# US 2024/0005487 A1 · Sleep apnea diagnostic auxiliary system using simple skull x-ray image and method for providing diagnostic auxiliary information using same

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

- Number: US 2024/0005487 A1
- Document ID: US20240005487A1
- Status: Published application
- Kind: A1
- Application number: 18/039,646
- Filed: 2021-12-01
- Published: 2024-01-04
- Earliest claimed: 2020-12-01
- Assignees: Seoul National University Hospital
- Applicants: Seoul National University Hospital
- Inventors: Han-Gil Jeong; Tackeun Kim; Chang-Ho Yun
- Web page: https://patentgrep.com/patent/US20240005487A1

## CPC

- G06T 7/0012: {Biomedical image inspection}
- A61B 5/4818: {Sleep apnoea}
- A61B 6/00: Apparatus or devices for radiation diagnosis; Apparatus or devices for radiation diagnosis combined with radiation therapy equipment (instruments measuring radiation intensity for application in the field of nuclear medicine, e.g. in vivo counting, G01T1/161)
- G06V 10/40: Extraction of image or video features
- G06V 10/82: using neural networks
- G06V 20/50: Context or environment of the image
- G16H 30/40: for processing medical images, e.g. editing
- G16H 50/20: for computer-aided diagnosis, e.g. based on medical expert systems
- G06T 2207/10116: X-ray image
- G06T 2207/20081: Training; Learning
- G06T 2207/20084: Artificial neural networks [ANN]
- G06T 2207/30008: Bone
- G06V 2201/03: Recognition of patterns in medical or anatomical images
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- A61B: DIAGNOSIS; SURGERY; IDENTIFICATION (usefulness limited to only animals A61D)
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G16H: HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA

## Abstract

The present invention relates to a sleep apnea diagnostic auxiliary system using a simple skull x-ray image, the system comprising: an input unit for receiving a simple skull x-ray image of a target patient; a prediction unit for analyzing the simple skull x-ray image to predict a possibility of the occurrence of sleep apnea of the target patient; an information providing unit for generating and providing diagnostic auxiliary information on the basis of the possibility of the occurrence of sleep apnea of the target patient; and an artificial intelligence learning model configured to train the prediction unit by using learning data including simple skull x-ray images of a plurality of patients and sleep apnea diagnosis results of the patients.

## Claims

### Claim 1

A sleep apnea diagnostic auxiliary system using a simple skull x-ray image, the system comprising:
an input unit configured to receive a simple skull x-ray image of a target patient;
a prediction unit configured to analyze the simple skull x-ray image to predict a possibility of the occurrence of sleep apnea of the target patient;
an information providing unit configured to generate and provide diagnostic auxiliary information on the basis of the possibility of the occurrence of sleep apnea of the target patient; and
an artificial intelligence learning model configured to train the prediction unit by using learning data including simple skull x-ray images of a plurality of patients and sleep apnea diagnosis results of respective patients.

### Claim 2 (depends on 1)

The sleep apnea diagnostic auxiliary system of claim 1, wherein the sleep apnea diagnostic results of the learning data is diagnostic results based on polysomnography.

### Claim 3 (depends on 1)

The sleep apnea diagnostic auxiliary system of claim 1, wherein the artificial intelligence learning model is an artificial neural network model.

### Claim 4 (depends on 3)

The sleep apnea diagnostic auxiliary system of claim 3, wherein the artificial neural network model comprises a plurality of layers, and
wherein each layer is configured to extract features from the simple skull x-ray image and correlate the features with the sleep apnea diagnostic results.

### Claim 5 (depends on 1)

The sleep apnea diagnostic auxiliary system of claim 1, wherein the learning data further comprises clinical information on the plurality of patients, and
wherein the prediction unit predicts the possibility of the occurrence of sleep apnea in consideration of the clinical information of the target patient.

### Claim 6 (depends on 5)

The sleep apnea diagnostic auxiliary system of claim 5, wherein the clinical information comprises at least one of a patient's age, gender, genetic disease, and the presence or absence of other diseases associated with sleep apnea.

### Claim 7 (depends on 1)

The sleep apnea diagnostic auxiliary system claim 1, wherein the diagnostic auxiliary information comprises interpretation information indicating features of the simple skull x-ray image considered by the prediction unit in predicting the possibility of the occurrence of sleep apnea.

### Claim 8 (depends on 7)

The sleep apnea diagnostic auxiliary system of claim 7, wherein the features of the simple skull x-ray image are focused around the upper respiratory tract, including the tongue and pharynx, in response to anatomical abnormalities of a patient with sleep apnea.

### Claim 9 (depends on 3)

The sleep apnea diagnostic auxiliary system of claim 3, further comprising a display unit configured to visualize areas affecting the prediction performance of the prediction unit by displaying the areas on the simple skull x-ray image of the target patient received by the input unit.

### Claim 10 (depends on 9)

The sleep apnea diagnostic auxiliary system of claim 9, wherein the display unit comprises a gradient-weighted CAM (Grad-CAM) model.

### Claim 11 (depends on 1)

The sleep apnea diagnostic auxiliary system of claim 1, wherein the learning data comprises data in which at least one or more techniques of angulation, zooming in or out, translocation, histogram equalizer, flipping, and adding noise have been performed on the simple skull x-ray images for the plurality of patients.

### Claim 12

A method of providing sleep apnea diagnostic auxiliary information using a simple skull x-ray image performed by a processor, the method comprising:
receiving a simple skull x-ray image of a target patient;
predicting a possibility of the occurrence of sleep apnea of a target patient by analyzing the simple skull x-ray image through an artificial intelligence learning model; and
generating and providing diagnostic auxiliary information on the basis of the possibility of the occurrence of sleep apnea of the target patient,
wherein the artificial intelligence learning model is trained using learning data including the simple skull x-ray images of a plurality of patients and sleep apnea diagnosis results of respective patients.

### Claim 13 (depends on 12)

A computer program stored on a computer-readable recording medium for executing the method of providing sleep apnea diagnostic auxiliary information using the simple skull x-ray image according to claim 12.
