# US 2023/0145270 A1 · Method to improve model performance by artificial blending of healthy tissue

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

- Number: US 2023/0145270 A1
- Document ID: US20230145270A1
- Status: Published application
- Kind: A1
- Application number: 17/523,937
- Filed: 2021-11-11
- Published: 2023-05-11
- Earliest claimed: 2021-11-11
- Assignees: International Business Machines Corporation
- Applicants: International Business Machines Corporation
- Inventors: Yoel Shoshan; Vadim Ratner
- Web page: https://patentgrep.com/patent/US20230145270A1

## CPC

- G06T 7/0012: {Biomedical image inspection}
- G06V 10/82: using neural networks
- G06F 18/2431: Multiple classes
- G06N 3/045: Combinations of networks
- G06N 3/08: Learning methods
- G06T 7/0014: {using an image reference approach}
- G06V 10/772: Determining representative reference patterns, e.g. averaging or distorting patterns; Generating dictionaries
- G06N 20/00: Machine learning
- G06T 2207/10116: X-ray image
- 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 2207/30068: Mammography; Breast
- G06T 2207/30096: Tumor; Lesion
- G06V 2201/031: of internal organs
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS

## Abstract

A method for improving machine learning algorithm performance is described. The method may comprise receiving a first constituent image of human tissue; receiving a second constituent image of human tissue; overlapping a portion of the second constituent image on a portion of the first constituent image to create an augmented image; and training a model using a dataset comprising at least the augmented image.

## Claims

### Claim 1

A method for improving machine learning algorithm performance comprising:
receiving a first constituent image comprising human tissue;
receiving a second constituent image comprising human tissue;
overlapping a portion of the second constituent image on a portion of the first constituent image to create an augmented image;
training a model using a dataset comprising at least the augmented image.

### Claim 2 (depends on 1)

The method of claim 1, wherein the first constituent image comprises healthy human tissue or unhealthy human tissue and the second constituent image comprises healthy human tissue or unhealthy human tissue.

### Claim 3 (depends on 2)

The method of claim 2, wherein training the model further comprises classifying the augmented image based on a classifier of the first constituent image and on a classifier of the second constituent image.

### Claim 4 (depends on 1)

The method of claim 1, further comprising:
generating, using a function, a value of a pixel of the augmented image at a location in the overlapping portion of the constituent images.

### Claim 5 (depends on 4)

The method of claim 4, wherein, the function receives as a first input a first value of a pixel of the first constituent image at the location and as a second input a second value of a pixel of the second constituent image at the location.

### Claim 6 (depends on 5)

The method of claim 5, wherein the function may comprise a maximum value of any of the pixels of the constituent images at the location.

### Claim 7 (depends on 5)

The method of claim 5, wherein the function may comprise a weighted sum of the values of the pixels of the constituent images at the location.

### Claim 8 (depends on 7)

The method of claim 7, wherein weights of the weighted sum may be based on at least one of the following: a first image classification, a second image classification, a position in the first constituent image, or a position in the second constituent image.

### Claim 9

A system for improving machine learning algorithm performance comprising:
a processor;
memory accessible by the processor; and
computer program instructions stored in the memory and executable by the processor to perform the steps of:
receiving a first constituent image comprising human tissue;
receiving a second constituent image comprising human tissue;
overlapping a portion of the second constituent image on a portion of the first constituent image to create an augmented image;
training a model using a dataset comprising at least the augmented image.

### Claim 10 (depends on 9)

The system of claim 9, wherein the first constituent image comprises healthy human tissue or unhealthy human tissue and the second constituent image comprises healthy human tissue or unhealthy human tissue.

### Claim 11 (depends on 9)

The system of claim 9, wherein training the model further comprises classifying the augmented image based on a classifier of the first constituent image and a classifier of the second constituent image.

### Claim 12 (depends on 9)

The system of claim 9, further comprising:
generating, using a function, a value of a pixel of the augmented image at a location in the overlapping portion of the constituent images.

### Claim 13 (depends on 12)

The system of claim 12, wherein, the function receives as a first input a first value of a pixel of the first constituent image at the location and as a second input a second value of a pixel of the second constituent image at the location.

### Claim 14 (depends on 13)

The system of claim 13, wherein the function may comprise a maximum value of any of the pixels of the constituent images at the location.

### Claim 15 (depends on 13)

The system of claim 13, wherein the function may comprise a weighted sum of the values of the pixels of the constituent images at the location.

### Claim 16 (depends on 15)

The system of claim 15, wherein weights of the weighted sum may be based on at least one of the following: a first image classification, a second image classification, a position in the first constituent image, or a position in the second constituent image.

### Claim 17

A computer program product for improving machine learning algorithm performance, the computer program product comprising a non-transitory computer readable storage having program instructions embodied therewith, the program instructions executable by a computer, to cause the computer to perform a method comprising:
receiving a first constituent image comprising human tissue;
receiving a second constituent image comprising human tissue;
overlapping a portion of the second constituent image on a portion of the first constituent image to create an augmented image;
training a model using a dataset comprising at least the augmented image.

### Claim 18 (depends on 17)

The computer program product of claim 17, wherein the first constituent image comprises healthy human tissue or unhealthy human tissue and the second constituent image comprises healthy human tissue or unhealthy human tissue and wherein training the model further comprises classifying the augmented image based on a classifier of the first constituent image and a classifier of the second constituent image.

### Claim 19 (depends on 17)

The computer program product of claim 17, further comprising, generating, using a function, a value of a pixel of the augmented image at a location in the overlapping portion of the constituent images, wherein the function receives as a first input a first value of a pixel of the first constituent image at the location and as a second input a second value of a pixel of the second constituent image at the location.

### Claim 20 (depends on 19)

The computer program product of claim 19, wherein the function may comprise a weighted sum of the values of the pixels of the constituent images at the location and wherein the weights of the weighted sum may be based on at least one of the following: a first image classification, a second image classification, a position in the first constituent image, or a position in the second constituent image.
