# US 2022/0036041 A1 · Fertility Window Prediction Using a Convolutional Neural Network (CNN) and Other Learning Methods

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

- Number: US 2022/0036041 A1
- Document ID: US20220036041A1
- Status: Published application
- Kind: A1
- Application number: 16/945,716
- Filed: 2020-07-31
- Published: 2022-02-03
- Earliest claimed: 2020-07-31
- Assignees: Bridging Biosciences, LLC
- Applicants: Bridging Biosciences, LLC
- Inventors: Tapley Holland
- Web page: https://patentgrep.com/patent/US20220036041A1

## CPC

- G01N 33/689: {related to pregnancy or the gonads}
- G06V 20/693: {Acquisition}
- G06T 7/0012: {Biomedical image inspection}
- G06V 10/82: using neural networks
- H04N 23/51: Housings
- H04N 23/56: provided with illuminating means
- A61B 10/0012: {Ovulation-period determination (for animals A61D17/002)}
- A61K 35/12: Materials from mammals; Compositions comprising non-specified tissues or cells; Compositions comprising non-embryonic stem cells; Genetically modified cells (vaccines or medicinal preparations containing antigens or antibodies A61K39/00)
- G01N 33/56972: {White blood cells}
- G06T 2200/24: involving graphical user interfaces [GUIs]
- G06T 2207/10056: Microscopic image
- G06T 2207/20081: Training; Learning
- G06T 2207/20084: Artificial neural networks [ANN]
- G06T 2207/30024: Cell structures in vitro; Tissue sections in vitro
- G01N: INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES (measuring or testing apparatus or processes other than immunoassay, involving enzymes or microorganisms C12M, C12Q)
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- H04N: PICTORIAL COMMUNICATION, e.g. TELEVISION
- A61B: DIAGNOSIS; SURGERY; IDENTIFICATION (usefulness limited to only animals A61D)
- A61K: PREPARATIONS FOR MEDICAL, DENTAL OR TOILETRY PURPOSES (devices or methods specially adapted for bringing pharmaceutical products into particular physical or administering forms A61J3/00; chemical aspects of, or use of materials for deodorisation of air, for disinfection or sterilisation, or for bandages, dressings, absorbent pads or surgical articles A61L; soap compositions C11D)

## Abstract

A system and method of biological testing and deep learning to predict fertility based on ferning patterns and detecting white blood cells in cervical mucous samples.

## Claims

### Claim 1

A method to predict a fertility window of a mammal, the method comprising:
providing a housing having a slide holder, a light source, and a camera;
providing a slide having first and second reservoirs;
placing a first mucous sample in the first reservoir and a second mucous sample in the second reservoir;
inserting the slide into the slide holder;
capturing one or more images of the first mucous sample and the second mucous sample; and
analyzing the one or more images to determine whether white blood cells are present within the first mucous sample and identify ferning patterns within the second mucous sample.

### Claim 2 (depends on 1)

The method of claim 1, wherein the first mucous sample is a cervical mucous of a subject mixed with a saline solution.

### Claim 3 (depends on 2)

The method of claim 2, wherein the saline solution has a concentration on the order of 0.9% salt.

### Claim 4 (depends on 2)

The method of claim 2, wherein the cervical mucous is mixed with the saline solution at a ratio of at least 1:50.

### Claim 5 (depends on 1)

The method of claim 1 and further comprising:
drying the second mucous sample on the slide, wherein the second mucous sample is a cervical mucous of a subject;
providing the one or more images to a computer vision model; and
determining, at the computer vision model, if the one or more images contain a ferning pattern indicative of a biological condition of the subject.

### Claim 6 (depends on 1)

The method of claim 1, wherein the capturing of the one or more images comprises:
capturing one or more first images;
moving the slide holder relative to the camera; and
capturing one or more second images.

### Claim 7 (depends on 1)

The method of claim 1, wherein the capturing of the one or more images comprises:
capturing one or more first images;
moving the light source relative to the camera; and
capturing one or more second images.

### Claim 8 (depends on 1)

The method of claim 1, wherein the analyzing the one or more images comprises a processor programmed to execute computer program instructions that, when executed, use a convolutional neural network to compare the one or more images to stored images.

### Claim 9 (depends on 1)

The method of claim 1, and further comprising analyzing the one or more images to determine whether red blood cells are present within the first mucous sample.

### Claim 10 (depends on 2)

The method of claim 2, wherein the saline solution does not contain a detergent or anticoagulant.

### Claim 11

A system comprising:
a housing comprising a camera having a field of view, a light source configured to provide illumination to the field of view, and a slide holder configured to hold a slide containing a cervical mucous sample from a subject such that at least a portion of the slide is disposed within the field of view; and
a computer system comprising one or more processors programmed to execute computer program instructions that, when executed, cause the computer system to:
capture, using the camera, a first image of the cervical mucous sample;
move the light source relative to the slide;
capture, using the camera, a second image of the cervical mucous sample; and
analyze the first image and the second image using a visual learning algorithm to determine if there are white blood cells in the cervical mucous sample.

### Claim 12 (depends on 11)

The system of claim 11, wherein the computer program instructions are configured to estimate a fertility window of the subject based at least in part on the determination by the visual learning algorithm that there are no white blood cells in the cervical mucous sample.

### Claim 13 (depends on 11)

The system of claim 11, wherein the visual learning algorithm is a convolutional neural network.

### Claim 14 (depends on 11)

The system of claim 11, wherein the computer program instructions are configured to cause the computer system to move the slide relative to the camera to capture a third image of the cervical mucous sample.

### Claim 15 (depends on 11)

The system of claim 11, wherein the computer program instructions are configured to identify any ferning patterns in the cervical mucous sample.

### Claim 16 (depends on 15)

The system of claim 15, wherein the computer program instructions are configured to determine a biological condition of the subject based on the determination there are white blood cells in the cervical mucous sample and the ferning patterns identified in the cervical mucous sample.

### Claim 17 (depends on 15)

The system of claim 15, wherein the computer program instructions are configured to correlate a biological condition of the subject to characteristics of the ferning patterns identified in the cervical mucous sample.

### Claim 18 (depends on 16)

The system of claim 16, wherein the biological condition is fertility disorder caused by PCOS.

### Claim 19 (depends on 11)

The system of claim 11 and further comprising a user interface coupled to the computer system that displays an output of the visual learning algorithm.
