# US 2021/0275085 A1 · Automatic association between physical and visual skin properties

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

- Number: US 2021/0275085 A1
- Document ID: US20210275085A1
- Status: Published application
- Kind: A1
- Application number: 16/809,609
- Filed: 2020-03-05
- Published: 2021-09-09
- Earliest claimed: 2020-03-05
- Assignees: International Business Machines Corporation
- Applicants: International Business Machines Corporation
- Inventors: Yasmeen Mourice George; Lenin Mehedy; Rahil Garnavi
- Web page: https://patentgrep.com/patent/US20210275085A1

## CPC

- A61B 5/441: {Skin evaluation, e.g. for skin disorder diagnosis}
- A61B 5/7267: {involving training the classification device}
- G06T 7/0012: {Biomedical image inspection}
- G06T 11/00: Two-dimensional [2D] image generation
- A61B 2576/00: Medical imaging apparatus involving image processing or analysis (A61B1/00009, A61B6/52 and A61B8/52 take precedence)
- G06T 2200/04: involving 3D image data
- G06T 2207/10024: Color image
- G06T 2207/10028: Range image; Depth image; 3D point clouds
- G06T 2207/10141: Special mode during image acquisition
- G06T 2207/20036: Morphological image processing
- G06T 2207/20081: Training; Learning
- G06T 2207/20084: Artificial neural networks [ANN]
- G06T 2207/30088: Skin; Dermal
- A61B: DIAGNOSIS; SURGERY; IDENTIFICATION (usefulness limited to only animals A61D)
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL

## Abstract

Techniques for automatic association between physical and visual skin properties are provided. A computer system receives a two-dimensional (2D) image and a three-dimensional (3D) image associated with a person and determines surface skin properties using the 2D image and physical skin properties using the 3D image. The computer system generates a skin disorder severity assessment using associations between the surface skin properties and the physical skin properties.

## Claims

### Claim 1

A computer-implemented method comprising:
receiving, by a computer system, a two-dimensional (2D) image and a three-dimensional (3D) image associated with a person;
determining, by the computer system, surface skin properties using the 2D image and physical skin properties using the 3D image; and
generating, by the computer system, a skin disorder severity assessment using associations between the surface skin properties and the physical skin properties.

### Claim 2 (depends on 1)

The computer-implemented method of claim 1, wherein the 2D image represents a surface of skin of the person.

### Claim 3 (depends on 1)

The computer-implemented method of claim 1, wherein the 3D image comprises a representation of inner layers of skin of the person.

### Claim 4 (depends on 1)

The computer-implemented method of claim 1, wherein determining the surface skin properties using the 2D image comprises using a trained model to determine the surface skin properties from the 2D image.

### Claim 5 (depends on 1)

The computer-implemented method of claim 1, wherein the surface skin properties comprise a redness severity score, a scale severity score, and an area severity score.

### Claim 6 (depends on 1)

The computer-implemented method of claim 1, wherein determining the physical skin properties using the 3D image comprises using a trained model to determine the physical skin properties.

### Claim 7 (depends on 1)

The computer-implemented method of claim 1, wherein the physical skin properties comprise an epidermal thickness value, a proliferation of keratinocytes value, an epidermal inflammation value, a blood vessel morphology value, and a keratinocyte morphology value.

### Claim 8 (depends on 1)

The computer-implemented method of claim 1, wherein:
a trained model is used to determine the associations and to generate the skin disorder severity assessment using the associations between the surface skin properties and the physical skin properties; and
the skin disorder severity assessment comprises a selection from skin disorder severity labels.

### Claim 9

A system comprising:
a memory having computer readable instructions; and
one or more processors for executing the computer readable instructions, the computer readable instructions controlling the one or more processors to perform operations comprising:
receiving a two-dimensional (2D) image and a three-dimensional (3D) image associated with a person;
determining surface skin properties using the 2D image and physical skin properties using the 3D image; and
generating a skin disorder severity assessment using associations between the surface skin properties and the physical skin properties.

### Claim 10 (depends on 9)

The system of claim 9, wherein the 2D image represents a surface of skin of the person.

### Claim 11 (depends on 9)

The system of claim 9, wherein the 3D image comprises a representation of inner layers of skin of the person.

### Claim 12 (depends on 9)

The system of claim 9, wherein determining the surface skin properties using the 2D image comprises using a trained model to determine the surface skin properties from the 2D image.

### Claim 13 (depends on 9)

The system of claim 9, wherein the surface skin properties comprise a redness severity score, a scale severity score, and an area severity score.

### Claim 14 (depends on 9)

The system of claim 9, wherein determining the physical skin properties using the 3D image comprises using a trained model to determine the physical skin properties.

### Claim 15 (depends on 9)

The system of claim 9, wherein the physical skin properties comprise an epidermal thickness value, a proliferation of keratinocytes value, an epidermal inflammation value, a blood vessel morphology value, and a keratinocyte morphology value.

### Claim 16 (depends on 9)

The system of claim 9, wherein:
a trained model is used to determine the associations and to generate the skin disorder severity assessment using the associations between the surface skin properties and the physical skin properties; and
the skin disorder severity assessment comprises a selection from skin disorder severity labels.

### Claim 17

A computer program product comprising a computer readable storage medium having program instructions embodied therewith, the program instructions executable by a processor to cause the processor to perform operations comprising:
receiving, by the processor, a two-dimensional (2D) image and a three-dimensional (3D) image associated with a person;
determining, by the processor, surface skin properties using the 2D image and physical skin properties using the 3D image; and
generating, by the processor, a skin disorder severity assessment using associations between the surface skin properties and the physical skin properties.

### Claim 18 (depends on 17)

The computer program product of claim 17, wherein the 2D image represents a surface of skin of the person.

### Claim 19 (depends on 17)

The computer program product of claim 17, wherein the 3D image comprises a representation of inner layers of skin of the person.

### Claim 20 (depends on 17)

The computer program product of claim 17, wherein determining the surface skin properties using the 2D image comprises using a trained model to determine the surface skin properties from the 2D image.
