# US 2022/0044362 A1 · Deep Learning Model for Noise Reduction in Low SNR Imaging Conditions

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

- Number: US 2022/0044362 A1
- Document ID: US20220044362A1
- Status: Published application
- Kind: A1
- Application number: 17/444,499
- Filed: 2021-08-05
- Published: 2022-02-10
- Earliest claimed: 2020-08-07
- Assignees: Nanotronics Imaging, Inc.
- Applicants: Nanotronics Imaging, Inc.
- Inventors: Denis Sharoukhov; Tonislav Ivanov; Jonathan Lee
- Web page: https://patentgrep.com/patent/US20220044362A1

## CPC

- G06T 5/70: Denoising; Smoothing
- G06T 3/4046: using neural networks
- G06T 5/50: using two or more images, e.g. averaging or subtraction
- G06T 5/60: using machine learning, e.g. neural networks
- G06T 2207/10016: Video; Image sequence
- G06T 2207/10056: Microscopic image
- G06T 2207/10064: Fluorescence image
- G06T 2207/20081: Training; Learning
- G06T 2207/20084: Artificial neural networks [ANN]
- G06T 2207/30024: Cell structures in vitro; Tissue sections in vitro
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL

## Abstract

Embodiments disclosed herein are generally related to a system for noise reduction in low signal to noise ratio imaging conditions. A computing system obtains a set of images of a specimen. The set of images includes at least two images of the specimen. The computing system inputs the set of images of the specimen into a trained denoising model. The trained denoising model is configured to output a single denoised image of the specimen. The computing system receives, as output from the trained denoising model, a single denoised image of the specimen.

## Claims

### Claim 1

A system, comprising:
an imaging apparatus configured to capture images of a specimen on a background; and
a computing system in communication with the imaging apparatus, the computing system comprising one or more processors and a memory, the memory having programming coded thereon, which, when executed by the one or more processors, causes the computing system to perform operations comprising:
obtaining, by the computing system, a set of images of the specimen from the imaging apparatus, wherein the set of images includes at least two images of the specimen against the background;
denoising, by the computing system, the set of images by inputting the set of images of the specimen into a denoising model, the denoising model configured to output a single denoised image of the specimen; and
generating, as output from the denoising model, the single denoised image of the specimen.

### Claim 2 (depends on 1)

The system of claim 1, wherein the operations further comprise:
generating, by the computing system, a synthetic data set for training the denoising model, the synthetic data set comprising a plurality of synthetic images and, for each synthetic image, a plurality of noisy images derived from the respective synthetic image; and
training, by the computing system, the denoising model to denoise a target set of images based on the synthetic data set.

### Claim 3 (depends on 2)

The system of claim 2, wherein the operations further comprise:
generating, by the computing system, an empirical data set for finetuning the denoising model following the training; and
finetuning, by the computing system, the denoising model based on the empirical data set.

### Claim 4 (depends on 3)

The system of claim 3, wherein generating, by the computing system, the empirical data set for finetuning the denoising model following the training comprises:
generating a plurality of geometric objects to be placed inside a background image for capturing by the imaging apparatus; and
receiving, from the imaging apparatus, a plurality of finetuning images based on the plurality of geometric objects placed inside the background image, the plurality of finetuning images defining the empirical data set.

### Claim 5 (depends on 4)

The system of claim 4, wherein the operations further comprise:
introducing shape irregularities to the plurality of geometric objects placed inside the background image.

### Claim 6 (depends on 1)

The system of claim 1, wherein the denoising model is a convolutional neural network comprising a downsampling portion followed by an upsampling portion.

### Claim 7 (depends on 1)

The system of claim 1, wherein the computing system is a component of the imaging apparatus.

### Claim 8

A method comprising:
obtaining, by a computing system, a set of images of a specimen from an imaging apparatus, wherein the set of images includes at least two images of the specimen against a background;
denoising, by the computing system, the set of images by inputting the set of images of the specimen into a denoising model, the denoising model configured to output a single denoised image of the specimen; and
generating, as output from the denoising model, the single denoised image of the specimen.

### Claim 9 (depends on 8)

The method of claim 8, further comprising:
generating, by the computing system, a synthetic data set for training the denoising model, the synthetic data set comprising a plurality of synthetic images and, for each synthetic image, a plurality of noisy images derived from the respective synthetic image; and
training, by the computing system, the denoising model to denoise a target set of images based on the synthetic data set.

### Claim 10 (depends on 9)

The method of claim 9, further comprising:
generating, by the computing system, an empirical data set for finetuning the denoising model following the training; and
finetuning, by the computing system, the denoising model based on the empirical data set.

### Claim 11 (depends on 10)

The method of claim 10, wherein generating, by the computing system, the empirical data set for finetuning the denoising model following the training comprises:
generating a plurality of geometric objects to be placed inside a background image for capturing by the imaging apparatus; and
receiving, from the imaging apparatus, a plurality of finetuning images based on the plurality of geometric objects placed inside the background image, the plurality of finetuning images defining the empirical data set.

### Claim 12 (depends on 11)

The method of claim 11, further comprising:
introducing shape irregularities to the plurality of geometric objects placed inside the background image.

### Claim 13 (depends on 8)

The method of claim 8, wherein the denoising model is a convolutional neural network comprising a downsampling portion followed by an upsampling portion.

### Claim 14 (depends on 8)

The method of claim 8, wherein the computing system is a component of the imaging apparatus.

### Claim 15

A non-transitory computer readable medium comprising one or more sequences of instructions, which, when executed by one or more processors, causes a computing system to perform operations, comprising:
obtaining, by the computing system, a set of images of a specimen from an imaging apparatus, wherein the set of images includes at least two images of the specimen against a background;
denoising, by the computing system, the set of images by inputting the set of images of the specimen into a denoising model, the denoising model configured to output a single denoised image of the specimen; and
generating, as output from the denoising model, the single denoised image of the specimen.

### Claim 16 (depends on 15)

The non-transitory computer readable medium of claim 15, further comprising:
generating, by the computing system, a synthetic data set for training the denoising model, the synthetic data set comprising a plurality of synthetic images and, for each synthetic image, a plurality of noisy images derived from the respective synthetic image; and
training, by the computing system, the denoising model to denoise a target set of images based on the synthetic data set.

### Claim 17 (depends on 16)

The non-transitory computer readable medium of claim 16, further comprising:
generating, by the computing system, an empirical data set for finetuning the denoising model following the training; and
finetuning, by the computing system, the denoising model based on the empirical data set.

### Claim 18 (depends on 17)

The non-transitory computer readable medium of claim 17, wherein generating, by the computing system, the empirical data set for finetuning the denoising model following the training comprises:
generating a plurality of geometric objects to be placed inside a background image for capturing by the imaging apparatus; and
receiving, from the imaging apparatus, a plurality of finetuning images based on the plurality of geometric objects placed inside the background image, the plurality of finetuning images defining the empirical data set.

### Claim 19 (depends on 18)

The non-transitory computer readable medium of claim 18, further comprising:
introducing shape irregularities to the plurality of geometric objects placed inside the background image.

### Claim 20 (depends on 15)

The non-transitory computer readable medium of claim 15, wherein the denoising model is a convolutional neural network comprising a downsampling portion followed by an upsampling portion.