# US 2023/0274447 A1 · System and method for automated cell positioning

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2023/0274447 A1
- Document ID: US20230274447A1
- Status: Published application
- Kind: A1
- Application number: 18/144,430
- Filed: 2023-05-08
- Published: 2023-08-31
- Earliest claimed: 2021-11-05
- Assignees: Thread Robotics Inc.
- Applicants: Thread Robotics Inc.
- Inventors: Kiran Joshi; Gregory Burd
- Web page: https://patentgrep.com/patent/US20230274447A1

## CPC

- G06T 7/248: {involving reference images or patches}
- C12N 5/0604: {Whole embryos; Culture medium therefor}
- C12N 5/0608: {Germ cells (production of embryos, nuclear transfer A01K67/027)}
- G06T 7/73: using feature-based methods
- G06T 2207/10016: Video; Image sequence
- G06T 2207/10056: Microscopic image
- G06T 2207/20081: Training; Learning
- G06T 2207/30024: Cell structures in vitro; Tissue sections in vitro
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- C12N: MICROORGANISMS OR ENZYMES; COMPOSITIONS THEREOF; PROPAGATING, PRESERVING, OR MAINTAINING MICROORGANISMS; MUTATION OR GENETIC ENGINEERING; CULTURE MEDIA (microbiological testing media C12Q1/00)

## Abstract

The method for automated cell positioning can include: sampling a video of a scene having a gamete, tracking the gamete, and positioning the gamete within a target region. The method can optionally include: determining attribute values for the gamete, selecting the gamete, reorienting the gamete, and/or manipulating the gamete, and/or any suitable steps.

## Claims

### Claim 1

A system, comprising:
an imaging system comprising a camera, wherein the imaging system is configured to sample a video of a gamete;
a processor configured to track the gamete across frames of the video;
a positioning system comprising a stage, wherein the positioning system is configured to position the gamete within a target region based on a gamete track; and
an aspirator configured to retrieve the gamete from the target region.

### Claim 2 (depends on 1)

The system of claim 1, wherein the positioning system is configured to automatically position the gamete in substantially real time.

### Claim 3 (depends on 1)

The system of claim 1, wherein the stage is actuatable in at least two dimensions.

### Claim 4 (depends on 3)

The system of claim 3, wherein the stage comprises an xy stage.

### Claim 5 (depends on 1)

The system of claim 1, wherein the target region comprises a center of a field of view of the imaging system.

### Claim 6 (depends on 1)

The system of claim 1, wherein the processor is further configured to determine a focus level based on the video using a focus model, wherein the imaging system comprises a focus actuation system, wherein the focus actuation system is automatically actuated based on the focus level.

### Claim 7 (depends on 1)

The system of claim 1, wherein the aspirator is configured to move to a target z-location and aspirate at the target z-location to retrieve the gamete.

### Claim 8 (depends on 1)

The system of claim 1, wherein the aspirator is configured to retrieve the gamete without immobilizing the gamete.

### Claim 9 (depends on 1)

The system of claim 1, wherein the imaging system is configured to sample the video at at least 15 frames per second.

### Claim 10 (depends on 1)

The system of claim 1, wherein the gamete is retrieved for use in an assistive reproductive technology.

### Claim 11

A method, comprising:
sampling a video of a gamete;
determining a gamete track across frames of the video;
automatically positioning the gamete within a target region based on the gamete track; and
retrieving the gamete within the target region.

### Claim 12 (depends on 11)

The method of claim 11, wherein retrieving the gamete comprises: positioning an aspirator and aspirating the gamete using the aspirator.

### Claim 13 (depends on 12)

The method of claim 12, wherein positioning the aspirator comprises moving the aspirator in the z-direction.

### Claim 14 (depends on 12)

The method of claim 12, wherein the gamete is aspirated from a head of the gamete.

### Claim 15 (depends on 11)

The method of claim 11, wherein the gamete is one of a set of gametes, the method further comprising:
determining an attribute value for the gamete based on the video, using a trained machine learning model; and
selecting the gamete from the set of gametes based on the attribute value.

### Claim 16 (depends on 15)

The method of claim 15, further comprising: evaluating whether a flat side of the gamete is depicted in a frame of the video, wherein the attribute value for the gamete is determined when the flat side of the gamete is depicted in the frame.

### Claim 17 (depends on 15)

The method of claim 15, wherein the attribute value comprises a timeseries of attribute values.

### Claim 18 (depends on 15)

The method of claim 15, wherein the attribute value comprises a morphology attribute value and a motility attribute value.

### Claim 19 (depends on 15)

The method of claim 15, wherein the gamete is selected using a trained selection model, wherein training the selection model is trained using specialist-labeled images.

### Claim 20 (depends on 11)

The method of claim 11, further comprising fertilizing an ovum using the gamete.
