Embryo evaluation using AI/ML analysis of real-time video for predicting offspring sex
A computer-implemented method for predicting the likelihood an embryo will produce specific sex offspring by processing video image data derived from video of a target embryo. The method includes receiving image data derived from video of a target embryo taken at substantially real-time frame speed during an embryo observation period of time. The video contains recorded morphokinetic movement of the target embryo occurring during the embryo observation period of time. The movement is represented in the received image data and the received image data is processed using a model generated utilizing machine learning and correlated embryo outcome data to predict the likelihood the target embryo will produce specific sex offspring.
1. A method for assessing a characteristic of an embryo by processing video of the embryo, the method comprising:
obtaining real-time video of a target embryo having a continuous recording duration of ten minutes or less, said video comprising image data representing micro-movement of the target embryo; and
processing said image data using a trained machine learning model and thereby assessing a likelihood the target embryo will produce a specific sex offspring.
2. The method of claim 1 , wherein said processing of the image data further comprises assessing viability of the target embryo.
3. The method of claim 1 , further comprising: predicting a likelihood of successful transfer of the target embryo into a recipient.
4. The method of claim 1 , wherein said processing of the image data comprises assessing a likelihood the target embryo will produce a male-sex offspring.
5. The method of claim 1 , wherein said video has a continuous recording duration of thirty seconds or less.
6. The method of claim 1 , wherein said video has a continuous recording duration greater than thirty seconds.
7. The method of claim 1 further comprising: predicting a likelihood the target embryo will produce a genetically superior offspring.
8. The method of claim 1 , further comprising: communicating a predicted embryo outcome of the target embryo to an originator of the video.
9. The method of claim 1 , wherein the model is generated utilizing machine learning and correlated embryo outcome data that represents embryo transfers into recipients that established a male-sex pregnancy.
10. The method of claim 1 , wherein the model is generated utilizing machine learning and correlated embryo outcome data that represents embryo transfers into recipients that produced livebirth male-sex offspring.
11. The method of claim 1 , wherein the model is generated utilizing machine learning and correlated embryo outcome data that represents embryo transfers into recipients that produced genetically inferior offspring.
12. The method of claim 1 , wherein the model is generated utilizing machine learning and correlated embryo outcome data that represents embryo transfers into recipients that produced genetically superior offspring.
13. The method of claim 1 , further comprising: obtaining outcome data indicative of whether successful transfer of the target embryo into a recipient occurred, wherein successful transfer is indicated by the target embryo producing male-sex pregnancy in the recipient.
14. The method of claim 1 , further comprising: obtaining outcome data indicative of whether successful transfer of the target embryo into a recipient occurred, wherein successful transfer is indicated by the target embryo producing male-sex livebirth offspring out of the recipient.
15. The method of claim 1 , further comprising: said video having a frame speed sufficiently fast to capture at least one individual micro-movement by the embryo during an embryo observation period of time.
16. The method of claim 1 , further comprising: said video having a frame speed sufficiently fast to capture a series of micro-movements by the embryo during an embryo observation period of time.
17. The method of claim 1 , wherein said video is taken through a microscope and micro-movements embodied therein are humanly imperceptible.
18. The method of claim 1 , further comprising: said video having a frame speed at least as fast as ten frames per second.
19. The method of claim 1 , further comprising: said video having a frame speed at least as fast as two frames per second.
20. The method of claim 1 , further comprising: said video having a substantially uniform frame speed.
21. The method of claim 1 , wherein said video has a continuous recording duration of less than two minutes.
22. The method of claim 1 , wherein said video has a continuous recording duration of at least thirty seconds.
23. The method of claim 1 , further comprising: selecting an embryo observation period of time less than two minutes.
24. The method of claim 1 , further comprising: selecting an embryo observation period of time that is at least thirty seconds.
25. The method of claim 1 , wherein the video is a product of an inverted microscope camera.
26. The method of claim 1 , wherein the video is a product of an inverted microscope camera positioned below a flat-bottom petri dish containing the target embryo.
27. The method of claim 1 , wherein the video is made using a smartphone camera.
28. The method of claim 1 , further comprising: obtaining from the same video, image data representing each of a plurality of target embryos.
29. The method of claim 28 , further comprising: processing the image data representing the plurality of target embryos utilizing the model and predicting an embryo outcome for at least one of the plurality of target embryos.
30. The method of claim 29 , further comprising: communicating the predicted embryo outcome of each of the plurality of the target embryos to an originator of the video.
31. The method of claim 29 , further comprising: communicating a predicted embryo outcome score of each the plurality of target embryos to an originator of the video.
32. The method of claim 1 , further comprising: transmitting display data to an observable display and causing an image of the target embryo to be displayed, wherein the image is sufficiently magnified making micro-movement of the target embryo humanly perceptible.
33. The method of claim 1 , wherein micro-movement of the target embryo comprises morphokinetic movement of the target embryo.
34. The method of claim 1 , wherein said real-time video is time-lapse free video.
35. The method of claim 1 , wherein said real-time video is prerecorded at a time before the image data is processed by the trained machine learning model.
36. The method of claim 1 , wherein at least one characteristic of the target embryo evidenced in the obtained image data is elasticity of the embryo's outer wall.
37. The method of claim 1 , further comprising: utilizing machine learning that comprises an artificial neural network.
38. The method of claim 1 , further comprising: predicting a likelihood the target embryo will produce a genetically inferior offspring.
39. The method of claim 1 , wherein said processing of the image data comprises assessing a likelihood the target embryo will produce a female-sex offspring.
40. The method of claim 1 , wherein the model is generated utilizing machine learning and correlated embryo outcome data that represents embryo transfers into recipients that established a female-sex pregnancy.
41. The method of claim 1 , wherein the model is generated utilizing machine learning and correlated embryo outcome data that represents embryo transfers into recipients that produced livebirth female-sex offspring.
42. The method of claim 1 , further comprising: obtaining outcome data indicative of whether successful transfer of the target embryo into a recipient occurred, wherein successful transfer is indicated by the target embryo producing female-sex pregnancy in the recipient.
43. The method of claim 1 , further comprising: obtaining outcome data indicative of whether successful transfer of the target embryo into a recipient occurred, wherein successful transfer is indicated by the target embryo producing female-sex livebirth offspring out of the recipient.
44. A system comprising:
one or more processors; and
a computer-readable medium comprising instructions stored therein, which when executed by the one or more processors, cause the one or more processors to:
predict an embryo outcome by processing video of an embryo, said prediction comprising:
obtaining real-time video of a target embryo having a continuous recording duration of ten minutes or less, said video comprising image data representing micro-movement of the target embryo; and
processing said image data using a trained machine learning model and thereby assessing a likelihood the target embryo will produce a specific sex offspring.
45. The system of claim 44 , wherein said video has a continuous recording duration of two minutes or less.
46. The system of claim 44 , wherein said video has a continuous recording duration of at least thirty seconds.
47. A non-transitory computer-readable storage medium comprising computer-readable instructions, which when executed by a computing system, cause the computing system to process video of an embryo comprising:
obtaining real-time video of a target embryo having a continuous recording duration of ten minutes or less, said video comprising image data representing micro-movement of the target embryo; and
processing said image data using a trained machine learning model and thereby assessing a likelihood the target embryo will produce a specific sex offspring.
48. The storage medium of claim 47 , wherein said video has a continuous recording duration of two minutes or less.
49. The storage medium of claim 47 , wherein said video has a continuous recording duration of at least thirty seconds.