# US 2023/0118333 A1 · Dental feature identification for assessing oral health

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

- Number: US 2023/0118333 A1
- Document ID: US20230118333A1
- Status: Published application
- Kind: A1
- Application number: 17/908,724
- Filed: 2021-02-26
- Published: 2023-04-20
- Earliest claimed: 2020-03-03
- Assignees: Adent ApS
- Applicants: Adent ApS
- Inventors: Richard BUNDSGAARD; Thøger BUNDSGAARD
- Web page: https://patentgrep.com/patent/US20230118333A1

## CPC

- 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}
- A61B 1/24: for the mouth, i.e. stomatoscopes, e.g. with tongue depressors; Instruments for opening or keeping open the mouth
- A61B 5/0022: {Monitoring a patient using a global network, e.g. telephone networks, internet}
- A61B 5/0088: {for oral or dental tissue}
- A61B 5/4547: {Evaluating teeth}
- A61B 5/4552: {Evaluating soft tissue within the mouth, e.g. gums or tongue}
- A61B 5/6898: {Portable consumer electronic devices, e.g. music players, telephones, tablet computers}
- A61B 5/7264: {Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems}
- A61B 5/7267: {involving training the classification device}
- A61B 5/743: {Displaying an image simultaneously with additional graphical information, e.g. symbols, charts, function plots}
- A61B 5/7465: {Arrangements for interactive communication between patient and care services, e.g. by using a telephone network (telemetry of measured physiological signal A61B5/0002)}
- A61B 5/7475: {User input or interface means, e.g. keyboard, pointing device, joystick}
- A61C 13/34: Making or working of models, e.g. preliminary castings, trial dentures; Dowel pins [4]
- G06N 3/0464: Convolutional networks [CNN, ConvNet]
- G06N 3/09: Supervised learning
- G06T 7/0012: {Biomedical image inspection}
- G06T 7/10: Segmentation; Edge detection (motion-based segmentation G06T7/215)
- G06V 40/10: Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G16H 30/40: for processing medical images, e.g. editing
- 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
- G06N 3/042: Knowledge-based neural networks; Logical representations of neural networks
- G06N 3/045: Combinations of networks
- G06N 3/08: Learning methods
- G06T 2207/10024: Color image
- G06T 2207/20081: Training; Learning
- G06T 2207/20084: Artificial neural networks [ANN]
- G06T 2207/30036: Dental; Teeth
- A61B: DIAGNOSIS; SURGERY; IDENTIFICATION (usefulness limited to only animals A61D)
- A61C: DENTISTRY; APPARATUS OR METHODS FOR ORAL OR DENTAL HYGIENE (non-driven toothbrushes A46B; {tongue scrapers A61B17/24;} preparations for dentistry A61K6/00; preparations for cleaning the teeth or mouth A61K8/00, A61Q11/00)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- 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

A computer program and computer-based system for remotely assessing oral health of a person by obtaining at least one digital image (1) of the person's oral cavity and additional non-image data (2) comprising anamnestic information about the person (30). The digital images (1) are segmented using statistical image segmentation algorithms (101,102) to extract visible segments (3), which are further processed to predict any invisible segments (6). The resulting segments are processed by a statistical object detection algorithm (104) using the non-image data (2) as further input to identify dental features (7), which are filtered to select only risk-related dental features (8) using a risk database (9) and mapped to respective tooth regions (11) or oral cavity regions (12) in an Oral Risk Atlas (10).

## Claims

### Claim 1

A computer program embodied on a non-transitory computer-readable medium and comprising instructions which, when the program is executed by a computer, cause the computer to:
obtain at least one digital image (1) of a person's oral cavity;
obtain non-image data (2) associated with the person, the non-image data (2) comprising anamnestic information about the person;
process the at least one digital image (1) or a representation thereof using a first statistical image segmentation algorithm (101) trained to identify at least one visible segment (3), the visible segment (3) being one of a tooth segment (4) or an oral cavity segment (5), wherein each tooth segment (4) relates to a distinct tooth and its related area within the oral cavity and each oral cavity segment (5) relates to a distinct non-tooth-related area within the oral cavity;
process the at least one visible segment (3) using a statistical algorithm (103) trained to predict any invisible segments (6) based on visible segments (3), each invisible segment (6) relating to an area within the oral cavity that is not visible on any of the at least one digital image (1); and
process the at least one visible segment (3) and the at least one invisible segment (6) using a statistical object detection algorithm (104) trained to identify dental features (7) linked to the respective segments, wherein the statistical object detection algorithm (104) uses the non-image data (2) as input regarding what dental features (7) to look for.

### Claim 2 (depends on 1)

The computer program according to claim 1, comprising further instructions which, when the program is executed by a computer, cause the computer to:
select risk-related dental features (8) from the identified dental features (7) using a risk database (9) that defines logical relationships between dental features (7) and their related oral health risks;
generate an Oral Risk Atlas (10) by
mapping risk-related dental features (8) linked to any tooth segment (4) to a respective tooth region (11) according to a predefined dental notation framework,
mapping risk-related dental features (8) linked to any oral cavity segment (5) to a respective oral cavity region (12) according to a predefined oral cavity surface identification framework, and
mapping risk-related dental features (8) linked to any invisible segment (6) to a respective tooth region (11) or oral cavity region (12) according to the predefined dental notation framework and the oral cavity surface identification framework; and
display the Oral Risk Atlas (10) on a user interface (24).

### Claim 3 (depends on 2)

The computer program according to claim 2, comprising further instructions which, when the program is executed by a computer, cause the computer to:
process the at least one tooth segment (4) using a second statistical image segmentation algorithm (102) trained to identify at least one tooth surface segment (13) and at least one periodontal surface segment (14), each tooth surface segment (13) relating to a distinct surface of a distinct tooth within the oral cavity and each periodontal surface segment (14) relating to a structure surrounding or supporting a distinct tooth within the oral cavity;
process the at least one tooth surface segment (13) and at least one periodontal surface segment (14) using a statistical algorithm (103) trained to predict any invisible surface segments (15), each invisible surface segment (15) relating to a distinct surface of distinct tooth or a structure surrounding or supporting a distinct tooth within the oral cavity that is not visible on any of the at least one digital image (1);
identify dental features (7) by processing the at least one tooth surface segment (13), periodontal surface segment (14) and invisible surface segment (15) using the statistical object detection algorithm (104); and
select risk-related dental features (8) from the identified dental features (7) using the risk database (9);
wherein generating the Oral Risk Atlas (10) further comprises:
mapping the risk-related dental features (8) linked to the tooth surface segments (13) to a respective tooth surface region (17) according to a predefined dental surface identification framework,
mapping the risk-related dental features (8) linked to the periodontal surface segments (14) to a respective periodontal surface region (18) according to a predefined dental surface identification framework, and
mapping the risk-related dental features (8) linked to the invisible surface segments (15) to a respective tooth surface region (17) or periodontal surface region (18) according to the predefined dental surface identification framework.

### Claim 4 (depends on 2)

The computer program according to claim 2, comprising further instructions which, when the program is executed by a computer, cause the computer to:
process the non-image data (2) to extract further risk-related dental features (16) linked to any one of the tooth region (11), oral cavity region (12), tooth surface region (17) or periodontal surface region wherein generating the Oral Risk Atlas (10) further comprises mapping the further risk-related dental features (16) to the respective regions.

### Claim 5 (depends on 2)

The computer program according to claim 2, comprising further instructions which, when the program is executed by a computer, cause the computer to:
determine a dental risk assessment (19) for each tooth region (11), oral cavity region (12), tooth surface region (17) and periodontal surface region (18) associated with an identified visible segment (3) using a statistical risk assessment algorithm (105) trained to predict dental risk assessments (19) based on risk-related dental features (8) determined from the respective visible segments (3); wherein
generating the Oral Risk Atlas (10) further comprises mapping the dental risk assessments (19) to the Oral Risk Atlas (10).

### Claim 6 (depends on 2)

The computer program according to claim 2, comprising further instructions which, when the program is executed by a computer, cause the computer to:
determine a dental risk assessment (19) for each tooth region (11), oral cavity region (12), tooth surface region (17) and periodontal surface region (18) associated with a predicted invisible segment (6) using a statistical risk prediction algorithm (106) trained to predict dental risk assessments (19) based on risk-related dental features (8) determined from visible segments (3) adjacent to a respective invisible segment (6);
wherein generating the Oral Risk Atlas (10) further comprises mapping the dental risk assessments (19) to the Oral Risk Atlas (10).

### Claim 7 (depends on 2)

The computer program according to claim 2, comprising further instructions which, when the program is executed by a computer, cause the computer to:
determine each dental risk assessment (19) by calculating a dental risk score (20) for each tooth region (11), oral cavity region (12), tooth surface region (17) and periodontal surface region (18) as a percentage value (ranging from 1 to 100%) or a discrete value (ranging from 1 to 5);
wherein generating the Oral Risk Atlas (10) further comprises mapping the dental risk scores (20) to the Oral Risk Atlas (10).

### Claim 8 (depends on 7)

The computer program according to claim 7, comprising further instructions which, when the program is executed by a computer, cause the computer to:
calculate an aggregate dental risk score (20A) based on aggregating the dental risk scores (20) for each tooth region (11), oral cavity region (12), tooth surface region (17) and periodontal surface region (18).

### Claim 9 (depends on 2)

The computer program according to claim 2, comprising further instructions which, when the program is executed by a computer, cause the computer to:
determine dental risk mitigation assessments (22) comprising possible actions to take for the person based on the risk-related dental features (8), the further risk-related dental features (16), the dental risk scores (20) or the aggregate dental risk score (20A), the possible actions comprising at least one of
home care actions related to following a dental routine or customized dental plan, such as prompts for more frequent flossing,
risk-related treatments, or
prompts to visit a dental professional;
wherein generating the Oral Risk Atlas (10) further comprises mapping potential gains of the possible actions to the Oral Risk Atlas (10).

### Claim 10 (depends on 2)

The computer program according to claim 2, comprising further instructions which, when the program is executed by a computer, cause the computer to at least one of:
map the risk-related dental features (8) or dental risk assessments (19) to respective regions using a matrix scheme; or
map the risk-related dental features (8) or dental risk assessments (19) to respective regions based on a 2D or 3D oral cavity model, the oral cavity model being generated using a standardized dental model or a dental model of the person.

### Claim 11 (depends on 2)

The computer program according to claim 2, wherein the digital image (1) is at least one of an intraoral or extraoral high resolution color photograph, preferably in the RGB or RGBA color space, obtained through a dental risk analysis application by prompting the person to take a photograph with a digital camera (23) of a client device (26) of one or more areas of the oral cavity of the person.

### Claim 12 (depends on 2)

The computer program according to claim 2, wherein the non-image data (2) is obtained, in the form of at least one of a text input, spoken input or input by selection of selecting at least one of several presented answers, through a dental risk analysis application by performing a dialogue with the person through a user interface (24) of a client device (26).

### Claim 13 (depends on 2)

The computer program according to claim 2, comprising further instructions which, when the program is executed by a computer, cause the computer to:
obtain additional non-image data (2) by extracting from a dental journal (27) or dental medical history of the person.

### Claim 14 (depends on 2)

A computer-based system comprising:
a digital camera (23) configured to obtain a digital image (1) of an oral cavity (31) of the person;
an input device (28) configured to obtain non-image data (2) associated with the person, the non-image data (2) comprising anamnestic information about the person;
a computer-readable storage medium comprising a computer program according to claim 2; and
one or more processors operable to execute the computer program; and
a user interface (24) configured to display an Oral Risk Atlas (10) generated by the computer program.

### Claim 15 (depends on 14)

A computer-based system according to claim 14, the system comprising:
a client device (26) comprising at least the digital camera (23), the input device (28) and the user interface (24); and
a server device (25) in data connection with the client device (26), the server device comprising at least the computer-readable storage medium and the one or more processors.
