# US 2022/0036558 A1 · Method and system for predicting expression of biomarker from medical image

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

- Number: US 2022/0036558 A1
- Document ID: US20220036558A1
- Status: Published application
- Kind: A1
- Application number: 17/502,260
- Filed: 2021-10-15
- Published: 2022-02-03
- Earliest claimed: 2020-03-06
- Assignees: Lunit Inc.
- Applicants: Lunit Inc.
- Inventors: Jae Hong AUM; Chanyoung OCK; Donggeun YOO
- Web page: https://patentgrep.com/patent/US20220036558A1

## CPC

- G06T 7/0016: {involving temporal comparison}
- G16H 30/40: for processing medical images, e.g. editing
- A61B 5/4887: {Locating particular structures in or on the body}
- A61B 5/7275: {Determining trends in physiological measurement data; Predicting development of a medical condition based on physiological measurements, e.g. determining a risk factor}
- G06N 20/00: Machine learning
- G06T 7/0012: {Biomedical image inspection}
- G06T 7/11: Region-based segmentation
- G06T 7/70: Determining position or orientation of objects or cameras (camera calibration G06T7/80)
- G16H 30/20: for handling medical images, e.g. DICOM, HL7 or PACS
- G16H 50/20: for computer-aided diagnosis, e.g. based on medical expert systems
- G16H 50/30: for calculating health indices; for individual health risk assessment
- G16H 50/70: for mining of medical data, e.g. analysing previous cases of other patients
- A61B 5/055: involving electronic [EMR] or nuclear [NMR] magnetic resonance, e.g. magnetic resonance imaging
- A61B 5/7264: {Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems}
- A61B 6/03: Computed tomography [CT]
- A61B 6/507: {for determination of haemodynamic parameters, e.g. perfusion CT}
- A61B 2576/02: specially adapted for a particular organ or body part
- G06T 2207/10081: Computed x-ray tomography [CT]
- G06T 2207/10088: Magnetic resonance imaging [MRI]
- G06T 2207/10104: Positron emission tomography [PET]
- G06T 2207/10108: Single photon emission computed tomography [SPECT]
- G06T 2207/20081: Training; Learning
- G06T 2207/20084: Artificial neural networks [ANN]
- G06T 2207/20132: Image cropping
- G06T 2207/30024: Cell structures in vitro; Tissue sections in vitro
- G06T 2207/30096: Tumor; Lesion
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G16H: HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- A61B: DIAGNOSIS; SURGERY; IDENTIFICATION (usefulness limited to only animals A61D)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS

## Abstract

The present disclosure relates to a method for predicting biomarker expression from a medical image. The method for predicting biomarker expression includes receiving a medical image, and outputting indices of biomarker expression for the at least one lesion included in the medical image by using a first machine learning model.

## Claims

### Claim 1

A method, performed by at least one processor, for predicting biomarker expression from a medical image, comprising:
receiving a medical image; and
outputting indices of biomarker expression for at least one lesion included in the medical image by using a first machine learning model.

### Claim 2 (depends on 1)

The method according to claim 1, wherein the outputting the indices of biomarker expression includes:
extracting regions for the at least one lesion from the received medical image; and
cropping the extracted regions for the at least one lesion from the medical images to generate partial images.

### Claim 3 (depends on 2)

The method according to claim 2, wherein the outputting the indices of biomarker expression further includes inputting the generated partial images to the first machine learning model to output the indices of biomarker expression for the at least one lesion.

### Claim 4 (depends on 2)

The method according to claim 2, wherein the outputting the indices of biomarker expression further includes inputting the received medical image and the generated partial images to the first machine learning model to output the indices of biomarker expression for the at least one lesion.

### Claim 5 (depends on 2)

The method according to claim 2, further comprising determining segmentation information of the at least one lesion included in the medical image, wherein
the outputting the indices of biomarker expression includes inputting the determined segmentation information of the at least one lesion and the generated partial images to the first machine learning model to output the indices of biomarker expression for the at least one lesion included in the medical image.

### Claim 6 (depends on 2)

The method according to claim 2, comprising acquiring an index of biomarker expression for a lesion different from the at least one lesion in the medical image, wherein
the outputting the indices of biomarker expression includes inputting the acquired index of biomarker expression of the different lesion and the generated partial images to the first machine learning model to output the indices of biomarker expression for the at least one lesion included in the medical image.

### Claim 7 (depends on 1)

The method according to claim 1, wherein the receiving the medical image includes receiving a first medical image and a second medical image captured at a point in time different from the first medical image, and
wherein the outputting the indices of biomarker expression includes:
extracting regions for the at least one lesion from each of the first medical image and the second medical image; and
inputting the regions for the at least one lesion extracted from the first medical image and the regions for the at least one lesion extracted from the second medical image to the first machine learning model to output the indices of biomarker expression for the at least one lesion.

### Claim 8 (depends on 1)

The method according to claim 1, further comprising inputting the output indices of biomarker expression into a third machine learning model to output information associated with tissue collection for the at least one lesion.

### Claim 9 (depends on 8)

The method according to claim 8, wherein the at least one lesion included in the medical image includes a plurality of lesions included in the medical image, and
the outputting the information associated with tissue collection for the at least one lesion includes outputting information on a priority of tissue collection for the plurality of lesions.

### Claim 10 (depends on 9)

The method according to claim 9, further comprising acquiring reference information on tissue collection associated with the medical image, wherein
the outputting the information on the priority of tissue collection for the plurality of lesions includes inputting the output indices of biomarker expression and the acquired reference information on tissue collection into the third machine learning model to output the information on a priority of tissue collection for the plurality of lesions.

### Claim 11

An information processing system comprising:
a memory storing one or more instructions; and
a processor configured to execute the stored one or more instructions to receive a medical image and output indices of biomarker expression for at least one lesion included in the medical image by using a first machine learning model.

### Claim 12 (depends on 11)

The information processing system according to claim 11, wherein the processor is further configured to extract regions for the at least one lesion from the received medical image and crop the extracted regions for the at least one lesion from the medical image to generate partial images.

### Claim 13 (depends on 12)

The information processing system according to claim 12, wherein the processor is further configured to input the generated partial images to the first machine learning model to output the indices of biomarker expression for the at least one lesion.

### Claim 14 (depends on 12)

The information processing system according to claim 12, wherein the processor is further configured to input the received medical image and the generated partial images to the first machine learning model to output the indices of biomarker expression for the at least one lesion.

### Claim 15 (depends on 12)

The information processing system according to claim 12, wherein the processor is further configured to:
determine segmentation information of the at least one lesion included in the medical image; and
input the determined segmentation information of the at least one lesion and the generated partial images to the first machine learning model to output the indices of biomarker expression for the at least one lesion included in the medical image.

### Claim 16 (depends on 12)

The information processing system according to claim 12, wherein the processor is further configured to:
acquire an index of biomarker expression for a lesion different from the at least one lesion in the medical image; and
input the acquired index of biomarker expression of the different lesion and the generated partial images to the first machine learning model to output the indices of biomarker expression for the at least one lesion included in the medical image.

### Claim 17 (depends on 11)

The information processing system according to claim 11, wherein the processor is further configured to:
receive a first medical image and a second medical image captured at a point in time different from the first medical image;
extract regions for the at least one lesion from each of the first medical image and the second medical image; and
input the regions for the at least one lesion extracted from the first medical image and the regions for the at least one lesion extracted from the second medical image to the first machine learning model to output the indices of biomarker expression for the at least one lesion.

### Claim 18 (depends on 11)

The information processing system according to claim 11, wherein the processor is further configured to input the output indices of biomarker expression into a third machine learning model to output information associated with tissue collection for the at least one lesion.

### Claim 19 (depends on 18)

The information processing system according to claim 18, wherein the at least one lesion included in the medical image includes a plurality of lesions included in the medical image, and
the processor is further configured to output the information on a priority of tissue collection for the plurality of lesions.

### Claim 20 (depends on 19)

The information processing system according to claim 19, wherein the processor is further configured to:
acquire reference information on tissue collection associated with the medical image; and
input the output indices of biomarker expression and the acquired reference information on tissue collection into the third machine learning model to output the information on a priority of tissue collection for the plurality of lesions.
