# US 12,191,037 B2 · Medical machine learning system

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

- Number: US 12,191,037 B2
- Document ID: US12191037B2
- Status: Granted
- Kind: B2
- Application number: 17/607,234
- Filed: 2020-04-06
- Published: 2022-08-04
- Granted: 2025-01-07
- Earliest claimed: 2019-05-13
- Assignees: Visual Terminology Inc.
- Applicants: Visual Terminology Inc.
- Inventors: Byung Kwon Choi
- Web page: https://patentgrep.com/patent/US12191037B2

## CPC

- G16H 15/00: ICT specially adapted for medical reports, e.g. generation or transmission thereof
- G16H 50/20: for computer-aided diagnosis, e.g. based on medical expert systems
- G06N 3/045: Combinations of networks
- G06N 3/0464: Convolutional networks [CNN, ConvNet]
- G06N 3/0475: Generative networks
- G06N 3/08: Learning methods
- G06N 3/09: Supervised learning
- G06N 20/00: Machine learning
- G16H 50/50: for simulation or modelling of medical disorders
- G16H 50/70: for mining of medical data, e.g. analysing previous cases of other patients
- G16H 30/40: for processing medical images, e.g. editing
- G16H: HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS

## Abstract

Disclosed is a medical equipment learning system which includes: a data extraction module configured to collect and then extract text-type data from medical data; a visualization module configured to generate image-type data as visualization data by using the text-type data extracted by the data extraction module; a pre-processing module configured to generate an input data set to execute equipment learning based on the visualization data; a learning module configured to execute equipment learning in the input data set generated by the pre-processing module; a prediction module configured to predict a disease when new image-type data is input based on the result learned in the learning module; and a storage module provided to store and check data of each module.

## Claims

### Claim 1

A medical machine learning system comprising:
a data extraction module configured to collect and then extract text-type data from medical data;
a visualization module configured to generate image-type data as visualization data by retrieving a previously stored medical information model which references the text-type data extracted by the data extraction module;
a pre-processing module configured to generate an input data set to execute machine learning based on the visualization data;
a learning module configured to execute machine learning in the input data set generated by the pre-processing module by using an algorithm including a support vector equipment, a convolutional neural network, or a generative adversarial neural network;
a prediction module configured to predict a disease when new image-type data is input based on a comparison with a result of the machine learning in the input data set in the learning module; and
a storage module provided to store and check data of each module,
wherein the data extraction module, the visualization module, the pre-processing module, the learning module, the prediction module, and the storage module are each implemented via at least one processor.

### Claim 2 (depends on 1)

The medical machine learning system of claim 1, wherein the image-type data generated by the visualization module is a predetermined 2D or 3D model.

### Claim 3 (depends on 1)

The medical machine learning system of claim 1, wherein the data extraction module collects the medical data by receiving materials from any one or more of a portable file, a hospital, a cloud server, and a personal device.

### Claim 4 (depends on 1)

The medical machine learning system of claim 1, wherein the visualization module expresses a name of a disease, a severity of the disease, a chronicity, a degree of malignancy, various test results, functional test results, and data results extracted from a machine by any one or more of colors, brightness or transparency, patterns, and textures of the visualization data.

### Claim 5 (depends on 1)

The medical machine learning system of claim 1, wherein the visualization module uses an image extracted from a medical image or an anatomical pathology photograph as a texture.

### Claim 6 (depends on 1)

The medical machine learning system of claim 1, wherein the visualization module uses one or more layers according to characteristics of the medical data.

### Claim 7 (depends on 1)

The medical machine learning system of claim 1, wherein the visualization module generates the image-type data by combining one or more medical information models.

### Claim 8 (depends on 1)

The medical machine learning system of claim 1, wherein the pre-processing module generates the input data set by normalizing various types of image-type data having different standards.

### Claim 9 (depends on 1)

The medical machine learning system of claim 1, wherein the visualization module further includes a medical information model expressing medical information which is not anatomically related inside and outside a body in a basic model.

### Claim 10 (depends on 1)

The medical machine learning system of claim 1, wherein the pre-processing module creates temporal data by combining several image-type data having different creation time points and generates the input data set according to a change in time.

### Claim 11 (depends on 1)

The medical machine learning system of claim 1, wherein the pre-processing module forms the input data set by selecting only a portion of an image-type data area.

### Claim 12 (depends on 1)

The medical machine learning system of claim 1, wherein the pre-processing module generates the input data set 2-dimensionally converted from the image-type data expressed 3-dimensionally.