Granted Patent B2

US 12,639,963 · App. 18/534,721 · Granted May 26, 2026

Inventor: Yasushi Shiraishi (Kanagawa, JP)

Assignee: FUJIFILM CORPORATION

G06V20/695C12M41/46G06V10/774G06V20/698G16B20/20

Abstract

Claims (89)

1 . An information processing apparatus that predicts a success or failure of differentiation of cells on the basis of a captured image obtained by imaging a cell population cultured in a cell-culture container, the information processing apparatus comprising:

at least one processor configured to:

extract a feature quantity based on an appearance of the cells by performing image processing on the captured image;

predict the success or failure of differentiation of the cells by comparing the extracted feature quantity with a determination criterion stored in a storage device, and output a prediction result; and

output an instruction for preventing a cell population predicted to have unsuccessful differentiation from being introduced into a differentiation induction process based on the prediction result,

wherein the image processing includes:

inputting the captured image into a trained model to generate an output image in which pixels are classified into classes including a cell nucleus, cytoplasm, and a culture medium;

detecting cell nuclei from the output image based on a result of the classification; and

extracting information related to the detected cell nuclei as the feature quantity.

2 . The information processing apparatus according to claim 1 , wherein the at least one processor is configured to predict the success or failure of differentiation of the cells on the basis of only the feature quantity based on the appearance of the cells.

3 . The information processing apparatus according to claim 1 , wherein the feature quantity includes a number of cells corresponding to a number of cell nuclei, an area of a cell nucleus, an area ratio between a cell nucleus and cytoplasm, or a proportion of a cell-occupied area in the cell-culture container.

4 . The information processing apparatus according to claim 1 , wherein the feature quantity includes an increase rate in a number of cells calculated on the basis of a plurality of captured images with different image-capturing times.

5 . The information processing apparatus according to claim 1 , wherein the at least one processor is configured to detect the cell nuclei from the captured image using a trained model obtained by performing machine learning using, as training data, a fluorescence image in which a cell nucleus is stained.

6 . The information processing apparatus according to claim 1 , wherein the at least one processor is configured to predict the success or failure of differentiation of the cells for each of a plurality of regions into which entirety of the cell-culture container is divided, by using, as the captured image, each of a plurality of region images obtained by imaging the plurality of regions.

7 . The information processing apparatus according to claim 6 , wherein the at least one processor is configured to calculate a ratio of an area for which differentiation is to be successful to a cell-culture area on the basis of prediction results about the success or failure of differentiation of the cells for the respective regions.

8 . The information processing apparatus according to claim 1 , wherein the cells are stem cells.

9 . The information processing apparatus according to claim 8 , wherein the stem cells are in an undifferentiated state.

10 . An information processing method for predicting a success or failure of differentiation of cells on the basis of a captured image obtained by imaging a cell population cultured in a cell-culture container, the information processing method comprising:

extracting a feature quantity based on an appearance of the cells by performing image processing on the captured image;

predicting the success or failure of differentiation of the cells by comparing the extracted feature quantity with a determination criterion stored in a storage device, and outputting a prediction result; and

outputting an instruction for preventing a cell population predicted to have unsuccessful differentiation from being introduced into a differentiation induction process based on the prediction result,

wherein the image processing includes:

inputting the captured image into a trained model to generate an output image in which pixels are classified into classes including a cell nucleus, cytoplasm, and a culture medium;

detecting cell nuclei from the output image based on a result of the classification; and

extracting information related to the detected cell nuclei as the feature quantity.

11 . A non-transitory computer-readable storage medium storing a program for causing a computer to execute a process of predicting a success or failure of differentiation of cells on the basis of a captured image obtained by imaging a cell population cultured in a cell-culture container, the process comprising:

extracting a feature quantity based on an appearance of the cells by performing image processing on the captured image;

predicting the success or failure of differentiation of the cells by comparing the extracted feature quantity with a determination criterion stored in a storage device, and outputting a prediction result; and

outputting an instruction for preventing a cell population predicted to have unsuccessful differentiation from being introduced into a differentiation induction process based on the prediction result,

wherein the image processing includes:

inputting the captured image into a trained model to generate an output image in which pixels are classified into classes including a cell nucleus, cytoplasm, and a culture medium;

detecting cell nuclei from the output image based on a result of the classification; and

extracting information related to the detected cell nuclei as the feature quantity.

12 . An information processing apparatus that predicts a success or failure of differentiation of cells on the basis of a captured image obtained by imaging a cell population cultured in a cell-culture container, the information processing apparatus comprising:

at least one processor configured to:

extract a feature quantity based on an appearance of the cells by performing image processing on the captured image;

predict the success or failure of differentiation of the cells by comparing the extracted feature quantity with a determination criterion stored in a storage device, and output a prediction result; and

output an instruction for preventing a cell population predicted to have unsuccessful differentiation from being introduced into a differentiation induction process based on the prediction result,

wherein the image processing includes:

inputting the captured image into a trained model to generate an output image in which pixels are classified into classes including a cell nucleus, cytoplasm, and a culture medium; and

extracting the feature quantity based on the output image,

wherein the at least one processor is further configured to:

predict the success or failure of differentiation of the cells for each of a plurality of regions into which entirety of the cell-culture container is divided, by using, as the captured image, each of a plurality of region images obtained by imaging the plurality of regions; and

calculate a ratio of an area for which differentiation is to be successful to a cell-culture area on the basis of prediction results about the success or failure of differentiation of the cells for the respective regions.

13 . An information processing apparatus that predicts a success or failure of differentiation of cells on the basis of a captured image obtained by imaging a cell population cultured in a cell-culture container, the information processing apparatus comprising:

at least one processor configured to:

extract a feature quantity based on an appearance of the cells by performing image processing on the captured image;

predict the success or failure of differentiation of the cells by comparing the extracted feature quantity with a determination criterion stored in a storage device, and output a prediction result; and

output an instruction for preventing a cell population predicted to have unsuccessful differentiation from being introduced into a differentiation induction process based on the prediction result,

wherein the image processing includes:

inputting the captured image into a trained model to generate an output image in which pixels are classified into classes including a cell nucleus, cytoplasm, and a culture medium; and

extracting the feature quantity based on the output image,

wherein the cells are stem cells in an undifferentiated state.

14 . An information processing method for predicting a success or failure of differentiation of cells on the basis of a captured image obtained by imaging a cell population cultured in a cell-culture container, the information processing method comprising:

extracting a feature quantity based on an appearance of the cells by performing image processing on the captured image;

predicting the success or failure of differentiation of the cells by comparing the extracted feature quantity with a determination criterion stored in a storage device, and outputting a prediction result; and

outputting an instruction for preventing a cell population predicted to have unsuccessful differentiation from being introduced into a differentiation induction process based on the prediction result,

wherein the image processing includes:

inputting the captured image into a trained model to generate an output image in which pixels are classified into classes including a cell nucleus, cytoplasm, and a culture medium; and

extracting the feature quantity based on the output image,

wherein the information processing method further comprises:

predicting the success or failure of differentiation of the cells for each of a plurality of regions into which entirety of the cell-culture container is divided, by using, as the captured image, each of a plurality of region images obtained by imaging the plurality of regions; and

calculating a ratio of an area for which differentiation is to be successful to a cell-culture area on the basis of prediction results about the success or failure of differentiation of the cells for the respective regions.

15 . An information processing method for predicting a success or failure of differentiation of cells on the basis of a captured image obtained by imaging a cell population cultured in a cell-culture container, the information processing method comprising:

extracting a feature quantity based on an appearance of the cells by performing image processing on the captured image;

predicting the success or failure of differentiation of the cells by comparing the extracted feature quantity with a determination criterion stored in a storage device, and outputting a prediction result; and

outputting an instruction for preventing a cell population predicted to have unsuccessful differentiation from being introduced into a differentiation induction process based on the prediction result,

wherein the image processing includes:

inputting the captured image into a trained model to generate an output image in which pixels are classified into classes including a cell nucleus, cytoplasm, and a culture medium; and

extracting the feature quantity based on the output image,

wherein the cells are stem cells in an undifferentiated state.

16 . A non-transitory computer-readable storage medium storing a program for causing a computer to execute a process of predicting a success or failure of differentiation of cells on the basis of a captured image obtained by imaging a cell population cultured in a cell-culture container, the process comprising:

extracting a feature quantity based on an appearance of the cells by performing image processing on the captured image;

predicting the success or failure of differentiation of the cells by comparing the extracted feature quantity with a determination criterion stored in a storage device, and outputting a prediction result; and

outputting an instruction for preventing a cell population predicted to have unsuccessful differentiation from being introduced into a differentiation induction process based on the prediction result,

wherein the image processing includes:

inputting the captured image into a trained model to generate an output image in which pixels are classified into classes including a cell nucleus, cytoplasm, and a culture medium; and

extracting the feature quantity based on the output image,

wherein the process further comprises:

predicting the success or failure of differentiation of the cells for each of a plurality of regions into which entirety of the cell-culture container is divided, by using, as the captured image, each of a plurality of region images obtained by imaging the plurality of regions; and

calculating a ratio of an area for which differentiation is to be successful to a cell-culture area on the basis of prediction results about the success or failure of differentiation of the cells for the respective regions.

17 . A non-transitory computer-readable storage medium storing a program for causing a computer to execute a process of predicting a success or failure of differentiation of cells on the basis of a captured image obtained by imaging a cell population cultured in a cell-culture container, the process comprising:

extracting a feature quantity based on an appearance of the cells by performing image processing on the captured image;

predicting the success or failure of differentiation of the cells by comparing the extracted feature quantity with a determination criterion stored in a storage device, and outputting a prediction result; and

outputting an instruction for preventing a cell population predicted to have unsuccessful differentiation from being introduced into a differentiation induction process based on the prediction result,

wherein the image processing includes:

inputting the captured image into a trained model to generate an output image in which pixels are classified into classes including a cell nucleus, cytoplasm, and a culture medium; and

extracting the feature quantity based on the output image,

wherein the cells are stem cells in an undifferentiated state.

Assignments (1)

Priority Claims (1)

Continuity (2)

References Cited (27)