls the dynamic display which concerns on the culture condition of the culture target containing the cell which has an ability is provided.
- the display control part 240 which concerns on one Embodiment of this indication controls the comparative display of the said culture condition which concerns on several culture
- FIG. 1 is an example of a user interface UI controlled by the display control unit 240 according to an embodiment of the present disclosure.
- FIG. 1 shows an example of a user interface UI when the culture target according to the present embodiment is a fertilized egg.
- time-lapse images of a plurality of fertilized eggs photographed by the photographing apparatus 10 are displayed side by side.
- the culture state estimated by the morphological analysis using the learned model generated by the processing unit 230 according to the present embodiment based on the machine learning algorithm may be added to the time-lapse image of each fertilized egg.
- the above-mentioned culture state includes the cleavage state of the fertilized egg.
- the above-described cleavage situation may include, for example, the cleavage stage of a fertilized egg or the occurrence situation of abnormal cleavage.
- the above-described culture situation may include, for example, a situation relating to dead cell formation of a fertilized egg.
- the situation concerning a fertilized egg that has already been shipped may be included.
- the display control unit 240 displays the state of the fertilized egg cleavage stage, dead cellization, and shipment status estimated by the processing unit 230 as the overlay color of each time-lapse image. It is shown by comparison.
- the cleavage stage includes, for example, morula, early blastocyst, blastocyst, expanding blastocyst and the like.
- the display control unit 240 it is possible to present to a user such as an embryo cultivator in a state in which the culture conditions relating to a large amount of fertilized eggs are compared.
- the display control unit 240 displays the time-lapse image and the culture state related to the plurality of fertilized eggs in association with the positions (coordinates) of the wells where the fertilized eggs are arranged in the culture dish. Control may be performed to
- the time-lapse image currently displayed on the user interface UI is cultured in the upper left section in the upper left culture dish D1 among the six culture dishes D1 to D6. It can be seen that it corresponds to a fertilized egg. Further, the display control unit 240 may perform control so that each time-lapse image is displayed in correspondence with the physical position of each fertilized egg in the region.
- the display control unit 240 it is possible to display the culture state related to a large amount of culture objects in association with the positions of the wells where the culture objects are arranged in the culture dish.
- a user such as an embryo cultivator intuitively grasps the culture state of each fertilized egg and accurately determines the shipment determination in a short time. Can be done.
- the culture target is a fertilized egg
- the culture target according to the present embodiment may widely include cells having division ability.
- Examples of cells having mitotic potential include cancer cells and various cultured cells used in the field of regenerative medicine.
- the “fertilized egg” at least conceptually includes a single cell and a collection of a plurality of cells.
- a single cell or a collection of cells can be an oocyte, egg (egg or ovum), fertilized egg (fertile ovum or zygote), undifferentiated germ cell (blastocyst), embryo (embryo) )
- oocyte egg
- egg or ovum fertilized egg
- fertilized egg fertilized egg
- blastocyst undifferentiated germ cell
- embryo embryo
- FIG. 2 is a block diagram illustrating a functional configuration example of the control system according to the present embodiment.
- the control system according to the present embodiment includes an imaging device 10, a control device 20, and a display device 30.
- the imaging device 10 and the control device 20, and the control device 20 and the display device 30 are connected via a network 40 so that they can communicate with each other.
- the imaging device 10 is a device that images a culture target such as a fertilized egg based on control by the control device 20.
- the photographing apparatus 10 according to the present embodiment may be an optical microscope having a photographing function, for example.
- the imaging device 10 includes an imaging unit 110, a holding unit 120, and an irradiation unit 130.
- the imaging unit 110 has a function of imaging a culture target based on control by the control device 20.
- the imaging unit 110 according to the present embodiment is realized by an imaging device such as a camera, for example.
- the photographing unit 110 may include a plurality of optical objective lenses having different magnifications.
- the control device 20 can control the photographing timing of the photographing unit 110, the photographing time (exposure time), the selection of the optical objective lens, the physical position of the photographing unit 110 in the horizontal direction or the vertical direction, and the like. .
- the holding unit 120 according to the present embodiment has a function of holding a culture dish in which a culture target is cultured.
- the holding unit 120 according to the present embodiment can be, for example, an observation stage.
- the control device 20 can control the horizontal position and the focal position of the culture target in photographing by controlling the physical position of the holding unit 120 in the horizontal direction or the vertical direction.
- the irradiation unit 130 according to the present embodiment has a function of irradiating various kinds of light used for photographing based on control by the control device 20. Further, the irradiation unit 130 according to the present embodiment may widely include an optical system such as a squeezing.
- the control device 20 can control the type, wavelength, intensity, irradiation time, irradiation interval, and the like of the light irradiated by the irradiation unit 130.
- Control device 20 The control device 20 according to the present embodiment has a function of controlling photographing of the culture target based on the recognition probability of the culture target calculated using the learned model generated based on the machine learning algorithm.
- the control device 20 according to the present embodiment may be implemented as an information processing server, for example, and may remotely control the imaging device 10 via the network 40.
- control device 20 dynamically estimates along the culture status time series of the culture target by morphological analysis using the learned model generated based on the machine learning algorithm, It has a function to control the comparison display.
- the imaging control unit 210 has a function of controlling time-lapse imaging of a culture target by the imaging device 10.
- the imaging control unit 210 according to the present embodiment uses the observation target recognition probability calculated using the learned model generated based on the machine learning algorithm, and the relative horizontal position of the imaging unit 110 and the observation target.
- One of the features is to control the focus position.
- the learning unit 220 has a function of performing learning related to recognition of an observation target based on an image obtained by photographing a culture target and a machine learning algorithm.
- the learning unit 220 according to the present embodiment may perform recognition learning of the observation target by machine learning using a multilayer neural network such as Deep Learning configured to include a plurality of Convolution layers.
- the learning unit 220 can learn features related to the shape, form, structure, and the like of the culture target by performing supervised learning based on, for example, an image of the culture target and teacher data.
- the above teacher data includes, for example, the classification of the culture target included in the image (eg, a fertilized egg) and the growth stage of the culture target (eg, 2 cells, 4 cells, morula, early blastocyst, Information on the cleavage stage, such as blastocysts, expanded blastocysts, or dead cells).
- the learning unit 220 performs machine learning (for example, using learning data including an image of a culture target and the teacher data (information on at least one of the shape, form, structure, etc. of the culture target).
- Machine learning using a multilayer neural network may be performed to generate a learned model for recognizing a culture target. That is, for example, in the case of machine learning using a multilayer neural network, the learning model adjusts the weight coefficients (parameters) between the input layer, the output layer, and the hidden layer constituting the neural network, and generates a learned model. Is done.
- the processing unit 230 according to the present embodiment has a function of performing morphological analysis of the culture target based on the learning knowledge learned by the learning unit 220. That is, the processing unit 230 according to the present embodiment may be a recognizer (also referred to as a classifier) generated by learning by the learning unit 220.
- the processing unit 230 according to the present embodiment receives, for example, an image to be cultured, and obtains a probability value related to the cleavage stage of a fertilized egg by morphological analysis using a learned model generated based on a machine learning algorithm. Can be output in time series. Details of the functions of the processing unit 230 according to this embodiment will be described later.
- the display control unit 240 has a function of controlling the dynamic display related to the culture state of the culture target estimated by the processing unit 230 along the time series by morphological analysis.
- the display control unit 240 according to the present embodiment may control the comparison display of the culture state related to a plurality of culture objects.
- the culture object includes, for example, a fertilized egg.
- the display control unit 240 can control the display device 30 so that the cleavage status of a plurality of fertilized eggs and the status related to dead cell formation are compared and displayed.
- the above-mentioned cleavage situation includes the cleavage stage of the fertilized egg, the abnormal cleavage, and the occurrence state of the cell resting phase (Lag-Phase).
- the display control unit 240 can control the display device 30 so that the cleavage stages of a plurality of fertilized eggs and the occurrence status of abnormal cleavage are compared and displayed.
- the display control unit 240 may control the comparative display of the culture state as described above on the user interface as shown in FIG.
- the user interface according to the present embodiment may be realized in the form of a Web service, for example.
- the user can check the culture state of the culture target through the user interface displayed on the display device 30 and can perform various operations such as recording the determination result.
- the display control unit 240 generates control information such as an HTML file that defines the display format of the user interface, and transmits the control information to the display device 30 via the communication unit 250, thereby displaying the display device.
- the display of the user interface by 30 can be controlled.
- the functions of the display control unit 240 according to this embodiment will be described in detail separately.
- the communication unit 250 has a function of performing information communication with the imaging device 10 and the display device 30 via the network 40.
- the communication unit 250 according to the present embodiment transmits, for example, a control signal related to the imaging control generated by the imaging control unit 210 to the imaging device 10 and receives an image of the culture target that has been imaged from the imaging device 10.
- the communication unit 250 according to the present embodiment transmits control information related to display control of the user interface generated by the display control unit 240 to the display device 30.
- the display device 30 is a device that performs comparative display of culture statuses related to a plurality of culture targets based on control by the control device 20.
- the display unit 310 according to the present embodiment has a function of outputting visual information such as an image and text.
- the display unit 310 according to the present embodiment displays a user interface for the user to check the culture state of the culture target based on the control information received from the control device 20.
- the display unit 310 according to the present embodiment may have a function equivalent to that of the display control unit 240 of the control device 20.
- the display unit 310 can receive various recognition results output from the processing unit 230 of the control device 20, and can control display of the user interface based on the recognition results.
- the display unit 310 includes a display device that presents visual information.
- the display device include a liquid crystal display (LCD) device, an organic light emitting diode (OLED) device, and a touch panel.
- LCD liquid crystal display
- OLED organic light emitting diode
- the network 40 has a function of connecting the imaging device 10 and the control device 20.
- the network 40 may include a public line network such as the Internet, a telephone line network, a satellite communication network, various local area networks (LANs) including Ethernet (registered trademark), a wide area network (WAN), and the like. Further, the network 40 may include a dedicated line network such as an IP-VPN (Internet Protocol-Virtual Private Network).
- the network 40 may include a wireless communication network such as Wi-Fi (registered trademark) or Bluetooth (registered trademark).
- control device 20 does not necessarily include the learning unit 220.
- the control device 20 according to the present embodiment may perform control of photographing by the photographing device 10 or estimation of a culture state related to a culture target based on learning knowledge learned by another device.
- the functional configuration of the control system and the control device 20 according to the present embodiment can be flexibly modified according to specifications and operations.
- the display control unit 240 controls the comparative display of the culture status related to a plurality of culture objects.
- the display control unit 240 according to the present embodiment controls the comparative display of the cleavage stage of a fertilized egg and the situation related to dead cell formation as an example of the culture situation.
- the display control unit 240 according to the present embodiment is not limited to the above example, and may control comparative display related to various culture conditions.
- FIG. 3 is a diagram for explaining the comparative display control of the culture state related to the culture target by the display control unit 240 according to the present embodiment.
- the display control unit 240 according to the present embodiment gives a box B1 indicating various culture conditions to the upper right of the time-lapse image displayed on the user interface UI shown in FIG. Realizes comparative display of culture status.
- the display control unit 240 assigns a color or character indicating the quality state of the fertilized egg to the left frame in the box B1.
- the above-mentioned quality state may comprehensively indicate the culture state of the fertilized egg.
- the display control unit 240 can indicate, for example, that the fertilized egg corresponding to the time-lapse image is normally developing or dead cells by different colors, characters, marks, and the like.
- the display control unit 240 indicates that the fertilized egg corresponding to the time-lapse image has become a dead cell by a predetermined color and the letter “D”.
- the display control unit 240 assigns a color or character indicating the cleavage status of the fertilized egg to the center frame in the box B1.
- the above cleavage situation includes, for example, the cleavage stage and the occurrence of abnormal cleavage.
- the display control unit 240 displays, for example, whether the fertilized egg corresponding to the time-lapse image is normally cracked, abnormally cracked, the cleavage stage and the type of abnormal cleavage, It can be indicated by an indicator such as a mark.
- the display control unit 240 indicates that the fertilized egg corresponding to the time-lapse image has caused a direct cleavage by using a predetermined color and the character “DC”.
- the direct cleaving is a kind of abnormal cleavage in which a fertilized egg performs non-equal division such as 1 to 3 cells or 2 to 6 cells. It is known that the fertility rate of a fertilized egg in which direct cleaving has occurred is significantly lower than that of a fertilized egg that has undergone normal cleavage.
- the fertilized egg in addition to the above direct cleaving, has a reverse cleavage that goes back to the cleavage stage, for example, from 3 cells to 2 cells or from 8 cells to 6 cells. Page (Reverse Cleavage) is included. It is known that the fertility rate of fertilized eggs with reverse cleaving is significantly lower than that of fertilized eggs that have undergone normal equal division, as is the pregnancy rate of fertilized eggs with direct cleaving. ing.
- an embryo culturer can intuitively and easily inferior a fertilized egg that has caused an abnormal cleavage such as a direct cleave and a reverse cleave. It is possible to easily grasp and take measures such as removing before shipping.
- the display control unit 240 gives a color or a character indicating another culture state related to the fertilized egg to the right frame in the box B1.
- the display control unit 240 indicates that the fertilized egg corresponding to the time-lapse image has undergone blastocyst contraction by using a predetermined color and the character “BC”.
- the display control unit 240 can display various information related to the culture state of the fertilized egg using colors, characters, marks, and the like. According to the above-described function of the display control unit 240 according to the present embodiment, a user such as an embryo culturer can comprehensively and comprehensively grasp the culture state related to a plurality of fertilized eggs, and is required for determination. Time, man-hours, number of people, etc. can be greatly reduced.
- the display control unit 240 can assist the above-described determination by the embryo cultivator by adding a state related to the determination of the fertilized egg to the time-lapse image.
- FIG. 4 is a view for explaining comparative display control of a state related to determination of a fertilized egg according to the present embodiment.
- the display control unit 240 according to the present embodiment provides a box B ⁇ b> 2 indicating a state related to the determination of a fertilized egg at the upper right of the time-lapse image displayed on the user interface UI illustrated in FIG. 1. By doing so, the comparison display of the judgment state is realized.
- the display control unit 240 gives a predetermined color or mark to the left frame in the box B2 when the determination related to the fertilized egg has not been made.
- the display control unit 240 displays the frame in the center of the box B2 when the fertilized egg is temporarily determined, and displays the right frame in the box B2 when the final determination of the fertilized egg is performed.
- Each is given a predetermined color or mark.
- the embryo cultivator instantly grasps the determination state of the fertilized eggs and is efficient. Judgment work can be performed.
- the comparison display control by the display control unit 240 according to the present embodiment has been described above.
- the display control unit 240 according to the present embodiment uses the indicators such as colors, characters, marks, and the like to present to the user in a state in which the culture state and the determination state relating to a plurality of fertilized eggs are compared. be able to.
- the comparative display control by the display control unit 240 according to the present embodiment is not limited to the example described above, and can be realized in various forms.
- the display control unit 240 indicates the cleavage stage by color overlay on the time-lapse image is described as an example. You may show the culture
- the display control unit 240 displays a detailed page that displays detailed data on the culture state of the fertilized egg corresponding to the time-lapse image. Transitions may be controlled.
- the display control unit 240 may control information display related to, for example, the cleavage timing of the fertilized egg and the elapsed time after the cleavage in the above detailed page. At this time, the display control unit 240 according to the present embodiment may control the time series display related to the culture state of the fertilized egg based on the estimation result by the processing unit 230.
- FIG. 5 is a diagram showing a display example of the cleavage timing of the fertilized egg and the elapsed time after the cleavage according to the present embodiment.
- the display control unit 240 displays the transition of the cleavage stage of the fertilized egg in time series in a graph based on the probability value related to the cleavage stage of the fertilized egg calculated by the processing unit 230. Yes.
- the display control unit 240 can indicate the cleavage timing according to the above estimated by the processing unit 230 by adding bars b1 and b2 and the like on the graph.
- the above-described bars b1 and b2 may be corrected, for example, by the user performing a slide operation.
- a user such as an embryo cultivator checks the graph and determines that the cleavage timing is estimated incorrectly, the determination can be corrected by sliding the positions of the bars b1 and b2.
- the display control unit 240 may calculate the elapsed time after the first cleavage and the elapsed time after the second cleavage based on the positions of the bars b1 and b2, and may display them in the field F1.
- the display control unit 240 As described above, according to the display control unit 240 according to the present embodiment, it becomes possible for the embryo culturer to easily check and correct the cleavage timing of the fertilized egg and the elapsed time after the cleavage.
- the display control unit 240 may control, for example, information display related to the cell resting period of a fertilized egg.
- a fertilized egg has a cell resting phase (also referred to as an induction phase) in which active cell growth stops.
- the cell resting phase occurs in the process of dividing from the 4-cell phase to the 8-cell phase.
- the number of starting cells in the cell resting phase is large, the start time is early, and the fertilized egg with a short period is generated after transplantation. It has been shown that the ability (such as pregnancy rate) is high.
- the cell resting period of a fertilized egg is attracting attention as an important index for identifying a fertilized egg having a high developmental potential.
- the display control unit 240 can assist the overall quality determination of the fertilized egg by the embryo cultivator by displaying information related to the cell resting phase estimated by the processing unit 230. It is.
- FIG. 6 is a diagram showing a display example of information related to the cell resting period of the fertilized egg according to the present embodiment.
- the display control unit 240 causes the processing unit 230 to display the movement amount on the graph obtained by visualizing changes in the movement amount of cells inside the fertilized egg (total value of velocity vectors) calculated by the processing unit 230. Bars b3 and b4 indicating the start and end of the cell resting phase estimated on the basis of the change in are displayed.
- the processing unit 230 for example, a period in which a change in the total amount of movement over time per unit culture time is equal to or less than a threshold and a change in the diameter of a fertilized egg over time per unit culture time. It is possible to estimate a period in which the period in which is equal to or less than the threshold overlap as the cell resting period.
- the display control unit 240 accepts a slide operation on the bars b3 and b4 as in the case shown in FIG. 5, and the embryo cultivator who confirms the graph can correct the cell resting period. Control may be performed as follows.
- the display control unit 240 may display the total time, start time, end time, etc. of the cell rest period in the field F2 based on the positions of the bars b3 and b4.
- the display control unit 240 As described above, according to the display control unit 240 according to the present embodiment, it becomes possible for the embryo culturer to easily check and correct the cell resting period of the fertilized egg.
- the display control unit 240 shows the cleavage stage of the fertilized egg estimated by the processing unit 230 and the cleavage stage determined and input by the embryo cultivator using the same graph. It may be displayed.
- FIG. 7 is a diagram showing an example of comparative display at the cleavage stage determined by the processing unit 230 and the embryo cultivator according to the present embodiment.
- the determination results of the cleavage stage related to the 1 to 4 cell stage by the processing unit 230 and the embryo cultivator are shown in time series.
- the determination result of the cleavage stage by the processing unit 230 is indicated by a circle, and the determination result of the cleavage stage by the embryo cultivator is indicated by a vertical bar.
- the display control unit 240 it is possible to display the determination result of the cleavage stage by the processing unit 230 and the determination result of the cleavage stage by the embryo cultivator by the same graph. It becomes.
- the display control unit 240 according to the present embodiment when the embryo cultivator determines the culture state related to a large amount of fertilized eggs, the difference from the determination result by the processing unit 230 is intuitively determined. It is possible to grasp and perform efficient work in a short time.
- the processing unit 230 performs morphological analysis of a photographed fertilized egg using a learned model generated based on a machine learning algorithm, thereby dividing the fertilized egg.
- the probability values related to the stages can be output in time series for each cleavage stage.
- the processing unit 230 (also referred to as a recognizer or a classifier) performs morphological analysis using learning knowledge learned based on, for example, images of fertilized eggs of 1 cell, 2 cells, 3 cells or more and teacher data. Thus, it is possible to output a probability that the fertilized egg in the input image is one cell, a probability that it is two cells, a probability value that is three or more cells, respectively. That is, by inputting a fertilized egg image as input data to the learned model of the processing unit 230, it is possible to output a probability value related to the cell stage of the fertilized egg.
- the display control unit 240 may control the time-series display of the probability values output from the processing unit 230.
- FIG. 8 is a diagram illustrating an example of a graph generated based on the probability value of the cleavage stage according to the present embodiment.
- the display control unit 240 generates a graph in which the probability values related to the cleavage stage output from the processing unit 230 are plotted along a time series.
- FIG. 8 shows an example of a graph when the processing unit 230 outputs probability values related to one cell, two cells, three cells or more based on the input image. In the above probability value, 1 is 100% and 0 is 0%.
- the embryo cultivator According to the above functions of the processing unit 230 and the display control unit 240 according to the present embodiment, it becomes possible for the embryo cultivator to easily grasp the temporal change of the probability value related to the cleavage stage of the fertilized egg.
- the processing unit 230 for example, the egg at each time when photographing is performed based on the probability value of the highest cleavage stage among the probability values of each cleavage stage calculated at each time.
- the split stage may be estimated.
- the display control unit 240 generates a graph in which only the probability value of the highest cleavage stage is plotted at each time, and the processing unit 230 is displayed on the graph. Information on the cleavage stage estimated by may be added.
- the processing unit 230 and the display control unit 240 According to the above functions of the processing unit 230 and the display control unit 240 according to the present embodiment, it becomes possible for the embryo cultivator to more intuitively understand the temporal change of the cleavage stage related to the fertilized egg.
- the processing unit 230 according to the present embodiment may output a probability waveform obtained by interpolating the probability value at the cleavage stage between the times when the images are taken. At this time, the processing unit 230 according to the present embodiment can output the inclination of the probability value learned based on the image of the fertilized egg photographed at a narrow interval such as 10 minutes, and the above probability waveform. .
- the shooting time it is possible to acquire the probability value of the cleavage stage between the two, and the cost for photographing and estimation can be greatly reduced.
- the display control unit 240 may generate a graph including the probability waveform output from the processing unit 230, for example, as illustrated in FIG.
- the display control unit 240 interpolates a probability waveform C1 in which a probability value of 1 cell is interpolated, a probability waveform C2 in which a probability value of 1 cell is interpolated, and a probability value of 3 cells or more.
- a graph including the probability waveform C3 is generated.
- the processing unit 230 can estimate and calculate the cleavage timing based on the acquired probability waveform, and can estimate the cleavage stage between each time based on the cleavage timing. is there.
- the processing unit 230 may detect, for example, an intersection where the probability waveforms related to two cleavage stages intersect and estimate the time corresponding to the intersection as the cleavage timing.
- the processing unit 230 may estimate the intersection of the probability waveform C1 related to 1 cell and the probability waveform C2 related to 2 cells as the cleavage timing from 1 cell to 2 cells. . Further, the processing unit 230 can estimate the intersection of the probability waveform C2 related to 2 cells and the probability waveform C3 related to 3 cells or more as the cleavage timing from 2 cells to 3 cells or more.
- the processing unit 230 it is possible to accurately estimate the cleavage stage of a fertilized egg with a finer granularity than the photographing interval, and the embryo cultivator can perform the fertilized egg in more detail.
- the culture situation can be grasped.
- the processing unit 230 may estimate the occurrence of the abnormal cleavage of the fertilized egg and its timing based on the acquired probability waveform.
- 12 and 13 are diagrams for explaining the estimation of abnormal cleavage based on the probability waveform by the processing unit 230 according to the present embodiment.
- the processing unit 230 detects the intersection where the probability waveform C1 related to one cell intersects with the probability waveform C3 related to three or more cells, thereby changing from one cell to three or more cells. It is possible to estimate that direct cleaving has occurred.
- the processing unit 230 may detect and output the intersection of the probability waveforms C1 and the probability waveform C3 as generation timing T dc direct chestnut Beji.
- the processing unit 230 detects the intersection where the probability waveform C3 related to 3 cells or more and the probability waveform C2 related to 2 cells intersect, thereby changing from 3 cells or more to 2 details. It is possible to estimate that reverse cleaving has occurred.
- the processing unit 230 may detect and output the intersection of the probability waveforms C3 probability waveform C2 as generation timing T rc of reverse chestnut Beji.
- the display control unit 240 displays the direct cribbing occurrence timing T dc and the reverse cribbing occurrence timing T rc detected as described above, and information related to the cleavage stage on a graph. Control may be performed to
- the embryo cultivator can easily grasp the abnormal cleavage of the fertilized egg and take measures such as removing the fertilized egg. Is possible.
- the processing unit 230 can also estimate an abnormal cleavage of a fertilized egg based on, for example, a probability waveform related to a certain cleavage stage.
- the processing unit 230 outputs a probability waveform C1 related to one cell.
- the processing unit 230 can estimate the period in which the probability waveform C1 exceeds the threshold as the 1-cell stage.
- the period estimated to be the 1-cell stage is detected again after the end of the 1-cell stage and the transition to another cell stage as shown in FIG. Is possible.
- the processing unit 230 can estimate the occurrence of an abnormal cleavage related to a fertilized egg based on various methods. For example, when the 4-cell stage is estimated before the 2-cell stage is estimated, the processing unit 230 can also estimate the occurrence of direct cleaving.
- FIGS. 14 to 17 are diagrams for explaining the estimation of the cleavage stage after the morulae according to the present embodiment.
- FIGS. 14 to 17 show an example in which the processing unit 230 performs estimation related to the morula, early blastocyst, blastocyst, and expanded blastocyst.
- the processing unit 230 can output the probability value and the probability waveform at each cleavage stage after the morulae by the above-described method.
- FIG. 14 illustrates a graph generated based on the probability value output from the display control unit 240
- FIG. 15 illustrates a graph generated based on the probability waveform output from the display control unit 240. Yes.
- stochastic waveforms relating to morula, early blastocyst, blastocyst, and expanded blastocyst are indicated by symbols C1 to C4, respectively.
- the processing unit 230 can estimate the cleavage stage at each time based on the acquired probability waveform and the like. At this time, in the cleavage stage after the morula, if the premise knowledge that reverse cleaving does not occur is not used, the processing unit 230, based on the probability value at time t9, as shown in FIG. It is erroneously estimated that the cleavage stage at time t9 (near) is a morula.
- the processing unit 230 performs the estimation using the premise that reverse cleaving does not occur in the cleavage stage after the morula, as shown in FIG. It is possible to correct the cleavage stage at time t9 (near) erroneously determined to be an expanded blastocyst.
- the cleavage stage after the mulberry embryo is obtained by using the premise that reverse cleaving does not occur in the cleavage stage after the mulberry embryo. It is possible to effectively improve the estimation accuracy.
- the processing unit 230 recognizes the shape of a culture target such as a fertilized egg and analyzes the physical form and characteristics such as the area and roundness of the culture target based on the recognition result. It is possible.
- the display control unit 240 may generate a graph showing the change with time of the recognition result and the analysis result output from the processing unit 230 and display them on the user interface UI.
- the display control unit 240 may generate an overlay image or the like based on the recognition probability image output from the processing unit 230 and display the overlay image together with the above graph.
- FIG. 18 is a diagram for explaining generation of an overlay image according to the present embodiment.
- an original image Io of the fertilized egg FA photographed by the photographing apparatus 10 at a certain time is schematically shown.
- the processing unit 230 according to the present embodiment can output a recognition probability image related to the fertilized egg FA by executing a shape recognition process using the original image Io as an input.
- the recognition probability image is a visualization of the probability distribution related to the recognition result of the culture target in the original image, for example, the closer to white, the higher the probability that the subject (pixel) is the culture target, The closer the color is to black, the lower the probability that the subject (pixel) is a culture target.
- the display control unit 240 generates a binarized image obtained by binarizing the recognition probability image output from the processing unit 230 based on a predetermined threshold, and converts the binarized image to the original image.
- a binarized image obtained by binarizing the recognition probability image output from the processing unit 230 based on a predetermined threshold, and converts the binarized image to the original image.
- an overlay image Ir as shown on the right side of FIG. 18 can be generated.
- the overlay color for example, green that can be easily recognized by an embryo cultivator may be employed.
- the display control unit 240 may display various images indicating the recognition result related to the shape of the culture target together with the above graph.
- the display control unit 240 may generate a segmentation image indicating the segmentation result of the specific portion of interest to be cultured in the image based on the recognition probability image, and may display the segmentation image together with the graph.
- FIG. 19 is an example of a graph generated based on the shape recognition result and analysis result of the culture target according to the present embodiment.
- the transition of the area of the fertilized egg is shown in time series.
- FIG. 19 shows an example in which a segmentation image is adopted as an image shown together with the graph.
- the plot on the graph and the segmentation image corresponding to the plot are indicated by the same number.
- the contraction and expansion related to the entire region of the fertilized egg are processed into a state that is easy to visually recognize. It is possible to assist in determining the quality of a fertilized egg by an embryo culture technician.
- FIG. 20 is a diagram for describing generation of an overlay image of a constituent included in a culture target according to the present embodiment.
- the processing unit 230 according to the present embodiment outputs a recognition probability image related to the shape of the cell mass CM of the fertilized egg FA based on the original image Io, and the display control unit 240 displays the recognition probability image.
- An example of the overlay image Ir generated based on the image is schematically shown.
- FIG. 21 is an example of a graph generated based on the shape recognition result and the analysis result of the structure included in the culture target according to the present embodiment.
- the transition of the area of the cell mass included in the fertilized egg is shown in time series.
- FIG. 21 shows an example in which a segmentation image is adopted as an image shown together with the graph. Further, in FIG. 21, the plot on the graph and the segmentation image corresponding to the plot are indicated by the same number.
- the contraction or expansion of a region related to a constituent such as a cell mass included in a fertilized egg is visually recognized. It becomes possible to provide it to users such as an embryo cultivator in an easy state.
- the culture status according to the present embodiment includes the status of fertilization of fertilized eggs, the appearance and disappearance of pronuclei, and the appearance and disappearance of polar bodies. The situation is included.
- the culture state according to the present embodiment includes a state of detailed fragmentation, a state of symmetry of blastomere, a state of appearance of morula compaction, an inner cell mass (Inner Cell) Mass, ICM), the appearance of trophectoderm, TE, the thickness of the zona and the state of hatching.
- the display control unit 240 displays various graphs related to the culture state of the culture target exemplified above on the user interface UI so that the graphs can be compared among a plurality of culture targets. Also good.
- the display control unit 240 may perform control such that graphs corresponding to a plurality of culture objects are displayed side by side as in the time-lapse image illustrated in FIG. 1.
- FIG. 22 is an example of a flowchart showing a flow of operations of the control device 20 according to the present embodiment.
- the culture target according to the present embodiment is a fertilized egg and the processing unit 230 estimates the cleavage stage of the fertilized egg or the occurrence of abnormal cleavage will be described as an example.
- the imaging control unit 210 controls the imaging device 10 to capture an image of a fertilized egg at time t (S1101).
- the processing unit 230 performs morphological analysis based on the fertilized egg image photographed in step S1101 (S1102).
- the processing unit 230 outputs a probability value related to the cleavage stage of the fertilized egg as a result of the morphological analysis in step S1102 (S1103).
- the processing unit 230 performs reverse cribbing determination based on the cleavage stage probability values at times t1 to tn (S1104).
- processing unit 230 determines direct cleaving based on the probability value of the cleavage stage at times t1 to tn (S1105).
- the display control unit 240 performs display control of the user interface UI based on the results obtained in steps S1101 to S1105 (S1106).
- FIG. 23 is a block diagram illustrating a hardware configuration example of the control device 20 according to an embodiment of the present disclosure.
- the control device 20 includes, for example, a processor 871, a ROM 872, a RAM 873, a host bus 874, a bridge 875, an external bus 876, an interface 877, an input device 878, and an output device 879.
- Storage 880, drive 881, connection port 882, and communication device 883 Note that the hardware configuration shown here is an example, and some of the components may be omitted. Moreover, you may further include components other than the component shown here.
- the processor 871 functions as, for example, an arithmetic processing unit or a control unit, and controls all or part of the operation of each component based on various programs recorded in the ROM 872, RAM 873, storage 880, or removable recording medium 901. .
- the ROM 872 is a means for storing a program read by the processor 871, data used for calculation, and the like.
- a program to be read by the processor 871 various parameters that change as appropriate when the program is executed, and the like are temporarily or permanently stored.
- the processor 871, the ROM 872, and the RAM 873 are connected to each other via, for example, a host bus 874 capable of high-speed data transmission.
- the host bus 874 is connected to an external bus 876 having a relatively low data transmission speed via a bridge 875, for example.
- the external bus 876 is connected to various components via an interface 877.
- the input device 878 for example, a mouse, a keyboard, a touch panel, a button, a switch, a lever, or the like is used. Furthermore, as the input device 878, a remote controller (hereinafter referred to as a remote controller) capable of transmitting a control signal using infrared rays or other radio waves may be used.
- the input device 878 includes a voice input device such as a microphone.
- the output device 879 is a display device such as a CRT (Cathode Ray Tube), LCD, or organic EL, an audio output device such as a speaker or a headphone, a printer, a mobile phone, or a facsimile. It is a device that can be notified visually or audibly.
- the output device 879 according to the present disclosure includes various vibration devices that can output a tactile stimulus.
- the storage 880 is a device for storing various data.
- a magnetic storage device such as a hard disk drive (HDD), a semiconductor storage device, an optical storage device, a magneto-optical storage device, or the like is used.
- the drive 881 is a device that reads information recorded on a removable recording medium 901 such as a magnetic disk, an optical disk, a magneto-optical disk, or a semiconductor memory, or writes information to the removable recording medium 901.
- a removable recording medium 901 such as a magnetic disk, an optical disk, a magneto-optical disk, or a semiconductor memory
- the removable recording medium 901 is, for example, a DVD medium, a Blu-ray (registered trademark) medium, an HD DVD medium, or various semiconductor storage media.
- the removable recording medium 901 may be, for example, an IC card on which a non-contact IC chip is mounted, an electronic device, or the like.
- connection port 882 is a port for connecting an external connection device 902 such as a USB (Universal Serial Bus) port, an IEEE 1394 port, a SCSI (Small Computer System Interface), an RS-232C port, or an optical audio terminal. is there.
- an external connection device 902 such as a USB (Universal Serial Bus) port, an IEEE 1394 port, a SCSI (Small Computer System Interface), an RS-232C port, or an optical audio terminal. is there.
- the external connection device 902 is, for example, a printer, a portable music player, a digital camera, a digital video camera, or an IC recorder.
- the communication device 883 is a communication device for connecting to a network.
- the control device 20 has the division ability estimated along the time series by the morphological analysis using the learned model generated based on the machine learning algorithm.
- the display control part 240 which controls the dynamic display which concerns on the culture condition of the culture object containing a cell is provided. Moreover, the display control part 240 which concerns on one Embodiment of this indication controls the comparison display of the culture condition which concerns on several culture
- each step related to the processing of the control device 20 of the present specification does not necessarily have to be processed in time series in the order described in the flowchart.
- each step related to the processing of the control device 20 may be processed in an order different from the order described in the flowchart, or may be processed in parallel.
- the following configurations also belong to the technical scope of the present disclosure.
- the cell having the division ability includes a fertilized egg, The control device according to (1) above.
- the culture state includes a cleavage situation, The display control unit controls comparison display related to the cleavage situation of a plurality of the fertilized eggs, The control device according to (2).
- the cleavage situation includes a cleavage stage, The display control unit displays a comparative display relating to the cleavage stage of a plurality of recipient eggs.
- the cleavage situation includes the occurrence of abnormal cleavage, The display control unit controls comparison display related to the occurrence status of the abnormal cleavage of the plurality of fertilized eggs, The control device according to (3) or (4).
- the abnormal cleavage includes at least one of a direct clear page or a reverse clear page, The control device according to (5).
- the culture state includes a state relating to dead cell formation of the fertilized egg
- the display control unit controls a comparative display of a situation relating to the dead cell formation of a plurality of the fertilized eggs.
- the control device according to any one of (2) to (6).
- the culture condition includes fertilization of the fertilized egg, pronucleus, polar body, fragmentation, cell blastomere, compaction of morula, inner cell mass, trophectoderm, zona pellucida, and the situation related to the zona pellucida, The control device according to any one of (2) to (7).
- the display control unit controls time series display related to the culture state of the fertilized egg, The control device according to any one of (2) to (8).
- the display control unit controls time-series display of probability values related to the cleavage stage of the fertilized egg estimated based on the captured image.
- the display control unit controls the display of a probability waveform in which the probability value of the cleavage stage is interpolated between the times when the image is captured.
- (12) The display control unit controls the display related to the cleavage timing of the fertilized egg estimated based on the probability value;
- (13) The display control unit controls the display of the occurrence timing related to the abnormal cleavage of the fertilized egg estimated based on the probability value.
- the control device according to any one of (10) to (12).
- the display control unit controls the display related to the estimated cell resting period of the fertilized egg.
- the control device according to (9) above.
- the display control unit displays the culture state of the plurality of fertilized eggs in association with the physical position of the fertilized egg in a culture dish.
- the control device according to any one of (2) to (14).
- (16) A process for dynamically estimating the culture state of the culture target in time series by morphological analysis using a learned model generated based on a machine learning algorithm using the captured image of the culture target as an input Part, Further comprising The control device according to any one of (1) to (15).
- the cell having the division ability includes a fertilized egg,
- the processing unit outputs the probability values related to the cleavage stage of the fertilized egg in time series by the morphological analysis.
- the control device estimates the occurrence of abnormal cleavage of the fertilized egg based on a probability waveform obtained by interpolating the probability value of the cleavage stage between the time when the image was taken.
- the control device estimates the occurrence of abnormal cleavage of the fertilized egg based on a probability waveform obtained by interpolating the probability value of the cleavage stage between the time when the image was taken.
- the control device (19)
- the processing unit outputs the probability waveform based on a slope of the probability value learned based on the image photographed at a narrow interval.
- the control device according to (18).
- the learned model is a recognizer generated using learning data including an image obtained by photographing the culture object and information related to at least one of the shape, form, and structure of the culture object.
- the control device according to any one of (1) to (19).
- the processor controls the dynamic display of the culture status of the culture target, including cells with mitotic potential, estimated along the time series by morphological analysis using a learned model generated based on a machine learning algorithm
- Including Controlling the display is to control a comparison display of the culture status related to a plurality of the culture objects, Further including Control method.
- (22) Computer Display control that controls the dynamic display of the culture state of the culture target, including cells with mitotic potential, estimated along the time series by morphological analysis using a learned model generated based on a machine learning algorithm Part, With The display control unit controls a comparison display of the culture state related to a plurality of the culture objects.
- Control device Program to function as.
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Theoretical Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- General Engineering & Computer Science (AREA)
- Biomedical Technology (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Zoology (AREA)
- Wood Science & Technology (AREA)
- Organic Chemistry (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Data Mining & Analysis (AREA)
- Analytical Chemistry (AREA)
- Biotechnology (AREA)
- Public Health (AREA)
- Software Systems (AREA)
- Artificial Intelligence (AREA)
- Sustainable Development (AREA)
- Biochemistry (AREA)
- Evolutionary Computation (AREA)
- Microbiology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Genetics & Genomics (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Databases & Information Systems (AREA)
- Pathology (AREA)
- Epidemiology (AREA)
- Primary Health Care (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Computational Linguistics (AREA)
- Quality & Reliability (AREA)
- Radiology & Medical Imaging (AREA)
- Human Computer Interaction (AREA)
- Cell Biology (AREA)
- Computer Hardware Design (AREA)
Abstract
Description
1.実施形態
1.1.概要
1.2.構成例
1.3.機能の詳細
1.4.動作の流れ
2.ハードウェア構成例
3.まとめ
<<1.1.概要>>
まず、本開示の一実施形態の概要について説明する。上述したように、近年、種々の分野において、細胞などの培養対象を時系列に沿って撮影し(タイムラプス撮影、とも称する)、当該細胞の経時変化を観察する手法が広く行われている。
少なくとも概念的に含む。ここで、単一の細胞または複数の細胞の集合体は、卵母細胞(oocyte)、卵子(eggまたはovum)、受精卵(fertile ovumまたはzygote)、未分化胚芽細胞(blastocyst)、胚(embryo)を含む受精卵の成長過程の一または複数のステージで観察される細胞に関連するものである。
次に、本実施形態に係る制御システムの構成例について説明する。図2は、本実施形態に係る制御システムの機能構成例を示すブロック図である。図2を参照すると、本実施形態に係る制御システムは、撮影装置10、制御装置20、および表示装置30を備える。また、撮影装置10と制御装置20、制御装置20と表示装置30は、互いに通信が行えるようにネットワーク40を介して接続される。
本実施形態に係る撮影装置10は、制御装置20による制御に基づいて、受精卵などの培養対象を撮影する装置である。本実施形態に係る撮影装置10は、例えば、撮影機能を有する光学顕微鏡などであってよい。
本実施形態に係る撮影部110は、制御装置20による制御に基づいて、培養対象を撮影する機能を有する。本実施形態に係る撮影部110は、例えば、カメラなどの撮影装置により実現される。また、撮影部110は、倍率の異なる複数の光学対物レンズを備えてもよい。
本実施形態に係る保持部120は、培養対象が培養される培養ディッシュを保持する機能を有する。本実施形態に係る保持部120は、例えば、観察ステージで有り得る。
((照射部130))
本実施形態に係る照射部130は、制御装置20による制御に基づいて、撮影に用いられる各種の光を照射する機能を有する。また、本実施形態に係る照射部130には、しぼりなどの光学系が広く含まれてもよい。
本実施形態に係る制御装置20は、機械学習アルゴリズムに基づいて生成された学習済みモデルを用いて算出した培養対象の認識確率に基づいて、培養対象の撮影を制御する機能を有する。本実施形態に係る制御装置20は、例えば、情報処理サーバとして実装され、ネットワーク40を介して撮影装置10を遠隔的に制御してもよい。
本実施形態に係る撮影制御部210は、撮影装置10による培養対象のタイムラプス撮影を制御する機能を有する。本実施形態に係る撮影制御部210は、機械学習アルゴリズムに基づいて生成された学習済みモデルを用いて算出された観察対象の認識確率に基づいて、撮影部110と観察対象の相対的な水平位置や焦点位置などを制御することを特徴の一つとする。
本実施形態に係る学習部220は、培養対象が撮影された画像と機械学習アルゴリズムとに基づいて観察対象の認識などに係る学習を行う機能を有する。本実施形態に係る学習部220は、例えば、複数のConvolutionレイヤーを含んで構成されるDeep Learningなどの多層ニューラルネットワークによる機械学習により観察対象の認識学習を行ってもよい。
本実施形態に係る処理部230は、学習部220により学習された学習知識に基づいて、培養対象の形態解析を行う機能を有する。すなわち、本実施形態に係る処理部230は、学習部220による学習により生成される認識器(または分類器とも呼ぶ)であってよい。本実施形態に係る処理部230は、例えば、培養対象の画像を入力とし、機械学習アルゴリズムに基づいて生成された学習済みモデルを用いた形態解析により、受精卵の卵割段階に係る確率値を時系列に出力することができる。本実施形態に係る処理部230が有する機能の詳細については、別途後述する。
本実施形態に係る表示制御部240は、処理部230が形態解析により時系列に沿って推定した培養対象の培養状況に係る動的な表示を制御する機能を有する。本実施形態に係る表示制御部240は、特に、複数の培養対象に係る培養状況の比較表示を制御してよい。
本実施形態に係る通信部250は、ネットワーク40を介して、撮影装置10や表示装置30との情報通信を行う機能を有する。本実施形態に係る通信部250は、例えば、撮影制御部210が生成した撮影制御に係る制御信号を撮影装置10に送信し、撮影装置10から、撮影された培養対象の画像を受信する。また、本実施形態に係る通信部250は、表示制御部240が生成したユーザインタフェースの表示制御に係る制御情報を表示装置30に送信する。
本実施形態に係る表示装置30は、制御装置20による制御に基づいて、複数の培養対象に係る培養状況の比較表示を行う装置である。
本実施形態に係る表示部310は、画像やテキストなどの視覚情報を出力する機能を有する。本実施形態に係る表示部310は、特に、制御装置20から受信した制御情報に基づいて、ユーザが培養対象の培養状況を確認するためのユーザインタフェースを表示する。一方で、本実施形態に係る表示部310は、制御装置20の表示制御部240と同等の機能を有してもよい。この場合、表示部310は、制御装置20の処理部230が出力する各種の認識結果を受信し、当該認識結果に基づいて、ユーザインタフェースの表示を制御することができる。
ネットワーク40は、撮影装置10と制御装置20とを接続する機能を有する。ネットワーク40は、インターネット、電話回線網、衛星通信網などの公衆回線網や、Ethernet(登録商標)を含む各種のLAN(Local Area Network)、WAN(Wide Area Network)などを含んでもよい。また、ネットワーク40は、IP-VPN(Internet Protocol-Virtual Private Network)などの専用回線網を含んでもよい。また、ネットワーク40は、Wi-Fi(登録商標)、Bluetooth(登録商標)など無線通信網を含んでもよい。
次に、本実施形態に係る制御装置20が有する機能について詳細に説明する。まず、本実施形態に係る表示制御部240による培養状況の比較表示制御について述べる。
Mass, ICM)や栄養外胚葉(Trophectoderm, TE)の出現の状況、透明帯(zona)の厚さや破れ(hatching)の状況などを含んでよい。
次に、本実施形態に係る制御装置20の動作の流れについて詳細に説明する。図22は、本実施形態に係る制御装置20の動作の流れを示すフローチャートの一例である。なお、以下では、本実施形態に係る培養対象が受精卵であり、処理部230が、受精卵の卵割段階や異常卵割の発生を推定する場合を例に述べる。
次に、本開示の一実施形態に係る制御装置20のハードウェア構成例について説明する。図23は、本開示の一実施形態に係る制御装置20のハードウェア構成例を示すブロック図である。図23を参照すると、制御装置20は、例えば、プロセッサ871と、ROM872と、RAM873と、ホストバス874と、ブリッジ875と、外部バス876と、インターフェース877と、入力装置878と、出力装置879と、ストレージ880と、ドライブ881と、接続ポート882と、通信装置883と、を有する。なお、ここで示すハードウェア構成は一例であり、構成要素の一部が省略されてもよい。また、ここで示される構成要素以外の構成要素をさらに含んでもよい。
プロセッサ871は、例えば、演算処理装置又は制御装置として機能し、ROM872、RAM873、ストレージ880、又はリムーバブル記録媒体901に記録された各種プログラムに基づいて各構成要素の動作全般又はその一部を制御する。
ROM872は、プロセッサ871に読み込まれるプログラムや演算に用いるデータ等を格納する手段である。RAM873には、例えば、プロセッサ871に読み込まれるプログラムや、そのプログラムを実行する際に適宜変化する各種パラメータ等が一時的又は永続的に格納される。
プロセッサ871、ROM872、RAM873は、例えば、高速なデータ伝送が可能なホストバス874を介して相互に接続される。一方、ホストバス874は、例えば、ブリッジ875を介して比較的データ伝送速度が低速な外部バス876に接続される。また、外部バス876は、インターフェース877を介して種々の構成要素と接続される。
入力装置878には、例えば、マウス、キーボード、タッチパネル、ボタン、スイッチ、及びレバー等が用いられる。さらに、入力装置878としては、赤外線やその他の電波を利用して制御信号を送信することが可能なリモートコントローラ(以下、リモコン)が用いられることもある。また、入力装置878には、マイクロフォンなどの音声入力装置が含まれる。
出力装置879は、例えば、CRT(Cathode Ray Tube)、LCD、又は有機EL等のディスプレイ装置、スピーカ、ヘッドホン等のオーディオ出力装置、プリンタ、携帯電話、又はファクシミリ等、取得した情報を利用者に対して視覚的又は聴覚的に通知することが可能な装置である。また、本開示に係る出力装置879は、触覚刺激を出力することが可能な種々の振動デバイスを含む。
ストレージ880は、各種のデータを格納するための装置である。ストレージ880としては、例えば、ハードディスクドライブ(HDD)等の磁気記憶デバイス、半導体記憶デバイス、光記憶デバイス、又は光磁気記憶デバイス等が用いられる。
ドライブ881は、例えば、磁気ディスク、光ディスク、光磁気ディスク、又は半導体メモリ等のリムーバブル記録媒体901に記録された情報を読み出し、又はリムーバブル記録媒体901に情報を書き込む装置である。
リムーバブル記録媒体901は、例えば、DVDメディア、Blu-ray(登録商標)メディア、HD DVDメディア、各種の半導体記憶メディア等である。もちろん、リムーバブル記録媒体901は、例えば、非接触型ICチップを搭載したICカード、又は電子機器等であってもよい。
接続ポート882は、例えば、USB(Universal Serial Bus)ポート、IEEE1394ポート、SCSI(Small Computer System Interface)、RS-232Cポート、又は光オーディオ端子等のような外部接続機器902を接続するためのポートである。
外部接続機器902は、例えば、プリンタ、携帯音楽プレーヤ、デジタルカメラ、デジタルビデオカメラ、又はICレコーダ等である。
通信装置883は、ネットワークに接続するための通信デバイスであり、例えば、有線又は無線LAN、Bluetooth(登録商標)、又はWUSB(Wireless USB)用の通信カード、光通信用のルータ、ADSL(Asymmetric Digital Subscriber Line)用のルータ、又は各種通信用のモデム等である。
以上説明したように、本開示の一実施形態に係る制御装置20は、機械学習アルゴリズムに基づいて生成された学習済みモデルを用いた形態解析により時系列に沿って推定された、分裂能を有する細胞を含む培養対象の培養状況に係る動的な表示を制御する表示制御部240を備える。また、本開示の一実施形態に係る表示制御部240は、複数の培養対象に係る培養状況の比較表示を制御すること、を特徴の一つとする。係る構成によれば、複数の培養対象に係る培養状況を効果的に可視化することが可能となる。
(1)
機械学習アルゴリズムに基づいて生成された学習済みモデルを用いた形態解析により時系列に沿って推定された、分裂能を有する細胞を含む培養対象の培養状況に係る動的な表示を制御する表示制御部、
を備え、
前記表示制御部は、複数の前記培養対象に係る前記培養状況の比較表示を制御する、
制御装置。
(2)
前記分裂能を有する細胞は、受精卵を含む、
前記(1)に記載の制御装置。
(3)
前記培養状況は、卵割状況を含み、
前記表示制御部は、複数の前記受精卵の前記卵割状況に係る比較表示を制御する、
前記(2)に記載の制御装置。
(4)
前記卵割状況は、卵割段階を含み、
前記表示制御部は、複数の受前記精卵の前記卵割段階に係る比較表示する、
前記(3)に記載の制御装置。
(5)
前記卵割状況は、異常卵割の発生状況を含み、
前記表示制御部は、複数の前記受精卵の前記異常卵割の発生状況に係る比較表示を制御する、
前記(3)または(4)に記載の制御装置。
(6)
前記異常卵割は、ダイレクトクリアベージまたはリバースクリアベージのうち少なくともいずれかを含む、
前記(5)に記載の制御装置。
(7)
前記培養状況は、前記受精卵の死細胞化に係る状況を含み、
前記表示制御部は、複数の前記受精卵の前記死細胞化に係る状況の比較表示を制御する、
前記(2)~(6)のいずれかに記載の制御装置。
(8)
前記培養状況は、前記受精卵の受精、前核、極体、フラグメンテーション、細胞割球、桑実胚のコンパクション、内細胞塊、栄養外胚葉、透明帯のうち少なくともいずれかに係る状況を含む、
前記(2)~(7)のいずれかに記載の制御装置。
(9)
前記表示制御部は、前記受精卵の培養状況に係る時系列表示を制御する、
前記(2)~(8)のいずれかに記載の制御装置。
(10)
前記表示制御部は、撮影された画像に基づいて推定された前記受精卵の卵割段階に係る確率値の時系列表示を制御する、
前記(9)に記載の制御装置。
(11)
前記表示制御部は、前記画像が撮影された時刻間における前記卵割段階の前記確率値が補間された確率波形の表示を制御する、
前記(10)に記載の制御装置。
(12)
前記表示制御部は、前記確率値に基づいて推定された前記受精卵の卵割タイミングに係る表示を制御する、
前記(10)または(11)に記載の制御装置。
(13)
前記表示制御部は、前記確率値に基づいて推定された前記受精卵の異常卵割に係る発生タイミングの表示を制御する、
前記(10)~(12)のいずれかに記載の制御装置。
(14)
前記表示制御部は、推定された前記受精卵の細胞休止期に係る表示を制御する、
前記(9)に記載の制御装置。
(15)
前記表示制御部は、複数の前記受精卵の培養状況を、培養ディッシュにおける前記受精卵の物理位置と対応づけて表示させる、
前記(2)~(14)のいずれかに記載の制御装置。
(16)
撮像された前記培養対象の画像を入力とし、機械学習アルゴリズムに基づいて生成された学習済みモデルを用いた形態解析により、前記培養対象の前記培養状況を時系列に沿って動的に推定する処理部、
をさらに備える、
前記(1)~(15)のいずれかに記載の制御装置。
(17)
前記分裂能を有する細胞は、受精卵を含み、
前記処理部は、前記形態解析により、前記受精卵の卵割段階に係る確率値を時系列に出力する、
前記(16)に記載の制御装置。
(18)
前記処理部は、前記画像が撮影された時刻間における前記卵割段階の前記確率値を補間した確率波形に基づいて、前記受精卵の異常卵割の発生を推定する、
前記(17)に記載の制御装置。
(19)
前記処理部は、狭間隔で撮影された前記画像に基づいて学習された前記確率値の傾きに基づいて前記確率波形を出力する、
前記(18)に記載の制御装置。
(20)
前記学習済みモデルは、前記培養対象を撮影した画像と、前記培養対象の形状、形態、構造のうち少なくとも一つに係る特徴に関する情報とを含む学習データを用いて生成された認識器である、
前記(1)~(19)に記載の制御装置。
(21)
プロセッサが、機械学習アルゴリズムに基づいて生成された学習済みモデルを用いた形態解析により時系列に沿って推定された、分裂能を有する細胞を含む培養対象の培養状況に係る動的な表示を制御すること、
を含み、
前記表示を制御することは、複数の前記培養対象に係る前記培養状況の比較表示を制御すること、
をさらに含む、
制御方法。
(22)
コンピュータを、
機械学習アルゴリズムに基づいて生成された学習済みモデルを用いた形態解析により時系列に沿って推定された、分裂能を有する細胞を含む培養対象の培養状況に係る動的な表示を制御する表示制御部、
を備え、
前記表示制御部は、複数の前記培養対象に係る前記培養状況の比較表示を制御する、
制御装置、
として機能させるためのプログラム。
110 撮影部
120 保持部
130 照射部
20 制御装置
210 撮影制御部
220 学習部
230 処理部
240 表示制御部
250 通信部
30 表示装置
310 表示部
Claims (22)
- 機械学習アルゴリズムに基づいて生成された学習済みモデルを用いた形態解析により時系列に沿って推定された、分裂能を有する細胞を含む培養対象の培養状況に係る動的な表示を制御する表示制御部、
を備え、
前記表示制御部は、複数の前記培養対象に係る前記培養状況の比較表示を制御する、
制御装置。 - 前記分裂能を有する細胞は、受精卵を含む、
請求項1に記載の制御装置。 - 前記培養状況は、卵割状況を含み、
前記表示制御部は、複数の前記受精卵の前記卵割状況に係る比較表示を制御する、
請求項2に記載の制御装置。 - 前記卵割状況は、卵割段階を含み、
前記表示制御部は、複数の受前記精卵の前記卵割段階に係る比較表示を制御する、
請求項3に記載の制御装置。 - 前記卵割状況は、異常卵割の発生状況を含み、
前記表示制御部は、複数の前記受精卵の前記異常卵割の発生状況に係る比較表示を制御する、
請求項3に記載の制御装置。 - 前記異常卵割は、ダイレクトクリベージまたはリバースクリベージのうち少なくともいずれかを含む、
請求項5に記載の制御装置。 - 前記培養状況は、前記受精卵の死細胞化に係る状況を含み、
前記表示制御部は、複数の前記受精卵の前記死細胞化に係る状況の比較表示を制御する、
請求項2に記載の制御装置。 - 前記培養状況は、前記受精卵の受精、前核、極体、フラグメンテーション、細胞割球、桑実胚のコンパクション、内細胞塊、栄養外胚葉、透明帯のうち少なくともいずれかに係る状況を含む、
請求項2に記載の制御装置。 - 前記表示制御部は、前記受精卵の培養状況に係る時系列表示を制御する、
請求項2に記載の制御装置。 - 前記表示制御部は、撮影された画像に基づいて推定された前記受精卵の卵割段階に係る確率値の時系列表示を制御する、
請求項9に記載の制御装置。 - 前記表示制御部は、前記画像が撮影された時刻間における前記卵割段階の前記確率値が補間された確率波形の表示を制御する、
請求項10に記載の制御装置。 - 前記表示制御部は、前記確率値に基づいて推定された前記受精卵の卵割タイミングに係る表示を制御する、
請求項10に記載の制御装置。 - 前記表示制御部は、前記確率値に基づいて推定された前記受精卵の異常卵割に係る発生タイミングの表示を制御する、
請求項10に記載の制御装置。 - 前記表示制御部は、推定された前記受精卵の細胞休止期に係る表示を制御する、
請求項9に記載の制御装置。 - 前記表示制御部は、複数の前記受精卵の培養状況を、培養ディッシュにおいて前記受精卵が配置されるウェルの位置と対応づけて表示させる、
請求項2に記載の制御装置。 - 撮像された前記培養対象の画像を入力とし、機械学習アルゴリズムに基づいて生成された学習済みモデルを用いた形態解析により、前記培養対象の前記培養状況を時系列に沿って動的に推定する処理部、
をさらに備える、
請求項1に記載の制御装置。 - 前記分裂能を有する細胞は、受精卵を含み、
前記処理部は、前記形態解析により、前記受精卵の卵割段階に係る確率値を時系列に出力する、
請求項16に記載の制御装置。 - 前記処理部は、前記画像が撮影された時刻間における前記卵割段階の前記確率値を補間した確率波形に基づいて、前記受精卵の異常卵割の発生を推定する、
請求項17に記載の制御装置。 - 前記処理部は、狭間隔で撮影された前記画像に基づいて学習された前記確率値の傾きに基づいて前記確率波形を出力する、
請求項18に記載の制御装置。 - 前記学習済みモデルは、前記培養対象を撮影した画像と、前記培養対象の形状、形態、構造のうち少なくとも一つに係る特徴に関する情報とを含む学習データを用いて生成された認識器である、
請求項1に記載の制御装置。 - プロセッサが、機械学習アルゴリズムに基づいて生成された学習済みモデルを用いた形態解析により時系列に沿って推定された、分裂能を有する細胞を含む培養対象の培養状況に係る動的な表示を制御すること、
を含み、
前記表示を制御することは、複数の前記培養対象に係る前記培養状況の比較表示を制御すること、
をさらに含む、
制御方法。 - コンピュータを、
機械学習アルゴリズムに基づいて生成された学習済みモデルを用いた形態解析により時系列に沿って推定された、分裂能を有する細胞を含む培養対象の培養状況に係る動的な表示を制御する表示制御部、
を備え、
前記表示制御部は、複数の前記培養対象に係る前記培養状況の比較表示を制御する、
制御装置、
として機能させるためのプログラム。
Priority Applications (6)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
JP2020521075A JP7420069B2 (ja) | 2018-05-25 | 2019-04-05 | 制御装置、制御方法、およびプログラム |
BR112020023511-3A BR112020023511A2 (pt) | 2018-05-25 | 2019-04-05 | Dispositivo de controle, método de controle, e, programa. |
AU2019273148A AU2019273148A1 (en) | 2018-05-25 | 2019-04-05 | Control device, control method, and program |
US17/056,730 US11521320B2 (en) | 2018-05-25 | 2019-04-05 | Control device, control method, and program |
EP19806384.4A EP3786277A4 (en) | 2018-05-25 | 2019-04-05 | CONTROL DEVICE, CONTROL METHOD AND PROGRAM |
CN201980032481.5A CN112119152A (zh) | 2018-05-25 | 2019-04-05 | 控制装置、控制方法和程序 |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
JP2018100358 | 2018-05-25 | ||
JP2018-100358 | 2018-05-25 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2019225176A1 true WO2019225176A1 (ja) | 2019-11-28 |
Family
ID=68615571
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/JP2019/015202 WO2019225176A1 (ja) | 2018-05-25 | 2019-04-05 | 制御装置、制御方法、およびプログラム |
Country Status (7)
Country | Link |
---|---|
US (1) | US11521320B2 (ja) |
EP (1) | EP3786277A4 (ja) |
JP (1) | JP7420069B2 (ja) |
CN (1) | CN112119152A (ja) |
AU (1) | AU2019273148A1 (ja) |
BR (1) | BR112020023511A2 (ja) |
WO (1) | WO2019225176A1 (ja) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP6956302B1 (ja) * | 2021-01-20 | 2021-11-02 | 医療法人浅田レディースクリニック | 胚培養装置および培養環境に保持された処置卵を表示する方法 |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2013099045A1 (ja) * | 2011-12-28 | 2013-07-04 | 大日本スクリーン製造株式会社 | 画像表示装置および画像表示方法 |
JP2016509845A (ja) * | 2013-02-28 | 2016-04-04 | プロジェニー, インコーポレイテッド | 画像ベースのヒト胚細胞分類のための装置、方法、およびシステム |
JP2018022216A (ja) * | 2016-08-01 | 2018-02-08 | ソニー株式会社 | 情報処理装置、情報処理方法、及びプログラム |
Family Cites Families (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US9053222B2 (en) * | 2002-05-17 | 2015-06-09 | Lawrence A. Lynn | Patient safety processor |
JP5807288B2 (ja) * | 2010-06-30 | 2015-11-10 | 大日本印刷株式会社 | 体外培養による胚の製造方法、並びに胚を選別するための方法、装置、及びシステム |
WO2014085545A1 (en) * | 2012-11-30 | 2014-06-05 | The University Of Chicago | Methods and compositions involving rad51 inhibitors |
WO2015086132A1 (en) * | 2013-12-13 | 2015-06-18 | Merck Patent Gmbh | Assays and monitoring paradigms for stem cell culture |
JP6278491B2 (ja) * | 2014-07-11 | 2018-02-14 | Sbiファーマ株式会社 | 受精卵の正常発生率向上剤 |
ES2826400T3 (es) * | 2015-04-23 | 2021-05-18 | Bd Kiestra Bv | Recolección de contraste de colonias |
CN105505879B (zh) * | 2015-12-17 | 2017-12-05 | 广州元曦生物科技有限公司 | 一种培养转基因动物胚胎细胞或转基因动物的方法及培养基 |
JP7001060B2 (ja) | 2016-11-02 | 2022-01-19 | ソニーグループ株式会社 | 情報処理装置、情報処理方法及び情報処理システム |
-
2019
- 2019-04-05 AU AU2019273148A patent/AU2019273148A1/en not_active Abandoned
- 2019-04-05 CN CN201980032481.5A patent/CN112119152A/zh active Pending
- 2019-04-05 JP JP2020521075A patent/JP7420069B2/ja active Active
- 2019-04-05 EP EP19806384.4A patent/EP3786277A4/en active Pending
- 2019-04-05 BR BR112020023511-3A patent/BR112020023511A2/pt not_active Application Discontinuation
- 2019-04-05 US US17/056,730 patent/US11521320B2/en active Active
- 2019-04-05 WO PCT/JP2019/015202 patent/WO2019225176A1/ja active Application Filing
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2013099045A1 (ja) * | 2011-12-28 | 2013-07-04 | 大日本スクリーン製造株式会社 | 画像表示装置および画像表示方法 |
JP2016509845A (ja) * | 2013-02-28 | 2016-04-04 | プロジェニー, インコーポレイテッド | 画像ベースのヒト胚細胞分類のための装置、方法、およびシステム |
JP2018022216A (ja) * | 2016-08-01 | 2018-02-08 | ソニー株式会社 | 情報処理装置、情報処理方法、及びプログラム |
Non-Patent Citations (1)
Title |
---|
See also references of EP3786277A4 |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP6956302B1 (ja) * | 2021-01-20 | 2021-11-02 | 医療法人浅田レディースクリニック | 胚培養装置および培養環境に保持された処置卵を表示する方法 |
WO2022157855A1 (ja) * | 2021-01-20 | 2022-07-28 | 医療法人浅田レディースクリニック | 胚培養装置および培養環境に保持された処置卵を表示する方法 |
Also Published As
Publication number | Publication date |
---|---|
CN112119152A (zh) | 2020-12-22 |
US11521320B2 (en) | 2022-12-06 |
US20210201491A1 (en) | 2021-07-01 |
EP3786277A4 (en) | 2021-07-07 |
AU2019273148A1 (en) | 2020-12-10 |
JPWO2019225176A1 (ja) | 2021-07-08 |
JP7420069B2 (ja) | 2024-01-23 |
BR112020023511A2 (pt) | 2021-03-30 |
EP3786277A1 (en) | 2021-03-03 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
JP6911866B2 (ja) | 情報処理装置および情報処理方法 | |
JP7072067B2 (ja) | 胚の生存率を推定するためのシステムおよび方法 | |
US10430707B2 (en) | Information processing device | |
EP3404586A1 (en) | Novelty detection using discriminator of generative adversarial network | |
JP7001060B2 (ja) | 情報処理装置、情報処理方法及び情報処理システム | |
US9171477B2 (en) | Method and system for recognizing and assessing surgical procedures from video | |
US20210287366A1 (en) | Information processing apparatus, information processing method, program, and information processing system | |
US11017527B2 (en) | Information processing device, information processing method, and information processing system | |
JP6690489B2 (ja) | 情報処理装置、情報処理方法、およびプログラム | |
WO2019225176A1 (ja) | 制御装置、制御方法、およびプログラム | |
US20210200986A1 (en) | Control device, control method, and program | |
JP2020155101A (ja) | 情報処理装置及び情報処理方法 | |
Guarin et al. | The effect of improving facial alignment accuracy on the video-based detection of neurological diseases | |
CN113469001A (zh) | 一种基于深度学习的学生课堂行为检测方法 | |
US20230169754A1 (en) | Information processing device and program | |
WO2020139662A1 (en) | Method and apparatus for measuring plant trichomes | |
JPWO2019176012A1 (ja) | 画像処理方法、画像処理装置、ユーザインタフェース装置、画像処理システム、およびサーバ | |
WO2018012353A1 (en) | Information processing device, information processing method, and information processing system | |
US20220157295A1 (en) | Information processing apparatus and information processing method | |
US20230298357A1 (en) | Information processing device and information processing method | |
US20230004783A1 (en) | Evaluation framework for time series data | |
JP2022064460A (ja) | 学習モデル生成装置、学習モデル、行動認識装置、学習データ生成装置、及び、学習データ生成方法 | |
CN117314755A (zh) | 一种基于跨模态图像生成的多视角植株生成方法和装置 | |
CN118506075A (zh) | 内镜尖端控制分类模型、技能评分系统和方法 | |
CN116421224A (zh) | 一种基于超声心动图的特征图滤波的预测方法及装置 |
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: 19806384 Country of ref document: EP Kind code of ref document: A1 |
|
ENP | Entry into the national phase |
Ref document number: 2020521075 Country of ref document: JP Kind code of ref document: A |
|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
WWE | Wipo information: entry into national phase |
Ref document number: 2019806384 Country of ref document: EP |
|
ENP | Entry into the national phase |
Ref document number: 2019806384 Country of ref document: EP Effective date: 20201126 |
|
REG | Reference to national code |
Ref country code: BR Ref legal event code: B01A Ref document number: 112020023511 Country of ref document: BR |
|
ENP | Entry into the national phase |
Ref document number: 2019273148 Country of ref document: AU Date of ref document: 20190405 Kind code of ref document: A |
|
ENP | Entry into the national phase |
Ref document number: 112020023511 Country of ref document: BR Kind code of ref document: A2 Effective date: 20201118 |