Processing

Please wait...

Settings

Settings

Goto Application

1. WO2020112723 - SYSTEMS AND METHODS FOR FACILITATING CLONE SELECTION

Note: Text based on automatic Optical Character Recognition processes. Please use the PDF version for legal matters

[ EN ]

What is claimed is:

1. A method for facilitating clone selection, the method comprising:

generating, by a first imaging unit, a plurality of time-sequence images of a well containing a medium, the plurality of time-sequence images including a first time-sequence image generated at a first time and a second time-sequence image generated at a second time later than the first time;

detecting, by one or more processors analyzing the first time-sequence image, one or more candidate objects depicted in the first time-sequence image;

for each of the one or more candidate objects, determining, by the one or more processors analyzing an image of the candidate object using a convolutional neural network, whether the candidate object is a single cell;

detecting, by the one or more processors analyzing the second time-sequence image, a cell colony depicted in the second time-sequence image;

determining, by the one or more processors, whether the cell colony was formed from only one cell based at least in part on whether each of the one or more candidate objects was determined to be a single cell; and

generating, by the one or more processors, output data indicating whether the cell colony was formed from only one cell.

2. The method of claim 1, wherein:

the method comprises determining, using the convolutional neural network, that a first candidate object of the one or more candidate objects is a single cell; and

determining whether the cell colony was formed from only one cell further comprises comparing a position of the first candidate object within the well to a position of the cell colony within the well.

3. The method of claim 1 or 2, wherein:

the plurality of time-sequence images further includes a third time-sequence image generated at a third time between the first time and the second time;

the method comprises determining, using the convolutional neural network, that a first candidate object of the one or more candidate objects is a single cell; and

determining whether the cell colony was formed from only one cell further comprises determining, by analyzing at least the third time-sequence image, whether the first candidate object developed into the cell colony.

4. The method of claim 3, wherein determining whether the first candidate object developed into the cell colony includes determining whether the third time-sequence image depicts an intermediate cell colony having one or both of (i) a smaller cell count than the cell colony, or (ii) a smaller size than that cell colony.

5. The method of claim 3, wherein determining whether the first candidate object developed into the cell colony includes (i) determining that the third time-sequence image depicts the intermediate cell colony, and (ii) comparing a position of the intermediate cell colony within the well to a position of the cell colony within the well and/or a position of the first candidate object within the well.

6. The method of any one of claims 1-5, wherein:

the first imaging unit generates the plurality of time-sequence images at a first magnification level;

the method further comprises, for each of the one or more candidate objects depicted in the first time-sequence image, generating, by a second imaging unit providing a second magnification level greater than the first magnification level, a zoomed-in image of a portion of the well that contains the candidate object; and

determining whether the candidate object is a single cell includes determining, by analyzing the zoomed-in image using the convolutional neural network, whether the candidate object is a single cell.

7. The method of claim 6, wherein generating the zoomed-in image includes shifting the well such that the well is aligned with an optical path of the second imaging unit

8. The method of any one of claims 1-7, wherein determining whether the candidate object is a single cell includes using the convolutional neural network to classify the candidate object as one of a plurality of possible object types, the plurality of object types including a type corresponding to a single cell.

9. The method of any one of claims 1-8, wherein detecting the cell colony depicted in the second time-sequence image includes processing the second time-sequence image using another convolutional neural network

10. The method of any one of claims 1-9, wherein:

the method comprises determining that the cell colony was formed from only one cell; and

the method further comprises transporting a cell from the well to a new culture environment; and culturing the cell in the new culture environment.

1 1. The method of any one of claims 1-9, wherein:

the method comprises determining that the cell colony was formed from only one cell; and

the method further comprises using contents of the well to develop a cell line for producing a biopharmaceutical product

12. The method of any one of claims 1-1 1 , wherein:

the method comprises determining that the cell colony was not formed from only one cell; and

the method further comprises discarding contents of the well.

13. One or more non-transitory computer-readable media storing instructions that, when executed by one or more processors, cause the one or more processors to:

receive a plurality of time-sequence images of a well containing a medium, the plurality of time-sequence images being generated by a first imaging unit, and including a first time-sequence image generated at a first time and a second time-sequence image generated at a second time later than the first time;

detect, by analyzing the first time-sequence image, one or more candidate objects depicted in the first time-sequence image;

for each of the one or more candidate objects, determine, by analyzing an image of the candidate object using a convolutional neural network, whether the candidate object is a single cell;

detect, by analyzing the second time-sequence image, a cell colony depicted in the second time-sequence image; determine whether the cell colony was formed from only one cell based at least in part on whether each of the one or more candidate objects was determined to be a single cell; and

generate output data indicating whether the cell colony was formed from only one cell.

14. The one or more non-transitory computer-readable media of claim 13, wherein the instructions cause the one or more processors to:

when determining that a first candidate object is a single cell, determine, by comparing a position of the first candidate object within the well to a position of the cell colony within the well, whether the first candidate object developed into the cell colony.

15. The one or more non-transitory computer-readable media of any one of claims 13-14, wherein the plurality of time-sequence images further includes a third time-sequence image generated at a third time between the first time and the second time, and wherein the instructions cause the one or more processors to:

when determining whether the cell colony was formed from only one cell, determine, by analyzing at least the third time-sequence image, whether the first candidate object developed into the cell colony.

16. The one or more non-transitory computer-readable media of any one of claims 13-15, wherein:

the plurality of time-sequence images being generated by the first imaging unit are generated at a first magnification

the instructions further cause the one or more processors to, for at least one of the one or more candidate objects, receive a zoomed-in image of a portion of the well that contains the candidate object, the zoomed-in image being generated at a second magnification level greater than the first magnification level; and

the instructions cause the one or more processors to determine, by analyzing the zoomed-in image using the convolutional neural network, whether the candidate object is a single cell.

17. The one or more non-transitory computer-readable media of claim 16, wherein the zoomed-in image is generated by a second imaging unit, wherein the instructions further cause the one or more processors to instruct a stage comprising the well disposed thereon to align the well with an optical path of the second imaging unit.

18. The one or more non-transitory computer-readable media of any one of claims 13-17, wherein the output data either (i) indicates that contents of the well can be used to develop a cell line for producing a biopharmaceutical product, or (ii) indicates that contents of the well should be discarded.

19. A system comprising:

a visual inspection system including

a stage configured to accept a well plate, and

a first imaging unit configured to generate images of wells within the well plate on the stage, wherein each image corresponds to a single well; and

a computer system including

one or more processors, and

one or more memories storing instructions that, when executed by the one or more processors, cause the computer system to

command the first imaging unit to generate a plurality of time-sequence images of a well containing a medium, the plurality of time-sequence images including a first time-sequence image generated at a first time and a second time-sequence image generated at a second time later than the first time,

detect, by analyzing the first time-sequence image, one or more candidate objects depicted in the first time-sequence image,

for each of the one or more candidate objects, determine, by analyzing an image of the candidate object using a convolutional neural network, whether the candidate object is a single cell, detect, by analyzing the second time-sequence image, a cell colony depicted in the second time- sequence image,

determine whether the cell colony was formed from only one cell based at least in part on whether each of the one or more candidate objects was determined to be a single cell, and

generate output data indicating whether the cell colony was formed from only one cell.

20. The system of claim 19, wherein the instructions cause the computer system to:

when determining that a first candidate object is a single cell, determine, by comparing a position of the first candidate object within the well to a position of the cell colony within the well, whether the first candidate object developed into the cell colony.

21. The system of any one of claims 19-20, wherein the plurality of time-sequence images further includes a third time-sequence image generated at a third time between the first time and the second time, and wherein the instructions cause the computer system to:

when determining whether the cell colony was formed from only one cell, determine, by analyzing at least the third time-sequence image, whether the first candidate object developed into the cell colony.

22. The system of any one of claims 19-21 , wherein:

the first imaging unit is configured to generate the plurality of time-sequence images at a first magnification level; the visual inspection system further comprises a second imaging unit configured to generate zoomed-in images of portions of the wells within the well plate;

the second imaging unit provides a second magnification level greater than the first magnification level;

the instructions further cause the computer system to, for each of at least one of the one or more candidate objects, command the second imaging unit to generate a zoomed-in image of a portion of the well that contains the candidate object; and the instructions cause the computer system to determine, by analyzing the zoomed-in image using the convolutional neural network, whether the candidate object is a single cell.

23. The system of claim 22, wherein the zoomed-in image is generated by a second imaging unit, wherein the instructions further cause the one or more processors to instruct the stage, causing the stage comprising the well disposed thereon to align the well with an optical path of the second imaging unit.