# US 2026/0073514 A1 · Methods and systems for image-to-image translation of microscopy images

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

- Number: US 2026/0073514 A1
- Document ID: US20260073514A1
- Status: Published application
- Kind: A1
- Application number: 19/322,309
- Filed: 2025-09-08
- Published: 2026-03-12
- Earliest claimed: 2024-09-09
- Assignees: Diffine LLC
- Applicants: Diffine LLC
- Inventors: Nikola ANDREJIC; Ivana MIKIC; Milica SPASIC; Igor MIHAJLOVIC; Petra MILOSAVLJEVIC; Danilo DELIBAŠIC; Sinisa TODOROVIC
- Web page: https://patentgrep.com/patent/US20260073514A1

## CPC

- G06T 7/0012: {Biomedical image inspection}
- 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 2207/30204: Marker
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL

## Abstract

Described herein are methods and systems for training image to image translation machine-learning models, wherein the image to image translation machine-learning models are trained using unpaired images. The trained image to image translation machine-learning models can be used to digitally identify markers of a fluorescent image depicting a plurality of markers in a single color channel from a single fluorophore and/or enhance a fluorescence image.

## Claims

### Claim 1

A method for digitally identifying markers for a fluorescence image depicting a plurality of markers, comprising:
receiving the fluorescence image, wherein the plurality of markers are represented in a single color channel from a single fluorophore; and
identifying the plurality of markers in the fluorescence image by inputting the fluorescence image into a trained machine-learning model,
wherein the trained machine-learning model is trained with a plurality of training single-channel fluorescence images and a plurality of training marker-separated fluorescence images, and
wherein the plurality of training single-channel fluorescence images and the plurality of training marker-separated fluorescence images are unpaired.

### Claim 2 (depends on 1)

The method of claim 1, wherein identifying the plurality of markers in the fluorescence image comprises displaying a marker-separated fluorescence image depicting the plurality of markers in a plurality of colors.

### Claim 3 (depends on 1)

The method of claim 1, wherein the plurality of markers is a first plurality of markers, and wherein the fluorescence image depicts a second plurality of markers represented in a second color channel from a second fluorophore, distinct from the single fluorophore.

### Claim 4 (depends on 1)

The method of claim 1, wherein the plurality of training marker-separated fluorescence images depicts each marker in the plurality of markers in a respective color channel.

### Claim 5 (depends on 1)

The method of claim 1, wherein the plurality of markers each indicates a structural or functional element of a sample depicted in the fluorescence image.

### Claim 6 (depends on 5)

The method of claim 5, wherein the sample is a biological specimen.

### Claim 7 (depends on 6)

The method of claim 6, wherein the biological specimen comprises tissues and/or cells.

### Claim 8 (depends on 1)

The method of claim 1, wherein the trained machine-learning model comprises a modified cycle Generative Adversarial Network (CycleGAN).

### Claim 9 (depends on 8)

The method of claim 8, wherein the modified CycleGAN is trained in one or more autoencoder modes and a translation mode.

### Claim 10 (depends on 9)

The method claim 9, wherein training in the one or more autoencoder modes is based on minimizing an L1 loss function.

### Claim 11 (depends on 9)

The method of claim 9, wherein the modified CycleGAN comprises a generator model in a forward direction, a generator models in a reverse direction, and one or more discriminator models.

### Claim 12 (depends on 11)

The method of claim 11, wherein training in the translation mode comprises minimizing one or more cycle consistency loss functions based on inputs for the forward direction and outputs from the reverse direction.

### Claim 13 (depends on 11)

The method of claim 11, wherein the generator model in the forward direction and/or the generator model in the reverse direction is a UNet generator.

### Claim 14 (depends on 13)

The method of claim 13, wherein the UNet generator comprises an encoder, a plurality of bottleneck blocks, and a decoder.

### Claim 15 (depends on 11)

The method of claim 11, wherein the generator model in the forward direction shares weights at one or more bottleneck blocks with the generator model in the reverse direction.

### Claim 16 (depends on 14)

The method of claim 14, wherein at least one of the encoder, the plurality of bottleneck blocks, the decoder, and the one or more discriminators comprises one or more layers, and spectral normalization is used in training the one or more layers.

### Claim 17 (depends on 16)

The method of claim 16, wherein spectral normalization comprises computing a lower bound approximation.

### Claim 18 (depends on 11)

The method of claim 11, wherein the one or more discriminators are trained based on an adversarial loss function.

### Claim 19

A method of training a machine-learning model, the method comprising:
obtaining training dataset comprising a plurality of training single-channel fluorescence images and a plurality of training marker-separated fluorescence images, wherein the plurality of training single-channel fluorescence images and the plurality of training marker-separated fluorescence images are unpaired; and
training, based on the training data, the machine learning model configured to receive an fluorescence image depicting a plurality of markers represented in a single color channel from a single fluorophore and output a marker-separated fluorescence image, depicting each marker in the plurality of markers in a respective color channel.

### Claim 20

A system comprising:
one or more processors; and
a non-transitory memory coupled to the one or more processors comprising instructions that, when executed by the processor, cause the processor to:
receive the fluorescence image, wherein the plurality of markers are represented in a single color channel from a single fluorophore; and
identify the plurality of markers in the fluorescence image by inputting the fluorescence image into a trained machine-learning model,
wherein the trained machine-learning model is trained with a plurality of training single-channel fluorescence images and a plurality of training marker-separated fluorescence images, and
wherein the plurality of training single-channel fluorescence images and the plurality of training marker-separated fluorescence images are unpaired.
