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

Abstract

The present disclosure generally relates to a method implemented by computer system for boosting blastocyst formation and oocyte quality analysis system. In some implementation examples, pressure is applied to an oocyte through a micropipette. An image sequence depicting the oocyte and the micropipette applying the pressure to the oocyte is obtained. Using a segmentation model, objects associated with the oocyte can be identified. Based on the objects identified, features such as morphological features and an aspiration depth associated with the oocyte can be determined. At least some of the features can then be fed into a machine learning model to generate an oocyte grade that indicates a likelihood of the oocyte developing into a usable blastocyst.

Description

Technical Field

[0001] This disclosure relates to a pressure generating device, and more particularly to the use of a pressure generating device associated with an oocyte quality analysis system to promote blastocyst formation. Prior Technology

[0002] In vitro fertilization (IVF) is an option for couples struggling with infertility to achieve pregnancy. During an IVF cycle, after follicle-stimulating hormone (FSH) is used to stimulate the mother's ovaries, multiple oocytes can be retrieved from the ovaries and fertilized in vitro. One or more of the fertilized oocytes are then transferred back into the mother's uterus. In some cases, the fertilized oocytes can further develop into embryos in vitro, and one or more embryos are then implanted back into the mother's uterus. To increase the live birth rate in an IVF cycle, it is necessary to select high-quality fertilized oocytes or embryos for implantation. Summary of the Invention

[0003] The systems, methods, and apparatuses disclosed herein each have several innovative embodiments, none of which alone is responsible for all the desirable properties of this disclosure. Details of one or more embodiments of the subject matter described herein are set forth in the accompanying drawings and the following description.

[0004] In some aspects, the techniques described herein relate to a method implemented by one or more computer systems, including: applying pressure generated by a pressure generating device to an oocyte using a micropipette; acquiring multiple images forming a time-related image sequence depicting the oocyte and portions of the micropipette applying pressure to the oocyte, wherein individual images are associated with individual pressure values ​​applied to the oocyte at their respective image capture times; identifying objects associated with the oocyte using a segmentation model; determining features associated with the oocyte based on geometric measurements of at least some of the objects associated with the oocyte, including morphological features indicative of oocyte measurements over the time period and the aspiration depth of the oocyte into the portion of the micropipette applying pressure to the oocyte; and generating an oocyte grade using a machine learning model based on input values ​​including the aspiration depth, wherein the oocyte grade at least indicates the likelihood of the oocyte developing into a usable blastocyst.

[0005] In some respects, the technique described herein relates to a method in which the pressure is between -0.5 psi and 0.5 psi.

[0006] In some respects, the technique described herein relates to a method in which pressure is applied to the oocyte for 0.5 to 10 seconds.

[0007] In some respects, the technology described herein relates to a method in which pressure is generated by a pressure generating device according to a two-stage pressure control process or a continuous pressure control process.

[0008] In some respects, the technique described herein relates to a method in which the inner diameter of the micropipette is between 25 micrometers and 100 micrometers.

[0009] In some respects, the technology described herein relates to a method in which objects associated with an oocyte include at least one of the following in a bounding box: 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 portion of a micropipette that applies pressure to the oocyte.

[0010] In some respects, the techniques described herein relate to a method in which morphological characteristics associated with the oocyte include at least one of the following: 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.

[0011] In some respects, the techniques described herein are associated with a method in which the segmentation model includes U-net and the machine learning model includes a regression model.

[0012] In some respects, the techniques described herein relate to a method in which applying pressure to oocytes increases the chances of the oocytes forming blastocysts.

[0013] In some respects, the technology described herein relates to a method implemented by one or more computer systems for increasing the probability of an oocyte forming a blastocyst, including: applying pressure generated by a pressure generating device to the oocyte via a micropipette, wherein applying pressure to the oocyte increases the probability of the oocyte forming a blastocyst.

[0014] In some aspects, the technology described herein relates to a method in which a pressure generating device includes: a tank having a chamber, including an opening and a connecting port in fluid communication with the chamber; a deformable membrane configured to seal the opening, the deformable membrane being deformable between a flat state and a deformable state; a drive mechanism disposed in the tank, 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 (where the first shaft end is away from the motor body) and a proximal position (where the first shaft end is close to 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 change between a flat state (where the first shaft end is in one of the distal and proximal positions) and a deformable state (where the first shaft end is in the other of the distal and proximal positions), such that when the deformable membrane changes from one of the flat and deformable states to the other of the flat and deformable states, a predetermined pressure is generated through the connecting port.

[0015] In some respects, the techniques described herein relate to a method that further includes: acquiring multiple images forming a time-related image sequence, the image sequence depicting an oocyte and portions of a micropipette applying pressure to the oocyte, wherein individual images are associated with individual pressure values ​​applied to the oocyte at their respective image capture times; identifying objects associated with the oocyte using a segmentation model; determining oocyte-related features based on geometric measurements of at least some of the objects associated with the oocyte, these features including morphological features indicative of oocyte measurements within the time period, and the aspiration depth of the oocyte into the portion of the micropipette to which pressure is applied; and generating an oocyte gradation using a machine learning model based on input values ​​including the aspiration depth, wherein the oocyte gradation indicates the likelihood of the oocyte developing into a usable blastocyst.

[0016] In some respects, the technique described herein relates to a method in which the pressure is between -0.5 psi and 0.5 psi.

[0017] In some respects, the technique described herein relates to a method in which pressure is applied to the oocyte for 0.5 to 10 seconds.

[0018] In some respects, the technology described herein relates to a method in which pressure is generated by a pressure generating device according to a two-stage pressure control process or a continuous pressure control process.

[0019] In some respects, the technique described herein relates to a method in which the inner diameter of the micropipette is between 25 micrometers and 100 micrometers.

[0020] In some respects, the technology described herein relates to a system comprising one or more processors and a non-transitory computer storage medium storing instructions, which, when executed by the one or more processors, causes the one or more processors to: apply pressure generated by a pressure generating device to an oocyte via a micropipette, wherein applying pressure to the oocyte increases the probability of the oocyte forming a blastocyst.

[0021] In some respects, the techniques described herein relate to a system in which instructions further cause one or more processors to: acquire multiple images forming a time-related image sequence, the image sequence depicting an oocyte and portions of a micropipette applying 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 oocyte-related features based on geometric measurements of at least some of the objects associated with the oocyte, the features including morphological features indicative of oocyte measurements 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 input values ​​including the aspiration depth, wherein the oocyte grade at least indicates the likelihood of the oocyte developing into a usable blastocyst.

[0022] In some aspects, the technology described herein relates to a system in which a pressure generating device includes: a tank having a chamber, including an opening and a connecting port in fluid communication with the chamber; a deformable membrane configured to seal the opening, the deformable membrane being deformable between a flat state and a deformable state; a drive mechanism disposed in the tank, 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 (where the first shaft end is away from the motor body) and a proximal position (where the first shaft end is close to 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 (where the first shaft end is in one of the distal and proximal positions) and a deformable state (where the first shaft end is in the other of the distal and proximal positions), such that a predetermined pressure is generated via the connecting port when the deformable membrane transitions from one of the flat and deformable states to the other of the flat and deformable states.

[0023] In some respects, the technique described herein relates to a system in which pressure is applied to the oocyte for 0.5 to 10 seconds. Simple Explanation of the Diagram

[0024] Other features and advantages disclosed herein will become more apparent in the detailed description of embodiments with reference to the accompanying drawings. It should be noted that the features may not be drawn to scale. Figure 1 is a schematic diagram illustrating a pressure generating device according to a first embodiment of the present disclosure. Figure 2 is a schematic diagram of the pressure generating device, similar to Figure 1 but in the pressure increasing state. Figure 3 is a schematic diagram illustrating a pressure generating device according to a second embodiment of the present disclosure. Figure 4 is a schematic diagram of the pressure generating device, which is similar to Figure 3 but is in a pressure reduction state. Figure 5 is a perspective view illustrating a pressure generating apparatus according to a third embodiment of the present disclosure. Figure 6 is an exploded perspective view illustrating some components of the pressure generating device shown in Figure 5. Figure 7 is an exploded perspective view illustrating the tank-side shell, deformable membrane, and connecting unit in the pressure generating device shown in Figure 5. Figure 8 is an exploded perspective view illustrating the side shell of the tank, the deformable membrane, and the connecting unit. It is similar to Figure 7 but in the opposite direction. Figure 9 is an exploded perspective view illustrating the drive device, connecting sleeve of the connecting unit, and marker in the pressure generating device shown in Figure 5. Figure 10 is a schematic diagram illustrating the main parts of a detection system according to an embodiment of the present disclosure. Figure 11 is a schematic diagram of a microscope of a detection system according to an embodiment of the present disclosure. Figure 12 is a diagram illustrating the test process for determining the quality of test samples according to some embodiments. Figures 13 and 14 are two microscopic images illustrating the oocytes in two states before and after the pressure generating device of the detection system provides a predetermined negative pressure. Figure 15 is a diagram illustrating another test procedure for determining the quality of test samples according to some embodiments. Figures 16A and 16B illustrate implementation examples of applying pressure to oocytes to increase the probability of oocytes forming blastocysts, and using an oocyte analysis system to generate oocyte grades, according to some embodiments of this disclosure. Figure 17 is an example flowchart for applying pressure to oocytes to increase the chances of oocytes forming blastocysts and to produce oocyte grades. Figure 18 illustrates the general architecture of an exemplary oocyte analysis system according to some embodiments of this disclosure. Implementation

[0025] Before describing this disclosure in more detail, it should be noted that, where appropriate, reference symbols or the terminal portion of reference symbols are repeated in the figures to indicate corresponding or similar elements that may selectively have similar characteristics.

[0026] It should be noted that, for clarity, spatially relative terms such as “top,” “bottom,” “upper,” “lower,” “above,” “above,” “downward,” “upward,” etc., may be used throughout the disclosure, while referring to the features shown in the figures. These features may be oriented in different directions (e.g., rotated 90 degrees or otherwise), and the use of spatially relative terms here is to be interpreted accordingly.

[0027] It should be noted that the illustrations are for illustrative purposes only, are not drawn to scale, and are not intended to represent the actual or relative dimensions of the apparatus or system components in this disclosure.

[0028] [Examples of pressure generating devices and detection systems]

[0029] Figures 1 and 2 each show a pressure generating device 1 according to a first embodiment of this disclosure. The pressure generating device 1 is used to generate pressure to a test sample S via a micropipette 3 (see Figures 13 and 14). The test sample S may be an oocyte (e.g., a mammalian oocyte that may be fertilized or unfertilized) or an embryo (e.g., a mammalian embryo). The quality of the test sample can be determined based on the aspiration depth D of the test sample S (see Figure 14) and other factors (e.g., morphology observed using the microscope 5 shown in Figure 11).

[0030] The pressure generating device 1 includes a tank 10, a deformable membrane 20, a driving device 30, and a connecting unit 40.

[0031] The tank 10 has a chamber 100 therein and includes an opening 101 and a connecting port 102 in fluid communication with the chamber 100. The deformable membrane 20 is configured to seal the opening 101 and is deformable between a flat state and a deformable state. A drive unit 30 may be disposed in the tank 10 by any possible element and includes a motor body 31 and a drive shaft 32. The drive shaft 32 has a first shaft end 321 configured to face the deformable membrane 20. The drive shaft 32 is driven by the motor body 31 to move between a distal position (the first shaft end 321 is away from the motor body 31) and a proximal position (the first shaft end 321 is close to the motor body 31). A connecting unit 40 is configured to couple the first shaft end 321 to the deformable membrane 20 and allow the deformable membrane 20 to be driven by the drive shaft 32 to change between a flat state and a deformable state. In the flat state, the first shaft end 321 is located in one of the distal and proximal positions, while in the deformed state, the first shaft end 321 is located in the other of the distal and proximal positions, such that when the deformable membrane 20 changes from one of the flat and deformed states to the other of the flat and deformed states, a predetermined pressure is generated through the communication port 102.

[0032] In the first embodiment, in the flat state, as shown in FIG1, the first shaft end 321 is located at the proximal position; while in the deformed state, as shown in FIG2, the first shaft end 321 is located at the distal position. Therefore, when the deformable membrane 20 changes from one of the flat state and the deformed state to the other of the flat state and the deformed state, a predetermined pressure is generated through the communication port 102.

[0033] In the first embodiment, in response to the movement of the drive shaft 32 from a proximal position (see FIG. 1) to a distal position (see FIG. 2), the deformable membrane 20 is deformed inward by the connecting unit 40 to change the deformable membrane 20 from a flat state to a deformable state. As the deformable membrane 20 deforms, the chamber 100 is converted to a pressure-increasing state. In this case, once the deformable membrane 20 returns from the deformable state to the flat state, a predetermined pressure can be generated from the communication port 102.

[0034] In some embodiments, the tank 10 may be made of metal, alloy, plastic, other suitable airtight rigid material, or a combination thereof. In some embodiments, the deformable membrane 20 may be made of silicone, polymer, fabric, any suitable airtight flexible material, or a combination thereof.

[0035] Figures 3 and 4 illustrate the pressure generating device 1 according to the disclosed second embodiment. The second embodiment is similar to the first embodiment, except that in the second embodiment, the deformable membrane 20 deforms outward in its deformable state. Specifically, in the second embodiment, the connecting unit 40 is fixed to the deformable membrane 20. When the drive shaft 32 is in the distal position, the deformable membrane 20 can remain in a flat state. In response to the drive shaft 32 moving from the distal position (see Figure 3) to the proximal position (see Figure 4), the deformable membrane 20 is pulled outward by the connecting unit 40 to change the deformable membrane 20 from a flat state to a deformable state. As the deformable membrane 20 deforms, the chamber 100 is converted to a pressure reduction state, thus a predetermined pressure can be generated from the communication port 102.

[0036] Figures 5 to 9 illustrate the pressure generating device 1 according to a third embodiment of this disclosure. The third embodiment is similar to the first or second embodiment, except that in the third embodiment, the tank 10, the deformable membrane 20, the drive device 30, and the connecting unit 40 are shown in detail.

[0037] As shown in Figures 5 and 6, the tank 10 includes a main shell 11 and a side shell 12. The main shell 11 has a chamber 100 and includes an opening 101 and a connection port 102. The side shell 12 is detachably mounted on the main shell 11, so that the deformable membrane 20 is fixed between the main shell 11 and the side shell 12, thereby sealing the opening 101.

[0038] In some embodiments, the main housing 11 extends along the longitudinal axis L and terminates at both ends at a closed end 111 and a connecting end 112 forming an opening 101. In some embodiments, the main housing 11 is provided with two communication ports 102.

[0039] In some embodiments, referring to FIGS. 7 and 8, the side shell 12 includes a side shell body 121 and a flange body 125. The side shell body 121 has a distal end 122 and a proximal end 123 opposite to the distal end 122, and forms a channel 124 extending from the distal end 122 to the proximal end 123. The flange body 125 extends radially outward from the proximal end 123 of the side shell body 121 and is detachably disposed on the main shell 11. In some embodiments, the deformable membrane 20 is maintained in a flat state by a holding force provided between the main shell 11 and the side shell 12.

[0040] In some embodiments, the tank 10 further includes two connecting rods 142. Each connecting rod 142 has an end that inserts into its respective communication port 102. Thus, the chamber 100 can be in fluid communication with the connecting pipe 4 (see Figures 1 to 4 and Figure 10) via one of the connecting rods 142. Each connecting rod 142 may be provided with a valve (not shown) that can switch between a first state and a second state, in which one of the connecting rods 142 is in an open state to allow fluid communication between the chamber 100 and the connecting pipe 4, and in a second state, one of the connecting rods 142 is in a closed state to block communication between the chamber 100 and the connecting pipe 4.

[0041] In some embodiments, a plurality of fasteners 126 are configured to pass through the flange body 125 and the deformable membrane 20 and extend into the connection end 112 of the main housing 11 to secure the side housing 12 to the main housing 11.

[0042] As shown in Figures 5 and 9, the drive device 30 is disposed in the groove 10. In some embodiments, the motor body 31 is immovably disposed on the side shell 12, and the drive shaft 32 extends through the motor body 31 along axis A and is driven by the motor body 31 to move along axis A toward or away from the deformable membrane 20, so that the deformable membrane 20 deforms between a flat state and a deformable state. In some embodiments, axis A may be aligned with the longitudinal axis L. In some embodiments, the drive device 30 is a linear motor, and the drive shaft 32 does not rotate about axis A when driven to move along axis A. In some other embodiments, the drive device 30 is a stepper motor, and the drive shaft 32 rotates about axis A when driven to move along axis A.

[0043] In some embodiments, referring to FIG9, the motor body 31 has an inner portion 311, an outer portion 312, and a flange portion 313. The inner portion 311 is received in a channel 124 of the side housing body 121. The outer portion 312 extends from the inner portion 311 in a direction away from the main housing 11 and is disposed on the outside of the side housing body 121. The flange portion 313 extends radially from the outer portion 312 and is detachably secured to the distal end 122 of the side housing body 121 by means of a fastener 314.

[0044] In some embodiments, the drive shaft 32 further has a second shaft end 322, which is opposite to the first shaft end 321 along axis A. The first shaft end 321 and the second shaft end 322 are located on two opposite sides of the motor body 31.

[0045] As shown in Figures 7 and 8, in some embodiments, the connecting unit 40 includes a connecting sleeve 41, a bearing sleeve 42, and a bearing cover 43.

[0046] A connecting sleeve 41 is coupled to a first shaft end 321 of a drive shaft 32 to allow the connecting sleeve 41 to move along axis A with the drive shaft 32. The connecting sleeve 41 has a first sleeve portion 411, a second sleeve portion 412, and a shoulder surface 413. The second sleeve portion 412 has a larger outer diameter than the first sleeve portion 411. The shoulder surface 413 is located between the first sleeve portion 411 and the second sleeve portion 412. In some embodiments, as shown in FIG9, the connecting sleeve 41 is provided with a through hole 414, and the first shaft end 321 is non-rotatably fixed in the through hole 414 by a fastener 415.

[0047] The bearing sleeve 42 is adaptedly fitted onto the second sleeve portion 412 so that the bearing sleeve 42 moves together with the connecting sleeve 41 along axis A and is disposed between the connecting sleeve 41 and the bearing cover 43. The bearing sleeve 42 has a first sleeve end 421 and a second sleeve end 422 opposite to the first sleeve end 421. In some embodiments, a plurality of bearing balls 423 are disposed in the second sleeve end 422 and are spaced apart from each other at an angle about axis A.

[0048] The bearing cap 43 has an engaging portion 431 and a mounting portion 432. The engaging portion 431 is provided with a groove 4311, which is configured to engage with the second sleeve end 422, so that the bearing cap 43 can move together with the bearing sleeve 42 along axis A. The mounting portion 432 is opposite to the engaging portion 431 on axis A and is fixed to the first surface 201 of the deformable membrane 20 so as to transmit the force from the drive shaft 32 to the deformable membrane 20.

[0049] In some embodiments, the deformable membrane 20 has a through hole 200, and the connecting unit 40 further includes a fastener 44. The fastener 44 has an enlarged head 441 and a fastening rod 442. The enlarged head 441 is disposed on a second surface 202 of the deformable membrane 20 opposite to the first surface 201. The fastening rod 442 extends from the enlarged head 441, passes through the through hole 200 of the deformable membrane 20, and terminates at a rod end 443. The rod end 443 engages tightly within a hole 433 formed in the mounting portion 432 of the bearing cap 43, so that the deformable membrane 20 is secured to the bearing cap 43 by the fastener 44.

[0050] In some embodiments, the connecting unit 40 further includes a first washer 45 and a second washer 46. The first washer 45 is disposed between the mounting portion 432 and the first surface 201 of the deformable membrane 20. The second washer 46 is disposed between the enlarged head 441 and the second surface 202 of the deformable membrane 20. In some embodiments, to improve torque transmission from the drive shaft 32 to the deformable membrane 20, each of the first washer 45 and the second washer 46 is made of a deformable material. Examples of deformable materials may be similar to materials suitable for forming the deformable membrane 20, therefore, for the sake of brevity, their details are omitted.

[0051] In some embodiments, referring to Figures 1, 2, and 5 through 9, the deformable membrane 20 deforms inward in a deformable state. In other words, when the drive shaft 32 moves from the proximal position to the distal position, the bearing cap 43 is moved toward the chamber 100 by the first shaft end 321 (via the connecting sleeve 41 and the bearing sleeve 42) and presses against the deformable membrane 20 to force the deformable membrane 20 to deform into a deformable state to resist the holding force provided between the main housing 11 and the side housing 12. When the drive shaft 32 moves from the distal position (see Figure 2) to the proximal position (see Figure 1), the bearing cap 43 is driven away from the chamber 100 so that the deformable membrane 20 returns to a flat state by the holding force, thereby generating a predetermined pressure (e.g., a predetermined negative pressure) in the communication port 102 (or one of the communication ports 102 shown in Figure 6).

[0052] In some other embodiments, referring to Figures 3 through 9, the deformable membrane 20 deforms outward in a deformable state. In this case, the drive unit 30 is a linear motor, and the connecting sleeve 41, bearing sleeve 42, and bearing cap 43 are fixed to each other. In some embodiments, each pair of adjacent connecting sleeves 41, bearing sleeves 42, and bearing caps 43 are interlocked. In some other embodiments, an adhesive may be additionally applied between each pair of adjacent connecting sleeves 41, bearing sleeves 42, and bearing caps 43. Specifically, when the drive shaft 32 moves from a distal position (see Figure 3) to a proximal position (see Figure 4), the deformable membrane 20 is pulled by the connecting unit 40 to deform outward into a deformable state to resist the holding force between the main housing 11 and the side housing 12, thereby generating a predetermined pressure (e.g., a predetermined negative pressure) from one of the communication ports 102 or the communication ports 102 shown in Figure 6. When the drive shaft 32 moves from the proximal position to the distal position, the connecting unit 40 moves toward the chamber 100 so that the deformable membrane 20 returns to a flat state by holding force.

[0053] In some embodiments, the deformable film 20 has a hardness range from 0 Shore A to 100 Shore A, for example, from 0 Shore A to 10 Shore A, from 5 Shore A to 15 Shore A, from 10 Shore A to 20 Shore A, from 15 Shore A to 25 Shore A, from 20 Shore A to 30 Shore A, from 25 Shore A to 35 Shore A, from 30 Shore A to 40 Shore A, from 35 Shore A to 45 Shore A, and from 40 Shore A... The hardness ranges from 45 Shore A to 55 Shore A, from 50 Shore A to 60 Shore A, from 55 Shore A to 65 Shore A, from 60 Shore A to 70 Shore A, from 65 Shore A to 75 Shore A, from 70 Shore A to 80 Shore A, from 75 Shore A to 85 Shore A, from 80 Shore A to 90 Shore A, from 85 Shore A to 95 Shore A, or from 90 Shore A to 100 Shore A. The drive unit 30 is configured to provide thrust ranging from 100 grams to 1000 grams, for example, from 100 grams to 200 grams, from 150 grams to 250 grams, from 200 grams to 300 grams, from 250 grams to 350 grams, from 300 grams to 400 grams, from 350 grams to 450 grams, from 400 grams to 500 grams, from 450 grams to 550 grams, from 500 grams to 600 grams, from 550 grams to 650 grams, from 600 grams to 700 grams, from 650 grams to 750 grams, from 700 grams to 800 grams, from 750 grams to 850 grams, from 800 grams to 900 grams, from 850 grams to 950 grams, or from 900 grams to 1000 grams. The travel range of the drive unit 30 is from 3 mm to 50 mm, for example, from 3 mm to 15 mm, from 9 mm to 21 mm, from 15 mm to 27 mm, from 21 mm to 33 mm, from 27 mm to 39 mm, from 33 mm to 45 mm, or from 39 mm to 50 mm.

[0054] The stroke and thrust of the drive device 30 are determined based on the required degree of deformation of the deformable membrane 20 and the stiffness of the deformable membrane 20, respectively. When the required stroke of the drive device 30 is relatively long and the stiffness of the deformable membrane 20 is relatively low, the operation of the drive device 30 is relatively easy (i.e., the required thrust of the drive device 30 is relatively small). When the stiffness of the deformable membrane 20 increases, the required thrust of the drive device 30 will increase if the required stroke of the drive device 30 does not decrease.

[0055] In some embodiments, the volume of the main housing 11 ranges from 1 cm³ to 50 cm³, for example, from 1 cm³ to 10 cm³, from 5 cm³ to 15 cm³, from 10 cm³ to 20 cm³, from 15 cm³ to 25 cm³, from 20 cm³ to 30 cm³, from 25 cm³ to 35 cm³, from 30 cm³ to 40 cm³, from 35 cm³ to 45 cm³, or from 40 cm³ to 50 cm³.

[0056] In some embodiments, the pressure generating device 1 further includes a photosensor 80 that is immovable relative to the tank 10, so that the photosensor 80 detects the displacement of the drive shaft 32. In some embodiments, a circuit board 81 is disposed on the side shell body 121, and the photosensor 80 is disposed on the circuit board 81 and electrically connected to the circuit of the circuit board 81.

[0057] In some embodiments, referring to Figures 5 and 9, the pressure generating device 1 further includes a marker 90 mounted on a second shaft end 322 of the drive shaft 32, such that the marker 90 moves with the drive shaft 32, and the marker 90 has a plurality of detectable positions that can be detected by a photosensor 80, thereby determining the displacement of the drive shaft 32. In some embodiments, the marker 90 is mounted to the second shaft end 322 by a fastener 91.

[0058] Figure 10 illustrates the main components of a detection system 2 for detecting the quality of a test sample (S) (see Figures 13 and 14) according to an embodiment of this disclosure. The detection system 2 includes a pressure generating device 1 (with one of the connecting rods 142 in an open state and the other in a closed state), a micropipette 3 for aspirating the test sample S (see Figures 13 and 14), and a connecting tube 4 configured to connect one of the communication ports 102 of the tank 10 (via one of the connecting rods 142) to the micropipette 3, so as to apply pre-pressure to the test sample S from the pressure generating device 1. A predetermined pressure (e.g., a predetermined negative pressure). In some other embodiments, the detection system 2 may include a pressure generating device 1 (with both connecting rods 142 in the open state), two micropipettes 3 (only one shown in Figures 13 and 14), and two connecting tubes 4 (only one shown in Figure 10), such that a predetermined pressure from the pressure generating device 1 can be applied to two test samples S (only one shown) respectively via the connecting rods 142. In the following description, each of the port 102, connecting rod 142, micropipettes 3, connecting tubes 4, etc., is described in the singular.

[0059] In some embodiments, the inner diameter of the micropipette 3 ranges from about 10 micrometers to about 100 micrometers (e.g., from about 40 micrometers to about 70 micrometers).

[0060] In some embodiments, the pressure generating device 1 generates a pressure ranging from about 0.5 psi to about -0.5 psi at the suction port 301 of the micropipette 3. For example, the pressure generated at the suction port 301 of the micropipette 3 can vary from about -0.03 psi to about -0.5 psi, from about 0.03 psi to about -0.5 psi, from about 0.03 psi to about 0.5 psi, or from about -0.03 psi to about 0.5 psi.

[0061] In some embodiments, referring to Figures 10, 11, 13, and 14, the detection system 2 further includes a microscope 5 and a syringe holder 18. The microscope 5 is used to monitor the test sample S and the aspiration port 301 of the micropipette 3. Specifically, the test sample S is placed on a culture dish 501 of the microscope 5, and the syringe holder 18 is connected between the connecting tube 4 and the micropipette 3. In operation, the aspiration port 301 of the micropipette 3 is held by the syringe holder 18 and positioned on the culture dish 501 of the microscope 5 so that the test sample S on the culture dish 501 can be adsorbed and / or drawn in by the aspiration port 301 of the micropipette 3.

[0062] In some embodiments, the connecting tube 4 includes a first tube section 401 connected to the communication port 102 of the tank 10, and a second tube section 402 connected to the micropipette 3 via a syringe holder 18. The first tube section 401 and the second tube section 402 are interconnected by a regulating valve 15 for adjusting the pressure generated at the suction port 301 of the micropipette 3. In some embodiments, the regulating valve 15 is a solenoid valve.

[0063] In some embodiments, the detection system 2 further includes a branch pipe 403 connected to the first pipe segment 401, having an exhaust port 17 opposite to the first pipe segment 401. Furthermore, an exhaust valve 16 is coupled to the branch pipe 403 to control fluid communication between the chamber 100 and the exhaust port 17. Specifically, when the exhaust valve 16 is open, the exhaust port 17 is in fluid communication with the chamber 100, and when the exhaust valve 16 is fully closed, the exhaust port 17 is prevented from fluidly communicating with the chamber 100. Therefore, when the exhaust valve 16 is open, the pressure within the chamber 100 is allowed to return to atmospheric pressure. In some embodiments, the exhaust valve 16 is a solenoid valve.

[0064] Figure 12 is a flowchart illustrating the test procedure for determining the quality of test sample S according to some embodiments. The test procedure shown in Figure 12 is described with reference to Figures 10, 13, and 14. During the test procedure illustrated in Figure 12, the regulating valve 15 is always in the open state.

[0065] Referring to Figures 10 and 12, initially, the exhaust valve 16 is fully closed, the pressure within chamber 100 is adjusted and maintained at an initial pressure (e.g., slightly positive or negative), and the position of the drive shaft 32 is also moved to allow the deformable membrane 20 to remain in its original state. For example, when the deformable membrane 20 deforms inward (e.g., in the embodiments shown in Figures 1 and 2), the original state of the deformable membrane 20 is the deformed state (see Figure 2); while when the deformable membrane 20 deforms outward (e.g., in the embodiments shown in Figures 3 and 4), the original state of the deformable membrane 20 is the flat state (see Figure 3). Due to the initial pressure in chamber 100, as shown in Figure 12, a slightly positive pressure (Ph) (e.g., approximately 0.01 ± 10% psi) is generated at the suction port 301 of the micropipette 3 and maintained for a period of time (th), thus the test sample S is adsorbed by the suction port 301 of the micropipette 3 and prevented from being drawn into the micropipette 3 (see Figure 13). Then, by activating the drive device 30, the deformable membrane 20 is deformed, and the pressure at the connection port 102 continuously decreases for a period of time (tg) (e.g., 2 ± 10% sec) to reach a predetermined pressure (e.g., a predetermined negative pressure). Simultaneously, the suction pressure generated at the suction port 301 of the micropipette 3 gradually decreases to the stress pressure (Ps) (e.g., -0.1 ± 10% psi). The stress pressure (Ps) is maintained for a period of time (ts) (e.g., 1 ± 10% sec). During this stage, as shown in the microscope image of Figure 14, the aspiration depth D of the test sample S is determined using a computer program (not shown). Finally, the drive device 30 is further activated to continuously increase the pressure within the chamber 100 for a period of time (tr), thereby returning the deformable membrane 20 to its original state. Afterward, the exhaust valve 16 is opened to restore the pressure within the chamber 100 to atmospheric pressure through the exhaust port 17. Note that the pressure within the chamber 100 is gradually increased to avoid blowing the test sample S away from the micropipette 3. In some other embodiments, the pressure (Ph) generated by the suction port 301 of the micropipette 3 may be maintained at a slightly negative pressure (e.g., -0.01 ± 10% psi) for a period of time (e.g., 2 ± 10% sec) and adhere to the test sample S before the arrival stress pressure (Ps) is reduced.

[0066] During the test procedure shown in Figure 12, drive shaft 32 can be driven to move between a proximal position and a distal position.

[0067] In some embodiments where the deformable membrane 20 is deformed inward in a deformed state (e.g., the embodiments shown in Figures 1 and 2), (i) during time period (th), the drive shaft 32 is at the distal position and the deformable membrane 20 is in a deformed state (see Figure 2), and (ii) during time period (ts), the drive shaft 32 is at the proximal position and the deformable membrane 20 is in a flat state (see Figure 1).

[0068] In some other embodiments, the deformable membrane 20 is deformed outward in a deformed state (e.g., the embodiments shown in Figures 3 and 4), (i) during time period (th), the drive shaft 32 is in a distal position and the deformable membrane 20 is in a flat state (see Figure 3), and (ii) during time period (ts), the drive shaft 32 is in a proximal position and the deformable membrane 20 is in a deformed state (see Figure 4).

[0069] Figure 15 is a diagram illustrating another test procedure for determining the quality of test sample S according to some embodiments. The test procedure shown in Figure 15 is described with reference to Figures 10, 13, and 14. During the test procedure illustrated in Figure 15, regulating valve 15 is switched to adjust the pressure generated at the suction port 301 of the micropipette 3.

[0070] Referring to Figures 10 and 15, initially, the exhaust valve 16 is fully closed, the regulating valve 15 is fully closed, the pressure within the chamber 100 is adjusted and maintained at an initial pressure (e.g., a lower positive pressure), and the position of the drive shaft 32 is also moved to keep the deformable membrane 20 in its original state. For example, when the deformable membrane 20 is deformed inward (e.g., in the embodiments shown in Figures 1 and 2), the original state of the deformable membrane 20 is the deformed state (see Figure 2); while when the deformable membrane 20 is deformed outward (e.g., in the embodiments shown in Figures 3 and 4), the original state of the deformable membrane 20 is the flat state (see Figure 3). Due to the initial pressure of the chamber 100, by opening the regulating valve 15, a slight positive pressure (Ph) (e.g., about 0.01 ± 10% psi) is generated at the suction port 301 of the micropipette 3 and maintained for a period of time (th) (see Figure 15), so the test sample S is adsorbed by the suction port 301 of the micropipette 3 and prevented from being sucked into the micropipette 3 (see Figure 13). Then, regulating valve 15 is closed, and deformable membrane 20 is deformed by activating drive device 30, causing the pressure in chamber 100 to decrease continuously for a period of time (tg) (e.g., 3 ± 10% sec) to reach the preset suction pressure (Pn) (e.g., -0.13 ± 10% psi). The preset suction pressure (Pn) is maintained for a period of time (ta) (e.g., 2 ± 10% sec). Then, for a period of time (ts) (e.g., 4 ± 10% sec), the pressure in chamber 100 is slightly increased and maintained at the stress pressure (Ps) (e.g., -0.1 ± 10% psi) by slightly or fully opening regulating valve 15, while the suction pressure generated by suction port 301 of micropipette 3 is substantially equal to the stress pressure (Ps). During this stage (i.e., the test sample S is under stress pressure (Ps)), as shown in the microscope image of Figure 14, the aspiration depth D of test sample S is determined using a computer program (not shown). Finally, the drive unit 30 is further activated to continuously increase the pressure within chamber 100 over a period of time (tr), thereby causing the deformable membrane 20 to return to its original state. Afterward, the exhaust valve 16 is opened to allow the pressure within chamber 100 to return to atmospheric pressure via the exhaust port 17. Note that the pressure within chamber 100 is increased gradually to avoid blowing the test sample S away from the micropipette 3. In some other embodiments, the pressure (Ph) generated at the suction port 301 of the micropipette 3 may be maintained at a slightly negative pressure (e.g., -0.01 ± 10% psi) for a period of time (e.g., 2 ± 10% sec) and adhere to the test sample S before the preset suction pressure (Pn) is reached.

[0071] During the test procedure shown in Figure 15, drive shaft 32 can be driven to move between a proximal position and a distal position.

[0072] In some embodiments where the deformable membrane 20 is deformed inward in a deformed state (e.g., the embodiments shown in Figures 1 and 2), (i) during time period (th), the drive shaft 32 is located at the distal position and the deformable membrane 20 is in a deformed state (see Figure 2), and (ii) during time periods (ta, ts), the drive shaft 32 is located at the proximal position and the deformable membrane 20 is in a flat state (see Figure 1).

[0073] In some other embodiments, the deformable membrane 20 is deformed outward in a deformed state (e.g., the embodiments shown in Figures 3 and 4), (i) during time period (th), the drive shaft 32 is located at the distal position and the deformable membrane 20 is in a flat state (see Figure 3), and (ii) during time periods (ta, ts), the drive shaft 32 is located at the proximal position and the deformable membrane 20 is in a deformed state (see Figure 4).

[0074] By providing a detection system 2 including a pressure generating device 1, suction pressure can be generated at the suction port 301 of the micropipette 3 to aspirate the test sample S. The quality of the test sample S can be determined based on the aspiration depth D of the test sample S. For example, a test sample S with a relatively small aspiration depth D may have better quality. Furthermore, because the suction pressure generated by the pressure generating device 1 is relatively small, the test sample S is less likely to be damaged during the testing process, and a qualified test sample S can be implanted back into the mother to establish a successful pregnancy. [Examples of pressure applications used to promote blastocyst formation] []

[0075] As discussed above with respect to Figures 1 and 15, the pressure generating device 1 can be used to generate and apply pressure (e.g., negative pressure) to a test sample S (shown in Figures 13 and 14) via a micropipette 3, such as an oocyte (e.g., a mammalian oocyte that may be fertilized or unfertilized) or an embryo (e.g., a mammalian embryo). The quality of the test sample S can be determined based on the aspiration depth D of the test sample S shown in Figure 14 and other factors (e.g., morphology observed using the microscope 5 shown in Figure 11).

[0076] As will be discussed below, according to some embodiments of this disclosure, the pressure generating device 1 can be used to promote blastocyst formation by applying pressure (e.g., negative pressure) to oocytes using a micropipette (e.g., micropipette 3 or any other micropipette). Advantageously, applying pressure to oocytes (e.g., using pressure generating device 1 or any other pressure generating device) provides a non-invasive mechanism to improve oocyte quality and / or developmental potential (e.g., blastocyst formation probability) without harming the oocyte, and is particularly useful for improving the developmental potential of oocytes that would otherwise have a low probability of forming blastocysts (e.g., oocytes whose quality declines with age).

[0077] In some embodiments, the pressure generating device (e.g., pressure generating device 1 or any other pressure generating device) can apply pressure (e.g., the "two-stage" pressure control process shown in FIG. 15 and / or the "continuous" pressure control process shown in FIG. 12), pressure range (e.g., different pressure levels), and / or time range (e.g., different durations of pressure application) to oocytes via a micropipette (e.g., micropipette 3) to promote the probability of oocytes developing into or forming blastocysts, thereby addressing the problem of declining oocyte quality and / or improving the success rate of in vitro fertilization (IVF) and intracytoplasmic sperm injection (ICSI) procedures.

[0078] In some instances, the pressure applied to the oocyte by the pressure-generating device via a micropipette can be a range of pressures of -0.5 psi, -0.4 psi, -0.3 psi, -0.2 psi, -0.15 psi, -0.14 psi, -0.13 psi, -0.12 psi, -0.11 psi, -0.11 psi, -0.1 psi, -0.05 psi, 0.05 psi, 0.1 psi, 0.2 psi, 0.3 psi, 0.4 psi, or 0.5 psi, or any value in between.

[0079] In some instances, the time range during which the pressure generating device is applied to the oocyte via a micropipette (e.g., the duration of applying pressure with different pressure control strokes and / or pressure ranges) can be a time interval of, approximately, at least, or at least about 0.5 seconds, 1.0 seconds, 2.0 seconds, 3.0 seconds, 4.0 seconds, 5.0 seconds, 6.0 seconds, 7.0 seconds, 8.0 seconds, 9.0 seconds, 10.0 seconds, or any numerical range therebetween.

[0080] An example of pressure applied to the oocyte corresponds to the "continuous" pressure control procedure shown in Figure 12, applying a pressure of -0.13 psi for 2.0 seconds. More specifically, in this example, the stress pressure (Ps) in Figure 12 is -0.13 psi, and the time period (ts) in Figure 12 is 2.0 seconds. Another example of pressure applied to the oocyte corresponds to the "two-stage" pressure control procedure shown in Figure 15, applying a pressure of -0.15 psi for 3.0 seconds. More specifically, in this example, the stress pressure (Ps) in Figure 15 is -0.15 psi, and the time period (ts) in Figure 15 is 3.0 seconds. Advantageously, by applying pressure to the oocyte through the above-described different pressure control procedures, pressure ranges, and / or time ranges, it is less likely to damage the oocyte and more likely to effectively activate, invigorate, and / or stimulate the oocyte, thereby increasing the probability of the oocyte developing into a blastocyst.

[0081] In addition and / or selectively, the inner diameter of the micropipette can be adjusted, and in some embodiments may be, approximately, at least, or at least about 25 micrometers, 30 micrometers, 40 micrometers, 50 micrometers, 60 micrometers, 70 micrometers, 80 micrometers, 90 micrometers, 100 micrometers, or any numerical range thereof.

[0082] Table 1 illustrates pressure control procedures, pressure ranges, and time ranges that can be applied by a pressure generating device (e.g., pressure generating device 1 or any other pressure generating device) via a pipette (e.g., micropipette 3 or any other micropipette) to increase the probability of oocyte blastocyst formation, including pressure control procedures, pressure ranges, and time ranges. Pressure control process Pressure range Time range Options / Range Continuous or two-stage -0.5 psi to 0.5 psi 0.5 sec to 10 sec Table 1

[0083] As an example demonstrating the effectiveness of applying pressure to oocytes to promote blastocyst formation, an experiment was conducted on two groups of oocytes. The first group (e.g., the control group) was not subjected to pressure to promote blastocyst formation, while the second group (e.g., the experimental group) was subjected to pressure (e.g., pressure within the specified pressure control procedures, pressure ranges, and / or time ranges, such as a "two-stage" pressure control procedure applying pressure from 2.0 seconds to 0.13 psi) to promote blastocyst formation. The results showed that for the first group of oocytes, 75% were fertilized, 48% formed good embryos (e.g., good embryos on day 3), and 45% formed blastocysts. For the second group of oocytes subjected to pressure to promote blastocyst formation, 77% were fertilized, 51% formed good embryos (e.g., good embryos on day 3), and 56% formed blastocysts. [Example of an Oocyte Analysis System] []

[0084] Figures 16A and 16B illustrate applying pressure to oocytes 1610 according to certain embodiments of this disclosure to increase the probability of oocytes 1610 forming blastocysts, and generating oocyte grades using an oocyte analysis system 1600. As shown in Figure 16A, pressure may be generated by a pressure generating device (e.g., pressure generating device 1 and any other pressure generating device not shown in Figure 16A) and applied to oocytes 1610 via a micropipette 3 to increase the probability of oocytes 1610 forming blastocysts. The pressure generated by the pressure generating device may include any combination of pressure control procedures, pressure ranges, and / or time ranges described in Table 1. It should be noted that pressure generated by a pressure generating device (e.g., pressure generating device 1) (e.g., negative pressure) may occur and / or be used in systems other than the oocyte analysis system 1600 to increase the probability of oocytes 1610 forming blastocysts in other embodiments.

[0085] Image sequence 1602 may be generated before, after, or simultaneously with applying pressure to oocyte 1610 to increase the probability of blastocyst formation. More specifically, image sequence 1602 may include multiple images (e.g., images 1604A-1604N), each depicting oocyte 1610 and micropipette 3. More specifically, images 1604A-1604N may form a video depicting the process of aspirating oocyte 1610 into micropipette 3 (e.g., due to the application of pressure to oocyte 1610). Image 1604A may represent, for example, the first frame of the video, while image 1604N may represent, for example, the last frame of the video. Image 1604A depicts oocyte 1610 that has not yet been aspirated into micropipette 3, while image 1604N depicts oocyte 1610 that has at least been partially aspirated into micropipette 3. In some instances, the image sequence 1602 may have frame rates of 10 Hz, 20 Hz, 70 Hz, 3000 Hz, and total video lengths of 1 second, 2 seconds, 10 seconds, etc.

[0086] In some embodiments, the micropipette 3 is a pipette with a diameter between specific thresholds (e.g., between 10 micrometers (μm), 20 μm, 40 μm, 50 μm, 60 μm, 70 μm, 100 μm, etc.). The micropipette 3 may apply negative pressure (e.g., the pressure inside the pipette is lower than the pressure outside the pipette) to the oocyte 1610 to draw the oocyte 1610 into the pipette without damaging the oocyte 1610. Examples of pressures applied during the generation of image sequence 1602 may include pressures between -0.01 psi and -0.5 psi. For example, the micropipette 3 may come into contact with or otherwise contact the oocyte 1610. While image sequence 1602 illustrates the drawing of oocyte 1610 into the micropipette 3, in some embodiments, the micropipette 3 may apply other forms of mechanical stimulation (e.g., positive pressure). In this way, different morphological reactions of oocytes 1610 can be obtained for further processing by the oocyte analysis system 1600.

[0087] As shown in Figure 16B, the oocyte analysis system 1600 may include a feature preprocessing engine 1620 and a machine learning model 1630 for analyzing image sequences 1602 to generate oocyte quality information 1632. In some embodiments, the feature preprocessing engine 1620 may receive image sequences 1602 of oocytes 1610. Based on image sequences 1602, a segmentation model 1640 may identify objects 1660 associated with oocytes 1610. Based on objects 1660, a feature extractor 1650 may determine or extract features 1622 associated with objects 1660 identified by the segmentation model 1640. Although not illustrated in Figure 16B, the feature preprocessing engine 1620 may additionally and / or selectively utilize other information (e.g., stress values ​​applied to oocytes 1610 during the generation of image sequences 1602 and / or clinical information related to the patient acquiring oocytes 1610 as input for generating features 1622). Based on at least a subset of feature 1622, machine learning model 1630 can generate oocyte quality information 1632, which includes at least one oocyte grade 1680 indicating the likelihood of the oocyte developing into a usable blastocyst. As shown, oocyte grade 1680 can be one of grade A, grade B, grade C, or indeterminate (INC), as will be described in more detail below. Oocyte grade 1680 can be presented to the user for further analysis via an interactive user interface.

[0088] As shown in Figure 16B, the segmentation model 1640 can process image sequences 1602 of oocytes 1610 (e.g., including images 1604A to 1604N) to identify objects 1660 associated with the oocytes 1610 (e.g., objects representing different parts of the oocyte). More specifically, the objects 1660 identified by the segmentation model 1640 may include BBOX 1660A (bounding box), ZP 1660E (zona pellucida), PVS 1660D (periovosal space), FPB 1660B (first polar body), and CPM 1660C (cytoplasm). In some instances, the segmentation model 1640 can utilize machine learning algorithms or architectures, such as the U-Net architecture (with an optional MobileNet_v2 encoder backbone), to generate image segmentation masks for identifying BBOX 1660A, FPB 1660B, CPM 1660C, PVS 1660D, and ZP 1660E. It can be understood that image segmentation masks help isolate and identify different parts of the oocyte.

[0089] In some instances, segmentation model 1640 can be trained, tuned, and / or validated using machine learning techniques. Training segmentation model 1640 may include data selection, model training, and model validation to ensure that segmentation model 1640 can accurately segment and identify BBOX 1660A, FPB 1660B, CPM 1660C, PVS 1660D, and ZP 1660E. Data selection may include a dataset of collected and organized oocyte images for model training and validation. This dataset may include images from various sources (e.g., human, bovine, and porcine oocytes) to ensure diversity and robustness. These images may be labeled with bounding boxes, first polar bodies, cytoplasm, perivitelline space, and zona pellucida. Raw and labeled images may be further separated, using Git and Data Version Control (DVC) for better data control and management. This dataset may be divided into training and validation sets.

[0090] Once the dataset is ready, the segmentation model 1640 can be trained. The model training process may involve selecting an appropriate model architecture (e.g., convolutional neural networks like U-Net, a visual converter architecture, or similar), defining hyperparameters (e.g., encoder depth, decoder channels, batch size, initial learning rate, optimizer, scheduler, or similar parameters), and using data enhancement techniques (e.g., mesh warping, optical warping, random cropping, motion scaling, and rotation) to improve model performance. Furthermore, combinations of loss functions, such as multi-class focus loss and dice loss, can be used to handle class imbalance and improve segmentation accuracy. Training progress can be monitored using metrics such as mean intersection over union (mIOU) and F1 score.

[0091] After training segmentation model 1640, it can be validated using a validation dataset. The validation process ensures that segmentation model 1640 generalizes well to unseen data and accurately segments different parts of the oocyte. Based on the data selection and management, model training, and model validation processes described above, segmentation model 1640 can accurately identify and segment various parts of the oocyte, achieving precise feature extraction and grading. This, in turn, helps to objectively determine oocyte grade and improve the success rate of in-vitro fertilization (IVF) treatment.

[0092] In some instances, ZP 1660E may be the outer layer of the oocyte and may protect the oocyte and / or facilitate sperm union during fertilization. PVS 1660D may be the space between ZP 1660E and CPM 1660C. PVS 1660D may contain FPB 1660B. FPB 1660B may be a relatively small cell expelled from the oocyte during meiosis. The presence and morphology of FPB 1660B can provide insights into the oocyte's developmental potential. CPM 1660C may contain various organelles. CPM 1660C may be crucial for the oocyte's metabolic activity and developmental capacity.

[0093] Based on some or all of the BBOX 1660A, FPB 1660B, CPM 1660C, PVS 1660D, and ZP 1660E identified by segmentation model 1640, feature extractor 1650 can determine features 1622 associated with oocyte 1610. More specifically, features 1622 can be determined or calculated based on various combinations of measurements and / or geometric information associated with object 1660 (e.g., BBOX 1660A, FPB 1660B, CPM 1660C, PVS 1660D, and ZP 1660E). Features 1622 may include morphological features representing measurements of oocyte 1610 and the aspiration depth D of oocyte 1610 shown in Figure 14. In some instances, morphological features may be associated with object 1660 identified by segmentation model 1640. For example, morphological characteristics may include at least one of the following: the ellipticity of FPB 1660B, the thickness of ZP 1660E, the diameter of oocyte 1610, the area of ​​CPM 1660C, the compactness of CPM 1660C, the roundness of CPM 1660C, and the ratio between the area of ​​CPM 1660C and the total area of ​​CPM 1660C and PVS 1660D.

[0094] Based on feature 1622, machine learning model 1630 can generate oocyte quality information 1632, including at least oocyte grade 1680. In some instances, machine learning model 1630 can be a regression model. The regression model can include multiple weights. In some instances, the multiple weights can be iteratively adjusted through a training process associated with the regression model. Each of the multiple weights can be associated with one of the features 1622 used to determine oocyte grade 1680. For example, a first weight can be used to multiply by a first feature (e.g., the ellipticity of FPB 1660B) to produce a first product, a second weight can be used to multiply by a second feature (e.g., the area of ​​CPM 1660C) to produce a second product, and so on. Oocyte grade 1680 can be obtained by summing the first product, the second product, etc.

[0095] In some instances, as described above, the oocyte grade 1680 can classify oocyte quality into grades: A, B, C, and Indeterminate (INC). Grades A, B, and C can represent the likelihood of the oocyte developing into a usable blastocyst, which is useful for successful in-vitro fertilization (IVF) treatment. In some embodiments, the oocyte grade 1680 can represent a value assigned to a specific range, reflecting one of the four grades or different numbers within a grade.

[0096] Grade A represents the highest probability of developing into a usable blastocyst. Oocytes with Grade A oocytes are likely to exhibit optimal morphological and mechanical characteristics, such as ideal ellipticity of the first polar body, appropriate thickness of the zona pellucida, and / or good compactness and roundness of the cytoplasm. High-quality indicators associated with Grade A oocytes suggest their strong potential for successful fertilization and subsequent embryonic development.

[0097] Grade B oocytes may have a good chance of developing into usable blastocysts, although not as high as grade A oocytes. Grade B oocytes may still exhibit favorable morphological and mechanical characteristics, but may deviate slightly from the best seen in grade A oocytes. Despite these slight deviations, grade B oocytes may still be considered developable and have a reasonable chance of successful fertilization and embryonic development.

[0098] Oocytes classified as Grade C may have a lower likelihood of developing into usable blastocysts. Grade C oocytes may exhibit several deviations from optimal morphological and mechanical characteristics, such as irregular ellipticity of the first polar body, suboptimal zona pellucida thickness, and less desirable cytoplasmic compactness and roundness. Although Grade C oocytes may not be ideal, they may still have some potential for successful fertilization and embryonic development, albeit at a lower probability compared to Grade A and B oocytes.

[0099] Oocytes classified as Indeterminate (INC) may have an uncertain likelihood of developing into a usable blastocyst. This classification may be due to insufficient or ambiguous data (e.g., blurry image sequences), making accurate assessment of oocyte quality challenging. Indeterminate oocytes may require further analysis or additional data to determine their developmental capacity. An INC grade indicates that current assessment cannot provide a definitive conclusion regarding the oocyte's potential for successful fertilization and embryonic development. By classifying oocytes into these grades, the Oocyte Analysis System 1600 provides a more objective, automated, and time-efficient assessment of oocyte quality, helping embryologists and clinicians make informed decisions in the IVF process. [Flowchart Example] []

[0100] Figure 17 is a flowchart of an exemplary procedure 1700 for applying pressure to oocytes to increase the probability of oocytes forming blastocysts and to produce oocyte grades. Procedure 1700 may be implemented, for example, by a pressure generating device (e.g., pressure generating device 1) and the oocyte analysis system 1600 of Figures 16A and 16B (collectively, the "System"). Advantageously, procedure 1700 can facilitate the chance of oocytes (e.g., oocyte 1610) forming blastocysts and / or provide a determination of oocyte developmental capacity (e.g., whether the oocyte will develop into a usable blastocyst) without relying on artificial and subjective assessment by an embryologist.

[0101] In block 1702, the system applies pressure to the oocyte to increase the probability of the oocyte forming a blastocyst. For example, the pressure generating device may apply a slight negative pressure to the oocyte 1610 according to Table 1 via a micropipette 3, thereby increasing the probability of the oocyte 1610 forming a blastocyst. In some embodiments, process 1700 may end after block 1702.

[0102] In some instances, the oocyte analysis system 1600 may determine or otherwise select specific pressure control procedures, pressure ranges, and / or time ranges (e.g., selected from the pressure control procedures, ranges, and time ranges shown in Table 1) based on oocyte quality information 1632 to promote blastocyst formation of oocyte 1610. For example, based on an oocyte grade 1680 (e.g., square 1710) generated by a machine learning model 1630 relating to the corresponding pressure applied to the oocyte by a pressure generating device, the oocyte analysis system 1600 may determine that applying pressure within a pressure range between a first value and a second value, or a constant value, is more likely to result in a better oocyte grade 1680 (e.g., grade A) compared to applying other pressure ranges to the oocyte. In this example, the oocyte analysis system 1600 may control a pressure generating device (e.g., pressure generating device 1) to apply pressure values ​​between the first and second values, or a constant value, to the oocyte 1610 via a micropipette to promote blastocyst formation.

[0103] As another example, the oocyte analysis system 1600 can select or determine pressure ranges and / or time ranges based on experimental results. In this example, experimental results may show that applying pressure values ​​between a first value (e.g., -0.2 psi) and a second value (e.g., -0.1 psi) to oocytes results in 56% of oocytes forming blastocysts, while applying pressure values ​​between other values ​​(e.g., -0.3 psi to -0.2 psi) results in 45% of oocytes forming blastocysts. Based on the experimental results, the oocyte analysis system 1600 can control the pressure generating device to apply pressure values ​​between -0.2 psi and -0.1 psi to oocytes 1610 via a micropipette to promote blastocyst formation. In this way, the oocyte analysis system 1600 can determine pressure values, ranges, etc.; time values, ranges, etc.

[0104] In block 1704, the system acquires images that form an oocyte image sequence. As described above, the images (e.g., image sequence 1602) can be captured by a microscope camera and depict a series of events showing the oocyte's geometry, deformation, and / or movement resulting from the application of force to the oocyte by a tool (e.g., micropipette 3). In some instances, the system acquires multiple images that form a time-related image sequence. This image sequence depicts an oocyte (e.g., oocyte 1610) and a portion of the tool (e.g., micropipette 3) applying pressure to the oocyte. Each individual image in the sequence may be associated with an individual pressure value applied to the oocyte at its respective image capture time. It should be understood that blocks 1702 and 1704 can be performed simultaneously or at least partially overlap in time. For example, images forming an oocyte image sequence can be acquired simultaneously while pressure (e.g., negative pressure) is applied to the oocyte.

[0105] In block 1706, the system identifies oocyte-related objects based on a segmentation model using an oocyte image sequence. In some examples, the system identifies oocyte-related objects using segmentation model 1640. These objects may include various parts of the oocyte, such as the zona pellucida (e.g., ZP 1660E), the perivitelline space (e.g., PVS 1660D), the first polar body (e.g., FPB 1660B), the cytoplasm (e.g., CPM 1660C), and the bounding box associated with the micropipette portion that applies pressure to the oocyte (e.g., BBOX 1660A).

[0106] In block 1708, the system determines features associated with the oocyte based on the identified object (e.g., feature 1622). In some instances, feature 1622 may include morphological features indicating measurements of the oocyte during a time period and the aspiration depth of the oocyte into the pressure-applied micropipette section 3. Morphological features may include characteristics such as the ellipticity of the first polar body, zona pellucida thickness, oocyte diameter, cytoplasmic area, cytoplasmic compactness, cytoplasmic roundness, and the ratio between the cytoplasmic area and the total area of ​​the cytoplasm and perivitelline space.

[0107] In block 1710, the system generates an oocyte grade based on at least one subset of the features identified in block 1708 using a machine learning model. In some examples, the system generates an oocyte grade (e.g., oocyte grade 1680) based on an input containing at least one subset of features 1622 using a machine learning model 1630. In some embodiments, this subset may include only aspiration depth. In some embodiments, this subset may include aspiration depth and at least one other feature. Oocyte grade 1680 may at least indicate the likelihood of an oocyte developing into a usable blastocyst. Machine learning model 1630 may be a regression model that includes multiple weights, each associated with one of the features, to generate oocyte grade 1680. Oocyte grade 1680 may then be provided via an interactive user interface for further analysis. [System Block Diagram Example] []

[0108] Figure 18 depicts the general architecture of an exemplary system. In some embodiments, the system can be used to perform the functions described herein. In some embodiments, the system may be an oocyte analysis system 1600, which includes an arrangement of computer hardware and software configured to implement the features disclosed herein, such as pressure generating devices and micropipettes. The oocyte analysis system 1600 may include more (or fewer) elements than shown in Figure 18. However, not all of these elements need to be shown to provide sufficient disclosure.

[0109] As shown, the oocyte analysis system 1600 includes a processor 1802, a pressure tool 1804 (e.g., the micropipette 3 of Figures 13, 14, and 16A), a pressure generating device 1806 (e.g., the pressure generating device 1 of Figure 1 or any other pressure generating device), an image sensor 1808 (e.g., one or more microscope cameras for capturing image sequences 1602 of Figure 16A), and data storage 1810, all of which can communicate with each other via a communication bus 1812. In some embodiments, the pressure tool 1804 may not be included, and the oocyte analysis system 1600 may represent a back-end processing system. As described above, the pressure generating device 1806 may be the pressure generating device 1 of Figure 1 or any other pressure generating device that can generate pressure (e.g., the pressure generated according to Table 1) which will be applied (e.g., by means of the pressure tool 1804 such as the micropipette 3) to the oocyte to increase the probability of the oocyte forming a blastocyst. In some embodiments, the oocyte analysis system 1600 may be configured to handle requests from other devices or modules, such as requests from remote devices or servers, to analyze oocyte quality via a network interface not shown in FIG18. Data storage 1810 may illustratively be any non-transitory computer-readable data storage, and in various embodiments may store any or all of the elements depicted in FIG18 that are loaded into memory 1814.

[0110] Processor 1802 may also communicate with memory 1814. Memory 1814 may contain computer program instructions (grouped into modules or components in some embodiments) executable by processor 1802 to implement one or more embodiments. Memory 1814 typically includes RAM, ROM, and / or other persistent, auxiliary, or non-transitory computer-readable media. Memory 1814 may store operating system 1816, which provides processor 1802 with computer program instructions for the general administration and operation of oocyte analysis system 1600. Memory 1814 may further store specific computer-executable instructions and other information (which may be referred to herein as "modules" or "engines") for implementing the features of this disclosure. For example, memory 1814 may include feature preprocessing engine 1620 and machine learning model 1630, which can implement the features of this disclosure as described above. Memory 1814 may further store, for example, a user interface module 1818 that enables information to be presented to the user interface of a user device (not shown in FIG. 18). Furthermore, memory 1814 may store database 1820 (e.g., for storing parameters of different types of machine learning models) and features 1830 (e.g., including at least feature 1622 of Figure 16B), which can be extracted by feature preprocessing engine 1620. As various operations are performed, all modules or elements loaded into memory 1814 may also be stored in data storage 1810.

[0111] It will be acknowledged that many of the components depicted in Figure 18 are optional, and embodiments of the oocyte analysis system 1600 may or may not combine these components. Furthermore, the components do not need to be unique or separate. Components can also be reorganized. In some embodiments, components illustrated as part of the oocyte analysis system 1600 may be additionally or alternatively included in other computing devices, such that some features of this disclosure can be performed by the oocyte analysis system 1600, while other features are performed by another computing device.

[0112] All methods and tasks described herein can be performed entirely automatically by a computer system. In some cases, a computer system may include multiple different computers or computing devices (e.g., physical servers, workstations, storage arrays, cloud computing resources, etc.) that communicate and collaborate via a network to perform the described functions. Each such computing device typically includes a processor (or multiple processors) that executes program instructions or modules stored in memory or other non-transitory computer-readable storage media or devices (e.g., solid-state storage devices, disk drives, etc.). The various functions disclosed herein may be embodied in these program instructions or implemented in computer system application-specific circuitry (e.g., ASICs or FPGAs). When a computer system includes multiple computing devices, these devices may, but do not necessarily, be located in the same location. The results of the disclosed methods and tasks can be persistently stored by converting physical storage devices (such as solid-state memory chips or disks) into different states. In some embodiments, the computer system may be a cloud computing system whose processing resources are shared by multiple different business entities or other users.

[0113] The processes described or illustrated in this disclosure may begin in response to an event, such as according to a predetermined or dynamically determined schedule, on demand when initiated by a user or system administrator, or in response to some other event. When these processes are initiated, a set of executable program instructions stored on one or more non-transitory computer-readable media (e.g., hard disk drives, flash memory, removable media, etc.) may be loaded into the memory (e.g., RAM) of a server or other computing device. The executable instructions can then be executed by the hardware-based computer processor of the computing device. In some embodiments, these processes, or portions thereof, may be implemented serially or in parallel on multiple computing devices and / or multiple processors.

[0114] According to embodiments, certain actions, events, or functions of any process or algorithm described herein may be performed in a different order, and may be added, combined, or omitted entirely (e.g., not all described operations or events are necessary for the practice of the algorithm). Furthermore, in some embodiments, operations or events may be performed in parallel, for example, through multithreading, interrupt handling, or multiple processors or processor cores or other parallel architectures, rather than sequentially.

[0115] The various illustrative logic blocks, modules, routines, and algorithm steps related to the embodiments disclosed herein can be implemented as electronic hardware (e.g., ASICs or FPGA devices), running computer software on computer hardware, or a combination of both. Furthermore, the various illustrative logic blocks and modules related to the embodiments disclosed herein can be implemented or executed by a machine, such as a processor device, a digital signal processor (“DSP”), an application-specific integrated circuit (“ASIC”), a field-programmable gate array (“FPGA”) or other programmable logic device, discrete gate or transistor logic, discrete hardware components, or any combination designed to perform the functions described herein. The processor device may be a microprocessor, but alternatively, it may be a controller, a microcontroller, or a state machine, a combination thereof, or the like. The processor device may include circuitry configured to process computer-executable instructions. In another embodiment, the processor device includes an FPGA or other programmable device that performs logic operations without processing computer-executable instructions. The processor device may also be implemented as a combination of computing devices, such as a combination of a DSP and a microprocessor, multiple microprocessors, one or more microprocessors combined with a DSP core, or any other such configuration. While this description primarily concerns digital technologies, processor devices may also primarily include analog elements. For example, some or all of the rendering techniques described herein can be implemented in analog circuitry or hybrid analog and digital circuitry. Computing environments can include any type of computer system, including but not limited to microprocessor-based computer systems, mainframes, digital signal processors, portable computing devices, device controllers, or computing engines within devices, to name just a few.

[0116] Elements of the methods, processes, routines, or algorithms related to the embodiments disclosed herein may be embodied directly in hardware, in a software module executed by a processor device, or a combination of both. The software module may reside in RAM memory, flash memory, ROM memory, EPROM memory, EEPROM memory, a register, a hard disk, a removable magnetic disk, a CD-ROM, or any other form of non-transitory computer-readable storage medium. Exemplary storage media may be coupled to a processor device, enabling the processor device to read information from and write information to the storage medium. Alternatively, the storage medium may be integrated into the processor device. The processor device and the storage medium may reside in an ASIC. The ASIC may reside in a user terminal. Alternatively, the processor device and the storage medium may reside as discrete components in the user terminal.

[0117] The conditional language used herein, such as “may,” “possibly,” “perhaps,” “can,” “for example,” etc., unless specifically stated or understood from the context, is generally intended to express that certain embodiments include certain features, elements, or steps, while other embodiments do not. Therefore, such conditional language does not generally imply that a feature, element, or step is necessary for one or more embodiments, or that one or more embodiments necessarily include logic for determining whether such features, elements, or steps are included in any particular embodiment, regardless of any additional input or prompting. The terms “comprising,” “including,” “having,” etc., are synonymous and used inclusively in an open-ended manner, not excluding additional elements, features, behaviors, operations, etc. Furthermore, the term “or” is used in its inclusive sense (rather than exclusive), so when used to connect lists of elements, the term “or” indicates one, some, or all of the elements in the list.

[0118] Unless otherwise specified, selective language such as "at least one of X, Y, or Z" is generally understood in context to mean that an item, term, etc., can be X, Y, or Z, or any combination thereof (e.g., X, Y, or Z). Therefore, such selective language is generally not intended to imply, nor should it imply, that certain embodiments require at least one of X, at least one of Y, and at least one of Z to be present.

[0119] While the above detailed description has shown, described, and pointed out novel features applicable to various embodiments, it is understood that various omissions, substitutions, and changes may be made to the form and details of the illustrated apparatus or algorithms without departing from the spirit of the disclosure. It will be appreciated that some embodiments described herein may be embodied in a form that does not provide all the features and benefits described herein, as certain features may be used or practiced separately from other features. All modifications within the meaning and equivalent scope of the claims should be included within its scope. [Example Clause] []

[0120] This disclosure can be described according to the following exemplary provisions. Features described in the following exemplary embodiments may be combined with additional features disclosed herein. Furthermore, additional inventive combinations of features disclosed herein are not specifically mentioned in the following exemplary embodiments and do not include features identical to those in the specific embodiments described below. For brevity, the following exemplary embodiments do not identify each inventive aspect of this disclosure. The following exemplary embodiments are not intended to identify any key or essential features of the subject matter described herein. Any of the following exemplary provisions, or any feature of the exemplary provisions, may be combined with any one or more other exemplary provisions, or features of the exemplary provisions, or other features of this disclosure.

[0121] Clause 1. Pressure generating device, comprising: A tank having a chamber therein, and including an opening and a communication port in fluid communication with the chamber; The deformable membrane is configured to seal the opening and can deform between a flat state and a deformable state; A drive unit is disposed in the tank and includes a motor body and a drive shaft having a first shaft end configured to face the deformable membrane. The drive shaft is driven by the motor body to move between a distal position (where the first shaft end is away from the motor body) and a proximal position (where the first shaft end is close to the motor body); and The connecting unit is configured to couple the second shaft end to the deformable membrane and allow the deformable membrane to be driven by the drive shaft to change between a flat state (where the first shaft end is in one of the distal and proximal positions) and a deformable state (where the first shaft end is 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.

[0122] Clause 2. The pressure generating device as claimed in Clause 1, wherein the deformable membrane deforms inward in a deformable state.

[0123] Clause 3. The pressure generating device as claimed in Clause 1, wherein the deformable membrane deforms outward in a deformable state.

[0124] Clause 4. The pressure generating device as claimed in Clause 1, wherein: The tank includes A main housing having the chamber therein, and including the opening and the communication port, and A side shell is detachably disposed on the main shell, such that the deformable membrane is fixed between the main shell and the side shell, thereby sealing the opening; The motor body is immovably mounted on the side housing; and The drive shaft extends along the axis and is driven by the motor body to move toward or away from the deformable membrane, thereby causing the deformable membrane to transition between a flat state and a deformable state.

[0125] Clause 5. The pressure generating device as claimed in Clause 4, wherein the main housing extends along a longitudinal axis and terminates at a closed end and a connecting end having the opening.

[0126] Clause 6. Pressure generating device as claimed in Clause 4, wherein: The side shell includes The side shell body has a distal end and a proximal end opposite to the distal end, and forms a channel extending from the distal end to the proximal end, and A flange body, extending radially and laterally from the proximal end of the side shell body, and detachably mounted on the main shell member; and The motor body has an internal portion that receives the motor within a channel in the side housing body. An outer portion extending from the inner portion in a direction away from the main housing and disposed outside the side housing body, and A flange portion extending radially from the outer portion and detachably fixed to the distal end of the side shell body.

[0127] Clause 7. The pressure generating device as claimed in Clause 1, wherein the connecting unit comprises: A connecting sleeve, coupled to a first end of the drive shaft to allow movement of the connecting sleeve with the drive shaft, the connecting sleeve having a first sleeve portion, a second sleeve portion with an external dimension smaller than the external dimension of the first sleeve portion, and a shoulder surface between the first sleeve portion and the second sleeve portion; a bearing sleeve, adapted to fit onto the second sleeve portion to allow movement of the bearing sleeve with the connecting sleeve, and disposed between the connecting sleeve and the deformable membrane, the bearing sleeve having a first sleeve edge end abutting against the shoulder surface, and a second sleeve edge end opposite the first sleeve edge end; and The bearing cap has a grooved engagement portion configured to engage with the second sleeve edge to allow the bearing cap to move together with the bearing sleeve. The mounting portion is opposite to the engagement portion and is fixed to the first surface of the deformable membrane so as to transmit force from the drive shaft to the deformable membrane.

[0128] Clause 8. The pressure generating device as claimed in Clause 7, wherein the deformable diaphragm has a through hole, and the connecting unit further includes having An enlarging head is disposed on the second surface of the deformable membrane opposite to the first surface, and A fastening rod extends from the enlarged head through a through hole in the deformable membrane to a rod end, the rod end of which engages tightly with a hole formed in the mounting portion of the bearing cap, so that the deformable membrane is secured to the bearing cap by the fastener.

[0129] Clause 9. The pressure generating device as claimed in Clause 7, wherein the connecting unit further includes A first washer is disposed between the mounting portion and the first surface of the deformable membrane, and A second washer is disposed between the enlarged head and the second surface of the deformable membrane.

[0130] Clause 10. The pressure generating device as claimed in Clause 1 further includes a light sensor that is immovable relative to the tank, such that the light sensor detects the displacement of the drive shaft.

[0131] Clause 11. The pressure generating device as claimed in Clause 10 further includes a marker mounted on a second end of the drive shaft opposite the first shaft end, such that the marker moves with the drive shaft and has a plurality of detectable positions detectable by the photosensitive sensor to determine the displacement of the drive shaft.

[0132] Clause 12. The pressure generating device as claimed in Clause 1, wherein The hardness range of this deformable membrane is from 0 Shore A to 100 Shore A. The thrust of this drive unit ranges from 100 grams to 1000 grams, and The drive unit has a stroke range from 3 mm to 50 mm.

[0133] Clause 13. A testing system for detecting the quality of test samples, including oocytes or embryos, comprising: The pressure generating device as claimed in Clause 1; the micropipette for drawing test samples; and A connecting tube configured to connect the communication port of the tank to the micropipette is used to apply a predetermined pressure to the test sample.

[0134] Clause 14. The detection system as claimed in Clause 13, wherein the inner diameter of the micropipette ranges from 10 micrometers to 100 micrometers.

[0135] Clause 15. The detection system as claimed in Clause 13, wherein a pressure ranging from 0.5 psi to -0.5 psi is generated at the aspiration port of the micropipette.

[0136] Clause 16. The detection system as claimed in Clause 15, wherein the connecting tube includes a first section connected to a communication port of the tank and a second section connected to a micropipette, the first and second sections being interconnected by a regulating valve for adjusting the pressure generated at the suction port of the micropipette.

[0137] 1: Pressure generating device 2: Detection System 3: Micropipettes 4: Connecting pipe 5: Microscope 10: Tank 11: Main shell 12: Side shell 15: Control valve 16: Exhaust valve 17: Exhaust port 18: Syringe holder 20: Deformable membrane 30: Drive unit 31: Motor body 32: Drive shaft 40: Connection Unit 41: Connecting sleeve 42: Bearing sleeve 43: Bearing cover 44, 91, 126, 415: Fasteners 45: First washer 46: Second washer 80: Light sensor 81: Circuit Board 90: Markings 100: Chamber 101: Opening 102: Connecting Port 111: Closed end 112: Connection end 121: Side shell body 122: Remote 123: Proximal end 124: Channel 125: Flange body 142: Connecting rod 200: Through hole 201: First Surface 202: Second Surface 301: Suction Port 311: Internal Parts 312: External Part 313: Flange portion 314: Fasteners 321: First shaft end 322: Second shaft end 401: First Pipe Section 402: Second Pipe Section 403: Branch pipe 411: First sleeve section 412: Second sleeve section 413: Shoulder surface 414: Through hole 421: The First Set of Edges 422: Second set of edges 423: Bearing Balls 431: Joint portion 432: Installation section 433: Hole 441: Enlarged head 442: Fastening rod 443: End of rod 501: Petri dish 1600: Oocyte Analysis System 1602: Image sequence 1604A, 1604N: Images 1610: Oocyte 1620: Feature Preprocessing Engine 1622, 1830: Characteristics 1630: Machine Learning Model 1632: Oocyte Quality Information 1640: Segmentation Model 1650: Feature Extractor 1660:Object 1660A:BBOX 1660B:FPB 1660C:CPM 1660D:PVS 1660E:ZP 1680: Oocyte grade 1700: Process 1702, 1704, 1706, 1708, 1710: Squares 1802: Processor 1804: Pressure Tools 1806: Pressure generating device 1808: Image Sensor 1810: Data Storage 1812: Communication Bus 1814: Memory 1816: Operating System 1818: User Interface Module 1820: Database 4311: Groove A, L: Axis D: Inhalation depth S: Test sample

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 one or more computer systems as described in claim 10, wherein the pressure is between -0.5 psi and 0.5 psi.

14. The method implemented by one or more computer systems 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 applied to the oocyte increases 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 an individual pressure value applied to the oocyte at a 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 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