# US 2023/0410256 A1 · System and method for improving image resolution of 3-d refractive index microscope based on ai technology

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

- Number: US 2023/0410256 A1
- Document ID: US20230410256A1
- Status: Published application
- Kind: A1
- Application number: 17/818,987
- Filed: 2022-08-11
- Published: 2023-12-21
- Earliest claimed: 2022-05-30
- Assignees: Tomocube, Inc.
- Applicants: Tomocube, Inc.
- Inventors: Hyunseok MIN; Dongmin RYU; Woonsoo LEE; Hansol YOON
- Web page: https://patentgrep.com/patent/US20230410256A1

## CPC

- G06T 3/4053: based on super-resolution, i.e. the output image resolution being higher than the sensor resolution
- G02B 21/367: {providing an output produced by processing a plurality of individual source images, e.g. image tiling, montage, composite images, depth sectioning, image comparison}
- G06T 3/4023: based on decimating pixels or lines of pixels; based on inserting pixels or lines of pixels
- G06T 3/4038: Image mosaicing, e.g. composing plane images from plane sub-images
- G06T 3/4046: using neural networks
- G06T 2200/04: involving 3D image data
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G02B: OPTICAL ELEMENTS, SYSTEMS OR APPARATUS

## Abstract

The present disclosure provides a system and method for improving image resolution of a three-dimensional (3-D) refractive index microscope based on an artificial intelligence (AI) technology. The present disclosure provides a technology for converting a low-resolution 3-D refractive index microscope image into a high-resolution 3-D refractive index image without physical machine conversion and re-photographing based on AI. That is, the present disclosure applies an AI technology, such as deep learning, in order to train an AI model with a physical correlation between a low-resolution 3-D refractive index microscope image and a high-resolution 3-D refractive index image of various samples, such as a cell and a tissue, and convert a low resolution image into a high resolution image without a change in a physical microscope based on the training. Furthermore, for the training of the AI model, the present disclosure uses physical characteristics of a refractive index image.

## Claims

### Claim 1

A system for improving resolution of a three-dimensional (3-D) refractive index image based on an artificial intelligence (AI) technology, the system comprising:
a 3-D refractive index cell image measuring unit configured to obtain a 3-D refractive index cell image; and
a 3-D refractive index image conversion unit configured to perform resolution improvement on the 3-D refractive index cell image based on a deep learning algorithm.

### Claim 2 (depends on 1)

The system of claim 1, wherein the 3-D refractive index image conversion unit comprises:
a 3-D patch extraction unit configured to generate a plurality of 3-D refractive index patches from the 3-D refractive index cell image;
a 3-D refractive index patch conversion unit configured to perform the resolution improvement on each of the 3-D refractive index patches based on the deep learning algorithm; and
a patch combination unit configured to combine the 3-D refractive index patches.

### Claim 3 (depends on 2)

The system of claim 2, wherein the 3-D patch extraction unit comprises:
an image padding unit configured to construct a padded image by adding a padding area to an outskirt of the 3-D refractive index cell image; and
a sampling unit configured to sample the 3-D refractive index patches from the padded image; and
wherein the patch combination unit is configured to remove the padding area after combining the 3-D refractive index patches.

### Claim 4 (depends on 1)

The system of claim 1, wherein the deep learning algorithm is constructed based on a combination of a mean squared error function and a Fourier conversion error function.

### Claim 5 (depends on 1)

The system of claim 1, wherein the 3-D refractive index cell image measuring unit is configured to:
obtain the 3-D refractive index cell image by measuring a 3-D refractive index distribution of a cell by using an interference system also if a coherent light source is used; and
obtain the 3-D refractive index cell image by measuring the 3-D refractive index distribution of the cell through deconvolution using a point diffusion score if a partial coherent light source is used.

### Claim 6

A method of a system improving resolution of a three-dimensional (3-D) refractive index image based on an artificial intelligence (AI) technology, the method comprising:
obtaining a 3-D refractive index cell image; and
performing resolution improvement on the 3-D refractive index cell image based on a deep learning algorithm.

### Claim 7 (depends on 6)

The method of claim 6, wherein the performing of the resolution improvement comprises: generating a plurality of 3-D refractive index patches from the 3-D refractive index cell image;
performing the resolution improvement on each of the 3-D refractive index patches based on the deep learning algorithm; and
combining the 3-D refractive index patches.

### Claim 8 (depends on 7)

The method of claim 7, wherein the generating of the 3-D refractive index patches comprises:
constructing a padded image by adding a padding area to an outskirt of the 3-D refractive index cell image; and
sampling the 3-D refractive index patches from the padded image,
wherein combining the 3-D refractive index patches comprises removing the padding area after combining the 3-D refractive index patches.

### Claim 9 (depends on 6)

The method of claim 6, wherein the deep learning algorithm is constructed based on a combination of a mean squared error function and a Fourier conversion error function.

### Claim 10 (depends on 6)

The method of claim 6, wherein the obtaining of the 3-D refractive index cell image comprises:
obtaining the 3-D refractive index cell image by measuring a 3-D refractive index distribution of a cell by using an interference system also if a coherent light source is used; and
obtaining the 3-D refractive index cell image by measuring the 3-D refractive index distribution of the cell through deconvolution using a point diffusion score if a partial coherent light source is used.
