# US 2025/0148577 A1 · Noise reduction in ophthalmic images

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

- Number: US 2025/0148577 A1
- Document ID: US20250148577A1
- Status: Published application
- Kind: A1
- Application number: 18/933,696
- Filed: 2024-10-31
- Published: 2025-05-08
- Earliest claimed: 2023-11-02
- Assignees: Optos PLC
- Applicants: Optos plc
- Inventors: Enrico Pellegrini; Peter Wakeford; Gavin Robertson
- Web page: https://patentgrep.com/patent/US20250148577A1

## CPC

- G06T 5/70: Denoising; Smoothing
- G06T 5/50: using two or more images, e.g. averaging or subtraction
- G06T 5/60: using machine learning, e.g. neural networks
- G06T 7/0012: {Biomedical image inspection}
- G06T 2207/10101: Optical tomography; Optical coherence tomography [OCT]
- G06T 2207/20081: Training; Learning
- G06T 2207/20084: Artificial neural networks [ANN]
- G06T 2207/20192: Edge enhancement; Edge preservation
- G06T 2207/20221: Image fusion; Image merging
- G06T 2207/30041: Eye; Retina; Ophthalmic
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL

## Abstract

A computer-implemented method of processing at least one image of a retina of an eye acquired by an ophthalmic imaging device, wherein the at least one image shows a texture of the retina. The method comprises processing a first image of the at least one image using a noise reduction algorithm based on machine learning to generate a de-noised image of the retina, wherein the texture of the retina shown in the first image is at least partially removed by the noise reduction algorithm to generate the de-noised image. The method further comprises combining a second image of the at least one image with the de-noised image to generate at least one hybrid image of the retina which shows more of the texture of the retina than the de-noised image.

## Claims

### Claim 1

A computer-implemented method of processing at least one image of a retina of an eye acquired by an ophthalmic imaging device (30), wherein the at least one image shows a texture of the retina, the method comprising:
processing a first image of the at least one image using a noise reduction algorithm based on machine learning to generate a de-noised image of the retina, wherein the texture of the retina shown in the first image is at least partially removed by the noise reduction algorithm to generate the de-noised image; and
combining a second image of the at least one image with the de-noised image to generate at least one hybrid image of the retina which shows more of the texture of the retina than the de-noised image.

### Claim 2 (depends on 1)

The computer-implemented method of claim 1, wherein the at least one hybrid image of the retina is generated by combining the second image with the de-noised image using respective weightings for the second image and the de-noised image.

### Claim 3 (depends on 2)

The computer-implemented method of claim 2, wherein the at least one hybrid image of the retina is generated by using the weightings to calculate one of a weighted sum or a weighted average of the second image and the de-noised image.

### Claim 4 (depends on 2)

The computer-implemented method of claim 2, further comprising receiving a setting indication from a user for setting the weightings, and setting the weightings using the setting indication.

### Claim 5 (depends on 2)

The computer-implemented method of claim 2, further comprising generating a control signal for a display device to display the at least one hybrid image.

### Claim 6 (depends on 5)

The computer-implemented method of claim 5, wherein a plurality of hybrid images is generated by combining the second image with the de-noised image using different respective weightings, and wherein a plurality of control signals are generated for the display device to display the plurality of hybrid images.

### Claim 7 (depends on 5)

The computer-implemented method of claim 5, further comprising receiving an update indication from a user for updating the weightings, and updating the weightings using the update indication.

### Claim 8 (depends on 1)

The computer-implemented method of claim 1, wherein the noise reduction algorithm is based on a convolutional neural network.

### Claim 9 (depends on 1)

The computer-implemented method of claim 1, wherein the at least one image of the retina of the eye is at least one fundus autofluorescence image of the retina of the eye.

### Claim 10 (depends on 1)

The computer-implemented method of claim 1, wherein the second image is the same as the first image.

### Claim 11

A non-transitory computer-readable storage medium storing a computer program comprising computer-readable instructions which, when executed by a processor, cause the processor to perform a set of operations, the set of operations comprising:
processing a first image of the at least one image using a noise reduction algorithm based on machine learning to generate a de-noised image of the retina, wherein the texture of the retina shown in the first image is at least partially removed by the noise reduction algorithm to generate the de-noised image; and
combining a second image of the at least one image with the de-noised image to generate at least one hybrid image of the retina that shows more of the texture of the retina than the de-noised image.

### Claim 12

A data processing apparatus, comprising:
at least one processor; and
memory storing instructions that, when executed by the at least one processor, cause the data processing apparatus to perform a set of operations, the set of operations comprising:
processing a first image of the at least one image using a noise reduction algorithm based on machine learning to generate a de-noised image of the retina, wherein the texture of the retina shown in the first image is at least partially removed by the noise reduction algorithm to generate the de-noised image; and
combining a second image of the at least one image with the de-noised image to generate at least one hybrid image of the retina that shows more of the texture of the retina than the de-noised image.

### Claim 13 (depends on 11)

The non-transitory computer-readable storage medium of claim 11, wherein the at least one hybrid image of the retina is generated by combining the second image with the de-noised image using respective weightings for the second image and the de-noised image.

### Claim 14 (depends on 13)

The non-transitory computer-readable storage medium of claim 13, wherein the at least one hybrid image of the retina is generated by using the weightings to calculate one of a weighted sum or a weighted average of the second image and the de-noised image.

### Claim 15 (depends on 13)

The non-transitory computer-readable storage medium of claim 13, wherein the set of operations further comprises generating a control signal for a display device to display the at least one hybrid image.

### Claim 16 (depends on 15)

The non-transitory computer-readable storage medium of claim 15, wherein a plurality of hybrid images is generated by combining the second image with the de-noised image using different respective weightings, and wherein a plurality of control signals are generated for the display device to display the plurality of hybrid images.

### Claim 17 (depends on 12)

The data processing apparatus of claim 12, wherein the at least one hybrid image of the retina is generated by combining the second image with the de-noised image using respective weightings for the second image and the de-noised image.

### Claim 18 (depends on 17)

The data processing apparatus of claim 17, wherein the at least one hybrid image of the retina is generated by using the weightings to calculate one of a weighted sum or a weighted average of the second image and the de-noised image.

### Claim 19 (depends on 17)

The data processing apparatus of claim 17, wherein the set of operations further comprises generating a control signal for a display device to display the at least one hybrid image.

### Claim 20 (depends on 19)

The data processing apparatus of claim 19, wherein a plurality of hybrid images is generated by combining the second image with the de-noised image using different respective weightings, and wherein a plurality of control signals are generated for the display device to display the plurality of hybrid images.
