Method implemented by computer system for boosting blastocyst formation and oocyte quality analysis system

Abstract

This disclosure is essentially about a computer-implemented method for promoting blastocyst formation and an oocyte quality analysis system. In some embodiments, pressure is applied to the oocyte via a micropipette. Image sequences depicting the oocyte and the micropipette applying pressure to the oocyte are acquired. Using a segmentation model, objects associated with the oocyte are identified. Based on the identified objects, features such as morphological characteristics and aspiration depth associated with the oocyte are determined. At least some of these features are then input into a machine learning model to generate an oocyte gradation indicating the likelihood of the oocyte developing into a usable blastocyst.

Claims

1. A method implemented by one or more computer systems, comprising: Pressure generated by a pressure generating device is applied to the oocyte using a micropipette; Acquire multiple images forming a time-related image sequence, the image sequence depicting the oocyte and a portion of the micropipette applying pressure to the oocyte, wherein each individual image is associated with an individual pressure value applied to the oocyte at its respective image capture time; identify objects associated with the oocyte using a segmentation model; determine features associated with the oocyte based on geometric measurements of at least some of the objects associated with the oocyte, the features including morphological features indicating measurements of the oocyte within the time period, and the aspiration depth of the oocyte into the portion of the micropipette applying pressure to the oocyte; and generate an oocyte grade using a machine learning model based on an input value including the aspiration depth, wherein the oocyte grade at least indicates the likelihood that the oocyte will develop into a usable blastocyst.

2. The method implemented by one or more computer systems as described in claim 1, wherein the pressure is between -0.5 psi and 0.5 psi.

3. The method implemented by one or more computer systems as described in claim 1, wherein the pressure is applied to the oocyte for 0.5 to 10 seconds.

4. The method implemented by one or more computer systems as described in claim 1, wherein the pressure is generated by the pressure generating device according to a two-stage pressure control process or a continuous pressure control process.

5. The method implemented by one or more computer systems as described in claim 1, wherein the inner diameter of the micropipette is between 25 micrometers and 100 micrometers.

6. The method implemented by one or more computer systems as described in claim 1, wherein the objects associated with the oocyte include at least one of the following: the zona pellucida of the oocyte, the perivitelline space of the oocyte, the first polar body of the oocyte, the cytoplasm of the oocyte, and a bounding box associated with the portion of the micropipette that applies pressure to the oocyte.

7. The method implemented by one or more computer systems as described in claim 6, wherein the morphological characteristics associated with the oocyte include at least one of the ellipticity of the first polar body, the thickness of the zona pellucida, the diameter of the oocyte, the area of ​​the cytoplasm, the compactness of the cytoplasm, the roundness of the cytoplasm, and the ratio between the area of ​​the cytoplasm and the total area of ​​the cytoplasm and the perivitelline space.

8. The method implemented by one or more computer systems as described in claim 1, wherein the segmentation model includes U-net and the machine learning model includes a regression model.

9. The method implemented by one or more computer systems as described in claim 1, wherein applying the pressure to the oocyte increases the probability of the oocyte forming a blastocyst.

10. A method implemented by one or more computer systems for increasing the probability of an oocyte forming a blastocyst, comprising: Pressure generated by a pressure generating device is applied to the oocyte using a micropipette, wherein the pressure is applied to the oocyte to increase the probability of the oocyte forming the blastocyst.

11. The method implemented by a system of one or more computers as described in claim 10, wherein the pressure generating device comprises: A tank having a chamber therein, and including an opening and a communication port in fluid communication with the chamber; A deformable membrane configured to seal the opening and deformable between a flat state and a deformable state; a drive device disposed in the tank and including a motor body and a drive shaft having a first shaft end configured to face the deformable membrane, the drive shaft being driven by the motor body to move between a distal position of the first shaft end away from the motor body and a proximal position of the first shaft end near the motor body; And a connecting unit configured to couple the first shaft end to the deformable membrane and allow the deformable membrane to be driven by the drive shaft to transition between a flat state in one of the distal and proximal positions of the first shaft end and a deformable state in the other of the distal and proximal positions, such that a predetermined pressure is generated through the communication port when the deformable membrane moves from one of the flat and deformable states to the other of the flat and deformable states.

12. The method implemented by one or more computer systems as described in claim 10, further comprising: Acquire multiple images forming a time-related image sequence, the image sequence depicting the oocyte and a portion of the micropipette applying pressure to the oocyte, wherein individual images are associated with an individual pressure value applied to the oocyte at their respective image capture times; identify objects associated with the oocyte using a segmentation model; determine features associated with the oocyte based on geometric measurements of at least some of the objects associated with the oocyte, the features including morphological features indicating measurements of the oocyte within the time period, and the aspiration depth of the oocyte into the portion of the micropipette applying pressure to the oocyte; and generate an oocyte grade using a machine learning model based on an input value including the aspiration depth, wherein the oocyte grade at least indicates the likelihood that the oocyte will develop into a usable blastocyst.

13. The method implemented by a system of one or more computers as described in claim 10, wherein the pressure is between -0.5 psi and 0.5 psi.

14. The method implemented by a system of one or more computers as described in claim 10, wherein the pressure is applied to the oocyte for 0.5 to 10 seconds.

15. The method implemented by a system of one or more computers as described in claim 10, wherein the pressure is generated by the pressure generating device according to a two-stage pressure control process or a continuous pressure control process.

16. The method implemented by one or more computer systems as described in claim 10, wherein the inner diameter of the micropipette is between 25 micrometers and 100 micrometers.

17. An oocyte quality analysis system comprising one or more processors and a non-transitory computer storage medium storing instructions, wherein when the instructions are executed by one or more of the processors, the one or more processors: apply pressure generated by a pressure generating device to the oocyte via a micropipette, wherein the pressure is applied to the oocyte to increase the probability of the oocyte forming a blastocyst.

18. The oocyte quality analysis system of claim 17, wherein the instructions further cause one or more of the processors to: acquire a plurality of images forming a time-related image sequence, the image sequence depicting the oocyte and a portion of the micropipette applying the pressure to the oocyte, wherein individual images are associated with individual pressure values ​​applied to the oocyte at their respective image capture times; identify objects associated with the oocyte using a segmentation model; determine features associated with the oocyte based on geometric measurements of at least a portion of the objects associated with the oocyte, the features including morphological features indicating measurements of the oocyte within the time period, and the aspiration depth of the oocyte into the portion of the micropipette applying the pressure to the oocyte; and generate an oocyte grade using a machine learning model based on an input value including the aspiration depth, wherein the oocyte grade at least indicates the likelihood that the oocyte will develop into a usable blastocyst.

19. The oocyte quality analysis system as claimed in claim 17, wherein the pressure generating device comprises: A tank having a chamber therein, and including an opening and a communication port in fluid communication with the chamber; A deformable membrane configured to seal the opening and deformable between a flat state and a deformable state; a drive device disposed in the tank and including a motor body and a drive shaft having a first shaft end configured to face the deformable membrane, the drive shaft being driven by the motor body to move between a distal position of the first shaft end away from the motor body and a proximal position of the first shaft end near the motor body; And a connecting unit configured to couple the first shaft end to the deformable membrane and allow the deformable membrane to be driven by the drive shaft to transition between a flat state in one of the distal and proximal positions of the first shaft end and a deformable state in the other of the distal and proximal positions, such that a predetermined pressure is generated through the communication port when the deformable membrane moves from one of the flat and deformable states to the other of the flat and deformable states.

20. The oocyte quality analysis system as claimed in claim 17, wherein the pressure is applied to the oocyte for a period of 0.5 seconds to 10 seconds.

Images